A comparison of two different proposed feature sets for trademark recognition using neural network

Proceedings. IEEE International Multi Topic Conference, 2001. IEEE INMIC 2001. Technology for the 21st Century. Pub Date : 2001-12-28 DOI:10.1109/INMIC.2001.995350

M. F. Zafar, Dzulkifli Mohamad

{"title":"A comparison of two different proposed feature sets for trademark recognition using neural network","authors":"M. F. Zafar, Dzulkifli Mohamad","doi":"10.1109/INMIC.2001.995350","DOIUrl":null,"url":null,"abstract":"The problem of trademark recognition relates to pattern recognition. Pattern recognition needs as basis knowledge about the object. The knowledge of object can be obtained by feature extraction with image processing tools. The success of any such practical system depends critically upon how far a set of appropriate numerical attributes or features can be extracted from the object of interest for the purpose of matching or recognition. In this paper, two different combinations of image features are proposed and their comparative results for trademarks recognition are discussed. The proposed features involve some simple ratios of the image pixels as well as some geometric moments. These features are invariant to translation, rotation and scaling. The goal was achieved by segmenting the image using a connected-component (nearest neighbours) algorithm. Then the features are used as inputs for a backpropagation neural network for the learning and matching tasks. The effectiveness of the proposed feature sets is tested with various trademarks, and the results are encouraging.","PeriodicalId":286459,"journal":{"name":"Proceedings. IEEE International Multi Topic Conference, 2001. IEEE INMIC 2001. Technology for the 21st Century.","volume":"119 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2001-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings. IEEE International Multi Topic Conference, 2001. IEEE INMIC 2001. Technology for the 21st Century.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/INMIC.2001.995350","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 2

Abstract

The problem of trademark recognition relates to pattern recognition. Pattern recognition needs as basis knowledge about the object. The knowledge of object can be obtained by feature extraction with image processing tools. The success of any such practical system depends critically upon how far a set of appropriate numerical attributes or features can be extracted from the object of interest for the purpose of matching or recognition. In this paper, two different combinations of image features are proposed and their comparative results for trademarks recognition are discussed. The proposed features involve some simple ratios of the image pixels as well as some geometric moments. These features are invariant to translation, rotation and scaling. The goal was achieved by segmenting the image using a connected-component (nearest neighbours) algorithm. Then the features are used as inputs for a backpropagation neural network for the learning and matching tasks. The effectiveness of the proposed feature sets is tested with various trademarks, and the results are encouraging.

查看原文本刊更多论文

基于神经网络的商标识别两种不同特征集的比较

商标识别问题涉及到模式识别问题。模式识别需要对象的基础知识。利用图像处理工具对目标进行特征提取，从而获得目标的知识。任何此类实际系统的成功关键取决于从感兴趣的对象中提取一组适当的数字属性或特征的程度，以便进行匹配或识别。本文提出了两种不同的图像特征组合，并对其用于商标识别的比较结果进行了讨论。所提出的特征涉及图像像素的一些简单比例以及一些几何矩。这些特征对于平移、旋转和缩放是不变的。目标是通过使用连接组件(最近邻)算法分割图像来实现的。然后将这些特征作为反向传播神经网络的输入，用于学习和匹配任务。用不同的商标对所提出的特征集的有效性进行了测试，结果令人鼓舞。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Proceedings. IEEE International Multi Topic Conference, 2001. IEEE INMIC 2001. Technology for the 21st Century.

自引率

0.00%

发文量