Directed searching optimized mean-exposure based sub-image histogram equalization for grayscale image enhancement

This paper presents a novel enhancement technique for low light grayscale images. The main goal of this work is to enhance the visual quality and improve the information contents (entropy) of the images using a novel Directed Searching Optimized mean-exposure based sub-image histogram equalization technique. Initially, the proposed method clips the original histogram to prevent over enhancement. The clipped histogram is divided into two sub-histograms, based on mean intensity value. A further division of the lower sub-histogram is carried out, based on an exposure threshold to avoid unnatural artifacts. Then, each sub-histogram is equalized independently followed by a modified transfer function. Two optimal constraint parameters are used in this paper, to reduce the information loss during histogram equalization. The Directed Searching Optimization algorithm is employed in this paper for automatic selection of the constraint parameters in order to maximize the fitness function. It makes the proposed technique more adaptive. Finally, the proposed method is compared with other existing histogram equalization based image enhancement techniques. Simulation results show that, the proposed method is able to maximize the information contents effectively and preserves the natural appearance of the image. It also results better visual quality image with improved PSNR, SSIM, FSIM and reduced MSE as compared to other state-of-the-art methods.

Automated summary

This paper introduces a novel enhancement technique for low light grayscale images, which improves visual quality and information contents through optimized histogram equalization. By clipping and dividing the histogram, the method prevents over enhancement and preserves natural appearance.