Search results for: image encryption
1478 Resisting Adversarial Assaults: A Model-Agnostic Autoencoder Solution
Authors: Massimo Miccoli, Luca Marangoni, Alberto Aniello Scaringi, Alessandro Marceddu, Alessandro Amicone
Abstract:
The susceptibility of deep neural networks (DNNs) to adversarial manipulations is a recognized challenge within the computer vision domain. Adversarial examples, crafted by adding subtle yet malicious alterations to benign images, exploit this vulnerability. Various defense strategies have been proposed to safeguard DNNs against such attacks, stemming from diverse research hypotheses. Building upon prior work, our approach involves the utilization of autoencoder models. Autoencoders, a type of neural network, are trained to learn representations of training data and reconstruct inputs from these representations, typically minimizing reconstruction errors like mean squared error (MSE). Our autoencoder was trained on a dataset of benign examples; learning features specific to them. Consequently, when presented with significantly perturbed adversarial examples, the autoencoder exhibited high reconstruction errors. The architecture of the autoencoder was tailored to the dimensions of the images under evaluation. We considered various image sizes, constructing models differently for 256x256 and 512x512 images. Moreover, the choice of the computer vision model is crucial, as most adversarial attacks are designed with specific AI structures in mind. To mitigate this, we proposed a method to replace image-specific dimensions with a structure independent of both dimensions and neural network models, thereby enhancing robustness. Our multi-modal autoencoder reconstructs the spectral representation of images across the red-green-blue (RGB) color channels. To validate our approach, we conducted experiments using diverse datasets and subjected them to adversarial attacks using models such as ResNet50 and ViT_L_16 from the torch vision library. The autoencoder extracted features used in a classification model, resulting in an MSE (RGB) of 0.014, a classification accuracy of 97.33%, and a precision of 99%.Keywords: adversarial attacks, malicious images detector, binary classifier, multimodal transformer autoencoder
Procedia PDF Downloads 1031477 Lithological Mapping and Iron Deposits Identification in El-Bahariya Depression, Western Desert, Egypt, Using Remote Sensing Data Analysis
Authors: Safaa M. Hassan; Safwat S. Gabr, Mohamed F. Sadek
Abstract:
This study is proposed for the lithological and iron oxides detection in the old mine areas of El-Bahariya Depression, Western Desert, using ASTER and Landsat-8 remote sensing data. Four old iron ore occurrences, namely; El-Gedida, El-Haraa, Ghurabi, and Nasir mine areas found in the El-Bahariya area. This study aims to find new high potential areas for iron mineralization around El-Baharyia depression. Image processing methods such as principle component analysis (PCA) and band ratios (b4/b5, b5/b6, b6/b7, and 4/2, 6/7, band 6) images were used for lithological identification/mapping that includes the iron content in the investigated area. ASTER and Landsat-8 visible and short-wave infrared data found to help mapping the ferruginous sandstones, iron oxides as well as the clay minerals in and around the old mines area of El-Bahariya depression. Landsat-8 band ratio and the principle component of this study showed well distribution of the lithological units, especially ferruginous sandstones and iron zones (hematite and limonite) along with detection of probable high potential areas for iron mineralization which can be used in the future and proved the ability of Landsat-8 and ASTER data in mapping these features. Minimum Noise Fraction (MNF), Mixture Tuned Matched Filtering (MTMF), pixel purity index methods as well as Spectral Ange Mapper classifier algorithm have been successfully discriminated the hematite and limonite content within the iron zones in the study area. Various ASTER image spectra and ASD field spectra of hematite and limonite and the surrounding rocks are compared and found to be consistent in terms of the presence of absorption features at range from 1.95 to 2.3 μm for hematite and limonite. Pixel purity index algorithm and two sub-pixel spectral methods, namely Mixture Tuned Matched Filtering (MTMF) and matched filtering (MF) methods, are applied to ASTER bands to delineate iron oxides (hematite and limonite) rich zones within the rock units. The results are validated in the field by comparing image spectra of spectrally anomalous zone with the USGS resampled laboratory spectra of hematite and limonite samples using ASD measurements. A number of iron oxides rich zones in addition to the main surface exposures of the El-Gadidah Mine, are confirmed in the field. The proposed method is a successful application of spectral mapping of iron oxides deposits in the exposed rock units (i.e., ferruginous sandstone) and present approach of both ASTER and ASD hyperspectral data processing can be used to delineate iron-rich zones occurring within similar geological provinces in any parts of the world.Keywords: Landsat-8, ASTER, lithological mapping, iron exploration, western desert
Procedia PDF Downloads 1351476 Application of Hyperspectral Remote Sensing in Sambhar Salt Lake, A Ramsar Site of Rajasthan, India
Authors: Rajashree Naik, Laxmi Kant Sharma
Abstract:
Sambhar lake is the largest inland Salt Lake of India, declared as a Ramsar site on 23 March 1990. Due to high salinity and alkalinity condition its biodiversity richness is contributed by haloalkaliphilic flora and fauna along with the diverse land cover including waterbody, wetland, salt crust, saline soil, vegetation, scrub land and barren land which welcome large number of flamingos and other migratory birds for winter harboring. But with the gradual increase in the irrational salt extraction activities, the ecological diversity is at stake. There is an urgent need to assess the ecosystem. Advanced technology like remote sensing and GIS has enabled to look into the past, compare with the present for the future planning and management of the natural resources in a judicious way. This paper is a research work intended to present a vegetation in typical inland lake environment of Sambhar wetland using satellite data of NASA’s EO-1 Hyperion sensor launched in November 2000. With the spectral range of 0.4 to 2.5 micrometer at approximately 10nm spectral resolution with 242 bands 30m spatial resolution and 705km orbit was used to produce a vegetation map for a portion of the wetland. The vegetation map was tested for classification accuracy with a pre-existing detailed GIS wetland vegetation database. Though the accuracy varied greatly for different classes the algal communities were successfully identified which are the major sources of food for flamingo. The results from this study have practical implications for uses of spaceborne hyperspectral image data that are now becoming available. Practical limitations of using these satellite data for wetland vegetation mapping include inadequate spatial resolution, complexity of image processing procedures, and lack of stereo viewing.Keywords: Algal community, NASA’s EO-1 Hyperion, salt-tolerant species, wetland vegetation mapping
Procedia PDF Downloads 1261475 Selfie: Redefining Culture of Narcissism
Authors: Junali Deka
Abstract:
