Details Enhancement In Low Contrast Region Of Inspection Image Based On Fuzzy Rough Set

In the large dynamic range of inspection images, low-density objects mostly exist in the areas with low contrast, which makes it difficult to identify or show them. The existing image enhancement algorithms mostly do not consider this characteristic of the X-ray inspection image. To solve the detail enhancement problem for quarantine inspection, an fuzzy rough set method is proposed to extract the low-density quarantine objects in X-ray inspection image. Firstly, after negative operating and noise filtering, the inspection image is divided into two parts with rough set method, one is the region of interest that may have the low-density quarantine object, and the other on the contrary. Then, within the region of interest, a fuzzy degree is used to determine the probability of a certain pixel to belong to the quarantine target. Finally, according to the pixel classification results, some pixel values are adjusted in HSV space to show quarantine target distinctly. The capability of detail enhancement in low-contrast region of high dynamic image is also evaluated with the experiments on simulation data and real X-ray images.