Search results for: stereo-based digital image correlation

Authors: Yuanchao Sang, Zhihao Gong, Longsheng Chen, Long Chen

Abstract:

Clothing fashion represents a human’s aesthetic appreciation towards everyday outfits and appetite for fashion, and it reflects the development of status in society, humanity, and economics. However, modelling fashion by machine is extremely challenging because fashion is too abstract to be efficiently described by machines. Even human beings can hardly reach a consensus about fashion. In this paper, we are dedicated to answering a fundamental fashion-related problem: what image feature best describes clothing fashion? To address this issue, we have designed and evaluated various image features, ranging from traditional low-level hand-crafted features to mid-level style awareness features to various current popular deep neural network-based features, which have shown state-of-the-art performance in various vision tasks. In summary, we tested the following 9 feature representations: color, texture, shape, style, convolutional neural networks (CNNs), CNNs with distance metric learning (CNNs&DML), AutoEncoder, CNNs with multiple layer combination (CNNs&MLC) and CNNs with dynamic feature clustering (CNNs&DFC). Finally, we validated the performance of these features on two publicly available datasets. Quantitative and qualitative experimental results on both intra-domain and inter-domain fashion clothing image retrieval showed that deep learning based feature representations far outweigh traditional hand-crafted feature representation. Additionally, among all deep learning based methods, CNNs with explicit feature clustering performs best, which shows feature clustering is essential for discriminative fashion feature representation.

Keywords: convolutional neural network, feature representation, image processing, machine modelling

Procedia PDF Downloads 139

Authors: Dennis Schmickle

Abstract:

Introductory statement: Augmented reality (AR) can be used to breathe life into traditional graphic design media, such as posters, book covers, and album art. AR superimposes a unique image/video on a user’s view of the real world, which makes it more immersive and realistic than traditional 2D media. This study developed a series of projects that utilize both traditional and AR media to teach the fundamental principles of graphic design. The results of this study suggest that AR can be an effective tool for teaching graphic design. Abstract: Traditional graphic design media, such as posters, book covers, and album art, could be considered to be “old media.” However, augmented reality (AR) can breathe life into these formats by making them more interactive and engaging for students and audiences alike. AR is a technology that superimposes a computer-generated image on a user’s view of the real world. This allows users to interact with digital content in a way that is more immersive and interactive than traditional 2D media. AR is becoming increasingly popular, as more and more people have access to smartphones and other devices that can support AR experiences. This study is comprised of a series of projects that utilize both traditional and AR media to teach the fundamental principles of graphic design. In these projects, students learn to create traditional design objects, such as posters, book covers, and album art. However, they are also required to create an animated version of their design and to use AR software to create an AR experience with which viewers can interact. The results of this study suggest that AR can be an effective and exciting tool for teaching graphic design. The students who participated in the study were able to learn the fundamental principles of graphic design, and they also developed the skills they need to create effective AR content. This study has implications for the future of graphic design education. As AR becomes more popular, it is likely that it will become an increasingly important tool for teaching graphic design.

Keywords: graphic design, augmented reality, print media, new media, AR, old media

Procedia PDF Downloads 67

Authors: Donatella Giuliani

Abstract:

In this research, we propose an unsupervised grayscale image segmentation method based on a combination of the Firefly Algorithm and the Gaussian Mixture Model. Firstly, the Firefly Algorithm has been applied in a histogram-based research of cluster means. The Firefly Algorithm is a stochastic global optimization technique, centered on the flashing characteristics of fireflies. In this context it has been performed to determine the number of clusters and the related cluster means in a histogram-based segmentation approach. Successively these means are used in the initialization step for the parameter estimation of a Gaussian Mixture Model. The parametric probability density function of a Gaussian Mixture Model is represented as a weighted sum of Gaussian component densities, whose parameters are evaluated applying the iterative Expectation-Maximization technique. The coefficients of the linear super-position of Gaussians can be thought as prior probabilities of each component. Applying the Bayes rule, the posterior probabilities of the grayscale intensities have been evaluated, therefore their maxima are used to assign each pixel to the clusters, according to their gray-level values. The proposed approach appears fairly solid and reliable when applied even to complex grayscale images. The validation has been performed by using different standard measures, more precisely: the Root Mean Square Error (RMSE), the Structural Content (SC), the Normalized Correlation Coefficient (NK) and the Davies-Bouldin (DB) index. The achieved results have strongly confirmed the robustness of this gray scale segmentation method based on a metaheuristic algorithm. Another noteworthy advantage of this methodology is due to the use of maxima of responsibilities for the pixel assignment that implies a consistent reduction of the computational costs.