“Pictures speak more than a thousand words”. It is the power of image which can have multiple meanings the way it is read by the viewers. This research article is an outcome of the extensive study of the phenomenon of‘selfie culture’ and dire need of self-constructed virtual identity among youths. In the recent times, there has been a revolutionary change in the concept of photography in terms of both techniques and applications. The popularity of ‘self-portraits’ mainly depend on the temporal space and time created on social networking sites like Facebook, Instagram. With reference to Stuart’s Hall encoding and decoding process, the article studies the behavior of the users who post photographs online. The photographic messages (Roland Barthes) are interpreted differently by different viewers. The notion of ‘self’, ‘self-love and practice of looking (Marita Sturken) and ways of seeing (John Berger) got new definition and dimensional together. After Oscars Night, show host Ellen DeGeneres’s selfie created the most buzz and hype in the social media. The term was judged the word of 2013, and has earned its place in the dictionary. “In November 2013, the word "selfie" was announced as being the "word of the year" by the Oxford English Dictionary. By the end of 2012, Time magazine considered selfie one of the "top 10 buzzwords" of that year; although selfies had existed long before, it was in 2012 that the term "really hit the big time an Australian origin. The present study was carried to understand the concept of ‘selfie-bug’ and the phenomenon it has created among youth (especially students) at large in developing a pseudo-image of its own. The topic was relevant and gave a platform to discuss about the cultural, psychological and sociological implications of selfie in the age of digital technology. At the first level, content analysis of the primary and secondary sources including newspapers articles and online resources was carried out followed by a small online survey conducted with the help of questionnaire to find out the student’s view on selfie and its social and psychological effects. The newspapers reports and online resources confirmed that selfie is a new trend in the digital media and it has redefined the notion of beauty and self-love. The Facebook and Instagram are the major platforms used to express one-self and creation of virtual identity. The findings clearly reflected the active participation of female students in comparison to male students. The study of the photographs of few selected respondents revealed the difference of attitude and image building among male and female users. The study underlines some basic questions about the desire of reconstruction of identity among young generation, such as - are they becoming culturally narcissist; responsible factors for cultural, social and moral changes in the society, psychological and technological effects caused by Smartphone as well, culminating into a big question mark whether the selfie is a social signifier of identity construction.Keywords: Culture, Narcissist, Photographs, Selfie
Procedia PDF Downloads 4021474 Application of Optical Method for Calcul of Deformed Object Samples
Authors: R. Daira
Abstract:
The electronic speckle interferometry technique used to measure the deformations of scatterers process is based on the subtraction of interference patterns. A speckle image is first recorded before deformation of the object in the RAM of a computer, after a second deflection. The square of the difference between two images showing correlation fringes observable in real time directly on monitor. The interpretation these fringes to determine the deformation. In this paper, we present experimental results of deformation out of the plane of two samples in aluminum, electronic boards and stainless steel.Keywords: optical method, holography, interferometry, deformation
Procedia PDF Downloads 3961473 Influence of Climate Change on Landslides in Northeast India: A Case Study
Authors: G. Vishnu, T. V. Bharat
Abstract:
Rainfall plays a major role in the stability of natural slopes in tropical and subtropical regions. These slopes usually have high slope angles and are stable during the dry season. The critical rainfall intensity that might trigger a landslide may not be the highest rainfall. In addition to geological discontinuities and anthropogenic factors, water content, suction, and hydraulic conductivity also play a role. A thorough geotechnical investigation with the principles of unsaturated soil mechanics is required to predict the failures in these cases. The study discusses three landslide events that had occurred in residual hills of Guwahati, India. Rainfall data analysis, history image analysis, land use, and slope maps of the region were analyzed and discussed. The landslide occurred on June (24, 26, and 28) 2020, on the respective sites, but the highest rainfall was on June (6 and 17) 2020. The factors that lead to the landslide occurrence is the combination of critical events initiated with rainfall, causing a reduction in suction. The sites consist of a mixture of rocks and soil. The slope failure occurs due to the saturation of the soil layer leading to loss of soil strength resulting in the flow of the entire soil rock mass. The land-use change, construction activities, other human and natural activities that lead to faster disintegration of rock mass may accelerate the landslide events. Landslides in these slopes are inevitable, and the development of an early warning system (EWS) to save human lives and resources is a feasible way. The actual time of failure of a slope can be better predicted by considering all these factors rather than depending solely on the rainfall intensities. An effective EWS is required with less false alarms in these regions by proper instrumentation of slope and appropriate climatic downscaling.Keywords: early warning system, historic image analysis, slope instrumentation, unsaturated soil mechanics
Procedia PDF Downloads 1101472 A Study on the Application of Machine Learning and Deep Learning Techniques for Skin Cancer Detection
Authors: Hritwik Ghosh, Irfan Sadiq Rahat, Sachi Nandan Mohanty, J. V. R. Ravindra
Abstract:
In the rapidly evolving landscape of medical diagnostics, the early detection and accurate classification of skin cancer remain paramount for effective treatment outcomes. This research delves into the transformative potential of Artificial Intelligence (AI), specifically Deep Learning (DL), as a tool for discerning and categorizing various skin conditions. Utilizing a diverse dataset of 3,000 images representing nine distinct skin conditions, we confront the inherent challenge of class imbalance. This imbalance, where conditions like melanomas are over-represented, is addressed by incorporating class weights during the model training phase, ensuring an equitable representation of all conditions in the learning process. Our pioneering approach introduces a hybrid model, amalgamating the strengths of two renowned Convolutional Neural Networks (CNNs), VGG16 and ResNet50. These networks, pre-trained on the ImageNet dataset, are adept at extracting intricate features from images. By synergizing these models, our research aims to capture a holistic set of features, thereby bolstering classification performance. Preliminary findings underscore the hybrid model's superiority over individual models, showcasing its prowess in feature extraction and classification. Moreover, the research emphasizes the significance of rigorous data pre-processing, including image resizing, color normalization, and segmentation, in ensuring data quality and model reliability. In essence, this study illuminates the promising role of AI and DL in revolutionizing skin cancer diagnostics, offering insights into its potential applications in broader medical domains.Keywords: artificial intelligence, machine learning, deep learning, skin cancer, dermatology, convolutional neural networks, image classification, computer vision, healthcare technology, cancer detection, medical imaging
