| ASM和BP网络在苹果果形研究中的方法比较 |
| |
| 引用本文： | 许月明,蔡健荣,杜丰玉. ASM和BP网络在苹果果形研究中的方法比较[J]. 食品科学, 2007, 28(4): 56-59 |
| |
| 作者姓名： | 许月明 蔡健荣 杜丰玉 |
| |
| 作者单位： | 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； |
| |
| 基金项目： | 江苏省高校自然科学基金 |
| |
| 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 |
| 文章编号： | 1002-6630（2007）04-0056-04 |
| 修稿时间： | 2006-04-30 |
Methods Compared between ASM and BP Network in Apple Shape Research |
| |
| XU Yue-ming,CAI Jian-rong,DU Feng-yu. Methods Compared between ASM and BP Network in Apple Shape Research[J]. Food Science, 2007, 28(4): 56-59 |
| |
| Authors: | XU Yue-ming CAI Jian-rong DU Feng-yu |
| |
| Affiliation: | 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 |
| |
| 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. |
| |
| Keywords: | ASM BP |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《食品科学》浏览原始摘要信息 |
|
点击此处可从《食品科学》下载全文 |
|
