33.3%。 Shape classification is an important step to pearl classification. After a series of preprocessing, the pearl image obtained by computer vision was transformed to the polar coordinates, and then eight F(h) (Fourier coefficient) values was computed as each kind of typical shape characteristic parameters. Subsequently the utilization of fuzzy pattern recognition method realized the shape effective distinction of each pearl image. Finally, the pearl shape distinction classification was realized by seeking and comparison of characteristics image through multi-angles of view. The experimental results indicate that the largest error judgments rate of the proposed distinction method is 33.3%.
參考文獻(xiàn)
相似文獻(xiàn)
引證文獻(xiàn)
引用本文
李革,李斌,王瑩,余智,李兢,趙華勇.珍珠形狀的計(jì)算機(jī)視覺(jué)識(shí)別[J].農(nóng)業(yè)機(jī)械學(xué)報(bào),2008,39(7):129-132.[J]. Transactions of the Chinese Society for Agricultural Machinery,2008,39(7):129-132.