ood foreign bodies harm the human health and hold back the food industry development. To detect food by computer vision and image processing technology, the examination has the advantages of non destruction, high speed, accuracy and reliable etc. The meat thickness on-line real-time detection system was first designed and constructed, which collected X-ray image of meat and laser image of meat, including filtering, enhancement and other image preprocessing. The X-ray image system of irregular meat was affected by the gray deviations of uneven thickness of meat. A meat thickness measurement method by laser triangular was proposed to eliminate the gray deviations of the X-ray image of the uneven thickness meat. This study established the mathematical model for the thickness of irregular meat, and a thickness measurement system by symmetrical structure of the laser double-triangulation method. Through calibration method two laser image collected by CCD camera were unified by means of the same coordinates. The meat images were synthesized using the image integration methods based on both gray scale method. The three-dimensional scanning experimental result show that the external shape of meat with corresponding profile, gray variation, and the variational thickness of meat image are close to meat thickness.