食品科学 ›› 2007, Vol. 28 ›› Issue (4): 56-59.

• 基础研究 • 上一篇    下一篇

ASM和BP网络在苹果果形研究中的方法比较

 许月明, 蔡健荣, 杜丰玉   

  1. 芜湖职业技术学院生物工程系; 江苏大学食品与生物工程学院; 莱阳农学院植物保护学院 安徽 芜湖 241000; 江苏 镇江 212013; 山东 青岛 266061;
  • 出版日期:2007-04-15 发布日期:2011-12-31

Methods Compared between ASM and BP Network in Apple Shape Research

 XU  Yue-Ming, CAI  Jian-Rong, DU  Feng-Yu   

  1. 1.Department of Biology Engineering,Wuhu Institute of Technology,Wuhu 241000,China; 2.School of Food and Biological Engineering, Jiangsu University,Zhenjiang 212013,China; 3.Institute of Plant Protection,Laiyang Agricultural College,Qingdao 266061,China
  • Online:2007-04-15 Published:2011-12-31

摘要: 形状判别是苹果外观品质检测中不可缺少的内容。本文先后采用主动形状模型(ASM)和基于傅立叶描述子的神经网络方法进行苹果形态分级。实验结果表明:传统神经网络方法的判别准确率为83.3%左右,而ASM方法的分级效果较好,对苹果果形的判别准确率高达95%,模型与实际对象匹配的时间不超过2s,且直观性强、鲁棒性好,具有较好的灵活性,能够满足苹果实时分级的需要。

关键词: 苹果, 果形, ASM, 主成分分析, BP, 傅立叶变换

Abstract: Apple shape identification is an essential character on appraising its appearance quality.This paper introduces a method of active shape models(ASM)as the neural network method based on Fourier to identify the apple shape.The experiment results demonstrate that the accuracy of the neural network is about 83.3% and the ASM method has good effect reaching as high as 95%.The matchin8 time between the model and the actual image does not surpass 2 sec.ASM has good visibility,high flexibility and strong robustness to satisfy the real-time graduation of apple.

Key words: apple, shape, ASM, principal component analysis, BP(error back propagation), Fourier transformation