A Dynamic Fuzzy Histogram Equalization for High Dynamic Range Images by Using Multi-Scale Retinex Algorithm

Abstract

High Dynamic Range (HDR) images are appropriate to compress as Low Dynamic Range (LDR) images to show in LDR devices. A Holo artifact, a large intensity gradient, affects the value of Low Dynamic Range image to HDR image conversion. Tone reproduction approaches, and combined tone reproduction technique and image edge protective filter are some of the techniques to exclude the Holo artifacts. LDR device users are not satisfied with the converted images displayed in the LDR devices, and this affects the device value in markets. In this paper, a Multi-Scale Retinex (MSR) based Tone Reproduction Operators (TRO) is proposed to remove the Holo artifacts present in the images during HDR image to LDR image conversion. Before tone reproduction, the divergence of an image has improved using Brightness by Maintaining Dynamic Fuzzy Histogram Equalization (BPFHE) method. After evaluating the algorithm in MATLAB, performance is measured based on input HDR image and LDR output image feature comparisons.