Improved localization accuracy by LocNet for Faster R-CNN based text detection in natural scene images. (December 2019)

• Record Type: Journal Article
• Authors: Zhong, Zhuoyao; Sun, Lei; Huo, Qiang
• Is Part Of: Pattern recognition. Volume 96(2019:Dec.)
• Publication Date: 2019-12
• Subjects: Text detection -- Text localization accuracy -- Faster R-CNN -- LocNet -- Natural scene images; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2019.106986
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We are motivated to address the text localization accuracy problem and propose replacing the bounding box regression module with a novel LocNet based localization module to improve the localization accuracy of a Faster R-CNN based text detector. We present a simple yet effective two-stage approach to convert the difficult multi-oriented text detection problem to a relatively easier horizontal text detection problem, which makes our approach able to robustly detect multi-oriented text instances with accurate bounding box localization. Experiments demonstrate that our proposed approach boosts the localization accuracy of Faster R-CNN based text detectors significantly. Our new text detector has achieved superior performance on both horizontal (ICDAR-2011, ICDAR-2013 and MULTILIGUL) and multi-oriented (MSRA-TD500, ICDAR-2015) text detection benchmark tasks. Abstract: Although Faster R-CNN based text detection approaches have achieved promising results, their localization accuracy is not satisfactory in certain cases due to their sub-optimal bounding box regression based localization modules. In this paper, we address this problem and propose replacing the bounding box regression module with a novel LocNet based localization module to improve the localization accuracy of a Faster R-CNN based text detector. Given a proposal generated by a region proposal network (RPN), instead of directly predicting the bounding box coordinates of the concerned text instance, the proposal is enlarged to create a search region so that an "In-Out" conditional probability to each row and column of this search region is assigned, which can then be used to accurately infer the concerned bounding box. Furthermore, we present a simple yet effective two-stage approach to convert the difficult multi-oriented text detection problem to a relatively easier horizontal text detection problem, which makes our approach able to robustly detect multi-oriented text instances with accurate bounding box localization. Experiments demonstrate that the proposed approach boosts the localization accuracy of Faster R-CNN based text detectors significantly. Consequently, our new text detector has achieved superior performance on both horizontal (ICDAR-2011, ICDAR-2013 and MULTILIGUL) and multi-oriented (MSRA-TD500, ICDAR-2015) text detection benchmark tasks.