Malaria prognosis, performed through the identification of parasites using microscopy, is a vital... more Malaria prognosis, performed through the identification of parasites using microscopy, is a vital step in the early initiation of treatment. Malaria inducing parasites such as Plasmodium falciparum are difficult to identify and thus have a high mortality rate. For these reasons, a deep convolutional neural network algorithm is proposed in this paper to aid in accurately identifying parasitic cells from red blood smears. By using a mixture of machine learning techniques such as transfer learning, a cyclical and constant learning rate, and ensemble methods, we have developed a model capable of accurately identifying parasitic cells within red blood smears. 14 networks pretrained from the ImageNet database are retrained with the fully connected layers replaced. A cyclical and constant learning rate are used to traverse local minima in each network. The output of each trained neural network is representing a single vote that is used in the classification process. Majority voting criteria are applied in the final classification decision between the candidate malaria cells. Several experiments were conducted to evaluate the performance of the proposed model. The NIH Malaria Dataset from the National Institute of Health, a dataset of 27,558 images formed from microscopic patches of red blood smears, is used in these experiments. The dataset is segmented into 80% training set, 10% validation set, and 10% test set. The validation set is used as the decision metric for choosing ensemble network architectures and the test set is used as the evaluation metric for each model. Different ensemble network architectures are experimented with and promising performance is observed on the test dataset with the best models achieving a test accuracy better than several state-of-the-art methodologies.
In this paper, we present a pedestrian detection descriptor called Fused Structure and Texture (F... more In this paper, we present a pedestrian detection descriptor called Fused Structure and Texture (FST) features based on the combination of the local phase information with the texture features. Since the phase of the signal conveys more structural information than the magnitude, the phase congruency concept is used to capture the structural features. On the other hand, the Center-Symmetric Local Binary Pattern (CSLBP) approach is used to capture the texture information of the image. The dimension less quantity of the phase congruency and the robustness of the CSLBP operator on the flat images, as well as the blur and illumination changes, lead the proposed descriptor to be more robust and less sensitive to the light variations. The proposed descriptor can be formed by extracting the phase congruency and the CSLBP values of each pixel of the image with respect to its neighborhood. The histogram of the oriented phase and the histogram of the CSLBP values for the local regions in the im...
Detection of human beings in a complex background environment is a great challenge in the area of... more Detection of human beings in a complex background environment is a great challenge in the area of computer vision. For such a difficult task, most of the time no single feature algorithm is rich enough to capture all the relevant information available in the image. To improve the detection accuracy we propose a new descriptor that fuses the local phase information, image gradient, and texture features as a single descriptor and is denoted as fused phase, gradient and texture features (FPGT). The gradient and the phase congruency concepts are used to capture the shape features, and a center-symmetric local binary pattern (CSLBP) approach is used to capture the texture of the image. The fusing of these complementary features yields the ability to localize a broad range of the human structural information and different appearance details which allow for more robust and better detection performance. The proposed descriptor is formed by computing the phase congruency, the gradient, and the CSLBP value of each pixel with respect to its neighborhood. The histogram of oriented phase and histogram of oriented gradient, in addition to CSLBP histogram are extracted for each local region. These histograms are concatenated to construct the FPGT descriptor. Principal components analysis (PCA) is performed to reduce the dimensionality of the resultant features. Several experiments were conducted to evaluate the detection performance of the proposed descriptor. A support vector machine (SVM) classifier is used in these experiments to classify the FPGT features. The results show that the proposed algorithm has better detection performance in comparison with the state of art feature extraction methodologies.
2018 IEEE International Symposium on Technologies for Homeland Security (HST), 2018
Many human detection algorithms are able to detect humans in various environmental conditions wit... more Many human detection algorithms are able to detect humans in various environmental conditions with high accuracy, but they lack the ability to give the exact region of where the human is located (usual detections as a bounding box). The proposed algorithm utilizes a two-stage approach for human detection: gradient and texture features and super-pixel segmentation. The first stage is a high accuracy human detection algorithm that uses gradient information through the Histogram of Oriented Gradients and texture information through the center-symmetric local binary pattern. Various binning strategies help keep the inherent structure embedded in the features, which provide enough information for robust detection of the humans in the scene. The second stage is the SLIC super-pixel segmentation algorithm to find the actual regions of the person that are not background information. The bounding box is assumed to have surrounding background information with foreground information as the hum...
