Search results for: depth images

Authors: Shaira L. Kee, Michael Aaron G. Sy, Myles Joshua T. Tan, Hezerul Abdul Karim, Nouar AlDahoul

Abstract:

Skin diseases are considered the fourth most common disease, with melanoma and non-melanoma skin cancer as the most common type of cancer in Caucasians. The alarming increase in Skin Cancer cases shows an urgent need for further research to improve diagnostic methods, as early diagnosis can significantly improve the 5-year survival rate. Machine Learning algorithms for image pattern analysis in diagnosing skin lesions can dramatically increase the accuracy rate of detection and decrease possible human errors. Several studies have shown the diagnostic performance of computer algorithms outperformed dermatologists. However, existing methods still need improvements to reduce diagnostic errors and generate efficient and accurate results. Our paper proposes an ensemble method to classify dermoscopic images into benign and malignant skin lesions. The experiments were conducted using the International Skin Imaging Collaboration (ISIC) image samples. The dataset contains 3,297 dermoscopic images with benign and malignant categories. The results show improvement in performance with an accuracy of 88% and an F1 score of 87%, outperforming other existing models such as support vector machine (SVM), Residual network (ResNet50), EfficientNetB0, EfficientNetB4, and VGG16.

Keywords: deep learning - VGG16 - efficientNet - CNN – ensemble – dermoscopic images - melanoma

Procedia PDF Downloads 71

Authors: Pongsawee Supanonth

Abstract:

This research is the study of Spectrum Management and the increase in efficiency of Spectrum Utilization. It also proves that Cognitive Radio is a newer technology that will change the face of e-communications network today. This study used qualitative research methods by using in-depth interviews to collect data from a sample specific to those who work in Radio channel from 6 key informant and literature review from the related documents in online database. The result is the technique of Dynamic Spectrum Allocation that is the most suitable for Thailand. We conduct in-depth research for future purposes. Moreover, we can also develop a model that can be used in regulating and managing spectrum that is most suitable for Thailand. And also develop an important tool which can be of importance to allocation of spectrum as a natural resource appropriately. It will also guarantee quality and high benefit in a substantial way.

Keywords: cognitive radio, management of radio spectrum, spectrum management, spectrum scarcity

Procedia PDF Downloads 302

Authors: U. Ravi Babu, Mohd Mastan

Abstract:

The present paper proposes a novel approach for handwritten digit recognition system. The present paper extract digit image features based on distance measure and derives an algorithm to classify the digit images. The distance measure can be performing on the thinned image. Thinning is the one of the preprocessing technique in image processing. The present paper mainly concentrated on an extraction of features from digit image for effective recognition of the numeral. To find the effectiveness of the proposed method tested on MNIST database, CENPARMI, CEDAR, and newly collected data. The proposed method is implemented on more than one lakh digit images and it gets good comparative recognition results. The percentage of the recognition is achieved about 97.32%.

Keywords: handwritten digit recognition, distance measure, MNIST database, image features

Procedia PDF Downloads 448

Authors: Ping Bo, Meng Yunshan

Abstract:

Satellite-derived sea surface temperature (SST) is a key parameter for many operational and scientific applications. However, the disadvantage of SST data is a high percentage of missing data which is mainly caused by cloud coverage. Data Interpolating Empirical Orthogonal Function (DINEOF) algorithm is an EOF-based technique for reconstructing the missing data and has been widely used in oceanographic field. The reconstruction of SST images within a long time series using DINEOF can cause large discontinuities and one solution for this problem is to filter the temporal covariance matrix to reduce the spurious variability. Based on the previous researches, an algorithm is presented in this paper to improve the temporal correlations in EOF expansion. Similar with the previous researches, a filter, such as Laplacian filter, is implemented on the temporal covariance matrix, but the temporal relationship between two consecutive images which is used in the filter is considered in the presented algorithm, for example, two images in the same season are more likely correlated than those in the different seasons, hence the latter one is less weighted in the filter. The presented approach is tested for the monthly nighttime 4-km Advanced Very High Resolution Radiometer (AVHRR) Pathfinder SST for the long-term period spanning from 1989 to 2006. The results obtained from the presented algorithm are compared to those from the original DINEOF algorithm without filtering and from the DINEOF algorithm with filtering but without taking temporal relationship into account.

Keywords: data interpolating empirical orthogonal function, image reconstruction, sea surface temperature, temporal filter

Procedia PDF Downloads 318

Authors: Sedat Aktas, Egemen Ulusoy, Remzi Yildirim

Abstract:

This article explains how to get a ram image from a computer with a Linux operating system and what steps should be followed while getting it. What we mean by taking a ram image is the process of dumping the physical memory instantly and writing it to a file. This process can be likened to taking a picture of everything in the computer’s memory at that moment. This process is very important for tools that analyze ram images. Volatility can be given as an example because before these tools can analyze ram, images must be taken. These tools are used extensively in the forensic world. Forensic, on the other hand, is a set of processes for digitally examining the information on any computer or server on behalf of official authorities. In this article, the protected mode architecture in the Linux operating system is examined, and the way to save the image sample of the kernel driver and system memory to disk is followed. Tables and access methods to be used in the operating system are examined based on the basic architecture of the operating system, and the most appropriate methods and application methods are transferred to the article. Since there is no article directly related to this study on Linux in the literature, it is aimed to contribute to the literature with this study on obtaining ram images. LIME can be mentioned as a similar tool, but there is no explanation about the memory dumping method of this tool. Considering the frequency of use of these tools, the contribution of the study in the field of forensic medicine has been the main motivation of the study due to the intense studies on ram image in the field of forensics.

