基于S和I区域特征的机采棉分割算法

Proceedings of 5th International Conference on Vehicle, Mechanical and Electrical Engineering Pub Date : 1900-01-01 DOI:10.5220/0008850503470353

Lei Li, Chengliang Zhang, Xinyu Zheng

{"title":"基于S和I区域特征的机采棉分割算法","authors":"Lei Li, Chengliang Zhang, Xinyu Zheng","doi":"10.5220/0008850503470353","DOIUrl":null,"url":null,"abstract":": A segmentation method based on regional color information is proposed for the complicated natural impurities in machine-harvested cotton. The color gradient operation of the filtered machine cotton picking image is carried out, and the marked image is obtained by extended minimum transformation operation. The initial segmented image is obtained by using the watershed algorithm on the modified gradient image. Spatial proximity and color information are considered comprehensively in the process of region merging. Saturation S and brightness I as color information feature are mainly used in the paper. In order to make the algorithm more accurately, the information features are updated in the process of merging. The experimental results show that the average segmentation accuracy of the method for natural impurities is 92%.","PeriodicalId":186406,"journal":{"name":"Proceedings of 5th International Conference on Vehicle, Mechanical and Electrical Engineering","volume":"45 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Segmentation Algorithm for Machine-Harvested Cotton based on S and I Regional Features\",\"authors\":\"Lei Li, Chengliang Zhang, Xinyu Zheng\",\"doi\":\"10.5220/0008850503470353\",\"DOIUrl\":null,\"url\":null,\"abstract\":\": A segmentation method based on regional color information is proposed for the complicated natural impurities in machine-harvested cotton. The color gradient operation of the filtered machine cotton picking image is carried out, and the marked image is obtained by extended minimum transformation operation. The initial segmented image is obtained by using the watershed algorithm on the modified gradient image. Spatial proximity and color information are considered comprehensively in the process of region merging. Saturation S and brightness I as color information feature are mainly used in the paper. In order to make the algorithm more accurately, the information features are updated in the process of merging. The experimental results show that the average segmentation accuracy of the method for natural impurities is 92%.\",\"PeriodicalId\":186406,\"journal\":{\"name\":\"Proceedings of 5th International Conference on Vehicle, Mechanical and Electrical Engineering\",\"volume\":\"45 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1900-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of 5th International Conference on Vehicle, Mechanical and Electrical Engineering\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.5220/0008850503470353\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of 5th International Conference on Vehicle, Mechanical and Electrical Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5220/0008850503470353","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

针对机采棉中复杂的天然杂质，提出了一种基于区域颜色信息的分割方法。对过滤后的机器采棉图像进行颜色梯度运算，通过扩展最小变换得到标记图像。利用分水岭算法对修改后的梯度图像进行初始分割。在区域合并过程中综合考虑了空间接近性和颜色信息。本文主要使用饱和度S和亮度I作为颜色信息特征。为了提高算法的准确性，在合并过程中对信息特征进行了更新。实验结果表明，该方法对天然杂质的平均分割准确率为92%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Segmentation Algorithm for Machine-Harvested Cotton based on S and I Regional Features

: A segmentation method based on regional color information is proposed for the complicated natural impurities in machine-harvested cotton. The color gradient operation of the filtered machine cotton picking image is carried out, and the marked image is obtained by extended minimum transformation operation. The initial segmented image is obtained by using the watershed algorithm on the modified gradient image. Spatial proximity and color information are considered comprehensively in the process of region merging. Saturation S and brightness I as color information feature are mainly used in the paper. In order to make the algorithm more accurately, the information features are updated in the process of merging. The experimental results show that the average segmentation accuracy of the method for natural impurities is 92%.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Proceedings of 5th International Conference on Vehicle, Mechanical and Electrical Engineering

自引率

0.00%

发文量