Endoscope Image Enhancement Algorithm Based on Pair of Complementary Gamma Functions

In order to solve the problem of uneven illumination and low contrast in most endoscope images, a simple and effective endoscope enhancement algorithm is proposed. It is mainly divided into two parts. The first part performs a complementary gamma function pair on the V component of HSV space to get a very dark and very bright image. The input image is divided into bright image, medium brightness image and dark image, and then different fusion functions are used to fuse the image to get the brightness adjusted image. The second part is the discrete wavelet transform of L component in Lab space to obtain the high frequency component and low frequency component. Adaptive space-weighted histogram equalization (CLASWHE) with contrast limitation is used to adjust the local contrast of the image at low frequency, and semi-soft threshold function is used to denoise the image at high frequency. Experimental results show that the proposed method achieves good results in brightness adjustment and contrast enhancement, and retains the sense of reality while suppressing noise.