Keywords: clustering images, firefly algorithm, Gaussian mixture model, meta heuristic algorithm, image segmentation

Procedia PDF Downloads 217

Authors: Parisa Mansour

Abstract:

The coronavirus disease 2019 (COVID-19) was discovered and rapidly spread to various countries around the world since the end of 2019. Computed tomography (CT) images have been used as an important alternative to the time-consuming RT. PCR test. However, manual segmentation of CT images alone is a major challenge as the number of suspected cases increases. Thus, accurate and automatic segmentation of COVID-19 infections is urgently needed. Because the imaging features of the COVID-19 infection are different and similar to the background, existing medical image segmentation methods cannot achieve satisfactory performance. In this work, we try to build a deep convolutional neural network adapted for the segmentation of chest CT images with COVID-19 infections. First, we maintain a large and novel chest CT image database containing 165,667 annotated chest CT images from 861 patients with confirmed COVID-19. Inspired by the observation that the boundary of an infected lung can be improved by global intensity adjustment, we introduce a feature variable block into the proposed deep CNN, which adjusts the global features of features to segment the COVID-19 infection. The proposed PV array can effectively and adaptively improve the performance of functions in different cases. We combine features of different scales by proposing a progressive atrocious space pyramid fusion scheme to deal with advanced infection regions with various aspects and shapes. We conducted experiments on data collected in China and Germany and showed that the proposed deep CNN can effectively produce impressive performance.

Keywords: chest, COVID-19, chest Image, coronavirus, CT image, chest CT

Procedia PDF Downloads 57

Authors: Sebastian Oportus, Fabrizio Alvarez

Abstract:

3D digitalization of heritage objects is widely used nowadays. However, the most advanced 3D scanners in the market that capture topology and texture at the same time, and are specifically made for this purpose, don’t deliver the accuracy that is needed for scientific research. In the last three years, we have developed a method that combines the use of Metrologic grade laser scans, that allows us to work with a high accuracy topology up to 15 times more precise and combine this mesh with a texture obtained from high definition photogrammetry with up to 100 times more pixel concentrations. The result is an accurate digitalization that promotes heritage preservation, scientific study, high detail reproduction, and digital restoration, among others. In Chile, we have already performed 478 digitalizations of high-value heritage pieces and compared the results with up to five different digitalization methods; the results obtained show a considerable better dimensional accuracy and texture resolution. We know the importance of high precision and resolution for academics and museology; that’s why our proposal is to set a worldwide standard using this open source methodology.

Keywords: 3D digitalization, digital heritage, heritage preservation, digital restauration, heritage reproduction

Procedia PDF Downloads 188

Authors: Imam Taufik, Hilkatul Ilmi, Puryani, Mochammad Yuwono, Aty Widyawaruyanti

Abstract:

Artocarpus champeden Spreng stembark (Moraceae) in Indonesia well known as ‘cempedak’ had been traditionally used for malarial remedies. The difference of growth locations could cause the difference of metabolite profiling. As a consequence, there were difference antimalarial activities in spite of the same plants. The aim of this research was to obtain the profile of metabolites that contained in A. champeden stembark from different locations in Indonesia for authentication and quality control purpose of this extract. The profiling had been performed by HPTLC-Densitometry technique and antimalarial activity had been also determined by HRP2-ELISA technique. The correlation between metabolite fingerprinting and antimalarial activity had been analyzed by Principle Component Analysis, Hierarchical Clustering Analysis and Partial Least Square. As a result, there is correlation between the difference metabolite fingerprinting and antimalarial activity from several different growth locations.

Keywords: antimalarial, artocarpus champeden spreng, metabolite fingerprinting, multivariate analysis

Procedia PDF Downloads 311

Authors: B. N. Emenyeonu

Abstract:

Initially identified as sensationalism in the eras of yellow journalism and tabloidization, the inclusion of news which shocks or provokes strong emotional responses among readers, viewers, and browsers has not only remained a persistent feature of journalism but has also seemingly escalated in the current climate of digital and social media. Whether in the relentless revelation of scandals in high places, profiles on people displaced by sporadic wars or natural disasters, gruesome accounts of trucks plowing into pedestrians in a city centre, or the coverage of mourners paying tributes to victims of a mass shooting, mainstream, and digital media are often awash with tragedy, tears, and trauma. While it may aim at inspiring sympathy, outrage, or even remedial reactions, it would appear that the deluge of grief and misery in the news merely generates in the audience a feeling that borders on hearing or seeing too much to care or act. This feeling also appears to be accentuated by the dizzying diffusion of social media news and views, most of whose authenticity is not easily verifiable. Through a survey of 400 regular consumers of news and an in-depth interview of 10 news managers in selected media organizations across the Middle East, this study therefore investigates public attitude to the profusion of bad news in mainstream and digital media. Among other targets, it examines whether the profusion of bad news generates empathy fatigue among the audience and, if so, whether there is any association between biographic variables (profession, age, and gender) and an inclination to empathy fatigue. It also seeks to identify which categories of bad news and media are most likely to drag the audience into indifference. In conclusion, the study discusses the implications of the findings for mass-mediated advocacies such as campaigns against conflicts, corruption, nuclear threats, terrorism, gun violence, sexual crimes, and human trafficking, among other threats to humanity.

