Detection of Stress Cracks in Rice Kernels Based on Machine Vision

作者：Xu Lizhang; Li Yaoming

来源：AMA-Agricultural Mechanization in Asia Africa and Latin America, 2009, 40(4): 38-41.

A machine vision system was developed to detect different types of stress cracks in rice kernels. An image processing algorithm was used to enhance the object and reduce noise in the acquired image. Rice kernels were classified as those with zero, single, double or multiple stress cracks. Zero and single stress cracks were the easiest to detect. Careful positioning of the kernel over the lighting aperture was necessary for accurate detection of double and multiple stress cracks. This system provided an average accuracy of approximately 96.5 % for no cracks, 93.4 % for a single crack, 84.2 % for double cracks and 83.4 % for multiple cracks compared to human inspection. The processing time was between 0.45 and 0.12 s/kernel.

• 出版日期2009
• 单位江苏大学