Reading Scene Text in Deep Convolutional Sequences
Reading Scene Text in Deep Convolutional Sequences
复制标题
DOI：
10.1609/aaai.v30i1.10465
复制
发表时间：
2015-06
期刊：
影响因子：
--
通讯作者：
Pan He;Weilin Huang;Y. Qiao;Chen Change Loy;Xiaoou Tang
中科院分区：
文献类型：
--
作者：
Pan He;Weilin Huang;Y. Qiao;Chen Change Loy;Xiaoou Tang
我们开发了一个深度文本递归网络（DTRN），将场景文本阅读视为序列标记问题。我们利用深度卷积神经网络的最新进展，从整个单词图像中生成有序的高级序列，避免了困难的字符分割问题。然后，开发了一个基于长短期记忆（LSTM）的深度递归模型，以鲁棒地识别生成的CNN序列，这与大多数现有的独立识别每个字符的方法不同。与现有的场景文本识别方法相比，我们的模型具有许多吸引人的特性：（i）它可以通过利用有意义的上下文信息来识别高度模糊的单词，使其能够在没有预处理或后处理的情况下可靠地工作;（ii）深度CNN特征对各种图像失真具有鲁棒性;（3）它保留了词意象中的显式顺序信息，这是区分词串所必需的;（iv）该模型不依赖于预定义的字典，并且可以处理未知词和任意字符串。它在几个基准上取得了令人印象深刻的结果，大大推进了最先进的水平。
We develop a Deep-Text Recurrent Network (DTRN)that regards scene text reading as a sequence labelling problem. We leverage recent advances of deep convolutional neural networks to generate an ordered highlevel sequence from a whole word image, avoiding the difficult character segmentation problem. Then a deep recurrent model, building on long short-term memory (LSTM), is developed to robustly recognize the generated CNN sequences, departing from most existing approaches recognising each character independently. Our model has a number of appealing properties in comparison to existing scene text recognition methods: (i) It can recognise highly ambiguous words by leveraging meaningful context information, allowing it to work reliably without either pre- or post-processing; (ii) the deep CNN feature is robust to various image distortions; (iii) it retains the explicit order information in word image, which is essential to discriminate word strings; (iv) the model does not depend on pre-defined dictionary, and it can process unknown words and arbitrary strings. It achieves impressive results on several benchmarks, advancing the-state-of-the-art substantially.