Keywords: linux, paging, addressing, ram-image, memory dumping, kernel modules, forensic

Procedia PDF Downloads 94

Authors: G. Balakrishnan

Abstract:

Stereo Correspondence plays a major role in estimation of distance of an object from the stereo camera pair for various applications. In this paper, a stereo correspondence algorithm based on block-matching technique is presented. Initially, an energy matrix is calculated for every disparity obtained using modified Sum of Absolute Difference (SAD). Higher energy matrix errors are removed by using threshold value in order to reduce the mismatch errors. A smoothening filter is applied to eliminate unreliable disparity estimate across the object boundaries. The purpose is to improve the reliability of calculation of disparity map. The experimental results obtained shows that the final depth map produce better results and can be used to all the applications using stereo cameras.

Keywords: stereo matching, filters, energy matrix, disparity

Procedia PDF Downloads 205

Authors: Y. Fekir, K. Mederbal, M. A. Hammadouche, D. Anteur

Abstract:

The cultural park of the Ahaggar, occupying a large area of Algeria, is characterized by a rich wetlands area to be preserved and managed both in time and space. The management of a large area, by its complexity, needs large amounts of data, which for the most part, are spatially localized (DEM, satellite images and socio-economic information...), where the use of conventional and traditional methods is quite difficult. The remote sensing, by its efficiency in environmental applications, became an indispensable solution for this kind of studies. Remote sensing imaging data have been very useful in the last decade in very interesting applications. They can aid in several domains such as the detection and identification of diverse wetland surface targets, topographical details, and geological features... In this work, we try to extract automatically wetlands area using multispectral remotely sensed data on-board the Earth Observing 1 (EO-1) and Landsat satellite. Both are high-resolution multispectral imager with a 30 m resolution. The instrument images an interesting surface area. We have used images acquired over the several area of interesting in the National Park of Ahaggar in the south of Algeria. An Extraction Algorithm is applied on the several spectral index obtained from combination of different spectral bands to extract wetlands fraction occupation of land use. The obtained results show an accuracy to distinguish wetlands area from the other lad use themes using a fine exploitation on spectral index.

Keywords: multispectral data, EO1, landsat, wetlands, Ahaggar, Algeria

Procedia PDF Downloads 366

Authors: W. R. M. Shehani Shanika

Abstract:

Selling goods and services using images, names and personalities of celebrities has become a common marketing strategy identified in modern physical and online markets. Two concepts called globalization and open economy have given numerous reasons to develop businesses to earn higher profits. Therefore, global market plus domestic markets in various countries have vigorously endorsing images of famous sport stars, film stars, singing stars and cartoon characters for the purpose of increasing demand for goods and services rendered by them. It has been evident that these trade strategies have become a threat to famous personalities in financially and personally. Right to the image is a basic human right which celebrities owned to avoid themselves from various commercial exploitations. In this respect, this paper aims to assess whether the law relating to character merchandising satisfactorily protects right to image of celebrities. However, celebrities can decide how much they receive for each representation to the general public. Simply they have exclusive right to decide monetary value for their image. But most commonly every country uses law relating to unfair competition to regulate matters arise thereof. Legal norms in unfair competition are not enough to protect image of celebrities. Therefore, celebrities must be able to avoid unauthorized use of their images for commercial purposes by fraudulent traders and getting unjustly enriched, as their images have economic value. They have the right for use their image for any commercial purpose and earn profits. Therefore it is high time to recognize right to image as a new dimension to be protected in the legal framework of character merchandising. Unfortunately, to the author’s best knowledge there are no any uniform, single international standard which recognizes right to the image of celebrities in the context of character merchandising. The paper identifies it as a controversial legal barrier faced by celebrities in the rapidly evolving marketplace. Finally, this library-based research concludes with proposals to ensure the right to image more broadly in the legal context of character merchandising.

Keywords: brand endorsement, celebrity, character merchandising, intellectual property rights, right to image, unfair competition

Procedia PDF Downloads 128

Authors: Sunday Oladele, Joseph Oluwagbeja Simeon

Abstract:

Subsurface exploration, integrating methods of geotechnics and geophysics, of a planned construction site in the coastal city of Lagos, Nigeria has been carried out with the aim of characterizing the soil properties and their implication for the proposed infrastructural development. Six Standard Penetration Tests (SPT), fourteen Dutch Cone Penetrometer Tests (DCPT) and 2D Electrical Resistivity Imaging employing Dipole-dipole and Pole-dipole arrays were implemented on the site. The topsoil (0 - 4m) consists of highly compacted sandy lateritic clay(10 to 5595Ωm) to 1.25m in some parts and dense sand in other parts to 5.50m depth. This topsoil was characterized as a material of very high shear strength (≤ 150kg/m2) and allowable bearing pressure value of 54kN/m2 to 85kN/m2 and a safety factor of 2.5. Soft amorphous peat/peaty clay (0.1 to 11.4Ωm), 3-6m thick, underlays the lateritic clay to about 18m depth. Grey, medium dense to very dense sand (0.37 to 2387Ωm) with occasional gravels underlies the peaty clay down to 30m depth. Within this layer, the freshwater bearing zones are characterized by high resistivity response (83 to 2387Ωm), while the clayey sand/saline water intruded sand produced subdued resistivity output (0.37 to 40Ωm). The overall ground-bearing pressure for the proposed structure would be 225kN/m2. Bored/cast-in-place pile at 18.00m depth with any of these diameters and respective safe working loads 600mm/1,140KN, 800mm/2,010KN and 1000mm/3,150KN is recommended for the proposed multi-story structure.