Procedia PDF Downloads 751471 The Role of the Youth in Rebranding Nigeria
Authors: Hamzah Kamil Adeyemi, Oyesikun Abayomi Nathaniel
Abstract:
The plural nature of Nigeria state has created a leadership gap in the 21st century. The leadership problem encapsulated socio-economic system has called for a reorientation in youth to channel a programme that will redeem the image (OT) the country among the committee of nations and chart a way forward in bailing the country out of bad governance unemployment corruption and other anti-development policies. The touth need to raise up to the challenges of nation building. This study engaged theoretical analysis, both written records was used to add value to its quality and recommendation was made with conclusion.Keywords: youth, education, unempolyment, rebranding, Nigeria
Procedia PDF Downloads 4221470 Random Variation of Treated Volumes in Fractionated 2D Image Based HDR Brachytherapy for Cervical Cancer
Authors: R. Tudugala, B. M. A. I. Balasooriya, W. M. Ediri Arachchi, R. W. M. W. K. Rathnayake, T. D. Premaratna
Abstract:
Brachytherapy involves placing a source of radiation near the cancer site which gives promising prognosis for cervical cancer treatments. The purpose of this study was to evaluate the effect of random variation of treated volumes in between fractions in the 2D image based fractionated high dose rate brachytherapy for cervical cancer at National Cancer Institute Maharagama, Sri Lanka. Dose plans were analyzed for 150 cervical cancer patients with orthogonal radiographs (2D) based brachytherapy. ICRU treated volumes was modeled by translating the applicators with the help of “Multisource HDR plus software”. The difference of treated volumes with respect to the applicator geometry was analyzed by using SPSS 18 software; to derived patient population based estimates of delivered treated volumes relative to ideally treated volumes. Packing was evaluated according to bladder dose, rectum dose and geometry of the dose distribution by three consultant radiation oncologist. The difference of treated volumes depends on types of the applicators, which was used in fractionated brachytherapy. The means of the “Difference of Treated Volume” (DTV) for “Evenly activated tandem (ET)” length” group was ((X_1)) -0.48 cm3 and ((X_2)) 11.85 cm3 for “Unevenly activated tandem length (UET) group. The range of the DTV for ET group was 35.80 cm3 whereas UET group 104.80 cm3. One sample T test was performed to compare the DTV with “Ideal treatment volume difference (0.00cm3)”. It is evident that P value was 0.732 for ET group and for UET it was 0.00 moreover independent two sample T test was performed to compare ET and UET groups and calculated P value was 0.005. Packing was evaluated under three categories 59.38% used “Convenient Packing Technique”, 33.33% used “Fairly Packing Technique” and 7.29% used “Not Convenient Packing” in their fractionated brachytherapy treatments. Random variation of treated volume in ET group is much lower than UET group and there is a significant difference (p<0.05) in between ET and UET groups which affects the dose distribution of the treatment. Furthermore, it can be concluded nearly 92.71% patient’s packing were used acceptable packing technique at NCIM, Sri Lanka.Keywords: brachytherapy, cervical cancer, high dose rate, tandem, treated volumes
Procedia PDF Downloads 1931469 Communicating Corporate Social Responsibility in Kuwait: Assessment of Environmental Responsibility Efforts and Targeted Stakeholders
Authors: Manaf Bashir
Abstract:
Corporate social responsibility (CSR) has become a tool for corporations to meet the expectations of different stakeholders about economic, social and environmental issues. It has become indispensable for an organization’s success, positive image and reputation. Equally important is how corporations communicate and report their CSR. Employing the stakeholder theory, the purpose of this research is to analyse CSR content of leading Kuwaiti corporations. No research analysis of CSR reporting has been conducted in Kuwait and this study is an attempt to redress in part this empirical deficit in the country and the region. It attempts to identify the issues and stakeholders of the CSR and if corporations are following CSR reporting standards. By analysing websites, annual and CSR reports of the top 100 Kuwaiti corporations, this study found low mentions of the CSR issues and even lower mentions of CSR stakeholders. Environmental issues were among the least mentioned despite an increasing global concern toward the environment. ‘Society’ was mentioned the most as a stakeholder and ‘The Environment’ was among the least mentioned. Cross-tabulations found few significant relationships between type of industry and the CSR issues and stakeholders. Independent sample t-tests found no significant difference between the issues and stakeholders that are mentioned on the websites and the reports. Only two companies from the sample followed reporting standards and both followed the Global Reporting Initiative. Successful corporations would be keen to identify the issues that meet the expectations of different stakeholders and address them through their corporate communication. Kuwaiti corporations did not show this keenness. As the stakeholder theory suggests, extending the spectrum of stakeholders beyond investors can open mutual dialogue and understanding between corporations and various stakeholders. However, Kuwaiti corporations focus on few CSR issues and even fewer CSR stakeholders. Kuwaiti corporations need to pay more attention to CSR and particularly toward environmental issues. They should adopt a strategic approach and allocate specialized personnel such as marketers and public relations practitioners to manage it. The government and non-profit organizations should encourage the private sector in Kuwait to do more CSR and meet the needs and expectations of different stakeholders and not only shareholders. This is in addition to reporting the CSR information professionally because of its benefits to corporate image, reputation, and transparency.Keywords: corporate social responsibility, environmental responsibility, Kuwait, stakeholder theory
Procedia PDF Downloads 1421468 Data Confidentiality in Public Cloud: A Method for Inclusion of ID-PKC Schemes in OpenStack Cloud
Authors: N. Nalini, Bhanu Prakash Gopularam
Abstract:
The term data security refers to the degree of resistance or protection given to information from unintended or unauthorized access. The core principles of information security are the confidentiality, integrity and availability, also referred as CIA triad. Cloud computing services are classified as SaaS, IaaS and PaaS services. With cloud adoption the confidential enterprise data are moved from organization premises to untrusted public network and due to this the attack surface has increased manifold. Several cloud computing platforms like OpenStack, Eucalyptus, Amazon EC2 offer users to build and configure public, hybrid and private clouds. While the traditional encryption based on PKI infrastructure still works in cloud scenario, the management of public-private keys and trust certificates is difficult. The Identity based Public Key Cryptography (also referred as ID-PKC) overcomes this problem by using publicly identifiable information for generating the keys and works well with decentralized systems. The users can exchange information securely without having to manage any trust information. Another advantage is that access control (role based access control policy) information can be embedded into data unlike in PKI where it is handled by separate component or system. In OpenStack cloud platform the keystone service acts as identity service for authentication and authorization and has support for public key infrastructure for auto services. In this paper, we explain OpenStack security architecture and evaluate the PKI infrastructure piece for data confidentiality. We provide method to integrate ID-PKC schemes for securing data while in transit and stored and explain the key measures for safe guarding data against security attacks. The proposed approach uses JPBC crypto library for key-pair generation based on IEEE P1636.3 standard and secure communication to other cloud services.Keywords: data confidentiality, identity based cryptography, secure communication, open stack key stone, token scoping
Procedia PDF Downloads 3741467 Clinical Application of Measurement of Eyeball Movement for Diagnose of Autism
Authors: Ippei Torii, Kaoruko Ohtani, Takahito Niwa, Naohiro Ishii
Abstract:
This paper shows developing an objectivity index using the measurement of subtle eyeball movement to diagnose autism. The developmentally disabled assessment varies, and the diagnosis depends on the subjective judgment of professionals. Therefore, a supplementary inspection method that will enable anyone to obtain the same quantitative judgment is needed. The diagnosis are made based on a comparison of the time of gazing an object in the conventional autistic study, but the results do not match. First, we divided the pupil into four parts from the center using measurements of subtle eyeball movement and comparing the number of pixels in the overlapping parts based on an afterimage. Then we developed the objective evaluation indicator to judge non-autistic and autistic people more clearly than conventional methods by analyzing the differences of subtle eyeball movements between the right and left eyes. Even when a person gazes at one point and his/her eyeballs always stay fixed at that point, their eyes perform subtle fixating movements (ie. tremors, drifting, microsaccades) to keep the retinal image clear. Particularly, the microsaccades link with nerves and reflect the mechanism that process the sight in a brain. We converted the differences between these movements into numbers. The process of the conversion is as followed: 1) Select the pixel indicating the subject's pupil from images of captured frames. 2) Set up a reference image, known as an afterimage, from the pixel indicating the subject's pupil. 3) Divide the pupil of the subject into four from the center in the acquired frame image. 4) Select the pixel in each divided part and count the number of the pixels of the overlapping part with the present pixel based on the afterimage. 5) Process the images with precision in 24 - 30fps from a camera and convert the amount of change in the pixels of the subtle movements of the right and left eyeballs in to numbers. The difference in the area of the amount of change occurs by measuring the difference between the afterimage in consecutive frames and the present frame. We set the amount of change to the quantity of the subtle eyeball movements. This method made it possible to detect a change of the eyeball vibration in numerical value. By comparing the numerical value between the right and left eyes, we found that there is a difference in how much they move. We compared the difference in these movements between non-autistc and autistic people and analyzed the result. Our research subjects consists of 8 children and 10 adults with autism, and 6 children and 18 adults with no disability. We measured the values through pasuit movements and fixations. We converted the difference in subtle movements between the right and left eyes into a graph and define it in multidimensional measure. Then we set the identification border with density function of the distribution, cumulative frequency function, and ROC curve. With this, we established an objective index to determine autism, normal, false positive, and false negative.Keywords: subtle eyeball movement, autism, microsaccade, pursuit eye movements, ROC curve
Procedia PDF Downloads 2741466 Field Emission Scanning Microscope Image Analysis for Porosity Characterization of Autoclaved Aerated Concrete
Authors: Venuka Kuruwita Arachchige Don, Mohamed Shaheen, Chris Goodier
Abstract:
Aerated autoclaved concrete (AAC) is known for its lightweight, easy handling, high thermal insulation, and extremely porous structure. Investigation of pore behavior in AAC is crucial for characterizing the material, standardizing design and production techniques, enhancing the mechanical, durability, and thermal performance, studying the effectiveness of protective measures, and analyzing the effects of weather conditions. The significant details of pores are complicated to observe with acknowledged accuracy. The High-resolution Field Emission Scanning Electron Microscope (FESEM) image analysis is a promising technique for investigating the pore behavior and density of AAC, which is adopted in this study. Mercury intrusion porosimeter and gas pycnometer were employed to characterize porosity distribution and density parameters. The analysis considered three different densities of AAC blocks and three layers in the altitude direction within each block. A set of understandings was presented to extract and analyze the details of pore shape, pore size, pore connectivity, and pore percentages from FESEM images of AAC. Average pore behavior outcomes per unit area were presented. Comparison of porosity distribution and density parameters revealed significant variations. FESEM imaging offered unparalleled insights into porosity behavior, surpassing the capabilities of other techniques. The analysis conducted from a multi-staged approach provides porosity percentage occupied by various pore categories, total porosity, variation of pore distribution compared to AAC densities and layers, number of two-dimensional and three-dimensional pores, variation of apparent and matrix densities concerning pore behaviors, variation of pore behavior with respect to aluminum content, and relationship among shape, diameter, connectivity, and percentage in each pore classification.Keywords: autoclaved aerated concrete, density, imaging technique, microstructure, porosity behavior
Procedia PDF Downloads 521465 New Approach for Constructing a Secure Biometric Database
Authors: A. Kebbeb, M. Mostefai, F. Benmerzoug, Y. Chahir
Abstract:
The multimodal biometric identification is the combination of several biometric systems. The challenge of this combination is to reduce some limitations of systems based on a single modality while significantly improving performance. In this paper, we propose a new approach to the construction and the protection of a multimodal biometric database dedicated to an identification system. We use a topological watermarking to hide the relation between face image and the registered descriptors extracted from other modalities of the same person for more secure user identification.Keywords: biometric databases, multimodal biometrics, security authentication, digital watermarking
