文章基本信息

标题：Research on Carrot Grading Based on Machine Vision Feature Parameters
本地全文：下载
作者：Weijun Xie ; Fenghe Wang ; Deyong Yang 等
期刊名称：IFAC PapersOnLine
印刷版ISSN：2405-8963
出版年度：2019
卷号：52
期号：30
页码：30-35
DOI：10.1016/j.ifacol.2019.12.485
语种：English
出版社：Elsevier
摘要：Carrot grading is a crucial part in the carrot processing and marketing. At present, the grading of carrots mainly depends on manual grading, which is labor intensive and low efficient In this paper, six shape parameters of carrot, including length, maximum diameter, average diameter, area, perimeter and aspect ratio, and six color parameters on R, G, B, H, S and V components were extracted by machine vision. Taking these 12 parameters as input feature parameters, the grading recognition models of back propagation neural network (BPNN), support vector machine (SVM) and extreme learning machine (ELM) are constructed, and compared by the recognition effects. The results show that the image acquisition system constructed in this paper can extract the feature parameters of carrot accurately. As a simple and easy to solve algorithm, the ELM model based on shape and color parameters has the best recognition effect and the recognition accuracy reaches 96.67%. It provides a reference classification method of carrots by digital.
关键词：KeywordsCarrotMachine VisionNeural NetworkSupport Vector MachineExtreme Learning Machine