Keywords: subsurface exploration, Geotechnical properties, resistivity imaging, pile

Procedia PDF Downloads 76

Authors: Ankit Kamboj, Shikha Talwar, Nilesh Powar

Abstract:

To successfully deliver our products in the market, the employees need to be in a safe environment, especially in an industrial and manufacturing environment. The consequences of delinquency in wearing safety glasses while working in industrial plants could be high risk to employees, hence the need to develop a real-time automatic detection system which detects the persons (violators) not wearing safety glasses. In this study a convolutional neural network (CNN) algorithm called faster region based CNN (Faster RCNN) with rotated bounding box has been used for detecting safety glasses on persons; the algorithm has an advantage of detecting safety glasses with different orientation angles on the persons. The proposed method of rotational bounding boxes with a convolutional neural network first detects a person from the images, and then the method detects whether the person is wearing safety glasses or not. The video data is captured at the entrance of restricted zones of the industrial environment (manufacturing plant), which is further converted into images at 2 frames per second. In the first step, the CNN with pre-trained weights on COCO dataset is used for person detection where the detections are cropped as images. Then the safety goggles are labelled on the cropped images using the image labelling tool called roLabelImg, which is used to annotate the ground truth values of rotated objects more accurately, and the annotations obtained are further modified to depict four coordinates of the rectangular bounding box. Next, the faster RCNN with rotated bounding box is used to detect safety goggles, which is then compared with traditional bounding box faster RCNN in terms of detection accuracy (average precision), which shows the effectiveness of the proposed method for detection of rotatory objects. The deep learning benchmarking is done on a Dell workstation with a 16GB Nvidia GPU.

Keywords: CNN, deep learning, faster RCNN, roLabelImg rotated bounding box, safety goggle detection

Procedia PDF Downloads 121

Authors: J. Sharib, D. N. A. Tugi, M. T. Ishak, M. I. A. Adziz

Abstract:

The main purpose of this research paper conducted was to study the penetration of ⁷Be onto the soil surface for two different seasons in different areas of agricultural activity. The study was conducted during the dry and wet seasons from January to May 2019 in the Sembrong catchment area. The Sembrong Catchment Area is located in the district of Kluang, Johor in the South of Peninsular Malaysia and was selected based on the small size of the catchment and surrounded by various agricultural activities. A total of twenty (20) core soil samples to a depth of 10 cm each were taken using a metal corer made of metal. All these samples were brought to the Radiochemistry and Environment Group (RAS), Nuclear Malaysia, Block 23, Bangi, Malaysia, to enable the preparation, drying and analysis work to be carried out. Furthermore, all samples were oven dried at 45 – 60 ºC so that the dry weight became constant and gently disaggregated. Lastly, dried samples were milled and sieved at 2 mm before being packed into a well-type container and ready for ⁷Be analysis. The result of the analysis shows that the penetration of ⁷Be into the soil surface decreases by an exponential decay. The distribution of profiles to the interior of the soil surface or ho values ranged from 1.56 to 3.62 kg m⁻² and from 2.59 to 4.17 kg m⁻² for both dry and wet seasons. Consequently, the dry season has given a lower ho value when compared to the wet season. In conclusion, ⁷Be is a very suitable tracer to be used in determining the penetration onto the soil surface or ho values for the two different seasons.

Keywords: depth penetration, dry season, wet season, sembrong catchment, well type container

Procedia PDF Downloads 112

Authors: Jonathan Gong

Abstract:

Purpose AI-driven solutions are at the forefront of many pathology and medical imaging methods. Using algorithms designed to better the experience of medical professionals within their respective fields, the efficiency and accuracy of diagnosis can improve. In particular, X-rays are a fast and relatively inexpensive test that can diagnose diseases. In recent years, X-rays have not been widely used to detect and diagnose COVID-19. The under use of Xrays is mainly due to the low diagnostic accuracy and confounding with pneumonia, another respiratory disease. However, research in this field has expressed a possibility that artificial neural networks can successfully diagnose COVID-19 with high accuracy. Models and Data The dataset used is the COVID-19 Radiography Database. This dataset includes images and masks of chest X-rays under the labels of COVID-19, normal, and pneumonia. The classification model developed uses an autoencoder and a pre-trained convolutional neural network (DenseNet201) to provide transfer learning to the model. The model then uses a deep neural network to finalize the feature extraction and predict the diagnosis for the input image. This model was trained on 4035 images and validated on 807 separate images from the ones used for training. The images used to train the classification model include an important feature: the pictures are cropped beforehand to eliminate distractions when training the model. The image segmentation model uses an improved U-Net architecture. This model is used to extract the lung mask from the chest X-ray image. The model is trained on 8577 images and validated on a validation split of 20%. These models are calculated using the external dataset for validation. The models’ accuracy, precision, recall, f1-score, IOU, and loss are calculated. Results The classification model achieved an accuracy of 97.65% and a loss of 0.1234 when differentiating COVID19-infected, pneumonia-infected, and normal lung X-rays. The segmentation model achieved an accuracy of 97.31% and an IOU of 0.928. Conclusion The models proposed can detect COVID-19, pneumonia, and normal lungs with high accuracy and derive the lung mask from a chest X-ray with similarly high accuracy. The hope is for these models to elevate the experience of medical professionals and provide insight into the future of the methods used.

