arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.05036cs.CV
收藏

GR-RNN:用于作者识别的全局上下文残差循环神经网络

GR-RNN: Global-Context Residual Recurrent Neural Networks for Writer Identification

University of Groningen(格罗宁根大学)

Sheng He, Lambert Schomaker

摘要:

本文提出了一个端到端的神经网络系统,通过手写文字图像,它联合集成了全局上下文信息和一系列的局部片段为基础的功能来识别作家。通过全局平均池化步骤从神经网络的尾部提取全局上下文信息。局部和基于片段的特征序列是从包含关于手写风格的细微信息的低级深度特征图中提取的。利用递归神经网络(RNN)对片段序列间的空间关系进行建模,以增强局部片段特征的区分能力。我们利用全局上下文和局部片段之间的互补信息,从而提出了全局上下文残差递归神经网络(GR-RNN)方法。在四个公共数据集上对所提出的方法进行了评估,实验结果表明,它可以提供最先进的性能。此外,在灰度图像上训练的神经网络比在二值化图像和轮廓图像上训练的神经网络提供更好的结果,表明纹理信息在作家识别中起着重要作用。将提供源代码:\url{https://github.com/shengfly/writer-identification}。

英文摘要:

This paper presents an end-to-end neural network system to identify writers through handwritten word images, which jointly integrates global-context information and a sequence of local fragment-based features. The global-context information is extracted from the tail of the neural network by a global average pooling step. The sequence of local and fragment-based features is extracted from a low-level deep feature map which contains subtle information about the handwriting style. The spatial relationship between the sequence of fragments is modeled by the recurrent neural network (RNN) to strengthen the discriminative ability of the local fragment features. We leverage the complementary information between the global-context and local fragments, resulting in the proposed global-context residual recurrent neural network (GR-RNN) method. The proposed method is evaluated on four public data sets and experimental results demonstrate that it can provide state-of-the-art performance. In addition, the neural networks trained on gray-scale images provide better results than neural networks trained on binarized and contour images, indicating that texture information plays an important role for writer identification. The source code will be available: \url{https://github.com/shengfly/writer-identification}.

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。

↑