Abstract:
针对传统车牌识别方法在车牌模糊和光照复杂的场景下难以快速准确识别车牌信息的问题,为提高网络的特征提取能力,将带残差的ResNet引入卷积循环神经网络(convolutional recurrent neural network, CRNN),提出了CRNN_ResNet车牌文本识别算法。该方法仅需0.012 s就能完成一张车牌图像的识别,在CCPD公开数据集上的识别准确率达到了98.5%。
Keyword:
Reprint 's Address:
Email:
Source :
集美大学学报(自然科学版)
Year: 2024
Issue: 06
Volume: 29
Page: 535-539
Cited Count:
SCOPUS Cited Count:
ESI Highly Cited Papers on the List: 0 Unfold All
WanFang Cited Count:
Chinese Cited Count:
30 Days PV: 0
Affiliated Colleges: