Fatimah Khalid

Face recognition using local geometrical features - PCA with euclidean classifier

The goal of this research is to get the minimum features and produce better recognition rates. Before doing the feature selection, we investigate automatic methods for detecting face anchor points with 412 3D-facial points of 60 individuals. There are 7 images per subject including views presenting light rotations and facial expressions. Each images have twelve anchor points which are Right Outer Eye, Right Inner Eye, Left Outer Eye, Left Inner Eye, Upper nose point, Nose Tip, Right Nose Base, Left Nose Base, Right Outer Face, Left Outer Face, Chin, and Upper Face. All the control points are based on the measurement on an absolute scale (mm). After all the control points have been determined, we will extract a relevant set of features. These features are classified in 3 : (1) distance of mass points, (2) angle measurements, and (3) angle measurements. There are fifty-three local geometrical features extracted from 3D points human faces to model the face for face recognition and the discriminating power calculation is to show the valuable feature among all the features. Experiment performed on the GavabDB dataset (412 faces) show that our algorithm achieved 86% of success when respectively the first rank matched.

3D multimodal cardiac data reconstruction using angiography and computerized tomographic angiography registration

BackgroundComputerized tomographic angiography (3D data representing the coronary arteries) and X-ray angiography (2D X-ray image sequences providing information about coronary arteries and their stenosis) are standard and popular assessment tools utilized for medical diagnosis of coronary artery diseases. At present, the results of both modalities are individually analyzed by specialists and it is difficult for them to mentally connect the details of these two techniques. The aim of this work is to assist medical diagnosis by providing specialists with the relationship between computerized tomographic angiography and X-ray angiography.MethodsIn this study, coronary arteries from two modalities are registered in order to create a 3D reconstruction of the stenosis position. The proposed method starts with coronary artery segmentation and labeling for both modalities. Then, stenosis and relevant labeled artery in X-ray angiography image are marked by a specialist. Proper control points for the marked artery in both modalities are automatically detected and normalized. Then, a geometrical transformation function is computed using these control points. Finally, this function is utilized to register the marked artery from the X-ray angiography image on the computerized tomographic angiography and get the 3D position of the stenosis lesion.ResultsThe result is a 3D informative model consisting of stenosis and coronary arteries’ information from the X-ray angiography and computerized tomographic angiography modalities. The results of the proposed method for coronary artery segmentation, labeling and 3D reconstruction are evaluated and validated on the dataset containing both modalities.ConclusionsThe advantage of this method is to aid specialists to determine a visual relationship between the correspondent coronary arteries from two modalities and also set up a connection between stenosis points from an X-ray angiography along with their 3D positions on the coronary arteries from computerized tomographic angiography. Moreover, another benefit of this work is that the medical acquisition standards remain unchanged, which means that no calibration in the acquisition devices is required. It can be applied on most computerized tomographic angiography and angiography devices.

Object detection and representation method for surveillance video indexing

The huge volume of videos produced by surveillance cameras has increased the demand for the fast and effective video surveillance indexing and retrieval systems. Although environmental condition such as light reflection, illumination changes, shadow, and occlusion can affect the indexing and retrieval result of any video surveillance system, nevertheless the use of reliable and robust object (blob) detection and representation methods can improve the performance of the system. This paper presents a video indexing module, which is part of a video surveillance indexing and retrieval framework, to overcome the above challenges. The proposed video indexing module is composed of seven components: background modeling, foreground extraction, blob detection, blob analysis, feature extraction, blob representation, and blob indexing. The experimental results showed that the selection of appropriate blob detection method could improve the performance of the system. Moreover, the experiments also demonstrated that the functionality of the proposed blob representation method was able to prevent the processing of redundant blobs information.

A Review of Ultrasound and Computed Tomography Registration Approaches

Ultrasound is widely used in minimally invasive cardiac procedures due to its convenience of use and noninvasive nature. However, the low quality of ultrasound images often limits their utility as a means for guiding procedures, since it is often difficult to relate the images to their anatomical context. To improve the interpretability of the ultrasound images while maintaining ultrasound as a flexible anatomical and functional real time imaging modality, there is need for some registration techniques that integrate them with their correspond context in high quality pre-operative models such as magnetic resonance imaging or computed tomography images. It is a challenging and remarkable step as through registration, the combined information from multi-modal image acquisition systems such as ultrasound and computed tomography can be obtained by the medical practitioner for better physiological understanding, effective image guidance surgery, treatment, monitoring and diagnostic purposes. An overview of ultrasound and computed tomography registration techniques is presented in this paper.

