Nonlinear Exposure Intensity Based Modification Histogram Equalization for Non-Uniform Illumination Image Enhancement

Non-uniform illumination image is often generated owing to various factors, such as an improper setting in the acquisition device and absorption or reflectance of objects that results existence different exposure regions image. Although Histogram Equalization (HE) well known widely used enhancement, existing HE-based methods generate washed-out effects show unnatural appearance due over-enhancement phenomenon, which limits capabilities achieving uniformity Therefore, this study proposes a modified HE method for non-uniform image, namely Nonlinear Exposure Intensity-Based Modification (NEIMHE). The proposed NEIMHE divides into five sub-regions modifies histogram each sub-region by nonlinear weight their cumulative density function (CDF) sub-region. Each then equalized using equations provide intensity expansion mapping directions under-exposed over-exposed sub-regions. A total 354 illuminated sample images were evaluate performance method, qualitatively quantitatively. was compared with state-of-the-art methods: Backlit, Adaptive Fuzzy Local Contrast Enhancement (AFELCE), Visual Algorithm Based on (VCEA), Region-based Multi (ERMHE); based Sub-Image (ESIHE). produced enhanced more uniform illumination, better preservation details, high capability maintaining naturalness. Quantitatively, achieved highest scores Discrete Entropy (DE), Measure (EME), (EMEE), Peak Signal Noise Ratio (PSNR); it attained second-best Absolute Mean Brightness Error (AMBE) Lightness Order (LOE). From both analyses, has shown its enhancing exist images.