Adaptive histogram equalization with cellular neural networks

Abstract

Adaptive histogram equalization (AHE), a method of contrast enhancement which is sensitive to local spatial information in image, has demonstrated its effectiveness in many applications. However, this technique is computationally intensive. In this paper we present two computational methods designed to fit well onto the locally interconnected array computer architecture of cellular neural networks (CNNs). CNNs are well known for their image processing capabilities, specially for grey-scale medical images and images of a natural scene. In many applications it would be very useful if the operation of a template or a complex analogic algorithm were highly illumination independent. Our results suggest that we can achieve this goal by using the AHE method in a pre-processing step.