Machine Learning Paradigms: Theory and Application, 2018
Big data collected from remote sensing satellites is creating new opportunities for modern develo... more Big data collected from remote sensing satellites is creating new opportunities for modern development. Remote sensing big data are very complex in terms of their structural, spectral, and textual features according to various satellites generating them. Investigating the character of remote sensed big data becomes an essential need. Land cover and crop types classification are of great importance for monitoring agricultural production and land-use patterns. Many classification approaches have used different parameters settings. In this chapter, we investigate the modern classifiers using the most effective parameters to enhance the classification accuracy of the major crops and land covers that exist in Sentinel-2 satellite images for Fayoum Region of Egypt. Many crop types and major land-cover types are classified according to the Egypt region. This chapter investigates the k-Nearest Neighbor (k-NN), Artificial Neural Network (ANN), Support Vector Machine (SVM), and Random Forest (RF) supervised classifiers. The experimental results show that the SVM and the RF report more robust results. The k-NN reports the least accuracy especially for crop types. The RT, k-NN, ANN, and SVM record 92.7%, 92%, 92.1% and 94.4% respectively. The SVM classifier out-performs the k-NN, ANN and RF classifiers.
Image classification has been acquiring special importance in the practical applications of remot... more Image classification has been acquiring special importance in the practical applications of remote sensing. This is done with the extraordinary rise of spatial and spectral resolution of satellite imaging sensors. Also it comes from the daily increase of remote sensing databases. Deep learning approaches, especially Convolutional Neural Networks (CNNs) techniques, have been recently outperforming other state-of-the-art classification approaches in various domains. In this chapter, we propose an enhanced technique for classification of satellite images using CNNs. There are two characteristics of satellite images that make performance issue very crucial; first, high information content within the satellite image, and secondly, high computational requisites involved by CNNs. The improvement technique is built on an effective selection of suitable image scale. As this scale achieves a respectively high classification accuracy alongside a minimal computational use. We conduct our proposed technique using three state-of-the-art datasets: WHU-RS Dataset, UCMerced Land Use Dataset, and Brazilian Coffee Scenes Dataset. The proposed technique results in enhancing the accuracy performance, instead of using the original scale directly.
This paper presents an swarm optimization approach based on flower pollination optimization algor... more This paper presents an swarm optimization approach based on flower pollination optimization algorithm for multilevel thresholding by the criteria of Otsu minimizes the weighted within-class variance to make the optimal thresholding more effective. An application of microscopic white blood cell imaging has been chosen and the proposed approach has been applied to see their ability and accuracy to segment and count the blood cells. An adaptive watershed segmentation algorithm was applied that depends on a mask created from the required microscopic image to detect the minima points for segmenting the overlapped cells. The cell counting process depends on labeling the connected regions of the segmented binary image and count the labeled cells. The proposed approach archives promised results with respect to quality measures of accuracy, peak to signal-to-noise ratio (PSNR) and the root mean square error (RMSE) on microscopic images. Experimental results are recorded for the proposed appr...
Land cover and crop-types classification are of great importance for monitoring agricultural prod... more Land cover and crop-types classification are of great importance for monitoring agricultural production and land-use patterns. Many classification approaches have used different parameters settings. In this paper, we investigate the modern classifiers using the most effective parameters to improve the classification accuracy of the major crops and land covers that exist in Sentinel-2 images for Fayoum region of Egypt. Four major crop-types and four major land-cover types are classified. This paper investigates the k-Nearest Neighbor (k-NN), Artificial Neural Network (ANN), Support Vector Machine (SVM), and Random Forest (RF) supervised classifiers. The experimental results show that the SVM and the RF report more robust results. The k-NN reports the least accuracy especially for crop types. The RT, K-NN, ANN, and SVM record 92.7%, 92%, 92.1% and 94.4% respectively. The SVM classifier out-performs the k-NN, ANN and RF classifiers.
