近红外窄带光照下不同水果背景中桔小实蝇的图像分割

›› 2014, Vol. 57 ›› Issue (8): 951-961.

近红外窄带光照下不同水果背景中桔小实蝇的图像分割

娄定风^1,2，刘新娇^1,2，徐浪^1,2，赖天树³，余道坚^1,2，焦懿^1,2，陈志粦^1,2，陈彦伦^4,*

（1. 深圳市检验检疫科学研究院, 广东深圳 518010; 2. 深圳出入境检验检疫局动植物检验检疫技术中心, 广东深圳 518045;
3. 中山大学物理科学与工程技术学院, 广州 510275; 4. 中国科学院深圳先进技术研究院, 广东深圳 518055）

出版日期:2014-08-20 发布日期:2014-08-20

Segmentation of the oriental fruit fly, Bactrocera dorsalis (Diptera, Tephritidae) on the background of fruits under the illumination of near-infrared narrow-band light

LOU Ding-Feng^1,2, LIU Xin-Jiao^1,2, XULang^1,2, LAI Tian-Shu³, YU Dao-Jian^1,2, JIAO Yi^1,2, CHEN Zhi-Lin^1,2, CHEN Yan-Lun^4,*

(1.Shenzhen Academy of Inspection and Quarantine, Shenzhen, Guangdong 518010, China; 2.Shenzhen Exit and Entry Inspection and Quarantine Bureau, Shenzhen, Guangdong 518045, China; 3.School of Physics and Engineering, Sun Yat-Sen University, Guangzhou 510275, China; 4.Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong 518055, China)

Online:2014-08-20 Published:2014-08-20

摘要/Abstract

摘要： 【目的】为了增强水果背景中桔小实蝇Bactrocera dorsalis Hendel（双翅目实蝇科）的识别效果，研究了该种昆虫与不同水果之间的反射光谱差异。【方法】采用紫外可见光近红外分光光度计测量了桔小实蝇与16种水果在400~2 500 nm波段的反射光谱。在中心波长为565 nm和827 nm的窄谱带光源及日光3种光源分别照射下，分别拍摄各种水果背景中的桔小实蝇照片，并用大津Otsu算法对照片进行二值化处理。【结果】发现桔小实蝇的反射率随波长增加而缓慢地增大，最大反射率小于40%。而16种水果的最强反射峰全部或部分落在在777～896 nm。不同水果平均最大反射率为41.10%～97.89%，与桔小实蝇在此波段的低反射率（约30%）形成强烈的反差。在827 nm中心波长窄带光源照射下拍摄的照片中，发现桔小实蝇为黑色，而背景水果呈现大面积的白色，形成高反差，桔小实蝇很容易被辨识。相反，在日光和565 nm中心波长窄带光源照射的照片中，水果背景存在较多的黑色斑块，容易与桔小实蝇的黑区混淆；或者该虫形成白斑，从而无法识别。【结论】选用近红外波段的窄带光源照射能明显提高桔小实蝇与水果图像的对比度，增强桔小实蝇的分割效果。

关键词: 桔小实蝇, 水果, 反射光谱, 近红外光, 图像识别

Abstract: 【Aim】 To enhance the recognition effect of Bactrocera dorsalis Hendel (Diptera, Tephritidae) on the background of fruits, the difference in the reflectivity spectra of the insect and different fruits was studied. 【Methods】 The reflectivity spectra of B. dorsalis and 16 species of fruits were first measured in the wavelength range of 400-2 500 nm using the UV-Vis-NIR spectrometer. Then images of the flies on the fruits were taken respectively under the illumination of narrow-band light with the central wavelengths of 565 and 827 nm as well as sunlight, and binarization of the images was made according to Otsu algorithm. 【Results】 We found that the reflectivity of B. dorsalis increased slowly with the wavelength, and approached to the maximum (<40%), while the strongest reflectivity peak of the sixteen species of fruits was located between 777 and 896 nm entirely or partially. The average maximum reflectivity of each species of fruit ranged from 41.10% to 97.89%, while that of B. dorsalis was approximately 30%, leading to a higher difference in this NIR (near-infrared light) range. It was found that B. dorsalis was dark on the large-area bright background of fruits in the images taken under the illustration of narrow-band light with a central wavelength of 827 nm, which can be recognized easily because of a high contrast between B. dorsalis and the fruits. Contrarily, under the illustration of sunlight and narrow-band light with a central wavelength of 565 nm, more black spots were found in the images of the fruits which were confused with the dark images of B. dorsalis, or the insect appeared as a white spot, causing recognition failure. 【Conclusion】 We confirmed that the image contrast between B. dorsalis and fruits, and the segmentation effect of B. dorsalis can be enhanced under the illumination of the NIR narrow-band light.

