The Effect of Training Data Selection on Face Recognition in Surveillance Application

Abstract

Abstract.Face recognition is an important biometric method because of its potential applications in many fields, such as access control and surveillance. In surveillance applications, the distance between the subject and the camera is changing. Thus, in this paper, the effect of the distance between the subject and the camera, distance class, the effect of the number of images per class, and also the effect of database used for training have been investigated. The images in the database were equally divided into three classes: CLOSE, MEDIUM, and FAR, according to the distance of the subject from the camera.

A Comparison of the YCBCR Color Space with Gray Scale for Face Recognition for Surveillance Applications

“…3 and in [6] are for the sam ey had different recognition rates is because of the diffe . Nevertheless, the same performance pattern is shown 1 gives the lowest performance while Case 8 gives th gation of the performance of different channels of th face recognition for surveillance applications has bee that, the gray scale gives better performance than any o nnel regardless of the cases used.…”

“…As can be seen from the review, there are evidence that using color can enhance face recognition systems and that most researchers reported that the YC B C R color space gives better recognition rate than other color spaces. Since, we have used gray scale images obtained from color images in our previous work [6], in this paper a comparison of the performance of the YC B C R color space with gray scale for face recognition for surveillance application is carried out. In addition, an investigation of which channel or combination of channels from the YC B C R color space gives the best performance is carried out.…”

“…In our previous work [6], on face recognition for su video images of the Chok ing images were proposed CR Color Space with Gray Scale for Face Recognition 20 so that their eyes are in the same horizontal line. Fig.…”

A Comparison of the YCBCR Color Space with Gray Scale for Face Recognition for Surveillance Applications

“…In our previous work (Dargham et al, 2015), the gray scale database provided by the ChokePoint Dataset was used while in this paper, the color video images of the ChokePoint Dataset are used. The video frames were divided into three classes, namely; FAR, MEDIUM, and CLOSE.…”

“…As can be seen from the review, there are evidence that using color can enhance face recognition systems and that most researchers reported that the YC B C R color space gives better recognition rate than other color spaces. Since, we have used gray scale images obtained from color images in our previous work (Dargham et al, 2015), in this paper a comparison of the performance of the YC B C R color space with gray scale for face recognition for surveillance application is carried out. In addition, an investigation of which channel or combination of channels from the YC B C R color space gives the best performance is carried out.…”