基于小波隐性马尔可夫树模型的车牌定位

Vehicle-License-Plate Location Based on Wavelet Hidden Markov Tree Model

根据小波隐性马尔可夫树模型对车牌纹理特征精确的多尺度描述,提出了一种基于WHMTM的车牌定位方法。该方法首先以小波域的高频滤波作为预处理,再根据车牌纹理的WHMTM参数采取从粗到精多尺度地分割车牌,从而快速、准确地在复杂的背景中定位车牌。实验结果表明该方法是一种速度快且抗扰性强的车牌定位方法。

According to multiscale and accurate characterization of vehicle-license-plate (VLP) texture feature by wavelet hidden Markov tree model (WHMTM), a method of VLP Location based on WHMTM is proposed in this paper. At first high-pass filter in wavelet-domain is used as preprocessing. Afterwards VLP is segmented multiscaly from coarse to fine by WHMTM parameter of VLP. So VLP can be located from complex background fast and correctly. Experimental results show this method is very fast and robust.