tailieunhanh - Image enhancement for face recognition using color segmentation and edge detection algorithm

This paper addresses and fixes the existing problem and proposes a method by using color segmentation algorithm and edge detection algorithm. | ISSN:2249-5789 Perumal et al , International Journal of Computer Science & Communication Networks,Vol 3(3),187-193 Image enhancement for face recognition using color segmentation and Edge detection algorithm 1 Dr. K Perumal and N Saravana Perumal Computer Centre, Madurai Kamaraj University, Madurai-625021, Tamilnadu, India Email: perumalmku@ 2 Computer Centre, Madurai Kamaraj University, Madurai -625 021, Tamilnadu, India Email: spmca@ 2 1 Abstract Nowadays Image Processing and Image depends upon the given input image quality. Enhancement play a vital role in many of numerous The accuracy rate of the whole process is applications. This paper introduces the new color much better when we are giving enhanced face recognition (FR) method that makes effective image from the low quality image by use of boosting learning as color-component feature selection framework. A facial recognition system is a method of automatically identifying or verifying a combining one or more color component algorithms [2]. person from a digital image or a video frame from a video source. The proposed boosting One of the ways to do this is by color- for finding the best set of color component features comparing selected facial features from the i mage and a facial database application [3]. from various color spaces (or models), aiming to It is typically used in security systems and achieve the best FR performance for a given FR task. can be compared to other biometrics such as f ingerprint or eye iris recognition systems. component feature selection framework is designed Most of the existing color FR methods are restricted to using a fixed color-component configuration comprising of only “two” or “three” color The overall framework of the proposed color components [5]. This paper addresses and fixes the FR method which largely consists of two existing problem and proposes a method by using parts color segmentation algorithm and .