This paper introduces a novel, reliable, hybrid, two-stage method for bone x-ray classification a... more This paper introduces a novel, reliable, hybrid, two-stage method for bone x-ray classification and abnormality detection. The proposed method considers bones from seven areas of the upper extremities: namely, shoulder, humerus, forearm, elbow, wrist, hand, and finger. The novelty of the proposed work is not only in the application, but also in the proposed method itself by combining GNG network and eight models built from scratch and inspired from VGG model to achieve best performance and least computations possible. The features extracted from GNG are fed into a two-stage classification step. The first stage classifies a bone X-ray into one of seven types, after which it is directed according to type to one of seven classifiers trained to detect bone abnormality. Hence, the classification step consists of eight different models: one for classification and seven for abnormality detection. Experiments have been carried out using the MURA database, the largest public dataset of bone x-ray images. The best average sensitivity and specificity obtained for the first stage is 95.86% and 99.63%, respectively. For the second stage, the best average sensitivity and specificity obtained is 92.50% and 92.12%, respectively. These results are superior compared to state of art pretrained models. In addition, the computation and processing time are significantly decreased by the proposed scheme. Furthermore, to the best knowledge of authors, the proposed method is the first to integrate seven bones together in the same scheme. Finally, the hierarchical nature of the proposed method allows considering two problems together: bone classification and abnormality detection. INDEX TERMS Computer-aided diagnosis (CAD), growing neural gas (GNG), convolution neural network (CNN), biomedical application, deep learning, x-rays, bones classification.
Handbook of Research on Machine Learning Innovations and Trends
BCI (Brain-Computer Interface) gives you the power to manipulate things around you just by thinki... more BCI (Brain-Computer Interface) gives you the power to manipulate things around you just by thinking of what you want to do. It allows your thoughts to be interpreted by the computer and hence act upon it. This could be utilized in helping disabled people, remote controlling of robots or even getting personalized systems depending upon your mood. The most important part of any BCI application is interpreting the brain signalsasthere are many mental tasks to be considered. In this chapter, the authors focus on interpreting motor imagery tasks and more specifically, imagining left hand, right hand, foot and tongue. Interpreting the signal consists of two main steps: feature extraction and classification. For the feature extraction,Empirical Mode Decomposition (EMD) was used and for the classification,the Support Vector Machine (SVM) with Radial Basis Function (RBF) kernel was used. The authors evaluated this system using the BCI competition IV dataset and reached a very promising accur...
2012 Seventh International Conference on Computer Engineering & Systems (ICCES), 2012
A regional chemical transport model assimilated with daily mean satellite and ground based Aeroso... more A regional chemical transport model assimilated with daily mean satellite and ground based Aerosol Optical Depth (AOD) observations is used to produce three dimensional distributions of aerosols throughout Europe for the year 2005. In this paper, the AOD measurements of the Ozone Monitoring Instrument (OMI) are assimilated with Polyphemus model. In order to overcome missing satellite data, a methodology for pre-processing AOD based on Neural Network (NN) is proposed. The aerosol forecasts involve a two-phase process assimilation, and then a feedback correction process. During the assimilation phase, the total column AOD is estimated from the model aerosol fields. The model state is then adjusted to improve the agreement between the simulated AOD and satellite retrievals of AOD. The results show that the assimilation of AOD observations significantly improves the forecast for total mass. The errors on aerosol chemical composition are reduced and are sometimes vanished by the assimilation procedure and NN preprocessing, which shows a big contribution to the assimilation process.
2014 14th International Conference on Hybrid Intelligent Systems, 2014
This paper presents a multi-label automatic GrabCut technique for the problem of image segmentati... more This paper presents a multi-label automatic GrabCut technique for the problem of image segmentation. GrabCut is considered as one of the binary-label segmentation techniques because it is based on the famous s/t graph cut minimization technique for image segmentation. This paper extends the automatic binary-label GrabCut to a multi-label technique that can segment a given image into its natural segments without user intervention. Since multi-label segmentation is an NP-hard problem, the proposed algorithm converts the segmentation problem into multiple iterative piecewise binary label GrabCut segmentations. This implies separating one segment from the image, under consideration, per iteration. In this way, the proposed algorithm maintains the powerful advantage of the GrabCut to get the optimal solution for the segmentation problem. Evaluation of the segmentation results was carried out using different accuracy metrics from the literature. The evaluations were conducted with human ground truth segmentations from Berkeley benchmark dataset of natural images. Although human segmentations are semantically more meaningful, experiments showed that the proposed multi-label GrabCut provided matching segmentation results to that of individual humans with acceptable accuracy.
