基于卷积循环神经网络的芯片表面字符识别  

Chip surface character recognition based on convolutional recurrent neural network

作　　者：熊帆 陈田[1] 卞佰成 刘军[1] XIONG Fan;CHEN Tian;BIAN Bai-cheng;LIU Jun(School of Mechanical Engineering,Shanghai Dianji University,Shanghai 201306,China)

机构地区：[1]上海电机学院机械学院,上海201306

出　　处：《浙江大学学报（工学版）》2023年第5期948-956,共9页Journal of Zhejiang University：Engineering Science

基　　金：上海市地方院校能力建设计划项目(22010501000);上海多向模锻工程技术研究中心资助项目(20DZ2253200).

摘　　要：基于积分图运算的阈值分割将图像二值化,使用仿射变换完成文本字段图像的方向校正,从而实现文本行的定位.在原始卷积循环神经网络(CRNN)的基础上,将骨干网络替换成MobileNet-V3结构,在2层LSTM之间加入注意力机制,同时引入中心损失函数.利用改进的CRNN实现文本行字符的识别.将改进后的CRNN在40510张芯片文本行图像上进行测试.通过小样本数据集进行模型微调训练得到多个子模型,从而实现集成推理,使用3个模型的综合识别准确率稳定在99.97%左右,单张芯片图像的总识别时间小于60 ms.实验结果表明,改进的CRNN算法的准确率比原始CRNN提升了大约27.48%,多模型集成推理的方法可以实现更高的准确率.A character recognition method based on an improved convolutional recurrent neural network(CRNN)was proposed for the recognition of characters on the chip surface.The image was binarized by the threshold segmentation based on integral map operation,and the orientation correction of the text field image was completed using affine transformation to achieve the localization of text lines.Based on the original CRNN,the backbone network was replaced with MobileNet-V3 structure and the attention mechanism was added between the two layers of LSTM,while the center loss function was introduced.The improved CRNN was used to implement the text line character recognition and tested on 40510 chip text line images.The multiple sub-models were obtained by finetuning the model training with small sample datasets to achieve integrated inference.The combined recognition accuracy used three models was stable at about 99.97%,and the total recognition time of a single chip image was less than 60 ms.The experimental results showed that the accuracy of the improved CRNN algorithm was improved by about 27.48%over the original CRNN,and the integrated inference of multiple models could achieve higher accuracy.

关 键 词：图像处理 积分图 卷积循环神经网络 字符识别 集成推理 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]