正在加载图片...
第8卷第4期 智能系统学报 Vol.8 No.4 2013年8月 CAAI Transactions on Intelligent Systems Aug.2013 D0I:10.3969/i.issn.1673-4785.201304041 网络出版地址:http://www.cnki.net/kcms/detail/23.1538.TP.20130828.0821.001.html 基于近红外高光谱图像的苹果轻微损伤检测 陈姗姗,宁纪锋,彭艺伟,张叶 (西北农林科技大学信息工程学院,陕西杨凌712100) 摘要:针对苹果轻微损伤时,基于可见光的机器视觉方法难以有效检测的缺点,开展了近红外高光谱图像的苹果 轻微损伤检测研究.首先,用900-1700m近红外波段范围对轻微损伤苹果高光谱成像,图像显示损伤部分与正常 部分区别明显.其次,采用特征波段比方法和不均匀二次差分方法对损伤苹果光谱图像进行处理,增强损伤处与正常 位置的可分性.最后,利用3种分割方案,对损伤部分进行自动分割.对50个含轻微损伤和正常的苹果进行分割,实 验结果表明,不均匀二次差分方法的损伤检测准确率为92%,比主成分分析法和波段比方法具有更高的检测准确 率,为轻微损伤苹果的准确检测提供了一种新的方法. 关键词:高光谱图像:轻微损伤:苹果缺陷检测:波段比:不均匀二次差分 中图分类号:TP391.41文献标志码:A文章编号:1673-4785(2013)04-356-05 中文引用格式:陈姗姗,宁纪锋,彭艺伟,等.基于近红外高光谱图像的苹果轻微损伤检测[J].智能系统学报,2013,8(4):356 360. 英文引用格式:CHEN Shanshan,NING Jifeng,PENG Yiwei,.etal.Detection of slight bruises on apples using near-infrared hyper- spectral image[J].CAAI Transactions on Intelligent Systems,2013,8(4):356-360. Detection of slight bruises on apples using near-infrared hyperspectral image CHEN Shanshan,NING Jifeng,PENG Yiwei,ZHANG Ye College of Information Engineering,Northwest A&F University,Yangling 712100,China) Abstract:A research of apple slight bruises was conducted by using hyperspectral images,aimed at solving the dif- ficulty of the traditional defect detection method of machine vision.This study is in part based on the fact that visi- ble light faces great challenges on it.First,the hyperspectral images of slight bruise apples between 900 and 1 700 nm are acquired by a hyperspectral imaging system.It can be found that the differences between the normal part and the bruise part are obvious.Next,we analyzed the hyperspectral images via the feature band ratio method and asymmetric second difference method to improve the divisibility of the normal part and the bruise part.Finally, the bruise parts were automatically segmented from the normal part with three defect detection methods.The experi- mental results show that the accuracy of detecting slight bruises on the 50 apples using asymmetric second difference method is 92%,which is higher than the principal component analysis and band ratio methods.Therefore,the work provides a new method to detect the slight bruise apples accurately. Keywords:hyperspectral image;slight bruises;apple defect detection;band ratio;asymmetric second difference 苹果作为最广泛种植的水果品种之一,是世界中,尤其是长途运输过程中,苹果易受到碰撞、挤压、 上的第二大消费水果,具有丰富的营养价值,因此, 摔伤等损伤,轻微损伤在苹果表面没有缺口,肉眼难 其品质的好坏至关重要]在人工采摘运输的过程以发现,经过一段时间后,果肉发生褐变,损伤部位 变软,苹果内部的化学成分以及口感味道发生改变, 收稿日期:2013-04-15.网络出版日期:2013-08-28. 