No abstract

Abstract-Face recognition is an interesting field of computer vision with many commercial and scientific applications. It is considered as a very hot topic and challenging problem at the moment. Many methods and techniques have been proposed and applied for this purpose, such as neural networks, PCA, Gabor filtering, etc. Each approach has its weaknesses as well as its points of strength. This paper introduces a highly efficient method for the recognition of human faces in digital images using a new feature extraction method that combines the global and local information in different views (poses) of facial images. Feature extraction techniques are applied on the images (faces) based on Zernike moments and structural similarity measure (SSIM) with local and semi-global blocks. Preprocessing is carried out whenever needed, and numbers of measurements are derived. More specifically, instead of the usual approach for applying statistics or structural methods only, the proposed methodology integrates higher-order representation patterns extracted by Zernike moments with a modified version of SSIM (M-SSIM). Individual measurements and metrics resulted from mixed SSIM and Zernike-based approaches give a powerful recognition tool with great results. Experiments reveal that correlative Zernike vectors give a better discriminant compared with using 2D correlation of the image itself. The recognition rate using ORL Database of Faces reaches 98.75%, while using FEI (Brazilian) Face Database we got 96.57%. The proposed approach is robust against rotation and noise.

Object detection and recognition is one of the important techniques in computer vision for searching and scanning and identifying an object in images or videos. Object detection and recognition enters into many important fields where one of the uses of object detection and recognition is to detect region of injury and determine the type of injury. This paper suggested a new effective method called Local Quadrant Pattern (LQP). The proposed method uses a window and passes it on all pixels of the image and uses the pixel direction to arrange the adjacent pixels. It also usesfour code values to encode and then produce a texture feature matrix which is used to detect objects as well as extract features based on magnitude of pixels for image classification. The experiments were conducted on the infected regions in the skin and the results showed the ability of the method to detect regions of infection as well as the high accuracy in the classification of those regions.

One of the most interesting problems and challenging issues within the pattern recognition computer vision is face recognition. Face recognition has gained special attention in the past few years due to its importance in relation to current applications such as security, forensic analysis, and surveillance systems. The whole system can be explained as the follows, after pre-processing, the first step is edge detection for the input image using the proposed filter, the second step is extraction the matrix of the Local Ternary Pattern (LTP) of the input image, the third step is capturing the features based on The Singular Value Decomposition (SVD). Fourth, extracted features are merged into a single vector. Finally, the matching has been performed between the features stored at the database and the features of the reference (test) image. The Proposed System has been applied to the variety databases. In the proposed system, the recognition ratio is 98% using city block distance and 98.5% using Structural Similarity (SSIM) as a classification method, the ORL ( AT&T) database is used.

No abstract