Real-Time Processing of Contrast Limited Adaptive Histogram Equalization on FPGA
Kentaro Kokufuta, Tsutomu Maruyama · 2010
Contrast limited adaptive histogram equalization (CLAHE) is a technique to enhance the visibility of local details of an image by increasing the contrast in local regions. In CLAHE, the enhancement is controlled to avoid excess amplification of the noises in the local regions. CLAHE computes several histograms of intensity values, each corresponding to a distinct region of the image, distributes the histograms to avoid the excess amplification, and remaps the intensity values using the distributed histograms. In this paper, we propose an approach for real-time computation of CLAHE using an FPGA. In our system, (1) a histogram is generated for each pixel in a image, and the intensity of only the pixel is remapped using the histogram to generate smooth images, and (2) each histogram is speculatively distributed without iterations by feeding back the distribution result of its previous pixel. With this approach, we can achieve real-time processing of HD images.