Multi-histogram equalization for image enhancement using adaptive fuzzy clustering and optimized clipping

Image enhancement plays a crucial role in medical imaging and engineering by highlighting details and key regions, thereby improving analytical and diagnostic accuracy. Histogram equalization (HE) is one of the most widely used techniques for image enhancement. However, traditional HE methods lack adaptability to varying brightness regions and often introduce local distortions and artifacts. To address these issues, this paper proposes a multi-histogram equalization algorithm based on adaptive fuzzy clustering and optimized clipping. First, a histogram density analysis method is employed to automatically detect peaks, and the fuzzy C-means (FCM) clustering algorithm is used to adaptively segment image brightness, achieving intelligent histogram partitioning. Then, an optimized clipping and redistribution strategy is designed for each sub-histogram, where a redistribution parameter is introduced to balance enhancement and detail preservation, effectively suppressing over-enhancement. Finally, the dynamic range of each sub-image is adjusted based on the original grayscale distribution and pixel proportion, followed by independent equalization. Experimental results demonstrate that the proposed method achieves superior enhancement across diverse brightness conditions and scenes, outperforming ten state-of-the-art HE algorithms in both visual quality and quantitative metrics.