摘要
Recently,segmentation-based scene text detection has drawn a wide research interest due to its flexibility in describing scene text instance of arbitrary shapes such as curved texts.However,existing methods usually need complex post-processing stages to process ambiguous labels,i.e.,the labels of the pixels near the text boundary,which may belong to the text or background.In this paper,we present a framework for segmentation-based scene text detection by learning from ambiguous labels.We use the label distribution learning method to process the label ambiguity of text annotation,which achieves a good performance without using additional post-processing stage.Experiments on benchmark datasets demonstrate that our method produces better results than state-of-the-art methods for segmentation-based scene text detection.
基金
supported by the National Key R&D Program of China(2018AAA0100104,2018AAA0100100)
the National Natural Science Foundation of China(Grant No.61702095)
the Natural Science Foundation of Jiangsu Province(BK20211164).
