An Algorithm for Selecting and Stitching the Conveyer Belt Joint Images Based on X-ray

The algorithm for selecting and stitching the joint images of the conveyer belt with steel ropes in X-ray imaging system is studied. Detecting the state of conveyer belt is important in production process such as coal mine. And selecting the joint images is a primary task for further processing, especially for the on-line nondestructive detection of product line. Moreover, in order to make the better visual effect and analyze the whole joint effectively, it is necessary to stitch the joint images containing the same joint information. Based on the character of the conveyer belt X-ray images, an algorithm using the gray level histogram statistics for selecting and stitching the conveyer belt joint images is put forward in this paper. The practical application shows that the correct selection rate of the joint image is 100%, and the whole joint image is stitched inextenso and correctly. This algorithm for joint detecting can greatly improve the performance of processing, especially for the on-line nondestructive detection of product line. The results of practical application show that the algorithm we proposed is effective.