The invention relates to a workpiece burr detection method based on image processing. A LED luminescent semiconductor is used as a light source to vertically irradiate that surface of the workpiece, aCCD camera is used as an image detecting device to continuously photograph that edge of a workpiece, finally, the image captured by the camera is captured by the computer, and then the image is filtered, segmented, the edge of the image is detected, and the edge is fused and processed by the region growth method, when the gray value reaches the set standard, the image does not need to expand, indicating that the edge is formed; then the spindle is determined to remove the pseudo-glitch, and finally the edge of the glitch is extracted. The guide line is obtained from the smallest circumscribedrectangle. The length of the contour, the angle difference between the contour and the reference line, the average distance, the variance and other positional relations are compared to determine whether the edge line is burr or not. The complexity of the method is not high. The measuring speed is fast. The detection accuracy is high, the requirement for the experimental environment is not high, and the measurement system is relatively simple.