Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/132177
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | AE TextSpotter: Learning visual and linguistic representation for ambiguous text spotting |
Author: | Wang, W. Liu, X. Ji, X. Xie, E. Liang, D. Yang, Z.B. Lu, T. Shen, C. Luo, P. |
Citation: | Lecture Notes in Artificial Intelligence, 2020, vol.12359, pp.457-473 |
Publisher: | Springer |
Publisher Place: | Cham, Switzerland |
Issue Date: | 2020 |
Series/Report no.: | Lecture Notes in Computer Science; 12359 |
ISBN: | 3030585670 9783030585679 |
ISSN: | 0302-9743 1611-3349 |
Conference Name: | European Conference on Computer Vision (ECCV) (23 Aug 2020 - 28 Aug 2020 : virtual online) |
Statement of Responsibility: | Wenhai Wang, Xuebo Liu, Xiaozhong Ji, Enze Xie, Ding Liang, ZhiBo Yang, Tong Lu, B, Chunhua Shen, and Ping Luo |
Abstract: | 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-theart methods by a large margin. For example, we carefully select a set of extremely ambiguous samples from the IC19-ReCTS dataset, where our approach surpasses other methods by more than 4%. |
Keywords: | Text spotting; Text detection; Text recognition; Text detection ambiguity |
Rights: | © Springer Nature Switzerland AG 2020 |
DOI: | 10.1007/978-3-030-58568-6_27 |
Published version: | https://link.springer.com/book/10.1007/978-3-030-58568-6 |
Appears in Collections: | Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.