Keywords: digital media, empathy fatigue, media campaigns, news selection

Procedia PDF Downloads 58

Authors: Nikolaos Vassilas, Theocharis Tsenoglou, Djamchid Ghazanfarpour

Abstract:

In this work we explore the capability of the mean shift algorithm as a powerful preprocessing tool for improving the quality of spatial data, acquired from airborne scanners, from densely built urban areas. On one hand, high resolution image data corrupted by noise caused by lossy compression techniques are appropriately smoothed while at the same time preserving the optical edges and, on the other, low resolution LiDAR data in the form of normalized Digital Surface Map (nDSM) is upsampled through the joint mean shift algorithm. Experiments on both the edge-preserving smoothing and upsampling capabilities using synthetic RGB-z data show that the mean shift algorithm is superior to bilateral filtering as well as to other classical smoothing and upsampling algorithms. Application of the proposed methodology for 3D reconstruction of buildings of a pilot region of Athens, Greece results in a significant visual improvement of the 3D building block model.

Keywords: 3D buildings reconstruction, data fusion, data upsampling, mean shift

Procedia PDF Downloads 315

Authors: Ahmed A. Khamis, Sherif A. Ibrahim, Mahmoud El Khatieb, Mohamed A. Barakat

Abstract:

Parametric design is an icon of the modern architectural that facilitate taking complex design decisions counting on altering various design parameters. Double skin facades are one of the parametric applications for using parametric designs. This paper opts to enhance different daylight parameters of a selected case study office building in Cairo using parametric double skin facade. First, the design and optimization process executed utilizing Grasshopper parametric design software which is a plugin in rhino. The daylighting performance of the base case building model was compared with the one used the double façade showing an enhancement in daylighting performance indicators like glare and task illuminance in the modified model, execution drawings are made for the optimized design to be executed through Revit, followed by computerized digital fabrication stages of the designed model with various scales to reach the final design decisions using Simplify 3D for mock-up digital fabrication

Keywords: parametric design, double skin facades, digital fabrication, grasshopper, simplify 3D

Procedia PDF Downloads 118

Authors: Mohammad Esmaeilpour

Abstract:

One of the important open problems in the field of medical image processing is detection and quantification of small changes. In this poster, we try to investigate that, how the algebraic decomposition techniques can be used for semiautomatically detecting and quantifying subtle changes in Magnetic Resonance (MR) neuroimaging volumes. We mostly focus on the low-rank values of the matrices achieved from decomposing MR image pairs during a period of time. Besides, a skillful neuroradiologist will help the algorithm to distinguish between noises and small changes.

Keywords: magnetic resonance neuroimaging, subtle change detection and quantification, algebraic decomposition, basis functions

Procedia PDF Downloads 474

Authors: Mohammed Saeed Jawad

Abstract:

Metaverse involves the convergence of three major technologies trends of AI, VR, and AR. Together these three technologies can provide an entirely new channel for delivering healthcare with great potential to lower costs and improve patient outcomes on a larger scale. Telepresence is the technology that allows people to be together even if they are physically apart. Medical doctors can be symbolic as interactive avatars developed to have smart conversations and medical recommendations for patients at the different stages of the treatment. Medical digital assets such as Medical IoT for real-time remote healthcare monitoring as well as the symbolic doctors’ avatars as well as the hospital and clinical physical constructions and layout can be immersed in extended realities 3D metaverse environments where doctors, nurses, and patients can interact and socialized with the related digital assets that facilitate the data analytics of the sensed and collected personal medical data with visualized interaction of the digital twin of the patient’s body as well as the medical doctors' smart conversation and consultation or even in a guided remote-surgery operation.

Keywords: personal healthcare, metaverse, telemedicine, telepresence, avatar, medical consultation, remote-surgery

Procedia PDF Downloads 135

Authors: Mohammad A. U. Khan, Tariq M. Khan, Yinan Kong

Abstract:

Fingerprint image enhancement is one of the most important step in an automatic fingerprint identification recognition (AFIS) system which directly affects the overall efficiency of AFIS. The conventional fingerprint enhancement like Gabor and Anisotropic filters do fill the gaps in ridge lines but they fail to tackle scar lines. To deal with this problem we are proposing a method for enhancing the ridges and valleys with scar so that true minutia points can be extracted with accuracy. Our results have shown an improved performance in terms of enhancement.

Keywords: fingerprint image enhancement, removing noise, coherence, enhanced diffusion

Procedia PDF Downloads 515

Authors: Rominkumar Busa, Shahira K. C., Lijiya A.

Abstract:

Text recognition is an important area in computer vision which deals with detecting and recognising text from an image. The Optical Character Recognition (OCR) is a saturated area these days and with very good text recognition accuracy. However the same OCR methods when applied on text with small font sizes like the text data of chart images, the recognition rate is less than 30%. In this work, aims to extract small text in images using the deep learning model, CRNN with CTC loss. The text recognition accuracy is found to improve by applying image enhancement by super resolution prior to CRNN model. We also observe the text recognition rate further increases by 18% by applying the proposed method, which involves super resolution and character segmentation followed by CRNN with CTC loss. The efficiency of the proposed method shows that further pre-processing on chart image text and other small text images will improve the accuracy further, thereby helping text extraction from chart images.

