Abstract: China is rich in agricultural seed resources, with the specialization of image processing technique, the decrease of the cost of computer hardware, and the heightening of the speed of computer, the application of machine vision technique to quality evaluation of seed resources has become possible. In the paper, we briefly explain the special property of agricultural seed resources and the demand of quality evaluation. The basic theory and the development status of machine vision are introduced. The application of machine vision to quality evaluation of agricultural seed resources is summarized in aspects of the development of algorithm, hardware and applied research. The application of machine vision technique instead of human vision to quality evaluation of agricultural seed resources has vast prospect.