PDNet:语义分割与原始-对偶网络相结合的文档二值化
PDNet: Semantic Segmentation integrated with a Primal-Dual Network for Document binarization
摘要:
数字文档的二值化是将文档图像中的每个像素分类为属于背景(羊皮纸/纸张)或前景(文本/墨水)的任务。历史文献经常受到破坏,这使得这项任务具有挑战性。在当前的工作中,提出了一种深度神经网络架构,该架构将完全卷积网络与展开的原始-对偶网络相结合,可以端到端训练该网络,以在七个数据集中的四个数据集上实现最先进的二值化。文档二值化被公式化为能量最小化问题。训练全卷积神经网络用于像素的语义分割,其提供与每个像素相关联的标记成本。该成本估计沿着边缘被细化,以使用原始-对偶方法来补偿前景类的任何过高或过低的估计。我们提供了必要的概述近端操作,有利于理论基础所需的训练使用梯度下降算法的原始-对偶网络。由于原始对偶方法的经常性遇到的数值不稳定性处理。我们提供了在文档二值化竞争数据集上的实验结果,以及网络稳定性和性能所需的网络变化和超参数调整。根据竞争指标,在合成数据集上进行预训练的网络表现更好。
英文摘要:
Binarization of digital documents is the task of classifying each pixel in an image of the document as belonging to the background (parchment/paper) or foreground (text/ink). Historical documents are often subjected to degradations, that make the task challenging. In the current work a deep neural network architecture is proposed that combines a fully convolutional network with an unrolled primal-dual network that can be trained end-to-end to achieve state of the art binarization on four out of seven datasets. Document binarization is formulated as an energy minimization problem. A fully convolutional neural network is trained for semantic segmentation of pixels that provides labeling cost associated with each pixel. This cost estimate is refined along the edges to compensate for any over or under estimation of the foreground class using a primal-dual approach. We provide necessary overview on proximal operator that facilitates theoretical underpinning required to train a primal-dual network using a gradient descent algorithm. Numerical instabilities encountered due to the recurrent nature of primal-dual approach are handled. We provide experimental results on document binarization competition dataset along with network changes and hyperparameter tuning required for stability and performance of the network. The network when pre-trained on synthetic dataset performs better as per the competition metrics.
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。