| 基于高光谱成像技术的柑橘缺陷无损检测 |
| |
| 引用本文： | 章海亮,高俊峰,何勇. 基于高光谱成像技术的柑橘缺陷无损检测[J]. 农业机械学报, 2013, 44(9): 177-181 |
| |
| 作者姓名： | 章海亮 高俊峰 何勇 |
| |
| 作者单位： | 浙江大学;华东交通大学;浙江大学;浙江大学 |
| |
| 基金项目： | 国家自然科学基金资助项目(61071220);浙江省科技计划资助项目（2011C22070）;中央高校基本科研业务费专项资金资助项目;江西省科技支撑计划资助项目(2010BNB01200、20123BDH80014);华东交通大学载运工具与装备教育部重点实验室资助项目 |
| |
| 摘 要： | 应用高光谱成像技术无损检测柑橘的缺陷。选取蒂腐、黑斑、褐腐、结痂缺陷果和正常果各30个,提取并分析了5类果皮感兴趣区域光谱曲线并结合主成分分析法确定2个最佳波长(615nm和680nm),然后基于特征波长作主成分分析,选取第2主成分作为分类识别图像,提出采用特征波长主成分分析法与波段比算法相结合的方法,识别率达到94%。试验结果表明,高光谱成像技术可以有效地对带有蒂腐、黑斑、褐腐、结痂缺陷的柑橘进行分类识别。
|
| 关 键 词： | 柑橘 缺陷检测 高光谱成像 主成分分析 |
Nondestructive Detection of Citrus Defection Using Hyper-spectra Imaging Technology |
| |
| Zhang Hailiang,Gao Junfeng and He Yong. Nondestructive Detection of Citrus Defection Using Hyper-spectra Imaging Technology[J]. Transactions of the Chinese Society for Agricultural Machinery, 2013, 44(9): 177-181 |
| |
| Authors: | Zhang Hailiang Gao Junfeng He Yong |
| |
| Affiliation: | Zhejiang University;East China Jiaotong University;Zhejiang University;Zhejiang University |
| |
| Abstract: | A hyperspectral imaging system was developed for detecting various common defects on citrus. Citrus with end rot, insect dot damage, rot damage, thrip scars and normal citrus were chosen. Hyperspectral images of citrus samples and principal component analysis (PCA) were used to confirm two best wavelengths (615nm and 680nm). PC2 of PCA was selected to classify the images. Finally, the detection algorithm combined PCA and band ratio was developed and achieved an accuracy of 94%. The results showed the feasibility of the proposed method. |
| |
| Keywords: | Citrus Defect detection Hyperspectral imaging Principal component analysis |
|
| 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》下载全文 |