Advances in Intelligent Systems and Computing, 2015
ABSTRACT Human action recognition is one of the most important fields in computer vision, because... more ABSTRACT Human action recognition is one of the most important fields in computer vision, because of the large number of applications that employ action recognition. Many techniques have been proposed for representing and classifying actions; yet these tasks are still non-trivial due to a number of challenges and characteristics. In this paper, a new action representation method is proposed. The proposed method utilizes the 3D Stationary Wavelet Analysis to encode the spatio-temporal characteristics of the motion available in the video sequences in a way similar to motion history images. The proposed representation was tested using Weizmann dataset, exhibiting promising results when compared to the existing state – of – the – art methods.
Communications in Computer and Information Science, 2012
A regional chemical transport model assimilated with daily mean satellite and ground based Aeroso... more A regional chemical transport model assimilated with daily mean satellite and ground based Aerosol Optical Depth (AOD) observations is used to produce three dimensional distributions of aerosols throughout Europe for the year 2005. In this paper, the AOD measurements of the Ozone Monitoring Instrument (OMI) are assimilated with Polyphemus model. In order to overcome missing satellite data, a methodology for pre-processing AOD based on Neural Network (NN) is proposed. The aerosol forecasts involve two-phase process assimilation, and then a feedback correction process. During the assimilation phase, the total column AOD is estimated from the model aerosol fields. The model state is then adjusted to improve the agreement between the simulated AOD and satellite retrievals of AOD. The results show that the assimilation of AOD observations significantly improves the forecast for total mass. The errors on aerosol chemical composition are reduced and are sometimes vanished by the assimilation procedure and NN preprocessing, which shows a big contribution to the assimilation process.
Communications in Computer and Information Science, 2014
ABSTRACT Super Resolution (SR) refers to the reconstruction of a high resolution image from one o... more ABSTRACT Super Resolution (SR) refers to the reconstruction of a high resolution image from one or more low resolution images for the same scene. The reconstruction process is considered an inverse problem to the observation model. In this paper the SR problem is formulated by using Support Vector Regression (SVR). SVR is a very expensive computationally algorithm, thus it could be accelerated by using the computational power of a Graphics Processing Unit (GPU). The proposed parallel SVR has been implemented using NVidia’s compute device unified architecture (CUDA). An experiment has been done for a real satellite image. The experimental result demonstrates the speedup of the presented GPU implementation and compared with the serial CPU implementation and state-of-the-art techniques. The speedup of the presented SVR GPU-based implementation is up to approximately 50 times faster than the corresponding optimized CPU.
Communications in Computer and Information Science, 2014
ABSTRACT This paper proposes a directional wavelet-based representation of natural human actions ... more ABSTRACT This paper proposes a directional wavelet-based representation of natural human actions in realistic videos. This task is very important for human action recognition, which has become one of the most important fields in computer vision. Its importance comes from the large number of applications that employ human action classification and recognition. The proposed method utilizes the 3D Stationary Wavelet Analysis to encode the directional spatio-temporal characteristics of the motion available in video sequences. It was tested using the Weizmann dataset, and produced promising preliminary results (92.47 % classification accuracy) when compared to existing state–of–the–art methods.
Advances in Intelligent Systems and Computing, 2015
This paper proposes a new technique for the problem of color image segmentation using GrabCut. Gr... more This paper proposes a new technique for the problem of color image segmentation using GrabCut. GrabCut is considered as one of the semi-automatic segmentation techniques, since it requires user interaction for the initialization of the segmentation process, via dragging a rectangle around an object to extract it. This restricts GrabCut for bi-label segmentation, where the image cannot be segmented into more than two; foreground and background segments. In order to set up for multi-label segmentation, this paper presents the use of SOFM as a powerful unsupervised clustering technique for the GrabCut initialization process. This converts the GrabCut from a semi-automatic into a complete automatic segmentation technique. The use of different SOFM architectures for the process of image segmentation was tested for real experiments. Evaluation and comparison with the original GrabCut show the efficiency of the proposed automatic technique in terms of segmentation quality and accuracy.
Advances in Intelligent Systems and Computing, 2014
The increasing growth of the world trade and growing concerns of food safety by consumers need a ... more The increasing growth of the world trade and growing concerns of food safety by consumers need a cutting-edge animal identication and traceability systems as the simple recording and reading of tags-based systems are only eective in eradication programs of national disease. Animal biometric-based solutions, e.g. muzzle imaging system, oer an eective and secure, and rapid method of addressing the requirements of animal identication and traceability systems. In this paper, we propose a robust and fast cattle identication approach. This approach makes use of Local Binary Pattern (LBP) to extract local invariant features from muzzle print images. We also applied dierent classiers including Nearest Neighbor, Naive Bayes, SVM and KNN for cattle identication. The experimental results showed that our approach is superior than existed works as ours achieves 99,5% identication accuracy. In addition, the results proved that our proposed method achieved this high accuracy even if the testing images are rotated in various angels or occluded with dierent parts of their sizes.
