arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.05945cs.CV
收藏

CentripetalText:一种用于场景文本检测的高效文本实例表示

CentripetalText: An Efficient Text Instance Representation for Scene Text Detection

Wangxuan Institute of Computer Technology(王选计算机技术研究所);Peking University(北京大学)

Tao Sheng, Jie Chen, Zhouhui Lian

摘要:

由于文本曲率、方向和纵横比的变化,场景文本检测仍然是一个巨大的挑战。这个任务中最困难的问题之一是如何表示任意形状的文本实例。虽然已经提出了许多方法来以灵活的方式对不规则文本进行建模,但大多数方法都失去了简单性和鲁棒性。它们复杂的后处理和Dirac delta分布下的回归削弱了检测性能和泛化能力。在本文中,我们提出了一个高效的文本实例表示命名为CentripetalText(CT),它分解成文本内核和向心位移的组合文本实例。具体来说,我们利用向心位移来实现像素聚合,将外部文本像素引导到内部文本内核。松弛操作被集成到向心位移的稠密回归中,允许在一个范围内而不是特定值内进行正确的预测。该方法对文本轮廓的快速重构和对预测误差的容忍度分别保证了较高的检测精度和较快的推理速度。此外,我们将我们的文本检测器缩小到一个提案生成模块,即CentripetalText Proposal Network,取代Mask TextSpotter v3中的Segmentation Proposal Network,并生成更准确的提案。为了验证我们的方法的有效性,我们进行了实验,几个常用的场景文本基准,包括弯曲和多方向的文本数据集。对于场景文本检测的任务,我们的方法实现了优于或竞争的性能相比,其他现有的方法,例如,F-measure在40.0 FPS时为86.3%,在MSRA-TD 500上为34.8 FPS时为86.1%,等等。对于端到端场景文本识别任务,我们的方法在Total-Text上的性能优于Mask TextSpotter v3 1.1%。

英文摘要:

Scene text detection remains a grand challenge due to the variation in text curvatures, orientations, and aspect ratios. One of the hardest problems in this task is how to represent text instances of arbitrary shapes. Although many methods have been proposed to model irregular texts in a flexible manner, most of them lose simplicity and robustness. Their complicated post-processings and the regression under Dirac delta distribution undermine the detection performance and the generalization ability. In this paper, we propose an efficient text instance representation named CentripetalText (CT), which decomposes text instances into the combination of text kernels and centripetal shifts. Specifically, we utilize the centripetal shifts to implement pixel aggregation, guiding the external text pixels to the internal text kernels. The relaxation operation is integrated into the dense regression for centripetal shifts, allowing the correct prediction in a range instead of a specific value. The convenient reconstruction of text contours and the tolerance of prediction errors in our method guarantee the high detection accuracy and the fast inference speed, respectively. Besides, we shrink our text detector into a proposal generation module, namely CentripetalText Proposal Network, replacing Segmentation Proposal Network in Mask TextSpotter v3 and producing more accurate proposals. To validate the effectiveness of our method, we conduct experiments on several commonly used scene text benchmarks, including both curved and multi-oriented text datasets. For the task of scene text detection, our approach achieves superior or competitive performance compared to other existing methods, e.g., F-measure of 86.3% at 40.0 FPS on Total-Text, F-measure of 86.1% at 34.8 FPS on MSRA-TD500, etc. For the task of end-to-end scene text recognition, our method outperforms Mask TextSpotter v3 by 1.1% on Total-Text.

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。

↑