Low Illumination Image Enhancement Algorithm Using Iterative Recursive Filter and Visual Gamma Transformation Function

Abstract

In this paper, a Retinex based enhancement algorithm is proposed for enhancing low illumination images. The novelty of algorithm lies in the use of Iterative Recursive filter for image decomposition and Visual Gamma transformation function for pixel mapping. The edge preserving Iterative Recursive Filter estimates the base layer efficiently and 2D Visual Gamma transformation function map the pixels based on Human Vision System (HVS). The proposed Visual gamma function mimics the local and global adoption capability of HVS. The experimental results show that algorithm produce naturally looking and artifact free enhanced images with improved visibility in local regions. The subjective and objective assessment on publicly available dataset illustrates the effectiveness of the proposed method comparing with other enhancement algorithms.