论文标题
使用门控完全卷积网络的无复发无约束的手写文本识别
Recurrence-free unconstrained handwritten text recognition using gated fully convolutional network
论文作者
论文摘要
无约束的手写文本识别是大多数文档分析任务的主要步骤。这通常由深层复发的神经网络处理，更具体地是使用长期短期记忆细胞的使用。这些组件的主要缺点是涉及的大量参数及其在训练和预测过程中的顺序执行。使用LSTM单元格的一种替代解决方案是，通过大量使用卷积层的卷积层来补偿长时间的记忆损失，其操作可以并行执行，这意味着较少的参数。在本文中，我们提出了一个完全卷积的网络架构，它是众所周知的CNN+LSTM体系结构的无复发替代品。我们的模型接受了CTC损失的培训，并在RIME和IAM数据集上都显示出竞争成果。我们发布所有代码以启用我们的实验的复制：https：//github.com/factodeeplearning/linepytorchocr。
Unconstrained handwritten text recognition is a major step in most document analysis tasks. This is generally processed by deep recurrent neural networks and more specifically with the use of Long Short-Term Memory cells. The main drawbacks of these components are the large number of parameters involved and their sequential execution during training and prediction. One alternative solution to using LSTM cells is to compensate the long time memory loss with an heavy use of convolutional layers whose operations can be executed in parallel and which imply fewer parameters. In this paper we present a Gated Fully Convolutional Network architecture that is a recurrence-free alternative to the well-known CNN+LSTM architectures. Our model is trained with the CTC loss and shows competitive results on both the RIMES and IAM datasets. We release all code to enable reproduction of our experiments: https://github.com/FactoDeepLearning/LinePytorchOCR.