This paper presents a comparative study using different color spaces to evaluate the performance ... more This paper presents a comparative study using different color spaces to evaluate the performance of color image segmentation using the automatic GrabCut technique. GrabCut is considered as one of the semiautomatic image segmentation techniques, since it requires user interaction for the initialization of the segmentation process. The automation of the GrabCut technique is proposed as a modification of the original semiautomatic one in order to eliminate the user interaction. The automatic GrabCut utilizes the unsupervised Orchard and Bouman clustering technique for the initialization phase. Comparisons with the original GrabCut show the efficiency of the proposed automatic technique in terms of segmentation, quality, and accuracy. As no explicit color space is recommended for every segmentation problem, automatic GrabCut is applied withRGB,HSV,CMY,XYZ, andYUVcolor spaces. The comparative study and experimental results using different color images show thatRGBcolor space is the best ...
2010 3rd International Conference on Computer Science and Information Technology, 2010
In computation flow visualization, integration based geometric flow visualization is often used t... more In computation flow visualization, integration based geometric flow visualization is often used to explore the flow field structure. A typical time-varying dataset from a Computational Fluid Dynamics (CFD) simulation can easily require hundreds of gigabytes to even terabytes of storage space, which creates challenges for the consequent dataanalysis tasks. This paper presents a new technique for pathlines visualization of extremely large time varying vector data using high performance computing. The high level requirements that guided the formulation of the new technique are (a) support for large dataset sizes, (b) support for temporal coherence of the vector data, (c) support for distributed memory high performance computing and (d) optimum utilization of the computing nodes with multi-cores (multi-core processors). The challenge is to design and implement a technique that meets these complex requirements and balances the conflicts between them. The fundamental innovation in this work is developing efficient distributed path-lines visualization for large time varying vector data. The maximum performance was reached through the parallelization of multiple processes on the multi-cores of each computing node. Accuracy of the proposed technique was confirmed compared to the results of the Visualization Tool Kit (VTK). In addition, the proposed technique exhibited acceptable scalability for different data sizes with better scalability for the larger ones. Finally, the utilization of the computing nodes was satisfactory for the considered test cases.
Advances in Intelligent Systems and Computing, 2014
In this paper, a recommender system based on rough mereology was presented for predicting best cu... more In this paper, a recommender system based on rough mereology was presented for predicting best cultivation dates for wheat in Egyptian Sinai Peninsula according to the required mean temperature for germination stage during October to December. The weather data was hourly collected from El-Arish weather station in north Sinai government from 1985 to 2013. As far as we know, this was the rst study in Egypt regarding a wheat recommender expert system for predicting temperature and sowing dates in North Sinai. In current study, accurate weather forecasting information and suitable cultivation dates of wheat were obtained from the proposed recommender system. The results show that the proposed system can forecast dierent temperatures with minimum Mean Absolute Error (MAE). These ndings may allow decision makers to take their proper decisions on managing agricultural development in new reclaimed areas like the Egyptian Sinai Peninsula.
The fundamental matrix (FM) describes the geometric relations that exist between two images of th... more The fundamental matrix (FM) describes the geometric relations that exist between two images of the same scene. Different error criteria are used for estimating FMs from an input set of correspondences. In this paper, the accuracy and efficiency aspects of the different error criteria were studied. We mathematically and experimentally proved that the most popular error criterion, the symmetric epipolar distance, is biased. It was also shown that despite the similarity between the algebraic expressions of the symmetric epipolar distance and Sampson distance, they have different accuracy properties. In addition, a new error criterion, Kanatani distance, was proposed and was proved to be the most effective for use during the outlier removal phase from accuracy and efficiency perspectives. To thoroughly test the accuracy of the different error criteria, we proposed a randomized algorithm for Reprojection Error-based Correspondence Generation (RE-CG). As input, RE-CG takes an FM and a desired reprojection error value d. As output, RE-CG generates a random correspondence having that error value. Mathematical analysis of this algorithm revealed that the success probability for any given trial is 1 − (2/3) 2 at best and is 1 − (6/7) 2 at worst while experiments demonstrated that the algorithm often succeeds after only one trial.
