{"title":"基于图像处理技术的生物污垢检测","authors":"V. Grishkin, O. Iakushkin, N. Stepenko","doi":"10.1109/CSITECHNOL.2017.8312162","DOIUrl":null,"url":null,"abstract":"Traditional methods for performing biofouling detection are based upon probing object surfaces for subsequent laboratory research. Such methods result in large effort, they are expensive, and require expert consultations. Knowledge of the type of biological contaminants is necessary to protect objects from their harmful impact. In this paper we propose a method for determination of types of biological contaminants existing on the objects surface. The proposed method uses a collection of object's images as input. The collection contains images obtained in the visible and near infrared spectral bands. During pre-processing the series, all images are converted to a selected shooting point, and the background is removed. Feature vector is built from combinations of formal vegetation indices. To recognize the type of biological contaminants, we used a pre-trained classifier based on SVM method with RBF kernel.","PeriodicalId":332371,"journal":{"name":"2017 Computer Science and Information Technologies (CSIT)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Biofouling detection based on image processing technique\",\"authors\":\"V. Grishkin, O. Iakushkin, N. Stepenko\",\"doi\":\"10.1109/CSITECHNOL.2017.8312162\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Traditional methods for performing biofouling detection are based upon probing object surfaces for subsequent laboratory research. Such methods result in large effort, they are expensive, and require expert consultations. Knowledge of the type of biological contaminants is necessary to protect objects from their harmful impact. In this paper we propose a method for determination of types of biological contaminants existing on the objects surface. The proposed method uses a collection of object's images as input. The collection contains images obtained in the visible and near infrared spectral bands. During pre-processing the series, all images are converted to a selected shooting point, and the background is removed. Feature vector is built from combinations of formal vegetation indices. To recognize the type of biological contaminants, we used a pre-trained classifier based on SVM method with RBF kernel.\",\"PeriodicalId\":332371,\"journal\":{\"name\":\"2017 Computer Science and Information Technologies (CSIT)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 Computer Science and Information Technologies (CSIT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CSITECHNOL.2017.8312162\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 Computer Science and Information Technologies (CSIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CSITECHNOL.2017.8312162","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Biofouling detection based on image processing technique
Traditional methods for performing biofouling detection are based upon probing object surfaces for subsequent laboratory research. Such methods result in large effort, they are expensive, and require expert consultations. Knowledge of the type of biological contaminants is necessary to protect objects from their harmful impact. In this paper we propose a method for determination of types of biological contaminants existing on the objects surface. The proposed method uses a collection of object's images as input. The collection contains images obtained in the visible and near infrared spectral bands. During pre-processing the series, all images are converted to a selected shooting point, and the background is removed. Feature vector is built from combinations of formal vegetation indices. To recognize the type of biological contaminants, we used a pre-trained classifier based on SVM method with RBF kernel.