Procedia PDF Downloads 3851464 Ill-Posed Inverse Problems in Molecular Imaging
Authors: Ranadhir Roy
Abstract:
Inverse problems arise in medical (molecular) imaging. These problems are characterized by large in three dimensions, and by the diffusion equation which models the physical phenomena within the media. The inverse problems are posed as a nonlinear optimization where the unknown parameters are found by minimizing the difference between the predicted data and the measured data. To obtain a unique and stable solution to an ill-posed inverse problem, a priori information must be used. Mathematical conditions to obtain stable solutions are established in Tikhonov’s regularization method, where the a priori information is introduced via a stabilizing functional, which may be designed to incorporate some relevant information of an inverse problem. Effective determination of the Tikhonov regularization parameter requires knowledge of the true solution, or in the case of optical imaging, the true image. Yet, in, clinically-based imaging, true image is not known. To alleviate these difficulties we have applied the penalty/modified barrier function (PMBF) method instead of Tikhonov regularization technique to make the inverse problems well-posed. Unlike the Tikhonov regularization method, the constrained optimization technique, which is based on simple bounds of the optical parameter properties of the tissue, can easily be implemented in the PMBF method. Imposing the constraints on the optical properties of the tissue explicitly restricts solution sets and can restore uniqueness. Like the Tikhonov regularization method, the PMBF method limits the size of the condition number of the Hessian matrix of the given objective function. The accuracy and the rapid convergence of the PMBF method require a good initial guess of the Lagrange multipliers. To obtain the initial guess of the multipliers, we use a least square unconstrained minimization problem. Three-dimensional images of fluorescence absorption coefficients and lifetimes were reconstructed from contact and noncontact experimentally measured data.Keywords: constrained minimization, ill-conditioned inverse problems, Tikhonov regularization method, penalty modified barrier function method
Procedia PDF Downloads 2651463 Image-Based UAV Vertical Distance and Velocity Estimation Algorithm during the Vertical Landing Phase Using Low-Resolution Images
Authors: Seyed-Yaser Nabavi-Chashmi, Davood Asadi, Karim Ahmadi, Eren Demir
Abstract:
The landing phase of a UAV is very critical as there are many uncertainties in this phase, which can easily entail a hard landing or even a crash. In this paper, the estimation of relative distance and velocity to the ground, as one of the most important processes during the landing phase, is studied. Using accurate measurement sensors as an alternative approach can be very expensive for sensors like LIDAR, or with a limited operational range, for sensors like ultrasonic sensors. Additionally, absolute positioning systems like GPS or IMU cannot provide distance to the ground independently. The focus of this paper is to determine whether we can measure the relative distance and velocity of UAV and ground in the landing phase using just low-resolution images taken by a monocular camera. The Lucas-Konda feature detection technique is employed to extract the most suitable feature in a series of images taken during the UAV landing. Two different approaches based on Extended Kalman Filters (EKF) have been proposed, and their performance in estimation of the relative distance and velocity are compared. The first approach uses the kinematics of the UAV as the process and the calculated optical flow as the measurement; On the other hand, the second approach uses the feature’s projection on the camera plane (pixel position) as the measurement while employing both the kinematics of the UAV and the dynamics of variation of projected point as the process to estimate both relative distance and relative velocity. To verify the results, a sequence of low-quality images taken by a camera that is moving on a specifically developed testbed has been used to compare the performance of the proposed algorithm. The case studies show that the quality of images results in considerable noise, which reduces the performance of the first approach. On the other hand, using the projected feature position is much less sensitive to the noise and estimates the distance and velocity with relatively high accuracy. This approach also can be used to predict the future projected feature position, which can drastically decrease the computational workload, as an important criterion for real-time applications.Keywords: altitude estimation, drone, image processing, trajectory planning
Procedia PDF Downloads 1051462 Hand Gesture Detection via EmguCV Canny Pruning
Authors: N. N. Mosola, S. J. Molete, L. S. Masoebe, M. Letsae
Abstract:
Hand gesture recognition is a technique used to locate, detect, and recognize a hand gesture. Detection and recognition are concepts of Artificial Intelligence (AI). AI concepts are applicable in Human Computer Interaction (HCI), Expert systems (ES), etc. Hand gesture recognition can be used in sign language interpretation. Sign language is a visual communication tool. This tool is used mostly by deaf societies and those with speech disorder. Communication barriers exist when societies with speech disorder interact with others. This research aims to build a hand recognition system for Lesotho’s Sesotho and English language interpretation. The system will help to bridge the communication problems encountered by the mentioned societies. The system has various processing modules. The modules consist of a hand detection engine, image processing engine, feature extraction, and sign recognition. Detection is a process of identifying an object. The proposed system uses Canny pruning Haar and Haarcascade detection algorithms. Canny pruning implements the Canny edge detection. This is an optimal image processing algorithm. It is used to detect edges of an object. The system employs a skin detection algorithm. The skin detection performs background subtraction, computes the convex hull, and the centroid to assist in the detection process. Recognition is a process of gesture classification. Template matching classifies each hand gesture in real-time. The system was tested using various experiments. The results obtained show that time, distance, and light are factors that affect the rate of detection and ultimately recognition. Detection rate is directly proportional to the distance of the hand from the camera. Different lighting conditions were considered. The more the light intensity, the faster the detection rate. Based on the results obtained from this research, the applied methodologies are efficient and provide a plausible solution towards a light-weight, inexpensive system which can be used for sign language interpretation.Keywords: canny pruning, hand recognition, machine learning, skin tracking
Procedia PDF Downloads 1761461 Normal and Peaberry Coffee Beans Classification from Green Coffee Bean Images Using Convolutional Neural Networks and Support Vector Machine
Authors: Hira Lal Gope, Hidekazu Fukai
Abstract:
