基于卷积循环神经网络的芯片表面字符识别

熊帆,陈田,卞佰成,刘军

Chip surface character recognition based on convolutional recurrent neural network

Fan XIONG,Tian CHEN,Bai-cheng BIAN,Jun LIU

表 3 CRNN各项改进的对比测试结果

Tab.3 Comparative test results of CRNN improvements

模型形态 A/% T/ms 原始CRNN 67.353 25.04 CNN改进后 74.068 14.58 LSTM改进后 78.474 19.14 损失函数改进后 90.751 23.90 综合改进后 94.831 11.85