Key words: Bactrocera dorsalis, fruit, reflectance spectroscopy, near-infrared light (NIR), image identification

娄定风，刘新娇，徐浪，赖天树，余道坚，焦懿，陈志粦，陈彦伦. 近红外窄带光照下不同水果背景中桔小实蝇的图像分割[J]. , 2014, 57(8): 951-961.

LOU Ding-Feng, LIU Xin-Jiao, XU Lang, LAI Tian-Shu, YU Dao-Jian, JIAO Yi, CHEN Zhi-Lin CHEN Yan-Lun. Segmentation of the oriental fruit fly, Bactrocera dorsalis (Diptera, Tephritidae) on the background of fruits under the illumination of near-infrared narrow-band light[J]. , 2014, 57(8): 951-961.

[1]	俞佩仕, 郭龙军, 姚青, 杨保军, 唐健, 许渭根, 陈渝阳, 朱旭华, 陈宏明, 张晨光, 段德康, 贝文勇, 彭晴晖. 基于移动终端的稻田飞虱调查方法[J]. 昆虫学报, 2019, 62(5): 615-623.
[2]	庾琴, 杜恩强, 封云涛, 郭晓君, 张润祥, 郝赤. 果实种类及发育阶段对梨小食心虫幼虫钻蛀率和蛹重的影响[J]. 昆虫学报, 2019, 62(11): 1297-1304.
[3]	林涛, 陈婷, 何余容, 胡学难, 梁帆, 雷妍圆, 吕利华. 一种可用于桔小实蝇表皮碳氢化合物分析的固体进样技术[J]. 昆虫学报, 2016, 59(3): 278-291.
[4]	陈小燕, 刘家莉, 郭文举, 曾鑫年. 桔小实蝇雄成虫联系性嗅觉学习[J]. , 2015, 58(9): 973-980.
[5]	陈朗杰, 刘昕, 吴善俊, 朱弋凡, 曾玲, 陆永跃. 桔小实蝇抗敌百虫品系的实验种群生物学比较研究[J]. , 2015, 58(8): 864-871.
[6]	袁瑞玲, 王晓渭, 杨珊, 陈鹏. 不同日龄和吊飞过程中桔小实蝇成虫飞行肌能量代谢相关酶活性的变化[J]. , 2015, 58(5): 471-478.
[7]	竺乐庆, 张大兴, 张真. 基于韦伯局部描述子和颜色直方图的鳞翅目昆虫翅图像特征描述与种类识别[J]. , 2015, 58(4): 419-426.
[8]	竺乐庆, 张大兴, 张真. 基于颜色名和OpponentSIFT特征的鳞翅目昆虫图像识别[J]. , 2015, 58(12): 1331-1337.
[9]	刘国成, 张杨, 黄建华, 汤文亮. 基于K-means聚类算法的叶螨图像分割与识别[J]. , 2015, 58(12): 1338-1343.
[10]	蔡玉音，武强，刘桂清，吕志创，李建伟，张桂芬，万方浩. 桔小实蝇细胞凋亡基因hid的克隆及不同发育阶段表达分析[J]. , 2014, 57(6): 673-680.
[11]	陈玲, 李红亮, 周宇翔, 赵磊, 张林雅, 倪翠侠, 商晗武. 桔小实蝇气味结合蛋白BdorOBP2的cDNA克隆、组织表达及配基结合特性[J]. , 2013, 56(6): 612-621.
[12]	李柏树，詹国平，王跃进，任荔荔，刘波，李天秀. 桔小实蝇、木瓜实蝇和番石榴实蝇耐热性的热动力学分析[J]. , 2013, 56(12): 1404-1412.
[13]	竺乐庆, 张真. 基于稀疏编码和SCG BPNN的鳞翅目昆虫图像识别[J]. , 2013, 56(11): 1335-1341.
[14]	刘慎思, 张桂芬, 武强, 张爱兵, 王进军, 万方浩. 桔小实蝇幼体及成虫残体DNA条形码识别技术的建立与应用[J]. , 2012, 55(3): 336-343.
[15]	申建梅, 胡黎明, 宾淑英, 林进添. 桔小实蝇肌球蛋白轻链2基因的克隆及表达分析[J]. , 2011, 54(5): 508-514.