The aim of this study is to develop a system which can identify and sort peaberries automatically at low cost for coffee producers in developing countries. In this paper, the focus is on the classification of peaberries and normal coffee beans using image processing and machine learning techniques. The peaberry is not bad and not a normal bean. The peaberry is born in an only single seed, relatively round seed from a coffee cherry instead of the usual flat-sided pair of beans. It has another value and flavor. To make the taste of the coffee better, it is necessary to separate the peaberry and normal bean before green coffee beans roasting. Otherwise, the taste of total beans will be mixed, and it will be bad. In roaster procedure time, all the beans shape, size, and weight must be unique; otherwise, the larger bean will take more time for roasting inside. The peaberry has a different size and different shape even though they have the same weight as normal beans. The peaberry roasts slower than other normal beans. Therefore, neither technique provides a good option to select the peaberries. Defect beans, e.g., sour, broken, black, and fade bean, are easy to check and pick up manually by hand. On the other hand, the peaberry pick up is very difficult even for trained specialists because the shape and color of the peaberry are similar to normal beans. In this study, we use image processing and machine learning techniques to discriminate the normal and peaberry bean as a part of the sorting system. As the first step, we applied Deep Convolutional Neural Networks (CNN) and Support Vector Machine (SVM) as machine learning techniques to discriminate the peaberry and normal bean. As a result, better performance was obtained with CNN than with SVM for the discrimination of the peaberry. The trained artificial neural network with high performance CPU and GPU in this work will be simply installed into the inexpensive and low in calculation Raspberry Pi system. We assume that this system will be used in under developed countries. The study evaluates and compares the feasibility of the methods in terms of accuracy of classification and processing speed.Keywords: convolutional neural networks, coffee bean, peaberry, sorting, support vector machine
Procedia PDF Downloads 1381460 An Overview of the SIAFIM Connected Resources
Authors: Tiberiu Boros, Angela Ionita, Maria Visan
Abstract:
Wildfires are one of the frequent and uncontrollable phenomena that currently affect large areas of the world where the climate, geographic and social conditions make it impossible to prevent and control such events. In this paper we introduce the ground concepts that lie behind the SIAFIM (Satellite Image Analysis for Fire Monitoring) project in order to create a context and we introduce a set of newly created tools that are external to the project but inherently in interventions and complex decision making based on geospatial information and spatial data infrastructures.Keywords: wildfire, forest fire, natural language processing, mobile applications, communication, GPS
Procedia PDF Downloads 5731459 Emotion Recognition in Video and Images in the Wild
Authors: Faizan Tariq, Moayid Ali Zaidi
Abstract:
Facial emotion recognition algorithms are expanding rapidly now a day. People are using different algorithms with different combinations to generate best results. There are six basic emotions which are being studied in this area. Author tried to recognize the facial expressions using object detector algorithms instead of traditional algorithms. Two object detection algorithms were chosen which are Faster R-CNN and YOLO. For pre-processing we used image rotation and batch normalization. The dataset I have chosen for the experiments is Static Facial Expression in Wild (SFEW). Our approach worked well but there is still a lot of room to improve it, which will be a future direction.Keywords: face recognition, emotion recognition, deep learning, CNN
Procedia PDF Downloads 1811458 Yacht DB Construction Based on Five Essentials of Sailing
Authors: Jae-Neung Lee, Myung-Won Lee, Jung-Su Han, Keun-Chang Kwak
Abstract:
The paper established DB on the basis of five sailing essentials in the real yachting environment. It obtained the yacht condition (tilt, speed and course), surrounding circumstances (wind direction and speed) and user motion. Gopro camera for image processing was used to recognize the user motion and tilt sensor was employed to see the yacht balance. In addition, GPS for course, wind speed and direction sensor and marked suit were employed.Keywords: DB consturuction, yacht, five essentials of sailing, marker, Gps
Procedia PDF Downloads 4571457 Towards Visual Personality Questionnaires Based on Deep Learning and Social Media
Authors: Pau Rodriguez, Jordi Gonzalez, Josep M. Gonfaus, Xavier Roca
Abstract:
Image sharing in social networks has increased exponentially in the past years. Officially, there are 600 million Instagrammers uploading around 100 million photos and videos per day. Consequently, there is a need for developing new tools to understand the content expressed in shared images, which will greatly benefit social media communication and will enable broad and promising applications in education, advertisement, entertainment, and also psychology. Following these trends, our work aims to take advantage of the existing relationship between text and personality, already demonstrated by multiple researchers, so that we can prove that there exists a relationship between images and personality as well. To achieve this goal, we consider that images posted on social networks are typically conditioned on specific words, or hashtags, therefore any relationship between text and personality can also be observed with those posted images. Our proposal makes use of the most recent image understanding models based on neural networks to process the vast amount of data generated by social users to determine those images most correlated with personality traits. The final aim is to train a weakly-supervised image-based model for personality assessment that can be used even when textual data is not available, which is an increasing trend. The procedure is described next: we explore the images directly publicly shared by users based on those accompanying texts or hashtags most strongly related to personality traits as described by the OCEAN model. These images will be used for personality prediction since they have the potential to convey more complex ideas, concepts, and emotions. As a result, the use of images in personality questionnaires will provide a deeper understanding of respondents than through words alone. In other words, from the images posted with specific tags, we train a deep learning model based on neural networks, that learns to extract a personality representation from a picture and use it to automatically find the personality that best explains such a picture. Subsequently, a deep neural network model is learned from thousands of images associated with hashtags correlated to OCEAN traits. We then analyze the network activations to identify those pictures that maximally activate the neurons: the most characteristic visual features per personality trait will thus emerge since the filters of the convolutional layers of the neural model are learned to be optimally activated depending on each personality trait. For example, among the pictures that maximally activate the high Openness trait, we can see pictures of books, the moon, and the sky. For high Conscientiousness, most of the images are photographs of food, especially healthy food. The high Extraversion output is mostly activated by pictures of a lot of people. In high Agreeableness images, we mostly see flower pictures. Lastly, in the Neuroticism trait, we observe that the high score is maximally activated by animal pets like cats or dogs. In summary, despite the huge intra-class and inter-class variabilities of the images associated to each OCEAN traits, we found that there are consistencies between visual patterns of those images whose hashtags are most correlated to each trait.Keywords: emotions and effects of mood, social impact theory in social psychology, social influence, social structure and social networks
