Symmetry features for license plate classification

作     者：Karpuravalli Srinivas Raghunandan Palaiahnakote Shivakumara Lolika Padmanabhan Govindaraju Hemantha Kumar Tong Lu Umapada Pal Karpuravalli Srinivas Raghunandan;Palaiahnakote Shivakumara;Lolika Padmanabhan;Govindaraju Hemantha Kumar;Tong Lu;Umapada Pal

作者机构：Department of Studies in Computer Science University of Mysore Karnataka India Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia PES Institute of Technology Bangalore Karnataka India National Key Lab for Novel Software Technology Nanjing University Nanjing People's Republic of China Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India 

出 版 物：《CAAI Transactions on Intelligence Technology》 (智能技术学报（英文）)

年 卷 期：2018年第3卷第3期

页      面：176-183页

核心收录：

学科分类：13[艺术学] 08[工学] 1305[艺术学-设计学（可授艺术学、工学学位）] 0810[工学-信息与通信工程] 1205[管理学-图书情报与档案管理] 0839[工学-网络空间安全] 081104[工学-模式识别与智能系统] 080203[工学-机械设计及理论] 0804[工学-仪器科学与技术] 0835[工学-软件工程] 0802[工学-机械工程] 081101[工学-控制理论与控制工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：车牌图像 图像识别 识别技术 计算机技术 

摘      要：Achieving high recognition rate for license plate images is challenging due to multi-type images. We present new symmetry features based on stroke width for classifying each input license image as private, taxi, cursive text, when they expand the symbols by writing and non-text such that an appropriate optical character recognition （OCR） can be chosen for enhancing recognition performance. The proposed method explores gradient vector flow （GVF） for defining symmetry features, namely, GVF opposite direction, stroke width distance, and stroke pixel direction. Stroke pixels in Canny and Sobel which satisfy the above symmetry features are called local candidate stroke pixels. Common stroke pixels of the local candidate stroke pixels are considered as the global candidate stroke pixels. Spatial distribution of stroke pixels in local and global symmetry are explored by generating a weighted proximity matrix to extract statistical features, namely, mean, standard deviation, median and standard deviation with respect the median. The feature matrix is finally fed to an support vector machine （SVM） classifier for classification. Experimental results on large datasets for classification show that the proposed method outperforms the existing methods. The usefulness and effectiveness of the proposed classification is demonstrated by conducting recognition experiments before and after classification.