Many human detection algorithms are able to detect humans in various environmental conditions wit... more Many human detection algorithms are able to detect humans in various environmental conditions with high accuracy, but they strongly use color information for detection, which is not robust to lighting changes and varying colors. This problem is further amplified with infrared imagery, which only contains gray scale information. The proposed algorithm for human detection uses intensity distribution, gradient and texture features for effective detection of humans in infrared imagery. For the detection of intensity, histogram information is obtained in the grayscale channel. For extracting gradients, we utilize Histogram of Oriented Gradients for better information in the various lighting scenarios. For extraction texture information, center-symmetric local binary pattern gives rotational-invariance as well as lighting-invariance for robust features under these conditions. Various binning strategies help keep the inherent structure embedded in the features, which provide enough informa...
2016 IEEE National Aerospace and Electronics Conference (NAECON) and Ohio Innovation Summit (OIS), 2016
In this paper we present a new descriptor based on phase congruency concept and LUV color space f... more In this paper we present a new descriptor based on phase congruency concept and LUV color space features. Since the phase of the signal conveys more information regarding signal structure than the magnitude and the indispensable quality of the color in describing the world around us, the proposed descriptor can precisely identify and localize image features over the gradient based techniques, especially in the regions affected by illumination changes. The proposed features can be formed by extracting the phase congruency information for each pixel in the three color image channels. The maximum phase congruency values are selected from the corresponding color channels. Histograms of the phase congruency values of the local regions in the image are computed with respect to its orientation. These histograms are concatenated to construct the proposed descriptor; called Color Histogram of Oriented Phase (CHOP). Several experiments were performed to evaluate the performance of the CHOP de...
Abstract. Despite all the significant advances in human detection in various environmental condit... more Abstract. Despite all the significant advances in human detection in various environmental conditions, it is still a challenging task. Most of the human detection algorithms mainly use color information, which is not robust to lighting changes and varying colors under which such a detector should operate namely day and nighttime. This problem is further amplified with infrared (IR) imagery, which only contains grayscale information. The proposed algorithm for human detection uses intensity distribution, gradient, and texture features for effective detection of humans in IR imagery. For the detection of intensity, histogram information is obtained in the grayscale channel. For extracting gradients, we utilize the histogram of oriented gradients for better information in the various lighting scenarios. For extracting texture information, center-symmetric local binary pattern gives rotational invariance as well as lighting invariance for robust features under these conditions. Various binning strategies help keep the inherent structure embedded in the features, which provide enough information for robust detection of the humans in the scene. The features are then classified using an AdaBoost classifier to provide a tree-like structure for detection in multiple scales. The algorithm has been trained and tested on IR imagery and has been found to be fairly robust to viewpoint changes and lighting changes in dynamic backgrounds and visual scenes.
International Journal of Monitoring and Surveillance Technologies Research, 2016
In this paper, a new descriptor based on phase congruency concept and LUV color space features is... more In this paper, a new descriptor based on phase congruency concept and LUV color space features is presented. Since the phase of the signal conveys more information regarding signal structure than the magnitude and the indispensable quality of the color in describing the world around us, the proposed descriptor can precisely identify and localize image features over the gradient based techniques, especially in the regions affected by illumination changes. The proposed features can be formed by extracting the phase congruency information for each pixel in the three-color image channels. The maximum phase congruency values are selected from the corresponding color channels. Histograms of the phase congruency values of the local regions in the image are computed with respect to its orientation. These histograms are concatenated to construct the proposed descriptor. Results of the experiments performed on the proposed descriptor show that it has better detection performance and lower err...
