基于3D卷积的图像序列特征提取与自注意力的车牌识别方法  

3D convolution-based image sequence feature extraction and self-attention for license plate recognition method

作　　者：曾淦雄 柯逍[1,2] ZENG Ganxiong;KE Xiao(College of Mathematics and Computer Science,Fuzhou University,Fuzhou 350116,China;Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing,Fuzhou 350116,China)

机构地区：[1]福州大学数学与计算机科学学院,福建福州350116 [2]福建省网络计算与智能信息处理重点实验室,福建福州350116

出　　处：《智能科学与技术学报》2021年第3期268-279,共12页Chinese Journal of Intelligent Science and Technology

基　　金：国家自然科学基金资助项目(No.61972097);福建省科技引导性项目(No.2017H0015);福建省自然科学基金资助项目(No.2018J01798)。

摘　　要：近年来,基于自注意力机制的神经网络在计算机视觉任务中得到广泛的应用。随着智能交通系统的广泛应用,面对复杂多变的交通场景,车牌识别任务的难度不断提高,准确识别的需求更加迫切。因此提出一个基于自注意力的免矫正的车牌识别方法T-LPR。首先对图像进行切片和序列化,并使用3D卷积对切片序列进行特征提取,从而得到图像的嵌入向量序列。然后将嵌入向量序列输入基于Transformer Encoder的编码器中,学习各个嵌入向量之间的关系并输出最终的编码结果。最后使用分类器进行分类。在多个公共数据集上的实验结果表明,所提方法对各类困难场景下的车牌识别都非常有效。In recent years,neural networks based on self-attentive mechanism have been widely used in computer vision tasks.As the intelligent transportation system is widely used,the task difficulty of license plate recognition is increasing and the need for correct recognition is getting more pressing in the face of complex and changing traffic scenes.Therefore,a rectification-free license plate recognition method T-LPR based on self-attention was proposed.Firstly,the images were sliced and sequenced,and 3D convolution was used for feature extraction of the sliced sequences to obtain a sequence of image embedding vectors.Secondly,the sequence of embedding vectors was fed into an encoder based on Transformer Encoder,which learned the relationship between the individual embedding vectors and outputs the final encoding result.Finally,the final encoding result was classified by a classifier.Experimental results on several public datasets show that T-LPR proposed is very effective for recognizing license plates in all kinds of difficult scenarios.

关 键 词：车牌识别 图像嵌入向量 自注意力 免矫正 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP39[自动化与计算机技术—控制科学与工程]