A novel optimally weighted framework of piecewise gamma corrected fractional order masking for satellite image enhancement. (May 2019)

• Record Type: Journal Article
• Authors: Singh, Himanshu; Kumar, Anil; Balyan, L.K.; Singh, G.K.
• Is Part Of: Computers & electrical engineering. Volume 75(2019)
• Page Start: 245
• Page End: 261
• Publication Date: 2019-05
• Subjects: Fractional order filter -- Unsharp masking filter -- Optimal mask designing -- Piecewise-gamma correction -- Remotely sensed images -- Contrast enhancement -- Image quality enhancement -- Grey-level co-occurrence matrix -- Adaptive gain adjustment; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2017.11.014
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: A highly optimal framework for textural and non-textural enhancement is proposed. A novel fractional-differential mask designing technique is proposed. Balanced counter gamma-corrected fractional-order differential masking is proposed. Optimal involvement of exponential, linear, and differential operations for mapping is introduced. Abstract: A novel image quality enhancement framework is proposed here through a collective inspiration of the exponential, differential and linear operational behavior of pixel intensities. Here, a new mask framing strategy (based on uniformity principle) is presented for harvesting the benefits of optimally ordered fractional differential (FD) unsharp masking, which is consequently counter-corrected by piecewise gamma correction (PGC) through a robustly framed weighted summation framework. PGC is imparted by the constructive involvement of reciprocal gamma values ( γ 1 = γ and γ 2 = 1 / γ, ∀ γ > 1 ), which leads to interim compressed as well as interim expanded images. Golden-ratio rule inspired gradient-free, modified Cuckoo Search (MCS) optimization model, utilizing a newly framed Grey-Level Co-occurrence Matrix (GLCM) features based objective-function is proposed here. Experimentation highlights the outperformance of the proposed approach by desired increment in contrast, entropy, colorfulness and sharpness along with least values of correlation, energy and homogeneity, for parallel texture enhancement along with dark image enhancement. Graphical abstract: Image, graphical abstract