Machine Learning Paradigms: Theory and Application, 2018
Big data collected from remote sensing satellites is creating new opportunities for modern develo... more Big data collected from remote sensing satellites is creating new opportunities for modern development. Remote sensing big data are very complex in terms of their structural, spectral, and textual features according to various satellites generating them. Investigating the character of remote sensed big data becomes an essential need. Land cover and crop types classification are of great importance for monitoring agricultural production and land-use patterns. Many classification approaches have used different parameters settings. In this chapter, we investigate the modern classifiers using the most effective parameters to enhance the classification accuracy of the major crops and land covers that exist in Sentinel-2 satellite images for Fayoum Region of Egypt. Many crop types and major land-cover types are classified according to the Egypt region. This chapter investigates the k-Nearest Neighbor (k-NN), Artificial Neural Network (ANN), Support Vector Machine (SVM), and Random Forest (RF) supervised classifiers. The experimental results show that the SVM and the RF report more robust results. The k-NN reports the least accuracy especially for crop types. The RT, k-NN, ANN, and SVM record 92.7%, 92%, 92.1% and 94.4% respectively. The SVM classifier out-performs the k-NN, ANN and RF classifiers.
Image classification has been acquiring special importance in the practical applications of remot... more Image classification has been acquiring special importance in the practical applications of remote sensing. This is done with the extraordinary rise of spatial and spectral resolution of satellite imaging sensors. Also it comes from the daily increase of remote sensing databases. Deep learning approaches, especially Convolutional Neural Networks (CNNs) techniques, have been recently outperforming other state-of-the-art classification approaches in various domains. In this chapter, we propose an enhanced technique for classification of satellite images using CNNs. There are two characteristics of satellite images that make performance issue very crucial; first, high information content within the satellite image, and secondly, high computational requisites involved by CNNs. The improvement technique is built on an effective selection of suitable image scale. As this scale achieves a respectively high classification accuracy alongside a minimal computational use. We conduct our proposed technique using three state-of-the-art datasets: WHU-RS Dataset, UCMerced Land Use Dataset, and Brazilian Coffee Scenes Dataset. The proposed technique results in enhancing the accuracy performance, instead of using the original scale directly.
This paper presents an swarm optimization approach based on flower pollination optimization algor... more This paper presents an swarm optimization approach based on flower pollination optimization algorithm for multilevel thresholding by the criteria of Otsu minimizes the weighted within-class variance to make the optimal thresholding more effective. An application of microscopic white blood cell imaging has been chosen and the proposed approach has been applied to see their ability and accuracy to segment and count the blood cells. An adaptive watershed segmentation algorithm was applied that depends on a mask created from the required microscopic image to detect the minima points for segmenting the overlapped cells. The cell counting process depends on labeling the connected regions of the segmented binary image and count the labeled cells. The proposed approach archives promised results with respect to quality measures of accuracy, peak to signal-to-noise ratio (PSNR) and the root mean square error (RMSE) on microscopic images. Experimental results are recorded for the proposed appr...
Land cover and crop-types classification are of great importance for monitoring agricultural prod... more Land cover and crop-types classification are of great importance for monitoring agricultural production and land-use patterns. Many classification approaches have used different parameters settings. In this paper, we investigate the modern classifiers using the most effective parameters to improve the classification accuracy of the major crops and land covers that exist in Sentinel-2 images for Fayoum region of Egypt. Four major crop-types and four major land-cover types are classified. This paper investigates the k-Nearest Neighbor (k-NN), Artificial Neural Network (ANN), Support Vector Machine (SVM), and Random Forest (RF) supervised classifiers. The experimental results show that the SVM and the RF report more robust results. The k-NN reports the least accuracy especially for crop types. The RT, K-NN, ANN, and SVM record 92.7%, 92%, 92.1% and 94.4% respectively. The SVM classifier out-performs the k-NN, ANN and RF classifiers.
