Intensity-Preserving Contrast Enhancement for Gray-Level Images using Multi-objective Particle Swarm Optimization

This paper addresses the enhancement of the contrast of gray-level digital images while preserving the mean image intensity, thus, providing better viewing consistency and effectiveness. The contrast enhancement is achieved by maximizing the information content carried in the image with a continuous intensity transform function and the mean image intensity is preserved, by using the gamma-correction approach. Since the contrast enhancement and intensity preservation are contradicting, a multi-objective particle swarm optimization (MPSO) algorithm is developed to resolve this trade-off. Benchmark images, street senses and skyline images are included to illustrate the effectiveness of the proposed approach

I. Introduction

Vision and image processing techniques are now becoming indispensable in our daily lives. In addition, there are various areas of automation engineering that these techniques may find their contributions. They include the use of vision for cephalic radiography in medical imaging [1], people identification [2], indoor security surveillance [3] and crowd monitoring in outdoor environments [4]. These application paradigms encompass a wide domain of the types of features contained in the captured images and a diversity of image processing techniques are anticipated to be employed for satisfactory performances in different situations.