Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting
european conference on computer vision, pp. 706-722, 2020.
Abstract:
Recent end-to-end trainable methods for scene text spotting, integrating detection and recognition, showed much progress. However, most of the current arbitrary-shape scene text spotters use region proposal networks (RPN) to produce proposals. RPN relies heavily on manually designed anchors and its proposals are represented with axis-al...More
Code:
Data:
Full Text
Tags
Comments