Keywords: small text extraction, OCR, scene text recognition, CRNN

Procedia PDF Downloads 125

Authors: Tashinga Matindike

Abstract:

By means of definition, digital artworks encompass an array of artistic productions that are expressed in a technological form as an essential part of a creative process. Examples include illustrations, photos, videos, sculptures, and installations. Within the context of the visual arts, the process of repatriation involves the return of once-appropriated goods. Archiving denotes the preservation of a commodity for storage purposes in order to nurture its continuity. The aforementioned definitions form the foundation of the academic framework and premise of the argument, which is outlined in this paper. This paper aims to define, discuss and decipher the complexities involved in digitising artworks, whilst explaining the benefits of the process, particularly within the South African context, which is rich in tangible and intangible traditional cultural material, objects, and performances. With the internet having been introduced to the African Continent in the early 1990s, this new form of technology, in its own right, initiated a high degree of efficiency, which also resulted in the progressive transformation of computer-generated visual output. Subsequently, this caused a revolutionary influence on the manner in which technological software was developed and uterlised in art-making. Digital technology and the digitisation of creative processes then opened up new avenues of collating and recording information. One of the first visual artists to make use of digital technology software in his creative productions was United States-based artist John Whitney. His inventive work contributed greatly to the onset and development of digital animation. Comparable by technique and originality, South African contemporary visual artists who make digital artworks, both locally and internationally, include David Goldblatt, Katherine Bull, Fritha Langerman, David Masoga, Zinhle Sethebe, Alicia Mcfadzean, Ivan Van Der Walt, Siobhan Twomey, and Fhatuwani Mukheli. In conclusion, the main objective of this paper is to address the following questions: In which ways has the South African art community of visual artists made use of and benefited from technology, in its digital form, as a means to further advance creativity? What are the positive changes that have resulted in art production in South Africa since the onset and use of digital technological software? How has digitisation changed the manner in which we record, interpret, and archive both written and visual information? What is the role of South African art institutions in the development of digital technology and its use in the field of visual art. What role does digitisation play in the process of the repatriation of artworks and artefacts. The methodology in terms of the research process of this paper takes on a multifacted form, inclusive of data analysis of information attained by means of qualitative and quantitative approaches.

Keywords: digital art, digitisation, technology, archiving, transformation and repatriation

Procedia PDF Downloads 52

Authors: Halimatu S. Abdullahi, Ray E. Sheriff, Fatima Mahieddine

Abstract:

Agriculture is essential to the continuous existence of human life as they directly depend on it for the production of food. The exponential rise in population calls for a rapid increase in food with the application of technology to reduce the laborious work and maximize production. Technology can aid/improve agriculture in several ways through pre-planning and post-harvest by the use of computer vision technology through image processing to determine the soil nutrient composition, right amount, right time, right place application of farm input resources like fertilizers, herbicides, water, weed detection, early detection of pest and diseases etc. This is precision agriculture which is thought to be solution required to achieve our goals. There has been significant improvement in the area of image processing and data processing which has being a major challenge. A database of images is collected through remote sensing, analyzed and a model is developed to determine the right treatment plans for different crop types and different regions. Features of images from vegetations need to be extracted, classified, segmented and finally fed into the model. Different techniques have been applied to the processes from the use of neural network, support vector machine, fuzzy logic approach and recently, the most effective approach generating excellent results using the deep learning approach of convolution neural network for image classifications. Deep Convolution neural network is used to determine soil nutrients required in a plantation for maximum production. The experimental results on the developed model yielded results with an average accuracy of 99.58%.

Keywords: convolution, feature extraction, image analysis, validation, precision agriculture

Procedia PDF Downloads 315

Authors: Taeho Park, Ming Zhou, Sangryul Shim

Abstract:

With the emergence of the global economy, today’s business environment is getting more competitive than ever in the past. And many supply chain (SC) strategies and operations have significantly been altered over the past decade to overcome more complexities and risks imposed onto the global business. First, offshoring and outsourcing are more adopted as operational strategies. Manufacturing continues to move to better locations for enhancing competitiveness. Second, international operations are a challenge to a company’s SC system. Third, the products traded in the SC system are not just physical goods, but also digital goods (e.g., software, e-books, music, video materials). There are three main flows involved in fulfilling the activities in the SC system: physical flow, information flow, and financial flow. An advance of the Internet and electronic communication technologies has enabled companies to perform the flows of SC activities in electronic formats, resulting in the advent of an electronic supply chain management (e-SCM) system. A SC system for digital goods is somewhat different from the supply chain system for physical goods. However, it involves many similar or identical SC activities and flows. For example, like the production of physical goods, many third parties are also involved in producing digital goods for the production of components and even final products. This research aims at identifying process flows of both physical and digital goods in a SC system, and then investigating all risk elements involved in the physical, information, and financial flows during the fulfilment of SC activities. There are many risks inherent in the e-SCM system. Some risks may have severe impact on a company’s business, and some occur frequently but are not detrimental enough to jeopardize a company. Thus, companies should assess the impact and frequency of those risks, and then prioritize them in terms of their severity, frequency, budget, and time in order to be carefully maintained. We found risks involved in the global trading of physical and digital goods in four different categories: environmental risk, strategic risk, technological risk, and operational risk. And then the significance of those risks was investigated through a survey. The survey asked companies about the frequency and severity of the identified risks. They were also asked whether they had faced those risks in the past. Since the characteristics and supply chain flows of digital goods are varying industry by industry and country by country, it is more meaningful and useful to analyze risks by industry and country. To this end, more data in each industry sector and country should be collected, which could be accomplished in the future research.

