Parallel Implementation of Eye Detection Algorithm on Color Facial Images

Abstract

Abstract: As processing power becomes cheaper and more available by using cluster of computers,<br><br>the need for parallel algorithms which can harness this computing potentials is increasing. Eye<br><br>detection is an application ofparallel algorithms. Detecting eyes in images plays an important role in<br><br>many applications such as face detection/recognition. In addition, its widespread usage as a part of<br><br>series applications made it a nontrivial task which should be worked on. Moreover, existing algorithms<br><br>are usually much time-consuming. In this paper we have proposed a parallel algorithm in EREW<br><br>PRAM model for eye detection in color images. Using color characteristics is a useful way to detect<br><br>b r eyes. We use special color space, YC C which its components give us worthwhile information about<br><br>eyes. We make two maps in parallel according to their components and merge them to obtain a final<br><br>map. The proposed algorithm has been examined with MPI and its implementation results on CVL<br><br>and Iranian databases showed that parallel approach reduces the time of detection efficiently.<br><br>Exploiting p processors has reduced the time of detection to n/p + c which c is the communication<br><br>overhead between the processors and n is the number of pixels of a particular image.