Underexposed and overexposed colour image enhancement using information set theory. (17th August 2016)

• Record Type: Journal Article
• Authors: Hanmandlu, M.; Arora, S.; Gupta, G.; Singh, L.
• Is Part Of: Imaging science journal. Volume 64:Number 6(2016)
• Page Start: 321
• Page End: 333
• Publication Date: 2016-08-17
• Subjects: Fuzzy sets -- Image enhancement -- Information sets -- Overexposed image -- Particle swarm optimisation -- Underexposed image; Imaging systems -- Periodicals; 621.36705
• DOI: 10.1080/13682199.2016.1215063
• Languages: English
• ISSNs: 1368-2199

Abstract

Abstract : This paper presents a new approach for improving the contrast of digital colour images in extreme lighting environment. The concept of information sets that are derived from fuzzy sets is applied for this purpose. The S and V components of the HSV (hue, saturation, value) colour model are fuzzified using Gaussian and triangular membership functions but H is preserved. Objective measures like contrast information, quality and visual factor ( Vf ) are defined to represent the image characteristics. A new entropy function and Vf are used to form the objective function which is optimised using particle swarm optimisation to learn the image-specific parameters required for the enhancement. These new measures defined here serve to evaluate the performance of the proposed algorithm. In addition to preserving the colour and specific image features, the subjective and objective evaluations clearly depict the improvement in the quality of both the underexposed and overexposed images. On comparison, it is found that the proposed technique outperforms the existing techniques in terms of entropy, information measure and mean opinion score.