This paper introduces a novel, reliable, hybrid, two-stage method for bone x-ray classification a... more This paper introduces a novel, reliable, hybrid, two-stage method for bone x-ray classification and abnormality detection. The proposed method considers bones from seven areas of the upper extremities: namely, shoulder, humerus, forearm, elbow, wrist, hand, and finger. The novelty of the proposed work is not only in the application, but also in the proposed method itself by combining GNG network and eight models built from scratch and inspired from VGG model to achieve best performance and least computations possible. The features extracted from GNG are fed into a two-stage classification step. The first stage classifies a bone X-ray into one of seven types, after which it is directed according to type to one of seven classifiers trained to detect bone abnormality. Hence, the classification step consists of eight different models: one for classification and seven for abnormality detection. Experiments have been carried out using the MURA database, the largest public dataset of bone x-ray images. The best average sensitivity and specificity obtained for the first stage is 95.86% and 99.63%, respectively. For the second stage, the best average sensitivity and specificity obtained is 92.50% and 92.12%, respectively. These results are superior compared to state of art pretrained models. In addition, the computation and processing time are significantly decreased by the proposed scheme. Furthermore, to the best knowledge of authors, the proposed method is the first to integrate seven bones together in the same scheme. Finally, the hierarchical nature of the proposed method allows considering two problems together: bone classification and abnormality detection. INDEX TERMS Computer-aided diagnosis (CAD), growing neural gas (GNG), convolution neural network (CNN), biomedical application, deep learning, x-rays, bones classification.
Handbook of Research on Machine Learning Innovations and Trends
BCI (Brain-Computer Interface) gives you the power to manipulate things around you just by thinki... more BCI (Brain-Computer Interface) gives you the power to manipulate things around you just by thinking of what you want to do. It allows your thoughts to be interpreted by the computer and hence act upon it. This could be utilized in helping disabled people, remote controlling of robots or even getting personalized systems depending upon your mood. The most important part of any BCI application is interpreting the brain signalsasthere are many mental tasks to be considered. In this chapter, the authors focus on interpreting motor imagery tasks and more specifically, imagining left hand, right hand, foot and tongue. Interpreting the signal consists of two main steps: feature extraction and classification. For the feature extraction,Empirical Mode Decomposition (EMD) was used and for the classification,the Support Vector Machine (SVM) with Radial Basis Function (RBF) kernel was used. The authors evaluated this system using the BCI competition IV dataset and reached a very promising accur...
2012 Seventh International Conference on Computer Engineering & Systems (ICCES), 2012
A regional chemical transport model assimilated with daily mean satellite and ground based Aeroso... more A regional chemical transport model assimilated with daily mean satellite and ground based Aerosol Optical Depth (AOD) observations is used to produce three dimensional distributions of aerosols throughout Europe for the year 2005. In this paper, the AOD measurements of the Ozone Monitoring Instrument (OMI) are assimilated with Polyphemus model. In order to overcome missing satellite data, a methodology for pre-processing AOD based on Neural Network (NN) is proposed. The aerosol forecasts involve a two-phase process assimilation, and then a feedback correction process. During the assimilation phase, the total column AOD is estimated from the model aerosol fields. The model state is then adjusted to improve the agreement between the simulated AOD and satellite retrievals of AOD. The results show that the assimilation of AOD observations significantly improves the forecast for total mass. The errors on aerosol chemical composition are reduced and are sometimes vanished by the assimilation procedure and NN preprocessing, which shows a big contribution to the assimilation process.
2014 14th International Conference on Hybrid Intelligent Systems, 2014
This paper presents a multi-label automatic GrabCut technique for the problem of image segmentati... more This paper presents a multi-label automatic GrabCut technique for the problem of image segmentation. GrabCut is considered as one of the binary-label segmentation techniques because it is based on the famous s/t graph cut minimization technique for image segmentation. This paper extends the automatic binary-label GrabCut to a multi-label technique that can segment a given image into its natural segments without user intervention. Since multi-label segmentation is an NP-hard problem, the proposed algorithm converts the segmentation problem into multiple iterative piecewise binary label GrabCut segmentations. This implies separating one segment from the image, under consideration, per iteration. In this way, the proposed algorithm maintains the powerful advantage of the GrabCut to get the optimal solution for the segmentation problem. Evaluation of the segmentation results was carried out using different accuracy metrics from the literature. The evaluations were conducted with human ground truth segmentations from Berkeley benchmark dataset of natural images. Although human segmentations are semantically more meaningful, experiments showed that the proposed multi-label GrabCut provided matching segmentation results to that of individual humans with acceptable accuracy.
Advances in Intelligent Systems and Computing, 2015
ABSTRACT Human action recognition is one of the most important fields in computer vision, because... more ABSTRACT Human action recognition is one of the most important fields in computer vision, because of the large number of applications that employ action recognition. Many techniques have been proposed for representing and classifying actions; yet these tasks are still non-trivial due to a number of challenges and characteristics. In this paper, a new action representation method is proposed. The proposed method utilizes the 3D Stationary Wavelet Analysis to encode the spatio-temporal characteristics of the motion available in the video sequences in a way similar to motion history images. The proposed representation was tested using Weizmann dataset, exhibiting promising results when compared to the existing state – of – the – art methods.
