基于高光谱成像的苹果虫伤缺陷与果梗/花萼识别方法

被引：32

作者：

田有文 ^{[1
]}

程怡 ^{[1
]}

王小奇 ^{[2
]}

刘思伽 ^{[1
]}

机构：

[1] 沈阳农业大学信息与电气工程学院

[2] 沈阳农业大学植物保护学院

来源：

农业工程学报 | 2015年 / 31卷 / 04期

关键词：

无损检测; 图像处理; 主成分分析; 苹果虫伤; 果梗/花萼; 高光谱成像; 支持向量机;

D O I：

暂无

中图分类号：

TP391.41 [];

学科分类号：

080203 ;

摘要：

为了快速、准确、无损检测在果梗/花萼的干扰下苹果虫伤缺陷,该文利用高光谱成像技术,首先选取正常果和虫伤果各80个,提取并分析了苹果表面感兴趣区域(虫伤区域、果梗区域、花萼区域、正常区域)的光谱曲线,结合824 nm波长特征图像的阈值分割和主成分分析,对获得的第一主成分图像提取160×120像素大小的感兴趣区域。然后提取感兴趣区域的能量、熵、惯性矩和相关性4个纹理特征,融合646、824 nm波段的相对光谱反射率的光谱特征,采用支持向量机对苹果虫伤区域和正常区域、果梗/花萼区域进行识别。试验结果表明:选取160×120像素大小的感兴趣区域图像、采用径向基核函数对正常果、果梗/花萼果与虫伤果的识别效果最好,总体识别率为97.8%。该研究为苹果质量等级在线评判提供理论依据。

引用

页码：325 / 331

页数：7

共 34 条

[11] Hyperspectral near-infrared imaging for the detection of physical damages of pear.[J].Wang-Hee Lee;Moon S. Kim;Hoonsoo Lee;Stephen R. Delwiche;Hanhong Bae;Dae-Yong Kim;Byoung-Kwan Cho.Journal of Food Engineering.2014,
[12] Studies on classification models to discriminate ‘Braeburn’ apples affected by internal browning using the optical properties measured by time-resolved reflectance spectroscopy.[J].Maristella Vanoli;Anna Rizzolo;Maurizio Grassi;Lorenzo Spinelli;Bert E. Verlinden;Alessandro Torricelli.Postharvest Biology and Technology.2014,
[13] Grading of apples based on firmness and soluble solids content using Vis/SWNIR spectroscopy and spectral scattering techniques.[J].Fernando Mendoza;Renfu Lu;Haiyan Cen.Journal of Food Engineering.2014,
[14] Automated apple stem end and calyx detection using evolution-constructed features
Zhang, Dong
Lillywhite, Kirt D.
Lee, Dah-Jye
Tippetts, Beau J.
[J]. JOURNAL OF FOOD ENGINEERING, 2013, 119 (03) : 411 - 418
[15] Automatic image analysis and spot classification for detection of fruit fly infestation in hyperspectral images of mangoes.[J].Ronald P. Haff;Sirinnapa Saranwong;Warunee Thanapase;Athit Janhiran;Sumaporn Kasemsumran;Sumio Kawano.Postharvest Biology and Technology.2013,
[16] Advanced applications of hyperspectral imaging technology for food quality and safety analysis and assessment: A review — Part I: Fundamentals.[J].Di Wu;Da-Wen Sun.Innovative Food Science and Emerging Technologies.2013,
[17] Supervised classification of bruised apples with respect to the time after bruising on the basis of hyperspectral imaging data.[J].Piotr Baranowski;Wojciech Mazurek;Joanna Pastuszka-Wo?niak.Postharvest Biology and Technology.2013,
[18] Principles and Applications of Hyperspectral Imaging in Quality Evaluation of Agro-Food Products: A Review
Elmasry, Gamal
Kamruzzaman, Mohammed
Sun, Da-Wen
Allen, Paul
[J]. CRITICAL REVIEWS IN FOOD SCIENCE AND NUTRITION, 2012, 52 (11) : 999 - 1023
[19] Recent Advances and Applications of Hyperspectral Imaging for Fruit and Vegetable Quality Assessment
Lorente, D.
Aleixos, N.
Gomez-Sanchis, J.
Cubero, S.
Garcia-Navarrete, O. L.
Blasco, J.
[J]. FOOD AND BIOPROCESS TECHNOLOGY, 2012, 5 (04) : 1121 - 1142
[20] Apple Grading Method Based on Features Fusion of Size; Shape and Color.[J].Xianfeng Li;Weixing Zhu.Procedia Engineering.2011,

← 1 2 3 4 →