Keywords: artificial intelligence, convolutional neural networks, deep learning, image processing, machine learning

Procedia PDF Downloads 116

Authors: E. K. Naseela, B. M. Dodamani, Chaithra Chandran

Abstract:

The GIS and remote sensing techniques facilitate accurate estimation of surface runoff from watershed. In the present study an attempt has been made to evaluate the applicability of Natural Resources Service Curve Number method using GIS and Remote sensing technique in the upper Krishna basin (69,425 Sq.km). Landsat 7 (with resolution 30 m) satellite data for the year 2012 has been used for the preparation of land use land cover (LU/LC) map. The hydrologic soil group is mapped using GIS platform. The weighted curve numbers (CN) for all the 5 subcatchments calculated on the basis of LU/LC type and hydrologic soil class in the area by considering antecedent moisture condition. Monthly rainfall data was available for 58 raingauge stations. Overlay technique is adopted for generating weighted curve number. Results of the study show that land use changes determined from satellite images are useful in studying the runoff response of the basin. The results showed that there is no significant difference between observed and estimated runoff depths. For each subcatchment, statistically positive correlations were detected between observed and estimated runoff depth (0.6Keywords: curve number, GIS, remote sensing, runoff

Procedia PDF Downloads 523

Authors: Anshika Kankane, Dongshik Kang

Abstract:

Marine debris has a significant influence on coastal environments, damaging biodiversity, and causing loss and damage to marine and ocean sector. A functional cost-effective and automatic approach has been used to look up at this problem. Computer vision combined with a deep learning-based model is being proposed to identify and categorize marine debris of seven kinds on different beach locations of Japan. This research compares state-of-the-art deep learning models with a suggested model architecture that is utilized as a feature extractor for debris categorization. The model is being proposed to detect seven categories of litter using a manually constructed debris dataset, with the help of Mask R-CNN for instance segmentation and a shape matching network called HOGShape, which can then be cleaned on time by clean-up organizations using warning notifications of the system. The manually constructed dataset for this system is created by annotating the images taken by fixed KaKaXi camera using CVAT annotation tool with seven kinds of category labels. A pre-trained HOG feature extractor on LIBSVM is being used along with multiple templates matching on HOG maps of images and HOG maps of templates to improve the predicted masked images obtained via Mask R-CNN training. This system intends to timely alert the cleanup organizations with the warning notifications using live recorded beach debris data. The suggested network results in the improvement of misclassified debris masks of debris objects with different illuminations, shapes, viewpoints and litter with occlusions which have vague visibility.

Keywords: computer vision, debris, deep learning, fixed live camera images, histogram of gradients feature extractor, instance segmentation, manually annotated dataset, multiple template matching

Procedia PDF Downloads 92

Authors: Rebone E. Mashapa, Phesheya E. Dlamini, Sandile S. Mthimkhulu

Abstract:

Woody plant encroachment, a land cover transformation that reduces grassland productivity may influence soil physical properties. The objective of the study was to determine the effect of woody plant encroachment on physical properties of vertic soils in a savanna grassland. In this study, we quantified and compared soil bulk density, aggregate stability and porosity in the top and subsoil of an open and woody encroached savanna grassland. The results revealed that soil bulk density increases, while porosity and mean weight diameter decreases with depth in both open and woody encroached grassland soil. Compared to open grassland, soil bulk density was 11% and 10% greater in the topsoil and subsoil, while porosity was 6% and 9% lower in the topsoil and subsoil of woody encroached grassland. Mean weight diameter, an indicator of soil aggregation increased by 38% only in the subsoil of encroached grasslands due to increasing clay content with depth. These results suggest that woody plant encroachment leads to compaction of vertic soils, which in turn reduces pore size distribution.

Keywords: soil depth, soil physical properties, vertic soils, woody plant encroachment

Procedia PDF Downloads 132

Authors: Bilha Paryente, Roni Gez Langerman

Abstract:

Background and Objectives: The current study focused on how kindergarten children have experienced the COVID-19 pandemic. The main goals were understanding children’s emotions, coping strategies, and thoughts regarding the presence of the COVID-19 virus in their daily lives, using the salute genic approach to study their sense of coherence, and to promote relevant professional instruction. Design and Method: Semistructured in-depth interviews were held with 130 five- to six-year-old children, with an equal number of boys and girls. All of the children were recruited from kindergartens affiliated with the state's secular education system. Results: Data were structured into three themes: 1) the child’s pandemic perception as manageable through meaningful accompanying and missing figures; 2) the child’s comprehension of the virus as dangerous, age differentiating, and contagious. 3) the child’s emotional processing of the pandemic as arousing fear of death and, through images, as thorny and as a monster. Conclusions: Results demonstrate the young children’s sense of coherence, characterized as extrapersonal perception, interpersonal coping, and intrapersonal emotional processing, and the need for greater acknowledgement of child-parent educators' informed interventions that could give children a partial feeling of the adult’s awareness of their needs.

Keywords: kindergarten children, continuous stress, COVID-19, salutogenic approach

Procedia PDF Downloads 167

Authors: Amina Sultan, Mohamed Ghonim, Eman Oweida, Aya Abdelaziz

Abstract:

Objective: To assess the diagnostic reliability of multi-detector CT in pre and post-operative evaluation of cochlear implant candidates. Material and Methods: The study includes 40 patients (18 males and 22 females); mean age 5.6 years. They were classified into two groups: Group A (20 patients): cochlear implant device was Nucleus-22 and Group B (20 patients): the device was MED-EL. Cochlear length (CL) and cochlear height (CH) were measured pre-operatively by 128-multidetector CT. Electrode length (EL) and insertion depth angle (α) were measured post-operatively by MDCT. Results: For Group A mean CL was 9.1 mm ± 0.4 SD; mean CH was 4.1 ± 0.3 SD; mean EL was 18 ± 2.7 SD; mean α angle was 299.05 ± 37 SD. Significant statistical correlation (P < 0.05) was found between preoperative CL and post-operative EL (r²=0.6); as well as EL and α angle (r²=0.7). Group B's mean CL was 9.1 mm ± 0.3 SD; mean CH was 4.1 ± 0.4 SD; mean EL was 27 ± 2.1 SD; mean α angle was 287.6 ± 41.7 SD. Significant statistical correlation was found between CL and EL (r²= 0.6) and α angle (r²=0.5). Also, a strong correlation was found between EL and α angle (r²=0.8). Significant statistical difference was detected between the two devices as regards to the electrode length. Conclusion: Multidetector CT is a reliable tool for preoperative planning and post-operative evaluation of the outcomes of cochlear implant operations. Cochlear length is a valuable prognostic parameter for prediction of the depth of electrode array insertion which can influence criteria of device selection.

Keywords: angle of insertion (α angle), cochlear implant (CI), cochlear length (CL), Multidetector Computed Tomography (MDCT)

Procedia PDF Downloads 184

Authors: Liat Shamri-Zeevi, Neta Ram-Vlasov

Abstract:

Today the world as a whole is attempting to cope with the COVID-19, which has affected all facets of personal and social life from country-wide confinement to maintaining social distance and taking protective measures to maintain hygiene. One of the populations faced with the most severe restrictions is seniors. Various studies have shown that creativity plays a crucial role in dealing with crisis events. Painting - regardless of media - allows for emotional and cognitive processing of these situations, and enables the expression of experiences in a tangible creative way that conveys and endows meaning to the artwork. The current study was conducted in Israel immediately after a 6-week lockdown. It was designed to specifically examine the impact of the COVID-19 pandemic on the quality of life of elderly women as reflected in their artworks. The sample was composed of 21 Israeli women aged 60-90, in good mental health (without diagnosed dementia or Alzheimer's), all of whom were Hebrew-speaking, and retired with an extended family, who indicated that they painted and had engaged in artwork on an ongoing basis throughout the lockdown (from March 12 to May 30, 2020). The participants' artworks were collected, and a semi-structured in-depth interview was conducted that lasted one to two hours. The participants were asked about their feelings during the pandemic and the artworks they produced during this time, and completed a questionnaire on well-being and mental health. The initial analysis of the interviews and artworks revealed themes related to the specific role of each piece of artwork. The first theme included notions that the artwork was an activity and a framework for doing, which supported positive emotions, and provided a sense of vitality during the closure. Most of the participants painted images of nature and growth which were ascribed concrete and symbolic meaning. The second theme was that the artwork enabled the processing of difficult and /or conflicting emotions related to the situation, including anxiety about death and loneliness that were symbolically expressed in the artworks, such as images of the Corona virus and the respiratory machines. The third theme suggested that the time and space prompted by the lockdown gave the participants time for a gathering together of the self, and freed up time for creative activities. Many participants stated that they painted more and more frequently during the Corona lockdown. At the conference, additional themes and findings will be presented.

Keywords: Corona virus, artwork, quality of life of elderly

Procedia PDF Downloads 130

Authors: Hana Rabbouch

Abstract:

In recent years, there has been considerable growth of denoising techniques mainly devoted to medical imaging. This important evolution is not only due to the progress of computing techniques, but also to the emergence of multi-resolution analysis (MRA) on both mathematical and algorithmic bases. In this paper, a comparative study is conducted between the two best-known MRA-based decomposition techniques: the Empirical Mode Decomposition (EMD) and the Discrete Wavelet Transform (DWT). The comparison is carried out in a framework of multi-scale denoising, where a Non-Local Means (NLM) filter is performed scale-by-scale to a sample of benchmark medical images. The results prove the effectiveness of the multiscaled denoising, especially when the NLM filtering is coupled with the EMD.

Keywords: medical imaging, non local means, denoising, multiscaled analysis, empirical mode decomposition, wavelets

Procedia PDF Downloads 128

Authors: Nadia Ben Youssef, Aicha Bouzid

Abstract:

Gradient estimation is one of the most fundamental tasks in the field of image processing in general, and more particularly for color images since that the research in color image gradient remains limited. The widely used gradient method is Di Zenzo’s gradient operator, which is based on the measure of squared local contrast of color images. The proposed gradient mechanism, presented in this paper, is based on the principle of the Di Zenzo’s approach using quaternion representation. This edge detector is compared to a marginal approach based on multiscale product of wavelet transform and another vector approach based on quaternion convolution and vector gradient approach. The experimental results indicate that the proposed color gradient operator outperforms marginal approach, however, it is less efficient then the second vector approach.

Keywords: gradient, edge detection, color image, quaternion

Procedia PDF Downloads 221

Authors: Jean-Francois Rajotte, Martin Sotir, Frank Gouineau

Abstract:

The installation and management of traffic monitoring devices can be costly from both a financial and resource point of view. It is therefore important to take advantage of in-place infrastructures to extract the most information. Here we show how low-quality urban road traffic images from cameras already available in many cities (such as Montreal, Vancouver, and Toronto) can be used to estimate traffic flow. To this end, we use a pre-trained neural network, developed for object detection, to count vehicles within images. We then compare the results with human annotations gathered through crowdsourcing campaigns. We use this comparison to assess performance and calibrate the neural network annotations. As a use case, we consider six months of continuous monitoring over hundreds of cameras installed in the city of Montreal. We compare the results with city-provided manual traffic counting performed in similar conditions at the same location. The good performance of our system allows us to consider applications which can monitor the traffic conditions in near real-time, making the counting usable for traffic-related services. Furthermore, the resulting annotations pave the way for building a historical vehicle counting dataset to be used for analysing the impact of road traffic on many city-related issues, such as urban planning, security, and pollution.

Keywords: traffic monitoring, deep learning, image annotation, vehicles, roads, artificial intelligence, real-time systems

Procedia PDF Downloads 183

Authors: Zeyu Zhou, Xiaojun Bi

Abstract:

Due to the limited environmental parameters and the limited resolution of the sensor, the universal existence of the mixed pixels in the process of remote sensing images restricts the spatial resolution of the remote sensing images. Sub-pixel mapping technology can effectively improve the spatial resolution. As the bilinear interpolation algorithm inevitably produces the edge blur effect, which leads to the inaccurate sub-pixel mapping results. In order to avoid the edge blur effect that affects the sub-pixel mapping results in the interpolation process, this paper presents a new edge-directed interpolation algorithm which uses the covariance adaptive interpolation algorithm on the edge of the low-resolution image and uses bilinear interpolation algorithm in the low-resolution image smooth area. By using the edge-directed interpolation algorithm, the super-resolution of the image with low resolution is obtained, and we get the percentage of each sub-pixel under a certain type of high-resolution image. Then we rely on the probability value as a soft attribute estimate and carry out sub-pixel scale under the ‘hard classification’. Finally, we get the result of sub-pixel mapping. Through the experiment, we compare the algorithm and the bilinear algorithm given in this paper to the results of the sub-pixel mapping method. It is found that the sub-pixel mapping method based on the edge-directed interpolation algorithm has better edge effect and higher mapping accuracy. The results of the paper meet our original intention of the question. At the same time, the method does not require iterative computation and training of samples, making it easier to implement.

Keywords: remote sensing images, sub-pixel mapping, bilinear interpolation, edge-directed interpolation

Procedia PDF Downloads 213

Authors: Adrien Marque, Daniel Delahaye, Pierre Maréchal, Isabelle Berry

Abstract:

Wind direction and uncertainty are crucial in aircraft or unmanned aerial vehicle trajectories. By computing wind covariance matrices on each spatial grid point, these spatial grids can be defined as images with symmetric positive definite matrix elements. A data pre-processing step, a specific convolution, a specific max-pooling, and a specific flatten layers are implemented to process such images. Then, the neural network is applied to spatial grids, whose elements are wind covariance matrices, to solve classification problems related to the feasibility of unmanned aerial vehicles based on wind direction and wind uncertainty.

Keywords: wind direction, uncertainty level, unmanned aerial vehicle, convolution neural network, SPD matrices

Procedia PDF Downloads 13

Authors: Alireza Akbari, Gelareh Babaee Khou

Abstract:

Ground Penetrating Radar (GPR) is an important nondestructive remote sensing tool that has been used in both military and civilian fields. Recently, GPR imaging has attracted lots of attention in detection of subsurface shallow small targets such as landmines and unexploded ordnance and also imaging behind the wall for security applications. For the monostatic arrangement in the space-time GPR image, a single point target appears as a hyperbolic curve because of the different trip times of the EM wave when the radar moves along a synthetic aperture and collects reflectivity of the subsurface targets. With this hyperbolic curve, the resolution along the synthetic aperture direction shows undesired low resolution features owing to the tails of hyperbola. However, highly accurate information about the size, electromagnetic (EM) reflectivity, and depth of the buried objects is essential in most GPR applications. Therefore hyperbolic curve behavior in the space-time GPR image is often willing to be transformed to a focused pattern showing the object's true location and size together with its EM scattering. The common goal in a typical GPR image is to display the information of the spatial location and the reflectivity of an underground object. Therefore, the main challenge of GPR imaging technique is to devise an image reconstruction algorithm that provides high resolution and good suppression of strong artifacts and noise. In this paper, at first, the standard back-projection (BP) algorithm that was adapted to GPR imaging applications used for the image reconstruction. The standard BP algorithm was limited with against strong noise and a lot of artifacts, which have adverse effects on the following work like detection targets. Thus, an improved BP is based on cross-correlation between the receiving signals proposed for decreasing noises and suppression artifacts. To improve the quality of the results of proposed BP imaging algorithm, a weight factor was designed for each point in region imaging. Compared to a standard BP algorithm scheme, the improved algorithm produces images of higher quality and resolution. This proposed improved BP algorithm was applied on the simulation and the real GPR data and the results showed that the proposed improved BP imaging algorithm has a superior suppression artifacts and produces images with high quality and resolution. In order to quantitatively describe the imaging results on the effect of artifact suppression, focusing parameter was evaluated.

Keywords: algorithm, back-projection, GPR, remote sensing

Procedia PDF Downloads 440

Authors: Woei-Shyan Lee, Yu-Liang Chuang

Abstract:

The nano-mechanical properties of as-deposited Cu/Si thin films indented to a depth of 2000 nm are investigated using a nanoindentation technique. The nanoindented specimens are annealed at a temperature of either 160 °C or 210°C, respectively. The microstructures of the as-deposited and annealed samples are then examined via transmission electron microscopy (TEM). The results show that both the loading and the unloading regions of the load-displacement curve are smooth and continuous, which suggests that no debonding or cracking occurs during nanoindentation. In addition, the hardness and Young’s modulus of the Cu/Si thin films are found to vary with the nanoindentation depth, and have maximum values of 2.8 GPa and 143 GPa, respectively, at the maximum indentation depth of 2000 nm. The TEM observations show that the region of the Cu/Si film beneath the indenter undergoes a phase transformation during the indentation process. In the case of the as-deposited specimens, the indentation pressure induces a completely amorphous phase within the indentation zone. For the specimens annealed at a temperature of 160°C, the amorphous nature of the microstructure within the indented zone is maintained. However, for the specimens annealed at a higher temperature of 210°C, the indentation affected zone consists of a mixture of amorphous phase and nanocrystalline phase. Copper silicide (η-Cu3Si) precipitates are observed in all of the annealed specimens. The density of the η-Cu3Si precipitates is found to increase with an increasing annealing temperature.

