Efficient Image Haze Removal using Aging Particle Swarm Optimization based Dark Channel Prior

Abstract

Haze reduces the visibility of a scene. Haze removal is one of the challenging tasks as it depends upon the unknown depth information. This paper presents an efficient method to remove haze from a single image based on the aging particle swarm optimization and dark channel prior. In the proposed method firstly, the thickness of the haze is evaluated using dark channel prior, then aging particle swarm optimization is used to monitor and locate the best-optimized value for restoration. The adaptive histogram equalization is applied to increase the contrast of the degraded image. An enhanced and optimized image is obtained. Some standard parameters such as mean square error, peak signal to noise ratio and bit error rate are utilized to compare the existing and proposed method. This method is useful for many computer vision and image understanding applications. The experimental results demonstrate that the proposed approach provides higher quality results.