周孟然,燕晶晶,来文豪,王锦国,胡 锋,卞 凯,孔茜茜.基于完全局部二值模式的多光谱法识别损伤苹果[J].食品安全质量检测学报,2021,12(23):9086-9092
基于完全局部二值模式的多光谱法识别损伤苹果
Multispectral damage identification of apple based on complete local binary pattern
投稿时间:2021-07-07  修订日期:2021-12-01
DOI:
中文关键词:  多光谱成像  完全局部二值模式  支持向量机  损伤苹果
英文关键词:multispectral imaging  complete local binary pattern  support vector machine  damaged apples
基金项目:国家重点研发计划项目(2018YFC0604503)
作者单位
周孟然 安徽理工大学电气与信息工程学院 
燕晶晶 安徽理工大学电气与信息工程学院 
来文豪 安徽理工大学电气与信息工程学院 
王锦国 安徽理工大学电气与信息工程学院 
胡 锋 安徽理工大学电气与信息工程学院 
卞 凯 安徽理工大学电气与信息工程学院 
孔茜茜 安徽理工大学电气与信息工程学院 
AuthorInstitution
ZHOU Meng-Ran College of Electrical and Information Engineering, Anhui University of Science and Technology 
YAN Jing-Jing College of Electrical and Information Engineering, Anhui University of Science and Technology 
LAI Wen-Hao College of Electrical and Information Engineering, Anhui University of Science and Technology 
WANG Jin-Guo College of Electrical and Information Engineering, Anhui University of Science and Technology 
HU Feng College of Electrical and Information Engineering, Anhui University of Science and Technology 
BIAN Kai College of Electrical and Information Engineering, Anhui University of Science and Technology 
KONG Xi-Xi College of Electrical and Information Engineering, Anhui University of Science and Technology 
摘要点击次数: 180
全文下载次数: 87
中文摘要:
      目的 建立一种基于完全局部二值模式的多光谱法识别损伤苹果。方法 搭建苹果的多光谱数据采集平台, 采集了558组苹果多光谱数据。使用完全局部二值模式算法提取苹果的特征向量, 再将特征向量送入支持向量机中, 以比较分类结果。结果 通过准确率、特异度和召回率3个平均指标, 在完全局部二值模式结合支持向量机分类模型下, 苹果多光谱图像的25个波段对表皮有损苹果和表皮无损苹果有很好的识别效果,并在第20波段的识别准确率达到最高为99.63%。结论 本方法可以实现有损苹果和无损苹果的高效识别, 对苹果的储运和分选都有一定的意义。
英文摘要:
      Objective To establish a multispectral method for identifying damaged apples based on complete local binary mode. Methods The apple multispectral data acquisition platform was built and 558 groups of apple multispectral data were collected. The full local binary pattern algorithm was used to extract the feature vectors of apples, and then the feature vectors were fed into the support vector machine to compare the classification results. Results Through the 3 average indicators of accuracy, specificity and recall, and under the complete local binary pattern combined with support vector machine classification model, the 25 bands of apple multispectral image had a good recognition effect on damaged apples and lossless apples, and the recognition accuracy rate in the 20th band reached the highest 99.63%. Conclusion This method can realize the efficient identification of damaged apples and lossless apples, and has certain significance for the storage, transportation and sorting of apples.
查看全文  查看/发表评论  下载PDF阅读器