An Efficient Parallel Eye Detection Algorithm on Facial Color Images

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