Keywords: digital goods, e-SCM, risk analysis, supply chain flows

Procedia PDF Downloads 421

Authors: Jerickson Abbie Flores, Jana Fragante, Jan Paolo Dipasupil, Jan Jorge Francisco

Abstract:

Malnutrition is one of the rapidly growing health problems affecting the world at present. Children affected are not only at risk for significant health problems, but are also faced with psychological and social consequences, including low self-esteem. School-age children are specifically vulnerable to develop poor self-esteem especially when their peers find them physically unattractive. Thus, malnutrition, whether obesity or undernourishment, contributes a significant role to a developing child’s health and behavior. This research aims to determine if there is a significant difference on the level of self-esteem among Filipino children ages 9-12 years old with abnormal body mass index (BMI) and those children with desirable BMI. Using a cross-sectional study design, the correlation between body mass index (BMI) and self-esteem was observed among children ages 9-12 years old. Participants took the Hare self esteem questionnaire, which is specifically designed to measure self-esteem in school age children. The lowest possible score is 15 and the highest possible score is 45. A total of 1140 students with ages 9-12 years old from Cembo Elementary School (public school) participated in the study. Among the participants, 239 out of the 1140 have desirable body mass index, 878 are underweight, and 23 are overweight. Using the test questionnaire, the computed mean scores were 36.599, 36.045 and 36.583 for normal, underweight and overweight categories respectively. Using Pearson’s Correlation Test and Spearman’s Correlation Coefficient Test, the study showed positive correlation (p value of 0.047 and 0.004 respectively) between BMI and Self-esteem scores which indicates that the higher the BMI, the higher the self-esteem of the participants.

Keywords: body mass index, malnutrition, school-age children, self-esteem

Procedia PDF Downloads 280

Authors: Thomas Louis, Irina Primac, Florent Morfoisse, Tania Durre, Silvia Blacher, Agnes Noel

Abstract:

In vitro and in vivo lymphangiogenesis assays are essential for the identification of potential lymphangiogenic agents and the screening of pharmacological inhibitors. In the present study, we analyse three biological models: in vitro lymphatic endothelial cell spheroids, in vivo ear sponge assay, and in vivo lymph node colonisation by tumour cells. These assays provide suitable 3D models to test pro- and anti-lymphangiogenic factors or drugs. 3D images were acquired by confocal laser scanning and light sheet fluorescence microscopy. Virtual scan microscopy followed by 3D reconstruction by image aligning methods was also used to obtain 3D images of whole large sponge and ganglion samples. 3D reconstruction, image segmentation, skeletonisation, and other image processing algorithms are described. Fixed and time-lapse imaging techniques are used to analyse lymphatic endothelial cell spheroids behaviour. The study of cell spatial distribution in spheroid models enables to detect interactions between cells and to identify invasion hierarchy and guidance patterns. Global measurements such as volume, length, and density of lymphatic vessels are measured in both in vivo models. Branching density and tortuosity evaluation are also proposed to determine structure complexity. Those properties combined with vessel spatial distribution are evaluated in order to determine lymphangiogenesis extent. Lymphatic endothelial cell invasion and lymphangiogenesis were evaluated under various experimental conditions. The comparison of these conditions enables to identify lymphangiogenic agents and to better comprehend their roles in the lymphangiogenesis process. The proposed methodology is validated by its application on the three presented models.

Keywords: 3D image segmentation, 3D image skeletonisation, cell invasion, confocal microscopy, ear sponges, light sheet microscopy, lymph nodes, lymphangiogenesis, spheroids

Procedia PDF Downloads 377

Authors: Basan Shrestha

Abstract:

The relationship between the household size and the poverty is not well understood. Malthus followers advocate that the increasing population add pressure to the dwindling resource base due to increasing demand that would lead to poverty. Others claim that bigger households are richer due to availability of household labour for income generation activities. Facts from Nepal were analyzed to examine the relationship between the household size and poverty rate. The analysis of data from 3,968 Village Development Committee (VDC)/ municipality (MP) located in 75 districts of all five development regions revealed that the average household size had moderate positive correlation with the poverty rate (Karl Pearson's correlation coefficient=0.44). In a regression analysis, the household size determined 20% of the variation in the poverty rate. Higher positive correlation was observed in eastern Nepal (Karl Pearson's correlation coefficient=0.66). The regression analysis showed that the household size determined 43% of the variation in the poverty rate in east. The relation was poor in far-west. It could be because higher incidence of poverty was there irrespective of household size. Overall, the facts revealed that the bigger households were relatively poorer. With the increasing level of awareness and interventions for family planning, it is anticipated that the household size will decrease leading to the decreased poverty rate. In addition, the government needs to devise a mechanism to create employment opportunities for the household labour force to reduce poverty.

