基于平均强度符号(AIS)特征的离线签名验证:基于机器学习的伪造检测

R. Sathya, S. Ananthi, R. Rupika, N. Santhiya, K. Lavanya
{"title":"基于平均强度符号(AIS)特征的离线签名验证:基于机器学习的伪造检测","authors":"R. Sathya, S. Ananthi, R. Rupika, N. Santhiya, K. Lavanya","doi":"10.1109/ICAISS55157.2022.10010812","DOIUrl":null,"url":null,"abstract":"The human offline signs are the utmost extensively approved biometric verification procedures in colleges, industries, banking and various domain due to its easiness and exclusivity. Numerous computerized technologies have been established to predict the human offline signature for forgery detection. Because, the offline biometric identification system has expanded a histrionic movement. This paper Suggests a technique for offline sign identification system using image processing techniques. The proposed offline sign identification system has four stages. In the first stage, the pre-processing of human sig can be done. The pre-processing stage can be done by means of image processing concepts which includes color conversion and next smoothening technique can be done using Gaussian filter. And followed by noise removal method can be done using morphological operation. The second stage of proposed system is sign detection using various edge detection algorithm. In the third stage, extract the Average Intensity Sign (AIS) featurefrom detected sign image. Finally, signature verification system can be utilized for forgery detection using machine learning SVM techniques. The proposed sign identification method demonstrations that the real time experimental output has extreme achievement ratio. This proposed algorithm yields average accuracyof 98.91% in SVM (RBF) in 36 AIS features when associated to an SVM(polynomial) classifier.","PeriodicalId":243784,"journal":{"name":"2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS)","volume":"695 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Average Intensity Sign (AIS) Feature based Offline Signature Verification for Forgery Detection using Machine Learning\",\"authors\":\"R. Sathya, S. Ananthi, R. Rupika, N. Santhiya, K. Lavanya\",\"doi\":\"10.1109/ICAISS55157.2022.10010812\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The human offline signs are the utmost extensively approved biometric verification procedures in colleges, industries, banking and various domain due to its easiness and exclusivity. Numerous computerized technologies have been established to predict the human offline signature for forgery detection. Because, the offline biometric identification system has expanded a histrionic movement. This paper Suggests a technique for offline sign identification system using image processing techniques. The proposed offline sign identification system has four stages. In the first stage, the pre-processing of human sig can be done. The pre-processing stage can be done by means of image processing concepts which includes color conversion and next smoothening technique can be done using Gaussian filter. And followed by noise removal method can be done using morphological operation. The second stage of proposed system is sign detection using various edge detection algorithm. In the third stage, extract the Average Intensity Sign (AIS) featurefrom detected sign image. Finally, signature verification system can be utilized for forgery detection using machine learning SVM techniques. The proposed sign identification method demonstrations that the real time experimental output has extreme achievement ratio. This proposed algorithm yields average accuracyof 98.91% in SVM (RBF) in 36 AIS features when associated to an SVM(polynomial) classifier.\",\"PeriodicalId\":243784,\"journal\":{\"name\":\"2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS)\",\"volume\":\"695 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICAISS55157.2022.10010812\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICAISS55157.2022.10010812","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

摘要

人体线下标志以其简单、独特的特点,在高校、工业、银行等各个领域得到了最广泛的认可。已经建立了许多计算机技术来预测用于伪造检测的人类离线签名。因为,离线生物识别系统已经发展成为一种戏剧性的运动。本文提出了一种基于图像处理技术的离线标识识别系统。本文提出的离线标识识别系统分为四个阶段。在第一阶段,可以对人的信号进行预处理。预处理阶段可以通过图像处理概念来完成,其中包括颜色转换,然后使用高斯滤波器进行平滑处理。然后利用形态学运算进行噪声去除。该系统的第二阶段是使用各种边缘检测算法进行符号检测。第三阶段,从检测到的标志图像中提取平均强度标志(AIS)特征。最后,利用机器学习支持向量机技术,将签名验证系统用于伪造检测。所提出的符号识别方法表明,实时实验输出具有极高的完成率。当与SVM(多项式)分类器相关联时,该算法在36个AIS特征中的SVM(RBF)平均准确率达到98.91%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Average Intensity Sign (AIS) Feature based Offline Signature Verification for Forgery Detection using Machine Learning
The human offline signs are the utmost extensively approved biometric verification procedures in colleges, industries, banking and various domain due to its easiness and exclusivity. Numerous computerized technologies have been established to predict the human offline signature for forgery detection. Because, the offline biometric identification system has expanded a histrionic movement. This paper Suggests a technique for offline sign identification system using image processing techniques. The proposed offline sign identification system has four stages. In the first stage, the pre-processing of human sig can be done. The pre-processing stage can be done by means of image processing concepts which includes color conversion and next smoothening technique can be done using Gaussian filter. And followed by noise removal method can be done using morphological operation. The second stage of proposed system is sign detection using various edge detection algorithm. In the third stage, extract the Average Intensity Sign (AIS) featurefrom detected sign image. Finally, signature verification system can be utilized for forgery detection using machine learning SVM techniques. The proposed sign identification method demonstrations that the real time experimental output has extreme achievement ratio. This proposed algorithm yields average accuracyof 98.91% in SVM (RBF) in 36 AIS features when associated to an SVM(polynomial) classifier.
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
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信