LOG和Fisher算法的壳类食品表面裂纹检测方法  

Surface Crack Detection of Shell Food Based on LOG and Fisher Algorithm

作　　者：吴剑杰[1] WU Jianjie(Shaoxing Vocational and Technical College,Shaoxing 312000)

机构地区：[1]绍兴职业技术学院,绍兴312000

出　　处：《食品工业》2020年第10期325-328,共4页The Food Industry

摘　　要：为提高禽蛋表面裂纹检测的准确性,以鸡蛋表面裂纹检测为研究对象,结合机器视觉设计一种表面裂纹检测方法。给出鸡蛋表面图像采集系统结构。重点论述裂纹图像分析方法,采用负LOG算子实现裂纹图像增强;利用双阈值分割算法实现裂纹区域识别;在消除鸡蛋边缘后,采用Fisher算法完成裂纹识别。试验结果表明,所述方法对裂纹的识别准确率达98.5%,具有较高检测精度;所述表面图像处理算法可有效避免噪声等干扰影响,处理效果较好,可满足检测要求;该方法可适用于绝大多数禽蛋表面裂纹检测。In order to improve the accuracy of egg surface crack detection,a method was designed for egg surface crack detection with machine vision.The structure of egg surface image acquisition system was presented.The method of crack image analysis was emphasized.Negative LOG operator was used to enhance the crack image.Double threshold segmentation algorithm was used to identify the crack region.After eliminating the edge of the egg,the Fisher algorithm was used to identify the crack.The experimental results showed that the accuracy of crack detection was up to 98.5%,which was high.The surface image processing algorithm could effectively avoid noise and other interference,and the processing effect was good,which could meet the detection requirements.This method could be used to detect most egg surface cracks.

关 键 词：裂纹检测 机器视觉 负LOG算子 双阈值分割 Fisher算法 

分 类 号：TS253.7[轻工技术与工程—农产品加工及贮藏工程] TP391.41[轻工技术与工程—食品科学与工程]