Keywords: household size, poverty rate, nepal, regional development

Procedia PDF Downloads 361

Authors: Ahmed Madian, Muaz Aljarhi

Abstract:

Coordinate Rotation Digital Computer (CORDIC) is a unique digital computing unit intended for the computation of mathematical operations and functions. This paper presents a multi-CORDIC processor that integrates different CORDIC architectures on a single FPGA chip and allows the user to select the CORDIC architecture to proceed with based on what he wants to calculate and his/her needs. Synthesis show that radix 2 CORDIC has the lowest clock delay, radix 8 CORDIC has the highest LUT usage and lowest register usage while Hybrid Radix 4 CORDIC had the highest clock delay.

Keywords: multi, CORDIC, FPGA, processor

Procedia PDF Downloads 470

Authors: Hussain Sajid, Jung-Hun Shin, Kum-Won Cho

Abstract:

Image super-resolution is the most common computer vision problem with many important applications. Generative adversarial networks (GANs) have promoted remarkable advances in single-image super-resolution (SR) by recovering photo-realistic images. However, high memory requirements of GAN-based SR (mainly generators) lead to performance degradation and increased energy consumption, making it difficult to implement it onto resource-constricted devices. To relieve such a problem, In this paper, we introduce an optimized and highly efficient architecture for SR-GAN (generator) model by utilizing model compression techniques such as Knowledge Distillation and pruning, which work together to reduce the storage requirement of the model also increase in their performance. Our method begins with distilling the knowledge from a large pre-trained model to a lightweight model using different loss functions. Then, iterative weight pruning is applied to the distilled model to remove less significant weights based on their magnitude, resulting in a sparser network. Knowledge Distillation reduces the model size by 40%; pruning then reduces it further by 18%. To accelerate the learning process, we employ the Horovod framework for distributed training on a cluster of 2 nodes, each with 8 GPUs, resulting in improved training performance and faster convergence. Experimental results on various benchmarks demonstrate that the proposed compressed model significantly outperforms state-of-the-art methods in terms of peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and image quality for x4 super-resolution tasks.

Keywords: single-image super-resolution, generative adversarial networks, knowledge distillation, pruning

Procedia PDF Downloads 96

Authors: Ahmed Abdelghany, Bernard Uguen, Christophe Moy, Dominique Lemur

Abstract:

The Internet of Things (IoT) is developed to ensure monitoring and connectivity within different applications. Thus, it is critical to study the channel propagation characteristics in Low Power Wide Area Network (LPWAN), especially Long Range Wide Area Network (LoRaWAN). In this paper, an in-depth investigation of the reciprocity between the uplink and downlink Channel State Information (CSI) is done by performing an outdoor measurement campaign in the area of Campus Beaulieu in Rennes. At each different location, the CSI reciprocity is quantified using the Pearson Correlation Coefficient (PCC) which shows a very high linear correlation between the uplink and downlink CSI. This reciprocity feature could be utilized for the physical layer security between the node and the gateway. On the other hand, most of the CSI shapes from different locations are highly uncorrelated from each other. Hence, it can be anticipated that this could achieve significant localization gain by utilizing the frequency hopping in the LoRa systems by getting access to a wider band.

Keywords: IoT, LPWAN, LoRa, effective signal power, onsite measurement

Procedia PDF Downloads 162

Authors: Armel Asongu Nkembi, Ahmad Fawad

Abstract:

The aim of this paper is to determine in a concise way the transfer function that characterizes a DC electrical motor with a helix. In practice it can be obtained by applying a particular input to the system and then, based on the observation of its output, determine an approximation to the transfer function of the system. In our case, we use a step input and find the transfer function parameters that give the simulated first-order time response. The simulation of the system is done using MATLAB/Simulink. In order to determine the parameters, we assume a first order system and use the Broida approximation to determine the parameters and then its Mean Square Error (MSE). Furthermore, we design a PID controller for the control process first in the continuous time domain and tune it using the Ziegler-Nichols open loop process. We then digitize the controller to obtain a digital controller since most systems are implemented using computers, which are digital in nature.