Procedia PDF Downloads 1861456 Femoropatellar Groove: An Anatomical Study
Authors: Mamatha Hosapatna, Anne D. Souza, Vrinda Hari Ankolekar, Antony Sylvan D. Souza
Abstract:
Introduction: The lower extremity of the femur is characterized by an anterior groove in which patella is held during motion. This groove separates the two lips of the trochlea (medial and lateral), prolongation of the two condyles. In humans, the lateral trochlear lip is more developed than the medial one, creating an asymmetric groove that is also specific to the human body. Because of femoral obliquity, contraction of quadriceps leads to a lateral dislocation stress on the patella, and the more elevated lateral side of the patellar groove helps the patella stays in its correct place, acting as a wall against lateral dislocation. This specific shape fits an oblique femur. It is known that femoral obliquity is not genetically determined but comes with orthostatism and biped walking. Material and Methodology: To measure the various dimensions of the Femoropatellar groove (FPG) and femoral condyle using digital image analyser. 37 dried adult femora (22 right,15 left) were used for the study. End on images of the lower end of the femur was taken. Various dimensions of the Femoropatellar groove and FP angle were measured using image J software. Results were analyzed statistically. Results: Maximum of the altitude of medial condyle of the right femur is 4.98± 0.35 cm and of the left femur is 5.20±.16 cm. Maximum altitude of lateral condyle is 5.44±0.4 and 5.50±0.14 on the right and left side respectively. Medial length of the groove is 1.30±0.38 cm on the right side and on the left side is 1.88±0.16 cm. The lateral length of the groove on the right side is 1.900±.16 cm and left side is 1.88±0.16 cm. Femoropatellar angle is 136.38◦±2.59 on the right side and on the left side it is 142.38◦±7.0 Angle and dimensions of the femoropatellar groove on the medial and lateral sides were measured. Asymmetry in the patellar groove was observed. The lateral lip was found to be wider and bigger which correlated with the previous studies. An asymmetrical patellar groove with a protruding lateral side associated with an oblique femur is a specific mark of bipedal locomotion. Conclusion: Dimensions of FPG are important in maintaining the stability of patella and also in knee replacement surgeries. The implants used in to replace the patellofemoral compartment consist of a metal groove to fit on the femoral end and a plastic disc that attaches to the undersurface of the patella. The location and configuration of the patellofemoral groove of the distal femur are clinically significant in the mechanics and pathomechanics of the patellofemoral articulation.Keywords: femoral patellar groove, femoro patellar angle, lateral condyle, medial condyle
Procedia PDF Downloads 3921455 Dosimetry in Interventional Radiology Examinations for Occupational Exposure Monitoring
Authors: Ava Zarif Sanayei, Sedigheh Sina
Abstract:
Interventional radiology (IR) uses imaging guidance, including X-rays and CT scans, to deliver therapy precisely. Most IR procedures are performed under local anesthesia and start with a small needle being inserted through the skin, which may be called pinhole surgery or image-guided surgery. There is increasing concern about radiation exposure during interventional radiology procedures due to procedure complexity. The basic aim of optimizing radiation protection as outlined in ICRP 139, is to strike a balance between image quality and radiation dose while maximizing benefits, ensuring that diagnostic interpretation is satisfactory. This study aims to estimate the equivalent doses to the main trunk of the body for the Interventional radiologist and Superintendent using LiF: Mg, Ti (TLD-100) chips at the IR department of a hospital in Shiraz, Iran. In the initial stage, the dosimeters were calibrated with the use of various phantoms. Afterward, a group of dosimeters was prepared, following which they were used for three months. To measure the personal equivalent dose to the body, three TLD chips were put in a tissue-equivalent batch and used under a protective lead apron. After the completion of the duration, TLDs were read out by a TLD reader. The results revealed that these individuals received equivalent doses of 387.39 and 145.11 µSv, respectively. The findings of this investigation revealed that the total radiation exposure to the staff was less than the annual limit of occupational exposure. However, it's imperative to implement appropriate radiation protection measures. Although the dose received by the interventional radiologist is a bit noticeable, it may be due to the reason for using conventional equipment with over-couch x-ray tubes for interventional procedures. It is therefore important to use dedicated equipment and protective means such as glasses and screens whenever compatible with the intervention when they are available or have them fitted to equipment if they are not present. Based on the results, the placement of staff in an appropriate location led to increasing the dose to the radiologist. Manufacturing and installation of moveable lead curtains with a thickness of 0.25 millimeters can effectively minimize the radiation dose to the body. Providing adequate training on radiation safety principles, particularly for technologists, can be an optimal approach to further decreasing exposure.Keywords: interventional radiology, personal monitoring, radiation protection, thermoluminescence dosimetry
Procedia PDF Downloads 581454 Star Images Constructed Based on Kramer vs. Kramer
Authors: Huailei Wen
Abstract:
The Kramers vs. Kramers (1979) is a film that comprehensively examines the role and status of women under the traditional secular vision, where women have become subordinate to the patriarchal society and family. Through the construction of the protagonist Joanna's dissatisfaction with the social and ethical status quo, her struggle to subvert the existing status of women, and her return to her own self, the story comprehensively reflects the difficult journey of women, represented by Joanna, to subvert the stereotypes and return to their own selves in the specific historical context of the time, revealing the self-value of Joanna's phenomenon to modern women.Keywords: star image, feminism, Kramers vs. Kramers, Hollywood
Procedia PDF Downloads 1031453 Digital Image Correlation Based Mechanical Response Characterization of Thin-Walled Composite Cylindrical Shells
Authors: Sthanu Mahadev, Wen Chan, Melanie Lim
Abstract:
Anisotropy dominated continuous-fiber composite materials have garnered attention in numerous mechanical and aerospace structural applications. Tailored mechanical properties in advanced composites can exhibit superiority in terms of stiffness-to-weight ratio, strength-to-weight ratio, low-density characteristics, coupled with significant improvements in fatigue resistance as opposed to metal structure counterparts. Extensive research has demonstrated their core potential as more than just mere lightweight substitutes to conventional materials. Prior work done by Mahadev and Chan focused on formulating a modified composite shell theory based prognosis methodology for investigating the structural response of thin-walled circular cylindrical shell type composite configurations under in-plane mechanical loads respectively. The prime motivation to develop this theory stemmed from its capability to generate simple yet accurate closed-form analytical results that can efficiently characterize circular composite shell construction. It showcased the development of a novel mathematical framework to analytically identify the location of the centroid for thin-walled, open cross-section, curved composite shells that were characterized by circumferential arc angle, thickness-to-mean radius ratio, and total laminate thickness. Ply stress variations for curved cylindrical shells were analytically examined under the application of centric tensile and bending loading. This work presents a cost-effective, small-platform experimental methodology by taking advantage of the full-field measurement capability of digital image correlation (DIC) for an accurate assessment of key mechanical parameters such as in-plane mechanical stresses and strains, centroid location etc. Mechanical property measurement of advanced composite materials can become challenging due to their anisotropy and complex failure mechanisms. Full-field displacement measurements are well suited for characterizing the mechanical properties of composite materials because of the complexity of their deformation. This work encompasses the fabrication of a set of curved cylindrical shell coupons, the design and development of a novel test-fixture design and an innovative experimental methodology that demonstrates the capability to very accurately predict the location of centroid in such curved composite cylindrical strips via employing a DIC based strain measurement technique. Error percentage difference between experimental centroid measurements and previously estimated analytical centroid results are observed to be in good agreement. The developed analytical modified-shell theory provides the capability to understand the fundamental behavior of thin-walled cylindrical shells and offers the potential to generate novel avenues to understand the physics of such structures at a laminate level.Keywords: anisotropy, composites, curved cylindrical shells, digital image correlation
Procedia PDF Downloads 3101452 Study on the Self-Location Estimate by the Evolutional Triangle Similarity Matching Using Artificial Bee Colony Algorithm
Authors: Yuji Kageyama, Shin Nagata, Tatsuya Takino, Izuru Nomura, Hiroyuki Kamata
Abstract:
In previous study, technique to estimate a self-location by using a lunar image is proposed. We consider the improvement of the conventional method in consideration of FPGA implementation in this paper. Specifically, we introduce Artificial Bee Colony algorithm for reduction of search time. In addition, we use fixed point arithmetic to enable high-speed operation on FPGA.Keywords: SLIM, Artificial Bee Colony Algorithm, location estimate, evolutional triangle similarity
Procedia PDF Downloads 5131451 Cinema and the Documentation of Mass Killings in Third World Countries: A Study of Selected African Films
Authors: Chijindu D. Mgbemere
Abstract:
Mass killing also known as genocide is the systematic killing of people from national, ethnic, or religious group, or an attempt to do so. The act has been there before 1948, when it was officially recognized for what it is. From then, the world has continued to witness genocide in diverse forms- negating different measures by the United Nations and its agencies to curb it. So far, all the studies and documentations on this subject are biased in favor of radio and the print. This paper therefore extended the interrogation of genocide, drumming its devastating effects, using the film medium; and in doing so devised innovative and pragmatic approach to genocide scholarship. It further centered attention on the factors and impacts of genocide, with a view to determine how effective film can be in such a study. The study is anchored on Bateson’s Framing Theory. Four films- Hotel Rwanda, Half of a Yellow Sun, Attack on Darfur, and sarafina, were analyzed, based on background, factors/causes, impacts, and development of genocide, via Content Analysis. The study discovered that: as other continents strive towards peace, acts of genocide are on the increase in African. Bloodletting stereotypes give Africa negative image in the global society. Difficult political frameworks, the trauma of postcolonial state, aggravated by ethnic and religious intolerance, and limited access to resources are responsible for high cases of genocide in Africa. The media, international communities, and peace agencies often abet other than prevent genocide or mass killings in Africa. High human casualty and displacement, children soldering, looting, hunger, rape, sex-slavery and abuse, mental and psychosomatic stress disorders are some of the impacts of genocide. Genocidaires are either condemned or killed. Grievances can be vented using civil resistance, negotiation, adjudication, arbitration, and mediation. The cinema is an effective means of studying and documenting genocide. Africans must factor the image laundering of their continent into consideration. Punishment of genocidaires without an attempt to de-radicalize them is counterproductive.Keywords: African film, genocide, framing theory, mass murder
Procedia PDF Downloads 1131450 Using the Dokeos Platform for Industrial E-Learning Solution
Authors: Kherafa Abdennasser
Abstract:
The application of Information and Communication Technologies (ICT) to the training area led to the creation of this new reality called E-learning. That last one is described like the marriage of multi- media (sound, image and text) and of the internet (diffusion on line, interactivity). Distance learning became an important totality for training and that last pass in particular by the setup of a distance learning platform. In our memory, we will use an open source platform named Dokeos for the management of a distance training of GPS called e-GPS. The learner is followed in all his training. In this system, trainers and learners communicate individually or in group, the administrator setup and make sure of this system maintenance.Keywords: ICT, E-learning, learning plate-forme, Dokeos, GPS
Procedia PDF Downloads 4731449 A Three-modal Authentication Method for Industrial Robots
Authors: Luo Jiaoyang, Yu Hongyang
Abstract:
In this paper, we explore a method that can be used in the working scene of intelligent industrial robots to confirm the identity information of operators to ensure that the robot executes instructions in a sufficiently safe environment. This approach uses three information modalities, namely visible light, depth, and sound. We explored a variety of fusion modes for the three modalities and finally used the joint feature learning method to improve the performance of the model in the case of noise compared with the single-modal case, making the maximum noise in the experiment. It can also maintain an accuracy rate of more than 90%.Keywords: multimodal, kinect, machine learning, distance image
Procedia PDF Downloads 73