BaiXiang——【arXi2015】An End-to-End Trainable Neural Network for Image-based Sequence Recognition and
2016-11-06 14:07
871 查看
BaiXiang的CRNN论文阅读
1. 论文题目BaiXiang——【arXiv2015】An End-to-End Trainable Neural Network forImage-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
2) 特征提取层
3) 序列标定层
4) 翻译层
5) 网络训练
6) 实验
7) 总结
8) 问题
相关文章推荐
- 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)
- An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to S
- 论文笔记:An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application
- 论文阅读(Lukas Neumann——【ICCV2017】Deep TextSpotter_An End-to-End Trainable Scene Text Localization and Recognition Framework)
- An End-to-End Trainable Neural Network...笔记
- Look Closer to See Better Recurrent Attention Convolutional Neural Network for Fine-grained Image Re
- 论文读书笔记-Using neural network to combine measures of word semantic similarity for image annotation
- [行为识别]RPAN:An end-to-end recurrent pose-attention network for action recognition
- 论文阅读:End-to-End Learning of Deformable Mixture of Parts and Deep Convolutional Neural Networks for H
- An End-to-End System for Unconstrained Face Verification with Deep Convolutional Neural Networks
- 论文笔记之:Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic
- 论文笔记之:Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic
- Towards End-to-End Car License Plates Detection and Recognition with Deep Neural Networks
- [ACL2015] A Dependency-Based Neural Network for Relation Classification
- Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image
- 车牌识别“Towards End-to-End Car License Plates Detection and Recognition with Deep Neural Networks”
- Bag-of-Words Based Deep Neural Network for Image Retrieval
- End-to-End Learning of Deformable Mixture of Parts and Deep Convolutional Neural Networks for Human
- [ACL2015]A Dependency-Based Neural Network for Relation Classification
- 车牌检测识别--Towards End-to-End Car License Plates Detection and Recognition with Deep Neural Networks