Communications in Computer and Information Science, 2012
A regional chemical transport model assimilated with daily mean satellite and ground based Aeroso... more A regional chemical transport model assimilated with daily mean satellite and ground based Aerosol Optical Depth (AOD) observations is used to produce three dimensional distributions of aerosols throughout Europe for the year 2005. In this paper, the AOD measurements of the Ozone Monitoring Instrument (OMI) are assimilated with Polyphemus model. In order to overcome missing satellite data, a methodology for pre-processing AOD based on Neural Network (NN) is proposed. The aerosol forecasts involve two-phase process assimilation, and then a feedback correction process. During the assimilation phase, the total column AOD is estimated from the model aerosol fields. The model state is then adjusted to improve the agreement between the simulated AOD and satellite retrievals of AOD. The results show that the assimilation of AOD observations significantly improves the forecast for total mass. The errors on aerosol chemical composition are reduced and are sometimes vanished by the assimilation procedure and NN preprocessing, which shows a big contribution to the assimilation process.
Communications in Computer and Information Science, 2014
ABSTRACT Super Resolution (SR) refers to the reconstruction of a high resolution image from one o... more ABSTRACT Super Resolution (SR) refers to the reconstruction of a high resolution image from one or more low resolution images for the same scene. The reconstruction process is considered an inverse problem to the observation model. In this paper the SR problem is formulated by using Support Vector Regression (SVR). SVR is a very expensive computationally algorithm, thus it could be accelerated by using the computational power of a Graphics Processing Unit (GPU). The proposed parallel SVR has been implemented using NVidia’s compute device unified architecture (CUDA). An experiment has been done for a real satellite image. The experimental result demonstrates the speedup of the presented GPU implementation and compared with the serial CPU implementation and state-of-the-art techniques. The speedup of the presented SVR GPU-based implementation is up to approximately 50 times faster than the corresponding optimized CPU.
Communications in Computer and Information Science, 2014
ABSTRACT This paper proposes a directional wavelet-based representation of natural human actions ... more ABSTRACT This paper proposes a directional wavelet-based representation of natural human actions in realistic videos. This task is very important for human action recognition, which has become one of the most important fields in computer vision. Its importance comes from the large number of applications that employ human action classification and recognition. The proposed method utilizes the 3D Stationary Wavelet Analysis to encode the directional spatio-temporal characteristics of the motion available in video sequences. It was tested using the Weizmann dataset, and produced promising preliminary results (92.47 % classification accuracy) when compared to existing state–of–the–art methods.
Advances in Intelligent Systems and Computing, 2015
This paper proposes a new technique for the problem of color image segmentation using GrabCut. Gr... more This paper proposes a new technique for the problem of color image segmentation using GrabCut. GrabCut is considered as one of the semi-automatic segmentation techniques, since it requires user interaction for the initialization of the segmentation process, via dragging a rectangle around an object to extract it. This restricts GrabCut for bi-label segmentation, where the image cannot be segmented into more than two; foreground and background segments. In order to set up for multi-label segmentation, this paper presents the use of SOFM as a powerful unsupervised clustering technique for the GrabCut initialization process. This converts the GrabCut from a semi-automatic into a complete automatic segmentation technique. The use of different SOFM architectures for the process of image segmentation was tested for real experiments. Evaluation and comparison with the original GrabCut show the efficiency of the proposed automatic technique in terms of segmentation quality and accuracy.
Advances in Intelligent Systems and Computing, 2014
The increasing growth of the world trade and growing concerns of food safety by consumers need a ... more The increasing growth of the world trade and growing concerns of food safety by consumers need a cutting-edge animal identication and traceability systems as the simple recording and reading of tags-based systems are only eective in eradication programs of national disease. Animal biometric-based solutions, e.g. muzzle imaging system, oer an eective and secure, and rapid method of addressing the requirements of animal identication and traceability systems. In this paper, we propose a robust and fast cattle identication approach. This approach makes use of Local Binary Pattern (LBP) to extract local invariant features from muzzle print images. We also applied dierent classiers including Nearest Neighbor, Naive Bayes, SVM and KNN for cattle identication. The experimental results showed that our approach is superior than existed works as ours achieves 99,5% identication accuracy. In addition, the results proved that our proposed method achieved this high accuracy even if the testing images are rotated in various angels or occluded with dierent parts of their sizes.