Keywords: transfer function, step input, MATLAB, Simulink, DC electrical motor, PID controller, open-loop process, mean square process, digital controller, Ziegler-Nichols

Procedia PDF Downloads 55

Authors: Nabilah Ibrahim, Khaliza Musa

Abstract:

The increment thickness of intima-media thickness (IMT) which involves the changes of diameter of the carotid artery is one of the early symptoms of the atherosclerosis lesion. The manual measurement of arterial diameter is time consuming and lack of reproducibility. Thus, this study reports the automatic approach to find the arterial diameter behavior for different gender, and body mass index (BMI) categories, focus on tracked region. BMI category is divided into underweight, normal, and overweight categories. Canny edge detection is employed to the B-mode image to extract the important information to be deal as the carotid wall boundary. The result shows the significant difference of arterial diameter between male and female groups which is 2.5% difference. In addition, the significant result of differences of arterial diameter for BMI category is the decreasing of arterial diameter proportional to the BMI.

Keywords: B-mode Ultrasound Image, carotid artery diameter, canny edge detection, body mass index

Procedia PDF Downloads 444

Authors: Jonathan Sohn

Abstract:

Deep neural networks (DNNs) have shown state-of-the-art performance for many applications, including computer vision, natural language processing, and speech recognition. Recently, adversarial attacks have been studied in the context of deep neural networks, which aim to alter the results of deep neural networks by modifying the inputs slightly. For example, an adversarial attack on a DNN used for object detection can cause the DNN to miss certain objects. As a result, the reliability of DNNs is undermined by their lack of robustness against adversarial attacks, raising concerns about their use in safety-critical applications such as autonomous driving. In this paper, we focus on studying the adversarial attacks and defenses on DNNs for image classification. There are two types of adversarial attacks studied which are fast gradient sign method (FGSM) attack and projected gradient descent (PGD) attack. A DNN forms decision boundaries that separate the input images into different categories. The adversarial attack slightly alters the image to move over the decision boundary, causing the DNN to misclassify the image. FGSM attack obtains the gradient with respect to the image and updates the image once based on the gradients to cross the decision boundary. PGD attack, instead of taking one big step, repeatedly modifies the input image with multiple small steps. There is also another type of attack called the target attack. This adversarial attack is designed to make the machine classify an image to a class chosen by the attacker. We can defend against adversarial attacks by incorporating adversarial examples in training. Specifically, instead of training the neural network with clean examples, we can explicitly let the neural network learn from the adversarial examples. In our experiments, the digit recognition accuracy on the MNIST dataset drops from 97.81% to 39.50% and 34.01% when the DNN is attacked by FGSM and PGD attacks, respectively. If we utilize FGSM training as a defense method, the classification accuracy greatly improves from 39.50% to 92.31% for FGSM attacks and from 34.01% to 75.63% for PGD attacks. To further improve the classification accuracy under adversarial attacks, we can also use a stronger PGD training method. PGD training improves the accuracy by 2.7% under FGSM attacks and 18.4% under PGD attacks over FGSM training. It is worth mentioning that both FGSM and PGD training do not affect the accuracy of clean images. In summary, we find that PGD attacks can greatly degrade the performance of DNNs, and PGD training is a very effective way to defend against such attacks. PGD attacks and defence are overall significantly more effective than FGSM methods.

Keywords: deep neural network, adversarial attack, adversarial defense, adversarial machine learning

Procedia PDF Downloads 194

Authors: Lakshay Kharbanda, Aabhas Chauhan

Abstract:

In this paper, an application of Normalized Compression Distance (NCD) to detect notable scene alterations occurring in videos is presented. Several research groups have been developing methods to perform image classification using NCD, a computable approximation to Normalized Information Distance (NID) by studying the degree of similarity in images. The timeframes where significant aberrations between the frames of a video have occurred have been identified by obtaining a threshold NCD value, using two compressors: LZMA and BZIP2 and defining scene alterations using Pixel Difference Percentage metrics.

Keywords: image compression, Kolmogorov complexity, normalized compression distance, root mean square error

Procedia PDF Downloads 340

Authors: R. Nandhini, Gaurab Mudbhari

Abstract:

Ranging from the field of health care to self-driving cars, machine learning and deep learning algorithms have revolutionized the field with the proper utilization of images and visual-oriented data. Segmentation, regression, classification, clustering, dimensionality reduction, etc., are some of the Machine Learning tasks that helped Machine Learning and Deep Learning models to become state-of-the-art models for the field where images are key datasets. Among these tasks, classification and clustering are essential but difficult because of the intricate and high-dimensional characteristics of image data. This finding examines and assesses advanced techniques in supervised classification and unsupervised clustering for image datasets, emphasizing the relative efficiency of Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), Deep Embedded Clustering (DEC), and self-supervised learning approaches. Due to the distinctive structural attributes present in images, conventional methods often fail to effectively capture spatial patterns, resulting in the development of models that utilize more advanced architectures and attention mechanisms. In image classification, we investigated both CNNs and ViTs. One of the most promising models, which is very much known for its ability to detect spatial hierarchies, is CNN, and it serves as a core model in our study. On the other hand, ViT is another model that also serves as a core model, reflecting a modern classification method that uses a self-attention mechanism which makes them more robust as this self-attention mechanism allows them to lean global dependencies in images without relying on convolutional layers. This paper evaluates the performance of these two architectures based on accuracy, precision, recall, and F1-score across different image datasets, analyzing their appropriateness for various categories of images. In the domain of clustering, we assess DEC, Variational Autoencoders (VAEs), and conventional clustering techniques like k-means, which are used on embeddings derived from CNN models. DEC, a prominent model in the field of clustering, has gained the attention of many ML engineers because of its ability to combine feature learning and clustering into a single framework and its main goal is to improve clustering quality through better feature representation. VAEs, on the other hand, are pretty well known for using latent embeddings for grouping similar images without requiring for prior label by utilizing the probabilistic clustering method.

