CAJ | 학술논문

车牌图像二值化是车辆牌照识别中的关键技术。由于光照不均、曝光不足、动态范围太窄和车牌被污染等原因，车牌图像的质量往往不佳，严重影响了牌照图像二值化效果。该文对一种车牌图像二值化算法--CASDA算法做了改进，能更好地适应不同质量的车牌图像。实验证明了该算法的有效性。
차패도상이치화시차량패조식별중적관건기술。유우광조불균、폭광불족、동태범위태착화차패피오염등원인，차패도상적질량왕왕불가，엄중영향료패조도상이치화효과。해문대일충차패도상이치화산법--CASDA산법주료개진，능경호지괄응불동질량적차패도상。실험증명료해산법적유효성。
Vehicle license plate binarization algorithms comprise a critical technology in VLPR (Vehicle license plate recognition). Because of the deficiency in illumination, exposure, dynamic range and license plate pollution, the quality of license plate image is always very poor, that makes the poor quality of binarization image. After analyzing the shortcomings of CASDA algorithm(Cluster Algorithm Based on Spatial Distribution Analysis), this paper proposes an improved binarization algorithm. The improved approach is robust to poor image. The experiment results have proved the advantages of the proposed algorithm.