CAJ | 학술논문

以提高车牌定位实时性和同时搜索多个车牌为目的，研究并提出一种基于分块投影和语义约束的车牌快速定位算法，通过投影分割处理得到候选车牌字符块，根据语义约束对字符块进行聚类得到候选车牌区域，根据纹理特征过滤伪车牌。对3000幅图像进行实验，定位成功率为97.1%，平均定位时间小于35 ms。实验证明这种算法适应性强、速度快，能够满足车牌实时识别的需求。
이제고차패정위실시성화동시수색다개차패위목적，연구병제출일충기우분괴투영화어의약속적차패쾌속정위산법，통과투영분할처리득도후선차패자부괴，근거어의약속대자부괴진행취류득도후선차패구역，근거문리특정과려위차패。대3000폭도상진행실험，정위성공솔위97.1%，평균정위시간소우35 ms。실험증명저충산법괄응성강、속도쾌，능구만족차패실시식별적수구。
This paper presents a novel algorithm for license plates location. The input image is segmented by block projec-tion to obtain potential regions with plate characters. It picks up candidate regions of plates by clustering those potential regions with semantic restrictions. False plate regions are deleted according to texture characteristic. 3000 images are pro-cessed with an accuracy of 97.1%. At the same time, the average time is less than 35 ms. The results prove that the algo-rithm is effective enough to support real-time license plate recognition.