Text proposals with location-awareness-attention network for arbitrarily shaped scene text detection and recognition
Document Type
Article
Publication Date
11-1-2022
Abstract
Unlike existing models that aim to address the challenge of scene text detection and recognition separately, the proposed work aims to address both text detection and recognition using a single architecture to deal with arbitrarily oriented/shaped text. Towards this aim, a novel Text Proposal with Location-AwarenessAttention Network (TPLAANet) for arbitrarily oriented/shaped text detection and recognition is proposed. For text detection, the proposed method explores central mask prediction for locating text instances, bounding box regression branch for tight bounding boxes, and mask branch for accurate positions of arbitrarily oriented/shaped text instances. For text recognition, the proposed method explores character information using a Location-Awareness-Attention Network (LAAN), which learns a two-dimensional attention weight and improves the recognition performance. To test the efficacy of the proposed model, we consider the commonly used horizontal and multi-oriented natural scene text datasets, namely, ICDAR2013, ICDAR2015, and the arbitrarily shaped scene text datasets, namely, Total-Text and CTW1500 for experimentation. Experimental results are provided to validate the effectiveness of the proposed method. The code is available at: https: //codeocean.com/capsule/5666319/tree/v1.
Keywords
Scene text detection, Scene text recognition, Text proposal, Attention model, Location-awareness-attention model
Divisions
Computer
Funders
National Key Research and Development Program of China (Grant No: 2020AAA0107903),National Natural Science Foundation of China (NSFC) (Grant No: 62176091 & 19ZR1415900
Publication Title
Expert Systems with Applications
Volume
205
Publisher
Elsevier
Publisher Location
THE BOULEVARD, LANGFORD LANE, KIDLINGTON, OXFORD OX5 1GB, ENGLAND