Abstract-In Facial Expression Recognition Systems (FERS), only particular regions of the face are utilized for discrimination. The areas of the eyes, eyebrows, nose, and mouth are the most important features in any FERS. Applying facial features descriptors such as the local binary pattern (LBP) on such areas results in an effective and efficient FERS. In this paper, we propose an automatic facial expression recognition system. Unlike other systems, it detects and extracts the informative and discriminant regions of the face (i.e., eyes, nose, and mouth areas) using Haar-feature based cascade classifiers and these region-based features are stored into separate image files as a preprocessing step. Then, LBP is applied to these image files for facial texture representation and a feature-vector per subject is obtained by concatenating the resulting LBP histograms of the decomposed region-based features. The one-vs.-rest SVM, which is a popular multi-classification method, is employed with the Radial Basis Function (RBF) for facial expression classification. Experimental results show that this approach yields good performance for both frontal and near-frontal facial images in terms of accuracy and time complexity. Cohn-Kanade and JAFFE, which are benchmark facial expression datasets, are used to evaluate this approach.

No abstract

Problem statement: Whereas most of the conventional techniques propose using multiview cineangiograms to reconstruct 3D objects this article proposes to integrate a Three Dimension (3D) model of the coronary artery tree using a standard single-view cineangiogram. Splitting the cineangiograms into non-sequenced and different angle views is how the data is supplied in this method. Each single view can be used to reconstruct a robust 3D model of the coronary artery from that angle of view. Although the dynamic variations of blood vessels curvature have been difficult to study in Two Dimension (2D) angiograms, there is both experimental and clinical evidence showing that 3D coronary reconstruction is very useful for surgery planning and clinical study. Approach: The algorithm has three stages. The first stage is the vessel extraction and labeling for each view for the purpose of constructing the 3D model, while in the second stage, the vessels information (x, y and z) will be saved in a data file to be forwarded to the next stage. Finally, we input the x, y and z of a specific coronary artery tree to the OPENGL library included in the software, which we developed and called Fast 3D (F3D) and which is displayed in R 3 . Results: Experimental evaluation has been done to clinical raw data sets where the experimental results revealed that the proposed algorithm has a robust 3D output. Conclusion: Results showed that our proposed algorithm has high robustness for a variety of image resolutions and voxel anisotropy.

No abstract

The purpose of this article was to represent the first experience of applying a picture archiving and communication system (PACS) at the Universiti Putra Malaysia with the cooperation of Universiti Teknologi MARA hospital, and to analyze the applicability of PACS, its impact on health care, its benefits to medical employees, and propose a prototype application of PACS. Methods: The main PACS components were discussed, HL7 and DICOM standards were introduced, and a prototype of WebXA application was proposed. Results: The results of WebXA revealed the ability of this application to retrieve, store, and display angiography images on a web browser anywhere, as long as an Internet connection is provided. Conclusion: This article presented PACS with its components and standards, a prototype application was discussed and evaluated, and a few recommendations have been provided for more improvements in the future.