Malaria prognosis, performed through the identification of parasites using microscopy, is a vital... more Malaria prognosis, performed through the identification of parasites using microscopy, is a vital step in the early initiation of treatment. Malaria inducing parasites such as Plasmodium falciparum are difficult to identify and thus have a high mortality rate. For these reasons, a deep convolutional neural network algorithm is proposed in this paper to aid in accurately identifying parasitic cells from red blood smears. By using a mixture of machine learning techniques such as transfer learning, a cyclical and constant learning rate, and ensemble methods, we have developed a model capable of accurately identifying parasitic cells within red blood smears. 14 networks pretrained from the ImageNet database are retrained with the fully connected layers replaced. A cyclical and constant learning rate are used to traverse local minima in each network. The output of each trained neural network is representing a single vote that is used in the classification process. Majority voting criteria are applied in the final classification decision between the candidate malaria cells. Several experiments were conducted to evaluate the performance of the proposed model. The NIH Malaria Dataset from the National Institute of Health, a dataset of 27,558 images formed from microscopic patches of red blood smears, is used in these experiments. The dataset is segmented into 80% training set, 10% validation set, and 10% test set. The validation set is used as the decision metric for choosing ensemble network architectures and the test set is used as the evaluation metric for each model. Different ensemble network architectures are experimented with and promising performance is observed on the test dataset with the best models achieving a test accuracy better than several state-of-the-art methodologies.
In this paper, we present a pedestrian detection descriptor called Fused Structure and Texture (F... more In this paper, we present a pedestrian detection descriptor called Fused Structure and Texture (FST) features based on the combination of the local phase information with the texture features. Since the phase of the signal conveys more structural information than the magnitude, the phase congruency concept is used to capture the structural features. On the other hand, the Center-Symmetric Local Binary Pattern (CSLBP) approach is used to capture the texture information of the image. The dimension less quantity of the phase congruency and the robustness of the CSLBP operator on the flat images, as well as the blur and illumination changes, lead the proposed descriptor to be more robust and less sensitive to the light variations. The proposed descriptor can be formed by extracting the phase congruency and the CSLBP values of each pixel of the image with respect to its neighborhood. The histogram of the oriented phase and the histogram of the CSLBP values for the local regions in the im...
Detection of human beings in a complex background environment is a great challenge in the area of... more Detection of human beings in a complex background environment is a great challenge in the area of computer vision. For such a difficult task, most of the time no single feature algorithm is rich enough to capture all the relevant information available in the image. To improve the detection accuracy we propose a new descriptor that fuses the local phase information, image gradient, and texture features as a single descriptor and is denoted as fused phase, gradient and texture features (FPGT). The gradient and the phase congruency concepts are used to capture the shape features, and a center-symmetric local binary pattern (CSLBP) approach is used to capture the texture of the image. The fusing of these complementary features yields the ability to localize a broad range of the human structural information and different appearance details which allow for more robust and better detection performance. The proposed descriptor is formed by computing the phase congruency, the gradient, and the CSLBP value of each pixel with respect to its neighborhood. The histogram of oriented phase and histogram of oriented gradient, in addition to CSLBP histogram are extracted for each local region. These histograms are concatenated to construct the FPGT descriptor. Principal components analysis (PCA) is performed to reduce the dimensionality of the resultant features. Several experiments were conducted to evaluate the detection performance of the proposed descriptor. A support vector machine (SVM) classifier is used in these experiments to classify the FPGT features. The results show that the proposed algorithm has better detection performance in comparison with the state of art feature extraction methodologies.
2018 IEEE International Symposium on Technologies for Homeland Security (HST), 2018
Many human detection algorithms are able to detect humans in various environmental conditions wit... more Many human detection algorithms are able to detect humans in various environmental conditions with high accuracy, but they lack the ability to give the exact region of where the human is located (usual detections as a bounding box). The proposed algorithm utilizes a two-stage approach for human detection: gradient and texture features and super-pixel segmentation. The first stage is a high accuracy human detection algorithm that uses gradient information through the Histogram of Oriented Gradients and texture information through the center-symmetric local binary pattern. Various binning strategies help keep the inherent structure embedded in the features, which provide enough information for robust detection of the humans in the scene. The second stage is the SLIC super-pixel segmentation algorithm to find the actual regions of the person that are not background information. The bounding box is assumed to have surrounding background information with foreground information as the hum...
