Comparative performance analysis of Fuzzy Logic and Particle Swarm Optimization (PSO) techniques for image quality improvement: With special emphasis to old and distorted folk paintings

Abstract

Cultural artwork has always held an important place in the society. These artworks hold within themselves a treasure trove of information about one’s society/community, their way of living and their history and many more things. However such artworks are not properly maintained and need to be carefully preserved. Preserving them digitally can give them a long life and the digital image processing techniques can be used to restore or enhance the quality of degraded artworks. This paper presents a comparison of two such techniques, PSO (Particle Swarm Optimization) and Fuzzy logic technique for enhancement of the distorted images. Image parameters like PSNR (Peak-to-Signal Noise Ratio), SSIM (Structure Similarity Index), AMBE (Absolute Mean Brightness Error), r (Pearson Correlation Coefficient), NMSE (Normalized Mean Square Error), IEF (Image Enhancement Factor) and CPP (Contrast per Pixel) have been tabulated to compare the performance of both the techniques. MATLAB software has been used for implementation of the algorithms and calculations of the parameters.