Adel Saleh

Exploiting the Kinematic of the Trajectories of the Local Descriptors to Improve Human Action Recognition

This paper presents a video representation that exploits the properties of the trajectories of local descriptors in human action videos. We use spatial-temporal information, which is led by trajectories to extract kinematic properties: tangent vector, normal vector, bi-normal vector and curvature. The results show that the proposed method provides comparable results compared to the state-of-the-art methods. In turn, it outperforms compared methods in terms of time complexity.

Multiphase Region-based Active Contours for Semi-automatic Segmentation of Brain MRI Images

Segmenting brain magnetic resonance (MRI) images of the brain into white matter (WM), grey matter (GM) and cerebrospinal fluid (CSF) is an important problem in medical image analysis. The study of these regions can be useful for determining different brain disorders, assisting brain surgery, post-surgical analysis, saliency detection and for studying regions of interest. This paper presents a segmentation method that partitions a given brain MRI image into WM, GM and CSF regions through a multiphase region-based active contour method followed by a pixel correction thresholding stage. The proposed region-based active contour method is applied in order to partition the input image into four different regions. Three of those regions within the brain area are then chosen by intersecting a hand-drawn binary mask with the computed contours. Finally, an efficient thresholding-based pixel correction method is applied to the computed WM, GM and CSF regions to increase their accuracy. The segmentation results are compared with ground truths to show the performance of the proposed method.

Conditional Generative Adversarial and Convolutional Networks for X-ray Breast Mass Segmentation and Shape Classification

This paper proposes a novel approach based on conditional Generative Adversarial Networks (cGAN) for breast mass segmentation in mammography. We hypothesized that the cGAN structure is well-suited to accurately outline the mass area, especially when the training data is limited. The generative network learns intrinsic features of tumors while the adversarial network enforces segmentations to be similar to the ground truth. Experiments performed on dozens of malignant tumors extracted from the public DDSM dataset and from our in-house private dataset confirm our hypothesis with very high Dice coefficient and Jaccard index (>94% and >89%, respectively) outperforming the scores obtained by other state-of-the-art approaches. Furthermore, in order to detect portray significant morphological features of the segmented tumor, a specific Convolutional Neural Network (CNN) have also been designed for classifying the segmented tumor areas into four types (irregular, lobular, oval and round), which provides an overall accuracy about 72% with the DDSM dataset.

Aggregating the temporal coherent descriptors in videos using multiple learning kernel for action recognition

Abstract Action recognition methods enable several intelligent machines to recognize human action in their daily life videos. Indeed, many action recognition methods give a noticeable misclassification rate due to the big variations within the videos of the same class, and the changes in viewpoint, scale and background. In this paper, we propose a new video representations method that captures temporal evolution of the action happening in the whole video. We show that 1) combining the descriptors of improved dense trajectories with a multiple kernel learning technique can reduce the misclassification rate, and also 2) aggregating the coherent frames in each video may have a different impact on the recognition results. Our experimental results using HMDB51 and Hollywood datasets demonstrate that our method is on par with the state-of-the-art methods.

Analysis of Temporal Coherence in Videos for Action Recognition

This paper proposes an approach to improve the performance of activity recognition methods by analyzing the coherence of the frames in the input videos and then modeling the evolution of the coherent frames, which constitute a sub-sequence, to learn a representation for the videos. The proposed method consist of three steps: coherence analysis, representation leaning and classification. Using two state-of-the-art datasets (Hollywood2 and HMDB51), we demonstrate that learning the evolution of subsequences in lieu of frames, improves the recognition results and makes actions classification faster.

Automatic nipple detection in breast thermograms

We propose an automatic and accurate method to detect nipples in thermograms.The proposed method determines the nipples using a novel selection algorithm.We achieve accurate nipple detection results in real-time. Breast cancer is one of the most dangerous diseases for women. Detecting breast cancer in its early stage may lead to a reduction in mortality. Although the study of mammographies is the most common method to detect breast cancer, it is outperformed by the analysis of thermographies in dense tissue (breasts of young women). In the last two decades, several computer-aided diagnosis (CAD) systems for the early detection of breast cancer have been proposed. Breast cancer CAD systems consist of many steps, such as segmentation of the region of interest, feature extraction, classification and nipple detection. Indeed, the nipple is an important anatomical landmark in thermograms. The location of the nipple is invaluable in the analysis of medical images because it can be used in several applications, such as image registration and modality fusion. This paper proposes an unsupervised, automatic, accurate, simple and fast method to detect nipples in thermograms. The main stages of the proposed method are: human body segmentation, determination of nipple candidates using adaptive thresholding and detection of the nipples using a novel selection algorithm. Experiments have been carried out on a thermograms dataset to validate the proposed method, achieving accurate nipple detection results in real-time. We also show an application of the proposed method, breast cancer classification in dynamic images, where the new nipple detection technique is used to segment the region of the two breasts from the infrared image. A dataset of dynamic thermograms has been used to validate this application, achieving good results.

Breast Tissue Characterization in X-Ray and Ultrasound Images using Fuzzy Local Directional Patterns and Support Vector Machines

Accurate breast mass detection in mammographies is a difficult task, especially with dense tissues. Although ultrasound images can detect breast masses even in dense breasts, they are always corrupted by noise. In this paper, we propose fuzzy local directional patterns for breast mass detection in X-ray as well as ultrasound images. Fuzzy logic is applied on the edge responses of the given pixels to produce a meaningful descriptor. The proposed descriptor can properly discriminate between mass and normal tissues under different conditions such as noise and compression variation. In order to assess the effectiveness of the proposed descriptor, a support vector machine classifier is used to perform mass/normal classification in a set of regions of interest. The proposed method has been validated using the well-known mini-MIAS breast cancer database (X-ray images) as well as an ultrasound breast cancer database. Moreover, quantitative results are shown in terms of area under the curve of the receiver operating curve analysis.