白翔的CRNN论文阅读

1.  论文题目

Xiang Bai——【PAMI2017】An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition

2.  论文思路和方法

1)  问题范围: 单词识别

2)  CNN层:使用标准CNN提取图像特征,利用Map-to-Sequence表示成特征向量;

3)  RNN层:使用双向LSTM识别特征向量,得到每列特征的概率分布;

4)  Transcription层:利用CTC和前向后向算法求解最优的label序列;

3.  亮点和创新点

1)  端到端可训练(把CNN和RNN联合训练)

2)  任意长度的输入(图像宽度任意,单词长度任意)

3)  训练集无需有字符的标定

4)  带字典和不带字典的库(样本)都可以使用

5)  性能好,而且模型小(参数少)

4.  相关链接

1)   白翔的个人主页:http://mc.eistar.net/~xbai/

2)   论文的下载地址:https://arxiv.org/pdf/1507.05717v1.pdf

3)   代码的下载地址:

http://mc.eistar.net/~xbai/CRNN/crnn_code.zip

5.  论文细节

1)   论文的框架

论文阅读(Xiang Bai——【PAMI2017】An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition)-LMLPHP

2)   特征提取层

论文阅读(Xiang Bai——【PAMI2017】An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition)-LMLPHP

3)   序列标定层

论文阅读(Xiang Bai——【PAMI2017】An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition)-LMLPHP

4)   翻译层

论文阅读(Xiang Bai——【PAMI2017】An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition)-LMLPHP论文阅读(Xiang Bai——【PAMI2017】An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition)-LMLPHP

论文阅读(Xiang Bai——【PAMI2017】An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition)-LMLPHP

5)   网络训练

论文阅读(Xiang Bai——【PAMI2017】An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition)-LMLPHP

6)   实验

论文阅读(Xiang Bai——【PAMI2017】An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition)-LMLPHP论文阅读(Xiang Bai——【PAMI2017】An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition)-LMLPHP论文阅读(Xiang Bai——【PAMI2017】An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition)-LMLPHP论文阅读(Xiang Bai——【PAMI2017】An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition)-LMLPHP

7)   总结

论文阅读(Xiang Bai——【PAMI2017】An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition)-LMLPHP

8)   问题

论文阅读(Xiang Bai——【PAMI2017】An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition)-LMLPHP

04-28 15:14