This paper presents a comparative study using different color spaces to evaluate the performance ... more This paper presents a comparative study using different color spaces to evaluate the performance of color image segmentation using the automatic GrabCut technique. GrabCut is considered as one of the semiautomatic image segmentation techniques, since it requires user interaction for the initialization of the segmentation process. The automation of the GrabCut technique is proposed as a modification of the original semiautomatic one in order to eliminate the user interaction. The automatic GrabCut utilizes the unsupervised Orchard and Bouman clustering technique for the initialization phase. Comparisons with the original GrabCut show the efficiency of the proposed automatic technique in terms of segmentation, quality, and accuracy. As no explicit color space is recommended for every segmentation problem, automatic GrabCut is applied withRGB,HSV,CMY,XYZ, andYUVcolor spaces. The comparative study and experimental results using different color images show thatRGBcolor space is the best ...
2010 3rd International Conference on Computer Science and Information Technology, 2010
In computation flow visualization, integration based geometric flow visualization is often used t... more In computation flow visualization, integration based geometric flow visualization is often used to explore the flow field structure. A typical time-varying dataset from a Computational Fluid Dynamics (CFD) simulation can easily require hundreds of gigabytes to even terabytes of storage space, which creates challenges for the consequent dataanalysis tasks. This paper presents a new technique for pathlines visualization of extremely large time varying vector data using high performance computing. The high level requirements that guided the formulation of the new technique are (a) support for large dataset sizes, (b) support for temporal coherence of the vector data, (c) support for distributed memory high performance computing and (d) optimum utilization of the computing nodes with multi-cores (multi-core processors). The challenge is to design and implement a technique that meets these complex requirements and balances the conflicts between them. The fundamental innovation in this work is developing efficient distributed path-lines visualization for large time varying vector data. The maximum performance was reached through the parallelization of multiple processes on the multi-cores of each computing node. Accuracy of the proposed technique was confirmed compared to the results of the Visualization Tool Kit (VTK). In addition, the proposed technique exhibited acceptable scalability for different data sizes with better scalability for the larger ones. Finally, the utilization of the computing nodes was satisfactory for the considered test cases.
Advances in Intelligent Systems and Computing, 2014
In this paper, a recommender system based on rough mereology was presented for predicting best cu... more In this paper, a recommender system based on rough mereology was presented for predicting best cultivation dates for wheat in Egyptian Sinai Peninsula according to the required mean temperature for germination stage during October to December. The weather data was hourly collected from El-Arish weather station in north Sinai government from 1985 to 2013. As far as we know, this was the rst study in Egypt regarding a wheat recommender expert system for predicting temperature and sowing dates in North Sinai. In current study, accurate weather forecasting information and suitable cultivation dates of wheat were obtained from the proposed recommender system. The results show that the proposed system can forecast dierent temperatures with minimum Mean Absolute Error (MAE). These ndings may allow decision makers to take their proper decisions on managing agricultural development in new reclaimed areas like the Egyptian Sinai Peninsula.
The fundamental matrix (FM) describes the geometric relations that exist between two images of th... more The fundamental matrix (FM) describes the geometric relations that exist between two images of the same scene. Different error criteria are used for estimating FMs from an input set of correspondences. In this paper, the accuracy and efficiency aspects of the different error criteria were studied. We mathematically and experimentally proved that the most popular error criterion, the symmetric epipolar distance, is biased. It was also shown that despite the similarity between the algebraic expressions of the symmetric epipolar distance and Sampson distance, they have different accuracy properties. In addition, a new error criterion, Kanatani distance, was proposed and was proved to be the most effective for use during the outlier removal phase from accuracy and efficiency perspectives. To thoroughly test the accuracy of the different error criteria, we proposed a randomized algorithm for Reprojection Error-based Correspondence Generation (RE-CG). As input, RE-CG takes an FM and a desired reprojection error value d. As output, RE-CG generates a random correspondence having that error value. Mathematical analysis of this algorithm revealed that the success probability for any given trial is 1 − (2/3) 2 at best and is 1 − (6/7) 2 at worst while experiments demonstrated that the algorithm often succeeds after only one trial.
Uploads
Papers by Mohammed Tolba