Automatic ridgelet image enhancement algorithm for road crack image based on fuzzy entropy and fuzzy divergence

True estimation of the boundary of a road crack and its size is a major task for its automatic detection. The improvement of visual effects of a road image is necessary for such a task. Therefore, we propose an automatic ridgelet image enhancement algorithm. A nonlinear function plays an important role in the enhancement algorithm in the ridgelet domain of an image. However, it is difficult to adjust the parameters of the nonlinear function adaptively with the variation of the road crack image input. Based on the fuzzy entropy criterion, we introduce two fuzzy divergences and two supplementary linear combinations between the fuzzy entropy and two fuzzy divergences as new measurements to solve the threshold segmentation problem in the ridgelet domain. According to the distribution histogram of magnitudes of the ridgelet high-frequency coefficients, we obtain the optimal segmentation thresholds that act as the parameters of the nonlinear function by using the maximum or minimum measurements of fuzzy entropy and fuzzy divergence, respectively. The self-adaptive nonlinear function makes it possible to realize the automatic enhancement of a road crack image. Experimental results show that our image enhancement algorithm can effectively enhance the global and local contrastive effects on road crack images.