基于网格特征和模糊匹配的徽标识别  

Logo recognition based on grid feature and fuzzy matching

作　　者：王刚[1] 靳彦青[2] 储瑞来[3] 

机构地区：[1]解放军信息工程大学,河南郑州450002 [2]国家数字交换系统工程技术研究中心,河南郑州450002 [3]南京理工大学,江苏南京210094

出　　处：《计算机工程与科学》2013年第7期119-123,共5页Computer Engineering & Science

基　　金：国家863高技术研究发展计划资助项目(2009AA011202);国家科技重大专项基金资助项目(2009ZX03006-007)

摘　　要：针对图像智能处理中对徽标识别的应用需求,提出了一种基于网格特征和模糊匹配的徽标识别算法。该算法通过提取徽标的网格特征并映射为模糊集隶属度特征,根据模糊匹配技术进行识别,显著增强了对质量不佳图像的适应性和抗干扰性。实验表明,该算法的识别准确率能达到95.5%,并能有效提高徽标识别系统的鲁棒性。Aim at the application requirement of logo recognition in image intelligent processing, a logo recognition algorithm based on grid feature and fuzzy matching is proposed. The grid feature of the logo is extracted, and then transformed into the membership degree of fuzzy sets. At last, closeness de- gree is used to accomplish logo recognition. This significantly enhances adaptability and anti-interference to the poor quality image, and effectively improves the flexible processing capability of logo recognition system. Experimental results show that the recognition rate of the logo recognition algorithm can reach as high as 95.5%.

关 键 词：徽标识别 网格特征 模糊匹配 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]