OrigamiNet：弱监督、无分割、一步、整页文本识别
OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold
摘要：
文本识别是一项主要的计算机视觉任务，具有大量相关挑战。这些传统挑战之一是文本识别和分割的耦合性质。在过去的几十年里，这个问题已经得到了逐步解决，从基于分割的识别到无分割的方法，事实证明，这种方法更准确，注释数据也更便宜。我们从无分割的单行识别向无分割的多行/整页识别迈出了一步。我们提出了一种新颖而简单的神经网络模块，称为\textbf{OrigamiNet}，它可以增强任何CTC训练的，完全卷积的单行文本识别器，通过为模型提供足够的空间容量，能够正确地将2D输入信号折叠成1D而不丢失信息，将其转换为多行版本。这种修改后的网络可以使用完全相同的简单原始过程进行训练，并且只使用\textbf{unsegmented}图像和文本对。我们进行了一组可解释性实验，表明我们的训练模型学习了准确的隐式线分割。我们在IAM \& ICDAR 2017 HTR手写识别基准测试中实现了最先进的字符出错率，超过了文献中的所有其他方法。在IAM上，我们甚至超过了在训练过程中使用准确定位信息的单线方法。我们的代码可在\url{https://github.com/IntuitionMachines/OrigamiNet}在线获取。
英文摘要：
Text recognition is a major computer vision task with a big set of associated challenges. One of those traditional challenges is the coupled nature of text recognition and segmentation. This problem has been progressively solved over the past decades, going from segmentation based recognition to segmentation free approaches, which proved more accurate and much cheaper to annotate data for. We take a step from segmentation-free single line recognition towards segmentation-free multi-line / full page recognition. We propose a novel and simple neural network module, termed \textbf{OrigamiNet}, that can augment any CTC-trained, fully convolutional single line text recognizer, to convert it into a multi-line version by providing the model with enough spatial capacity to be able to properly collapse a 2D input signal into 1D without losing information. Such modified networks can be trained using exactly their same simple original procedure, and using only \textbf{unsegmented} image and text pairs. We carry out a set of interpretability experiments that show that our trained models learn an accurate implicit line segmentation. We achieve state-of-the-art character error rate on both IAM \& ICDAR 2017 HTR benchmarks for handwriting recognition, surpassing all other methods in the literature. On IAM we even surpass single line methods that use accurate localization information during training. Our code is available online at \url{https://github.com/IntuitionMachines/OrigamiNet}.
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。