基金项目:国家自然科学基金资助项目(61003151):中央高校基本科 最终导致苹果腐烂变质起初损伤难于观察,并且在 研业务费专项基金资助项目(QN2013055,QN2013062):国 家级大学生创新创业训练计划资助项目(1210712132) 存储、运输处于不恰当的环境下发展很快,因此检测 通信作者:宁纪锋.E-mail:jf_ing@sina.com 苹果的轻微损伤十分必要由于苹果表面颜色、纹理第 8 卷第 4 期 智 能 系 统 学 报 Vol.8 №.4 2013 年 8 月 CAAI Transactions on Intelligent Systems Aug. 2013 DOI:10.3969 / j.issn.1673⁃4785.201304041 网络出版地址:http: / / www.cnki.net / kcms/ detail / 23.1538.TP.20130828.0821.001.html 基于近红外高光谱图像的苹果轻微损伤检测 陈姗姗,宁纪锋, 彭艺伟,张叶 (西北农林科技大学 信息工程学院,陕西 杨凌 712100) 摘 要:针对苹果轻微损伤时,基于可见光的机器视觉方法难以有效检测的缺点,开展了近红外高光谱图像的苹果 轻微损伤检测研究.首先,用 900~ 1 700 nm 近红外波段范围对轻微损伤苹果高光谱成像,图像显示损伤部分与正常 部分区别明显.其次,采用特征波段比方法和不均匀二次差分方法对损伤苹果光谱图像进行处理,增强损伤处与正常 位置的可分性.最后,利用 3 种分割方案,对损伤部分进行自动分割.对 50 个含轻微损伤和正常的苹果进行分割,实 验结果表明,不均匀二次差分方法的损伤检测准确率为 92%,比主成分分析法和波段比方法具有更高的检测准确 率,为轻微损伤苹果的准确检测提供了一种新的方法. 关键词:高光谱图像;轻微损伤;苹果缺陷检测;波段比;不均匀二次差分 中图分类号:TP391.41 文献标志码:A 文章编号:1673⁃4785(2013)04⁃356⁃05 中文引用格式:陈姗姗, 宁纪锋, 彭艺伟,等.基于近红外高光谱图像的苹果轻微损伤检测[ J]. 智能系统学报, 2013, 8( 4): 356⁃ 360. 英文引用格式:CHEN Shanshan, NING Jifeng, PENG Yiwei,et al. Detection of slight bruises on apples using near-infrared hyper⁃ spectral image[J]. CAAI Transactions on Intelligent Systems, 2013, 8(4): 356⁃360. Detection of slight bruises on apples using near⁃infrared hyperspectral image CHEN Shanshan, NING Jifeng, PENG Yiwei, ZHANG Ye (College of Information Engineering, Northwest A&F University, Yangling 712100, China) Abstract:A research of apple slight bruises was conducted by using hyperspectral images, aimed at solving the dif⁃ ficulty of the traditional defect detection method of machine vision. This study is in part based on the fact that visi⁃ ble light faces great challenges on it. First, the hyperspectral images of slight bruise apples between 900 and 1 700 nm are acquired by a hyperspectral imaging system. It can be found that the differences between the normal part and the bruise part are obvious. Next, we analyzed the hyperspectral images via the feature band ratio method and asymmetric second difference method to improve the divisibility of the normal part and the bruise part. Finally, the bruise parts were automatically segmented from the normal part with three defect detection methods. The experi⁃ mental results show that the accuracy of detecting slight bruises on the 50 apples using asymmetric second difference method is 92%, which is higher than the principal component analysis and band ratio methods. Therefore, the work provides a new method to detect the slight bruise apples accurately. Keywords:hyperspectral image; slight bruises; apple defect detection; band ratio; asymmetric second difference 收稿日期:2013⁃04⁃15. 网络出版日期:2013⁃08⁃28. 基金项目:国家自然科学基金资助项目(61003151);中央高校基本科 研业务费专项基金资助项目(QN2013055,QN2013062);国 家级大学生创新创业训练计划资助项目(1210712132). 通信作者:宁纪锋. E⁃mail: jf_ning@ sina.com. 苹果作为最广泛种植的水果品种之一,是世界 上的第二大消费水果,具有丰富的营养价值,因此, 其品质的好坏至关重要[1⁃2] .在人工采摘运输的过程 中,尤其是长途运输过程中,苹果易受到碰撞、挤压、 摔伤等损伤,轻微损伤在苹果表面没有缺口,肉眼难 以发现,经过一段时间后,果肉发生褐变,损伤部位 变软,苹果内部的化学成分以及口感味道发生改变, 最终导致苹果腐烂变质.起初损伤难于观察,并且在 存储、运输处于不恰当的环境下发展很快,因此检测 苹果的轻微损伤十分必要.由于苹果表面颜色、纹理
向下翻页>>
©2008-现在 cucdc.com 高等教育资讯网 版权所有