一种高效的手写文本识别端到端神经网络模型
An Efficient End-to-End Neural Model for Handwritten Text Recognition
摘要：
从图像中进行脱机手写文本识别对于试图识别大量带手写标记的扫描文档/报告的企业来说是一个重要的问题。深度递归模型（如多维LSTM）已被证明比传统的基于隐马尔可夫模型的方法具有更好的性能，这些方法受到马尔可夫假设的影响，因此缺乏RNN的代表性。在本文中，我们介绍了一种新的方法，该方法将深度卷积网络与递归编码器-解码器网络相结合，将图像映射到与图像中存在的文本相对应的字符序列。整个模型使用焦点损失进行端到端训练，这是对标准交叉熵损失的改进，解决了文本识别固有的类不平衡问题。为了提高模型的解码能力，采用了束搜索算法，该算法基于单个字符的联合分布从一组假设中搜索最佳序列。我们的模型将原始图像的下采样版本作为输入，从而使其在计算和内存方面都很高效。实验结果对两个公开可用的数据集，IAM和RIMES进行了基准测试。在两个数据集的评估集上，我们分别超过了3.5%和1.1%。
英文摘要：
Offline handwritten text recognition from images is an important problem for enterprises attempting to digitize large volumes of handmarked scanned documents/reports. Deep recurrent models such as Multi-dimensional LSTMs have been shown to yield superior performance over traditional Hidden Markov Model based approaches that suffer from the Markov assumption and therefore lack the representational power of RNNs. In this paper we introduce a novel approach that combines a deep convolutional network with a recurrent Encoder-Decoder network to map an image to a sequence of characters corresponding to the text present in the image. The entire model is trained end-to-end using Focal Loss, an improvement over the standard Cross-Entropy loss that addresses the class imbalance problem, inherent to text recognition. To enhance the decoding capacity of the model, Beam Search algorithm is employed which searches for the best sequence out of a set of hypotheses based on a joint distribution of individual characters. Our model takes as input a downsampled version of the original image thereby making it both computationally and memory efficient. The experimental results were benchmarked against two publicly available datasets, IAM and RIMES. We surpass the state-of-the-art word level accuracy on the evaluation set of both datasets by 3.5% & 1.1%, respectively.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
