Abstract A method based on computer vision for recognizing the pearls' shape is presented to solve the problem of low productivity and low accuracy of peal sort by hand. Firstly, the preprocessed color image is segmented according to its' grey degree histogram. Then the morphological closing operation is adopted to eliminate the noise points in the image. An 8-directional boundary-tracing algorithm is applied to obtain the sequences of the boundary to abstract the Fourier Descriptor of peal's boundary curve. And then the Euclidean distance between the peals under checking and the ones in the standard template library, which is utilized to distinguish the pearls' shape. Finally the experimental result demonstrates the validity and practicability of this method.
ZHENG Hua-Wen, CAO Yan-Long, YANG Jiang-Xin. Separation method for shape grading of pearls using computer vision. Chinese Journal of Engineering Design, 2008, 15(5): 365-368.
