A Novel Algorithm for Vehicle License Localization Based on Wavelet Transform
The paper presents a novel algorithm is proposed for detecting vehicle license, based on wavelet transform.Firstly, it adopts the mean, energy and entropy on the wavelet coefficients of color vehicle image as textural features. Secondly, an algorithm based on dynamic threshold is chosen to characterize license and non-license areas. Thirdly, a morphological operation was used to classify the image into license candidates and background.Finally, the detected text candidates undergo the empirical-rules analysis to identify license area.Experimental results demonstrate that the proposed approach could efficiently be used as a vehicle license detection system, which is robust for license-size,license-color and background complexity.
License Localization Wavelet Transform Wavelet Coefficients C-Means
Yonghui Pan Fang Bao ShiTong Wang
School of Information Technology, Southern Yangtze University No.1800, Lihudadao, Wuxi Jiangsu 21412 School of Information Technology, Southern Yangtze University No.1800, Lihudadao, Wuxi Jiangsu 21412
国际会议
杭州
英文
519-523
2006-10-12（万方平台首次上网日期，不代表论文的发表时间）