Keywords: machine learning, deep learning, image classification, image clustering

Procedia PDF Downloads 8

Authors: Muhammad Ashfaq

Abstract:

Main theme: This prime focus of this study is on the role of digital technology in crime prevention, with special focus on Cellular Forensic Unit, Capital City Police Peshawar-Khyber Pakhtunkhwa-Pakistan. Objective(s) of the study: The prime objective of this study is to provide statistics, strategies, and pattern of analysis used for crime prevention in Cellular Forensic Unit of Capital City Police Peshawar, Khyber Pakhtunkhwa-Pakistan. Research Method and Procedure: Qualitative method of research has been used in the study for obtaining secondary data from research wing and Information Technology (IT) section of Peshawar police. Content analysis was the method used for the conduction of the study. This study is delimited to Capital City Police and Cellular Forensic Unit Peshawar-KP, Pakistan. information technologies. Major finding(s): It is evident that the old traditional approach will never provide solutions for better management in controlling crimes. The best way to control crimes and promotion of proactive policing is to adopt new technologies. The study reveals that technology have transformed police more effective and vigilant as compared to traditional policing. The heinous crimes like abduction, missing of an individual, snatching, burglaries, and blind murder cases are now traceable with the help of technology. Recommendation(s): From the analysis of the data, it is reflected that Information Technology (IT) expert should be recruited along with research analyst to timely assist and facilitate operational as well as investigation units of police. A mobile locator should be Provided to Cellular Forensic Unit to timely apprehend the criminals. Latest digital analysis software should be provided to equip the Cellular Forensic Unit.

Keywords: criminology-pakistan, crime prevention-KP, digital forensics, digital technology-pakistan

Procedia PDF Downloads 97

Authors: Chika Ethel Esege

Abstract:

Electronic learning is learning facilitated by technology which has basically altered approaches globally, including the field of education. This trend is compelling educators to focus on approaches that improve classroom practices in order to enhance students’ learning and participation in a global digital society. However, e-learning is not fully utilized across subject disciplines particularly in the field of humanities, in the context of Nigerian secondary education. This study focused on the use of e-learning to enhance the development of digital skills, particularly, collaboration and communication in secondary school students in Nigeria. The study adopted an ‘action research’ involving 210 students and 7 teachers, who utilised the e-learning platform designed by the researcher for the survey. Mixed methods- qualitative and quantitative- were used for data collection including questionnaire, observation, interview, and analysis of statutory documents. The data were presented using frequency counts for questionnaire responses and figures of screenshots for learning tasks. The VOD Burner software was also used to analyse interviews and video recordings. The study showed that the students acquired collaboration and communication skills through e-learning intervention lesson, and demonstrated satisfaction with this approach. However, the study further revealed that the traditional teaching approach could not provide digital education or develop the digital skills of the students. Based on these findings, recommendations were made that the Nigerian Government should incorporate digital content across subject disciplines into secondary school education curricular and provide adequate infrastructure in order to enable educators to adopt relevant approaches necessary for the enhancement of students’ learning especially in a technologically evolving and advancing world.

Keywords: developing collaboration and communication skills, electronic learning, improving classroom teaching, secondary schools in Nigeria

Procedia PDF Downloads 134

Authors: A. Ikhlef

Abstract:

Image noise in computed tomography, is mainly caused by the statistical noise, system noise reconstruction algorithm filters. Since last few years, low dose x-ray imaging became more and more desired and looked as a technical differentiating technology among CT manufacturers. In order to achieve this goal, several technologies and techniques are being investigated, including both hardware (integrated electronics and photon counting) and software (artificial intelligence and machine learning) based solutions. From a hardware point of view, electronic noise could indeed be a potential driver for low and ultra-low dose imaging. We demonstrated that the reduction or elimination of this term could lead to a reduction of dose without affecting image quality. Also, in this study, we will show that we can achieve this goal using conventional electronics (low cost and affordable technology), designed carefully and optimized for maximum detective quantum efficiency. We have conducted the tests using large imaging objects such as 30 cm water and 43 cm polyethylene phantoms. We compared the image quality with conventional imaging protocols with radiation as low as 10 mAs (<< 1 mGy). Clinical validation of such results has been performed as well.

Keywords: computed tomography, electronic noise, scintillation detector, x-ray detector

Procedia PDF Downloads 126