Keywords: nanoindentation, Cu/Si thin films, microstructural evolution, annealing temperature

Procedia PDF Downloads 379

Authors: Hanamariam Mekonnen

Abstract:

Ethiopian farmers traditionally produce charcoal under several kilns on cultivated land: particularly in Kasiry micro-watershed Fagita Lekoma district of Northwestern Ethiopia. However, the effects of such soil heating and remnants of charcoal leftover on soils have not been adequately documented. Hence, this study tried to quantify the effects of such kiln sites on selected soil properties and wheat crop performance. Soils from four kiln sites were thus purposively sampled at depths of 0-20 cm, 20-40 cm and 40-60 cm and were compared with the respective soil layers of none-kiln sites from similar adjacent fields. While soil moisture content was sampled at kiln and none-kiln site in wet and dry seasons from each depth. In addition, a pot experiment was conducted using two sources of biochar (Acacia decurrens and Eucalyptus Camaldulensis) with four rates (0, 10, 20, and 40 t/ha) and compared with crops grown from soils of 1kiln sites without biochar application laid out in a CRD with three replications. The data were analyzed using SAS software Version 9.4.The result revealed notable variations of kiln site soils and along soil depth. The appreciable increased (p<0.05) soil pH (5.5 to 5.74), organic carbon (3.89 to 4.27%), TN (0.30 to 0.32%), CEC (32.59 to 35.23 cmolckg-1), Ca (6.44 to 7.9 cmolckg-1), Mg (4.48 to 5.46 cmolckg-1), and significantly (p<0.01) Av. P (30.25 to 46.4 ppm) and K (2.11 to 2.82 cmolckg-1) were recorded from the none-kiln to kiln soils, respectively. On the other hand, ex. acidity and aluminum, available Fe and Mn were reduced from 2.20 to 1.54, 1.95 to 1.31 cmolckg-1 and 57.46 to 41.40 and 5.65 to 3.86 ppm, respectively, from the control to the kiln. Soil texture was significantly affected by soil heating and along soil depth. The sand content was (p<0.05) varied between the value of 23% to 29% from none-kiln to kiln site, and clay content was (p<0.01) increased from 0-20 cm (32%) soil depth to 40-60 cm (43%) deeper soil. Significantly (p<0.05) higher Soil moisture content was recorded at none-kiln site (45.85%) compared to kiln (40.44%) in wet season, whereas in dry season, lower moisture content was revealed at kiln site (26%) compared to none-kiln (30.7%). As wet to dry season, soil moisture was decreased from 43% to 28% respectively. Bulk density (P<0.01) varied between 0.88 to 0.94 gcm-3 from control to kiln in dry season. Similarly, the value of soil pH (6.10), Av. P (58.12), exchangeable bases (Ca (9.83), Mg (6.19) and K (3.67)) were (p<0.01) higher at the 0-20 cm soil depth as compared to the deeper soils, the result of soil moisture (30 to 42%) and CEC (31 to 36 cmolckg-1) increased down the soil profile. After wheat harvest, soil pH, Av. P, CEC, and exchangeable bases (Mg, K and Na) were significantly higher in the kiln soil, while soil moisture and OC increased by the applied biochar of 20 and 40 ton/ha. High yield 2.28 gpot-1 (p<0.01) was recorded in kiln soil, growth parameters of wheat were significantly increased with increasing biochar rates.

Keywords: biochar, kasiry micro-watershed, kiln site, none-kiln site, soil properties

Procedia PDF Downloads 72

Authors: B. R. Faleye, M. I. Titocan, M. P. Ibitola

Abstract:

Investigation was carried out at Opic Estate in Isheri-Osun River Basin environment using Electrical Resistivity method to study saltwater intrusion into a fresh water aquifer system from the proximal estuarine water body. The investigation is aimed at aquifer characterisation using electrical resistivity method in order to provide the depth to which fresh water fit for both domestic and industrial consumption. The 2D Electrical Resistivity and Vertical Electrical Resistivity techniques alongside Laboratory analysis of water samples obtained from the boreholes were adopted. Three traverses were investigated using Wenner and Pole-Dipole array with multi-electrode system consisting of 84 electrodes and a spread of 581 m, 664 m and 830 m were attained on the traverses. The main lithologies represented in the study area are Sand, Clay and Clayey Sand of which Sand constitutes the aquifer in the study area. Vertical Electrical Sounding data obtained at different lateral distance on the traverses have indicated that the water in the aquifer in the subsurface is brackish. Brackish water is represented by lowelectrical resistivity value signature while fresh water is characterized by relatively high electrical resistivity and in some regionfresh water is existent at depth greater than 200 m. Results of laboratory analysis of samples showed that the pH, Salinity, Total Dissolved Solid and Conductivity indicated existence of water with poor quality, indicating that salinity, TDS and Conductivity is higher in the Northern part of the study area. The 2D electrical resistivity and Vertical Electrical Sounding methods indicate that fresh water region is at ≥200m depth. Aquifers not fit for domestic use in the study area occur downwards to about 200 m in depth. In conclusion, it is recommended that wells should be sunkbeyond 220 m for the possible procurement of portable fresh water.

