| 水果表面亮度不均校正及单阈值缺陷提取研究 |
| |
| 引用本文： | 李江波,饶秀勤,应义斌.水果表面亮度不均校正及单阈值缺陷提取研究[J].农业机械学报,2011,42(8):159-163. |
| |
| 作者姓名： | 李江波 饶秀勤 应义斌 |
| |
| 作者单位： | 浙江大学生物系统工程与食品科学学院,杭州,310059 |
| |
| 基金项目： | 国家高技术研究发展计划（863计划）资助项目（2010AA101401） |
| |
| 摘 要： | 提出了一种水果表面亮度不均校正算法.以脐橙为研究对象,首先提取R分量图像并除去背景后获得原始图像；然后根据照度-反射模型,利用低通滤波获得该图像的入射分量图,将此入射分量图作为该图像的亮度图像；最后,原始图像与亮度图像相除后即为亮度校正后的图像.基于亮度校正后的图像,利用单阈值对水果表面缺陷一次性成功分割.利用开发的算法对正常样本和带有10类不同缺陷的样本共计788幅图像进行处理,总体识别正确率达到97％.
|
| 关 键 词： | 脐橙 缺陷检测 计算机视觉 亮度校正 |
Correction Algorithm of Illumination Nonuniformity on Fruit Surface and Defects Extraction Using Single Threshold Value |
| |
| Li Jiangbo,Rao Xiuqin and Ying Yibin.Correction Algorithm of Illumination Nonuniformity on Fruit Surface and Defects Extraction Using Single Threshold Value[J].Transactions of the Chinese Society of Agricultural Machinery,2011,42(8):159-163. |
| |
| Authors: | Li Jiangbo Rao Xiuqin and Ying Yibin |
| |
| Institution: | Zhejiang University;Zhejiang University;Zhejiang University |
| |
| Abstract: | An algorithm was proposed to overcome the difficulty that defects could not be successfully segmented at one time due to illumination nonuniformity on fruit surface.Navel orange was selected as experiment object.Firstly,the R-component image of navel orange was extracted and original image was obtained by removed R-component image background.Then,incident component of original image was obtained by low pass filtering based on illumination-reflectance model.The incident component was considered as illuminati... |
| |
| Keywords: | Navel orange Defect detection Computer vision Illumination correction |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《农业机械学报》浏览原始摘要信息 |
| 点击此处可从《农业机械学报》下载免费的PDF全文 |