Fast marching method and modified features fusion in enhanced dynamic hand gesture segmentation and detection method under complicated background

Recent development in the field of human–computer interaction has led renewed interest in dynamic hand gesture segmentation based on gesture recognition system. Despite its long clinical success, dynamic hand gesture segmentation using webcam vision becomes technically challenging and suffers the problem of non-accurate and poor hand gesture segmentation where the hand region is not integral due to complicated environment, partial occlusion and light effects. Therefore, for segmenting complete hand gesture region and improving the segmentation accuracy, this study proposes a combination of four modified visual features segmentation procedures, which are skin, motion, skin moving as well as contour features and fast marching method. Quantitative measurement was performed for evaluating hand gesture segmentation algorithm. Besides, qualitative measurement was done to conduct a comparison based on segmentation accuracy with previous studies. Consequently, the experiment results showed a great enhancement in hand area segmentation with a high accuracy rate of 98%.

Low Cost Skin Segmentation Scheme in Videos Using Two Alternative Methods for Dynamic Hand Gesture Detection Method

Recent years have witnessed renewed interest in developing skin segmentation approaches. Skin feature segmentation has been widely employed in different aspects of computer vision applications including face detection and hand gestures recognition systems. This is mostly due to the attractive characteristics of skin colour and its effectiveness to object segmentation. On the contrary, there are certain challenges in using human skin colour as a feature to segment dynamic hand gesture, due to various illumination conditions, complicated environment, and computation time or real-time method. These challenges have led to the insufficiency of many of the skin color segmentation approaches. Therefore, to produce simple, effective, and cost efficient skin segmentation, this paper has proposed a skin segmentation scheme. This scheme includes two procedures for calculating generic threshold ranges in Cb-Cr colour space. The first procedure uses threshold values trained online from nose pixels of the face region. Meanwhile, the second procedure known as the offline training procedure uses thresholds trained out of skin samples and weighted equation. The experimental results showed that the proposed scheme achieved good performance in terms of efficiency and computation time.

A new human heart vessel identification, segmentation and 3D reconstruction mechanism.

BackgroundThe identification and segmentation of inhomogeneous image regions is one of the most challenging issues nowadays. The surface vessels of the human heart are important for the surgeons to locate the region where to perform the surgery and to avoid surgical injuries. In addition, such identification, segmentation, and visualisation helps novice surgeons in the training phase of cardiac surgery.MethodsThis article introduces a new mechanism for identifying the position of vessels leading to the performance of surgery by enhancement of the input image. In addition, develop a 3D vessel reconstruction out of a single-view of a real human heart colour image obtained during open-heart surgery.ResultsReduces the time required for locating the vessel region of interest (ROI). The vessel ROI must appear clearly for the surgeons. Furthermore, reduces the time required for training cardiac surgery of the novice surgeons. The 94.42% accuracy rate of the proposed vessel segmentation method using RGB colour space compares to other colour spaces.ConclusionsThe advantage of this mechanism is to help the surgeons to perform surgery in less time, avoid surgical errors, and to reduce surgical effort. Moreover, the proposed technique can reconstruct the 3D vessel model from a single image to facilitate learning of the heart anatomy as well as training of cardiac surgery for the novice surgeons. Furthermore, extensive experiments have been conducted which reveal the superior performance of the proposed mechanism compared to the state of the art methods.

Cardiac Components Categorization and Coronary Artery Enhancement in CT Angiography

Coronary artery analysis is an important phase of each cardiac image processing system. Once physicians decide to check up coronary arteries and also other cardiac components in CT Angiography, it should be done precisely to give the correct information about them. In this paper, we proposed a new method for cardiac components categorization, aorta segmentation, and coronary artery enhancement from CT Angiography images. This method is very helpful for the surgeon and cardiologist to have a clear view of each components and also to visualize coronary arteries prior to coronary artery bypass graft surgery or other types of cardiac treatments. To this end, firstly we constructed a proper mask based on the Hounsfield Unit to categorize CT Angiography slices components. Then aorta as an important component is segmented from initial slices. And finally coronary arteries are enhanced as tubular shape objects in all slices.

A new clustering approach for group detection in scene-independent dense crowds

Despite significant progress in crowd behaviour analysis over the past few years, most of todays state of the art algorithms focus on analysing individual behaviour in a specific-scene. Recently, the widespread availability of cameras and a growing need for public safety have shifted the attention of researchers in video surveillance from individual behavior analysis to group and crowd behavior analysis. However, dangerous and illegal behaviours are mostly occurred from groups of people. Group detection is the main process to separate people in crowded scene into different group based on their interactions. Results of group detection can further to apply in analyze group and crowd behaviour. This paper present a study of the group detection and propose a novel approach for clustering group of people in different crowded scenes based on trajectories. For the clustering of group of people we propose novel formula to compute the weights based on the distance, the occurrence, and the speed correlations of two people in a tracklet cluster to infer the people relationship in a tracklet clusters with Expectation Maximization (EM) in order to overcome occlusion in crowded scenes.