Keywords: 2D electrical resistivity, aquifer, brackish water, lithologies

Procedia PDF Downloads 419

Authors: Daoudi Abdelaziz, Mahmoudi Saïd, Chikh Mohamed Amine

Abstract:

This paper presents a fully automatic segmentation method of the left ventricle at End Systolic (ES) and End Diastolic (ED) in the ultrasound images by means of an implicit deformable model (level set) based on Geodesic Active Contour model. A pre-processing Gaussian smoothing stage is applied to the image, which is essential for a good segmentation. Before the segmentation phase, we locate automatically the area of the left ventricle by using a detection approach based on the Hough Transform method. Consequently, the result obtained is used to automate the initialization of the level set model. This initial curve (zero level set) deforms to search the Endocardial border in the image. On the other hand, quantitative evaluation was performed on a data set composed of 15 subjects with a comparison to ground truth (manual segmentation).

Keywords: level set method, transform Hough, Gaussian smoothing, left ventricle, ultrasound images.

Procedia PDF Downloads 451

Authors: Kaustav Mukherjee

Abstract:

In this paper we propose a Neural Style Transfer solution whereby we have created a Lightweight Separable Convolution Kernel Based GAN Architecture (SC-GAN) which will very useful for designing filter for Mobile Phone Cameras and also Edge Devices which will convert any image to its 2D ANIMATED COMIC STYLE Movies like HEMAN, SUPERMAN, JUNGLE-BOOK. This will help the 2D animation artist by relieving to create new characters from real life person's images without having to go for endless hours of manual labour drawing each and every pose of a cartoon. It can even be used to create scenes from real life images.This will reduce a huge amount of turn around time to make 2D animated movies and decrease cost in terms of manpower and time. In addition to that being extreme light-weight it can be used as camera filters capable of taking Comic Style Shots using mobile phone camera or edge device cameras like Raspberry Pi 4,NVIDIA Jetson NANO etc. Existing Methods like CartoonGAN with the model size close to 170 MB is too heavy weight for mobile phones and edge devices due to their scarcity in resources. Compared to the current state of the art our proposed method which has a total model size of 31 MB which clearly makes it ideal and ultra-efficient for designing of camera filters on low resource devices like mobile phones, tablets and edge devices running OS or RTOS. .Owing to use of high resolution input and usage of bigger convolution kernel size it produces richer resolution Comic-Style Pictures implementation with 6 times lesser number of parameters and with just 25 extra epoch trained on a dataset of less than 1000 which breaks the myth that all GAN need mammoth amount of data. Our network reduces the density of the Gan architecture by using Depthwise Separable Convolution which does the convolution operation on each of the RGB channels separately then we use a Point-Wise Convolution to bring back the network into required channel number using 1 by 1 kernel.This reduces the number of parameters substantially and makes it extreme light-weight and suitable for mobile phones and edge devices. The architecture mentioned in the present paper make use of Parameterised Batch Normalization Goodfellow etc al. (Deep Learning OPTIMIZATION FOR TRAINING DEEP MODELS page 320) which makes the network to use the advantage of Batch Norm for easier training while maintaining the non-linear feature capture by inducing the learnable parameters

Keywords: comic stylisation from camera image using GAN, creating 2D animated movie style custom stickers from images, depth-wise separable convolutional neural network for light-weight GAN architecture for EDGE devices, GAN architecture for 2D animated cartoonizing neural style, neural style transfer for edge, model distilation, perceptual loss

Procedia PDF Downloads 120

Authors: Abhisek Dash

Abstract:

This study had three neural networks, one for number segmentation, one for number detection and one for number recognition all of which are coupled to one another. All networks were trained on the MNIST dataset and were convolutional. It was assumed that the images had lighter background and darker foreground. The segmentation network took 28x28 images as input and had sixteen outputs. Segmentation training starts when a dark pixel is encountered. Taking a window(7x7) over that pixel as focus, the eight neighborhood of the focus was checked for further dark pixels. The segmentation network was then trained to move in those directions which had dark pixels. To this end the segmentation network had 16 outputs. They were arranged as “go east”, ”don’t go east ”, “go south east”, “don’t go south east”, “go south”, “don’t go south” and so on w.r.t focus window. The focus window was resized into a 28x28 image and the network was trained to consider those neighborhoods which had dark pixels. The neighborhoods which had dark pixels were pushed into a queue in a particular order. The neighborhoods were then popped one at a time stitched to the existing partial image of the number one at a time and trained on which neighborhoods to consider when the new partial image was presented. The above process was repeated until the image was fully covered by the 7x7 neighborhoods and there were no more uncovered black pixels. During testing the network scans and looks for the first dark pixel. From here on the network predicts which neighborhoods to consider and segments the image. After this step the group of neighborhoods are passed into the detection network. The detection network took 28x28 images as input and had two outputs denoting whether a number was detected or not. Since the ground truth of the bounds of a number was known during training the detection network outputted in favor of number not found until the bounds were not met and vice versa. The recognition network was a standard CNN that also took 28x28 images and had 10 outputs for recognition of numbers from 0 to 9. This network was activated only when the detection network votes in favor of number detected. The above methodology could segment connected and overlapping numbers. Additionally the recognition unit was only invoked when a number was detected which minimized false positives. It also eliminated the need for rules of thumb as segmentation is learned. The strategy can also be extended to other characters as well.

Keywords: convolutional neural networks, OCR, text detection, text segmentation

Procedia PDF Downloads 144