Edge Detection Optimization Using Fractional Order Calculus
Mohammed Mekideche and Youcef Ferdi
Department of Electrical Engineering, Skikda
University, Algeria
Abstract: In computer vision and image processing, time
and quality are major factors taken into account. In edge detection process,
the smoothing operation by a low-pass filter is commonly performed first in
order to reduce noise effect. However, performing the smoothing operation
partially requires additional computational time and alters true edges as well.
Attempting to resolve such problems, a new approach dealing with edge detection
optimization is addressed in this paper. For this purpose, a short edge
detector algorithm without smoothing operation is proposed and investigated.
This algorithm is based on a fractional order mask used as kernel of
convolution for edge enhancement. It has been shown that in the proposed
algorithm, the smoothing pre-process is no longer necessary; because, the
efficiency of our fractional order mask is expressed in term of immunity to
noise and the capability of detecting edges. Simulation results show how the
quality of edge detection can be enhanced on adjusting the fractional order
parameter. Then, our proposed edge detection method can be very useful in real time
applications in some fields such as, satellite and medical imaging.
Keywords:
Edge detection, fractional order calculus,
computational time, smoothing operation, performances evaluation.