Mine image enhancement method based on multi-scale local histogram equalization

There are problems of under-enhancement and over-enhancement in commonly mine image enhancement methods such as histogram equalization, Retinex theory, homomorphic filtering, wavelet analysis, etc. In order to solve the above problems, a mine image enhancement method based on multi-scale local histogram equalization is proposed. According to the independent features of color components (hue component and saturation component) and brightness component of image in HSI color space, the low-light RGB mine image is converted into the HSI color space. The method uses bilateral filtering to decompose the brightness component into lighted images and reflected images. The method divides the lighting image into small, medium, and large blocks, and performs local histogram equalization on each image block to improve image brightness and contrast. The method performs 8-direction gradient enhancement on the reflected image to enrich the texture edges of the image. The method performs Retinex inverse transformation on the light image after multi-scale local histogram equalization and reflection image after directional gradient enhancement to obtain the enhanced brightness component. Then the brightness, hue and saturation components are transformed into RGB color space to obtain an enhanced mine image. Experimental verification of the mine image enhancement method based on multi-scale local histogram equalization is conducted by using actual monitoring images of coal mines. The enhancement effect is evaluated subjectively and objectively. The results show that compared with existing image enhancement methods, this method has a greater improvement in image brightness and contrast with richer detail information. The information entropy has increased by over 7.23%, and the mean average gradient has increased by over 31.6%. It has better image enhancement effects.