Many human detection algorithms are able to detect humans in various environmental conditions wit... more Many human detection algorithms are able to detect humans in various environmental conditions with high accuracy, but they strongly use color information for detection, which is not robust to lighting changes and varying colors. This problem is further amplified with infrared imagery, which only contains gray scale information. The proposed algorithm for human detection uses intensity distribution, gradient and texture features for effective detection of humans in infrared imagery. For the detection of intensity, histogram information is obtained in the grayscale channel. For extracting gradients, we utilize Histogram of Oriented Gradients for better information in the various lighting scenarios. For extraction texture information, center-symmetric local binary pattern gives rotational-invariance as well as lighting-invariance for robust features under these conditions. Various binning strategies help keep the inherent structure embedded in the features, which provide enough informa...
2016 IEEE National Aerospace and Electronics Conference (NAECON) and Ohio Innovation Summit (OIS), 2016
In this paper we present a new descriptor based on phase congruency concept and LUV color space f... more In this paper we present a new descriptor based on phase congruency concept and LUV color space features. Since the phase of the signal conveys more information regarding signal structure than the magnitude and the indispensable quality of the color in describing the world around us, the proposed descriptor can precisely identify and localize image features over the gradient based techniques, especially in the regions affected by illumination changes. The proposed features can be formed by extracting the phase congruency information for each pixel in the three color image channels. The maximum phase congruency values are selected from the corresponding color channels. Histograms of the phase congruency values of the local regions in the image are computed with respect to its orientation. These histograms are concatenated to construct the proposed descriptor; called Color Histogram of Oriented Phase (CHOP). Several experiments were performed to evaluate the performance of the CHOP de...
Abstract. Despite all the significant advances in human detection in various environmental condit... more Abstract. Despite all the significant advances in human detection in various environmental conditions, it is still a challenging task. Most of the human detection algorithms mainly use color information, which is not robust to lighting changes and varying colors under which such a detector should operate namely day and nighttime. This problem is further amplified with infrared (IR) imagery, which only contains grayscale information. The proposed algorithm for human detection uses intensity distribution, gradient, and texture features for effective detection of humans in IR imagery. For the detection of intensity, histogram information is obtained in the grayscale channel. For extracting gradients, we utilize the histogram of oriented gradients for better information in the various lighting scenarios. For extracting texture information, center-symmetric local binary pattern gives rotational invariance as well as lighting invariance for robust features under these conditions. Various binning strategies help keep the inherent structure embedded in the features, which provide enough information for robust detection of the humans in the scene. The features are then classified using an AdaBoost classifier to provide a tree-like structure for detection in multiple scales. The algorithm has been trained and tested on IR imagery and has been found to be fairly robust to viewpoint changes and lighting changes in dynamic backgrounds and visual scenes.
International Journal of Monitoring and Surveillance Technologies Research, 2016
In this paper, a new descriptor based on phase congruency concept and LUV color space features is... more In this paper, a new descriptor based on phase congruency concept and LUV color space features is presented. Since the phase of the signal conveys more information regarding signal structure than the magnitude and the indispensable quality of the color in describing the world around us, the proposed descriptor can precisely identify and localize image features over the gradient based techniques, especially in the regions affected by illumination changes. The proposed features can be formed by extracting the phase congruency information for each pixel in the three-color image channels. The maximum phase congruency values are selected from the corresponding color channels. Histograms of the phase congruency values of the local regions in the image are computed with respect to its orientation. These histograms are concatenated to construct the proposed descriptor. Results of the experiments performed on the proposed descriptor show that it has better detection performance and lower err...
Uploads
Papers by hussin ragb