脱囊衣橘片自动分拣机器视觉算法研究  

Research on machine vision algorithm for automatic sorting of membrane-removed mandarin segments

作　　者：任磊[1] 张俊[2] 陆胜民[2] 

机构地区：[1]浙江师范大学化学与生命科学院,浙江金华321004 [2]浙江省农业科学院食品科学研究所/浙江省果蔬保鲜与加工技术研究重点实验室,浙江杭州310021

出　　处：《浙江农业学报》2015年第12期2212-2217,共6页Acta Agriculturae Zhejiangensis

基　　金：基金项目:国家现代农业( 柑橘) 产业技术体系

摘　　要：柑橘罐头生产过程中,脱囊衣后橘片存在囊衣、橘核残留,橘片破损等缺陷,影响产品品质。目前,生产中都采用人工分拣剔除,试验针对以上3种缺陷橘片设计了基于LabVIEW的机器视觉快速检测算法,并构建试验平台,检测算法准确率与效率。结果表明,采用该算法检测准确率可达到(99.1±0.5)%,平均耗时(17±5)ms,可实现每秒(64±19)片的检测速度。During the production of mandarin cans, some membrane-removed mandarin segments have defects such as membrane residues, seed residues or segment damage, which would affect the quality of products. Currently, fac- tories adopt manual inspection to reject defective segments, which increased the cost and may cause hygiene prob- lems. Based on LabVIEW, a machine vision program for the automatic sorting of membrane-removed mandarin seg- ments was designed. An experimental platform was built with color GigE camera, white ring light and red fiat light, to test inspection accuracy and duration. It was shown that the accuracy of inspection program reached （99. 1 ±0. 5 ） % , and the average time consumption was （ 17± 5 ） ms. The inspect speed was able to achieve （ 64 ± 19 ） pieces per second.

关 键 词：LABVIEW 机器视觉 自动分拣算法 脱囊衣橘片 

分 类 号：TS201.1[轻工技术与工程—食品科学] S666[轻工技术与工程—食品科学与工程]