Subpixel Edge Detection Algorithm of the Glass Bottle Based on Zernike Moments

The accuracy of edge detection determines the accuracy of actual dimension measurement, in order to improve the measuring accuracy, this paper proposes a fast algorithm of detecting the glass bottle dimension based on Zernike moments. Firstly, combines the traditional Zernike moment-based method with Otsu adaptive threshold algorithm and a new fast algorithm for edge detection is proposed. Then uses this fast algorithm to detect the edge of glass bottle with subpixel-level and uses the least square method to fit ellipses formed by the glass bottle mouth and bottom. Calibrated the system with standard gauge block and obtain the actual dimension at last. Experimental results show that the improved algorithm not only can make the edge detection reach the subpixel-level accuracy, but also can avoid the edge misidentification and inefficient causing by repeatedly manual adjustments to select the threshold value when detecting the edge. Making a rapid, accurate, non-contact measuring system becomes a reality.