AE TextSpotter:学习用于歧义文本识别的视觉和语言表示
AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting
摘要:
场景文本识别的目的是在自然图像中检测和识别包含多个字符的完整单词或句子。它仍然具有挑战性,因为当字符之间的间距很大或字符均匀分布在多个行和列中时,经常会出现歧义,从而使许多视觉上看似合理的字符分组(例如,在图1(c)中,“BERLIN”被错误地检测为“BERL”和“IN”)。不同于以往的作品,仅仅采用视觉特征的文本检测,这项工作提出了一种新的文本spotter,名为歧义消除文本Spotter(AE TextSpotter),学习视觉和语言特征,以显着减少文本检测中的歧义。拟议的AE TextSpotter有三个重要的好处。1)语言表征与视觉表征一起在一个框架中学习。据我们所知,这是第一次通过使用语言模型来改进文本检测。2)一个精心设计的语言模块被用来降低检测不正确的文本行的信心,使他们很容易修剪在检测阶段。3)大量的实验表明,AE TextSpotter优于其他国家的最先进的方法,由一个很大的利润。例如,我们从IC 19-ReCTS数据集中仔细选择了一组非常模糊的样本,我们的方法比其他方法高出4%以上。该代码已在https://github.com/whai362/AE_TextSpotter上发布。验证集的图像列表和评估脚本已在https://github.com/whai362/TDA-ReCTS上发布。
英文摘要:
Scene text spotting aims to detect and recognize the entire word or sentence with multiple characters in natural images. It is still challenging because ambiguity often occurs when the spacing between characters is large or the characters are evenly spread in multiple rows and columns, making many visually plausible groupings of the characters (e.g. "BERLIN" is incorrectly detected as "BERL" and "IN" in Fig. 1(c)). Unlike previous works that merely employed visual features for text detection, this work proposes a novel text spotter, named Ambiguity Eliminating Text Spotter (AE TextSpotter), which learns both visual and linguistic features to significantly reduce ambiguity in text detection. The proposed AE TextSpotter has three important benefits. 1) The linguistic representation is learned together with the visual representation in a framework. To our knowledge, it is the first time to improve text detection by using a language model. 2) A carefully designed language module is utilized to reduce the detection confidence of incorrect text lines, making them easily pruned in the detection stage. 3) Extensive experiments show that AE TextSpotter outperforms other state-of-the-art methods by a large margin. For example, we carefully select a validation set of extremely ambiguous samples from the IC19-ReCTS dataset, where our approach surpasses other methods by more than 4%. The code has been released at https://github.com/whai362/AE_TextSpotter. The image list and evaluation scripts of the validation set have been released at https://github.com/whai362/TDA-ReCTS.
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。