Search

In this paper the effects of image resolution on recognition have been discussed using linear dimension reduction face recognition technique and image scale normalization is carried out through Automatic Cropping Algorithm (ACA). Linear dimension technique is based on the verity that a specific pattern of interest could reside in a low dimensional sub manifold in original input data and at the same time varying image resolution affect the pattern / face recognition results but reaching at a specific level few features of face become so prominent that it provides best matching with template image on same resolution and in return gives best success rate.. The experiments have been carried out on ORL, Yale, FERET and EME color databases and it is established that for each database there is always an optimal image resolution exits where the recognition performance is always best. This model consists of two parts, first part is preprocessing of the image, which includes conversion of a color image to gray scale image and then sobel edge detector mask is applied to detect the outer curvature of the face. Later on Automatic Cropping Algorithm is applied to carry out automatic face normalization. In Second part, the Gaussian pyramid of varying image resolution is obtained and effects of resolution on recognition are discussed.

In this paper, an efficient method for personal identification based on the pattern of human iris is proposed. The system initially detects boundaries of iris, and then unwraps it into rectangular strip. A single vector is obtained corresponding to maximum eigen value and it is used as distinct feature of the iris. In the next step training is done and recognition decision is carried out by comparing the Euclidean distances with other feature vectors which determine whether two irises are similar or not. The results show that the success rate of the proposed method is 95.91%.

This paper proposes a face recognition scheme that enhances the correct face recognition rate as compared to conventional Principal Component Analysis (PCA). The proposed scheme, Sub-Holistic PCA (SH-PCA), was tested using ORL database and out performed PCA for all test scenarios. SH-PCA requires more computational power and memory as compared to PCA however it yields an improvement of 6% correct recognition on the complete ORL database of 400 images. The correct recognition rate for the complete ORL database is 90% for the SH-PCA technique.