Incidental scene text detection, especially for multi-oriented text regions, is one of the most challenging tasks in many computer vision applications. Different from the common object detection task, scene text often suffers from a large variance of aspect ratio, scale, and orientation. To solve this problem, we propose a novel end-to-end scene text detector IncepText from an instance-aware segmentation perspective. We design a novel Inception-Text module and introduce deformable PSROI pooling to deal with multi-oriented text detection. Extensive experiments on ICDAR2015, RCTW-17, and MSRA-TD500 datasets demonstrate our method's superiority in terms of both effectiveness and efficiency. Our proposed method achieves 1st place result on ICDAR2015 challenge and the state-of-the-art performance on other datasets. Moreover, we have released our implementation as an OCR product which is available for public access.
翻译:偶然现场文本探测,特别是对多方向文本区域而言,是许多计算机视觉应用中最具挑战性的任务之一。与常见的物体探测任务不同,现场文本往往在方位比、规模和方向上有很大差异。为了解决这个问题,我们提议从实例认知分解的角度来一个新的端到端现场文本检测器 IncepText 。我们设计了一个新型的“感知-感知”模块,并引入了可变化的 PSROI 集合,以处理多方向文本探测。关于ICDAR2015、RCTW-17和MSRA-TD500数据集的广泛实验显示了我们的方法在效力和效率方面的优势。我们提出的方法在ICDAR2015挑战和其他数据集的最新性能上取得了第一点成果。此外,我们发布了作为可供公众访问的OCR产品的实施。