| Abstract: | In this paper, a new face recognition technique based on
Hidden Markov Model (HMM), Pre-processing, and
feature extraction (Canny) is proposed. Two main
contributions are presented. In the pre-processing, the
input image’s edge is fixed to five pixels and spacing
between various parts of the pixels is fixed to a trial
threshold. The second contribution is a new technique to
extract the image's features by splitting the image into
non-uniform height depending on the distribution of the
foreground pixels. The foreground pixels are extracting
by using the vertical sliding windows. The pre-processing
steps have enhanced the performance of the system, for
example, speed is the essence. In this paper, Hidden
Markov models alongside the canny operator which
proved high accuracy recognition of the face and its
boundary. The presented technique is faster than some
other techniques that are investigated for comparison. In
addition to that, it reveals, its ability to recognize the
normal face and face boundary very efficiently
|