Thresholded and Optimized Histogram Equalization for contrast enhancement of images

• “Thresholded and Optimized Histogram Equalization using Swarm Intelligence” is developed to achieve contrast enhancement.
• It segments the input histogram into two using Otsu’s threshold.
• Then, it equalizes them using a set of weighing constraints optimized by PSO.
• Metrics used for qualitative assessment are Discrete Entropy and Contrast Improvement Index.
• It performs better than contemporary techniques and suitable for consumer electronics, video frame analysis, etc.

A novel technique, Thresholded and Optimized Histogram Equalization (TOHE) is presented in this paper for the purpose of enhancing the contrast as well as to preserve the essential details of any input image. The central idea of this technique is to first segment the input image histogram into two using Otsu’s threshold, based on which a set of weighing constraints are formulated. A decision is made whether to apply those constraints to any one of the sub-histograms or to both, with respect to the input image’s histogram pattern. Then, those two sub-histograms are equalized independently and their union produces a contrast enhanced output image. While formulating the weighing constraints, Particle Swarm Optimization (PSO) is employed to find the optimal constraints in order to optimize the degree of contrast enhancement. This technique is proved to have an edge over the other contemporary methods in terms of Entropy and Contrast Improvement Index.

Figure optionsDownload as PowerPoint slide