A Graph-Transformer Network for Scene Text Detection

被引：0

作者：

Wu, Yongrong ^{[1
]}

Lin, Jingyu ^{[1
]}

Chen, Houjin ^{[1
]}

Chen, Dinghao ^{[1
]}

Yang, Lvqing ^{[1
]}

Xiahou, Jianbing ^{[2
]}

机构：

[1] Xiamen Univ, Sch Informat, Xiamen 361000, Peoples R China

[2] Quanzhou Normal Univ, Quanzhou 362000, Fujian, Peoples R China

来源：

ADVANCED INTELLIGENT COMPUTING TECHNOLOGY AND APPLICATIONS, ICIC 2023, PT V | 2023年 / 14090卷

关键词：

Scene Text Detection; Transformer; Graph convolutional network;

D O I：

10.1007/978-981-99-4761-4_57

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Detecting text in natural images with varying orientations and shapes is challenging. Existing detectors often fail with text instances having extreme aspect ratios. This paper introduces GTNet, a Graph- Transformer network for scene text detection. GTNet uses a Graph-based Shared Feature Learning Module (GSFL) for feature extraction and a Transformer-based Regression Module (TRM) for bounding box prediction. Our architecture offers a flexible receptive field, combining global attention and local features for enhanced text representation. Extensive experiments show our method surpasses existing detectors in accuracy and effectiveness.

引用

页码：680 / 690

页数：11

共 50 条

[31] RECURRENT GLOBAL CONVOLUTIONAL NETWORK FOR SCENE TEXT DETECTION
Mohanty, Sabyasachi
Dutta, Tanima
Gupta, Hari Prabhat
2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2018, : 2750 - 2754
[32] SPN: short path network for scene text detection
Cai, Yuanqiang
Wang, Weiqiang
Ren, Haiqing
Lu, Ke
NEURAL COMPUTING & APPLICATIONS, 2020, 32 (10): : 6075 - 6087
[33] A Unified Deep Neural Network for Scene Text Detection
Li, Yixin
Ma, Jinwen
INTELLIGENT COMPUTING THEORIES AND APPLICATION, ICIC 2017, PT I, 2017, 10361 : 101 - 112
[34] Scene Text Detection with Supervised Pyramid Context Network
Xie, Enze
Zang, Yuhang
Shao, Shuai
Yu, Gang
Yao, Cong
Li, Guangyao
THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 9038 - 9045
[35] Scene Graph based Fusion Network for Image-Text Retrieval
Wang, Guoliang
Shang, Yanlei
Chen, Yong
Zhen, Chaoqi
Cheng, Dequan
2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME, 2023, : 138 - 143
[36] CAPTIONING TRANSFORMER WITH SCENE GRAPH GUIDING
Chen, Haishun
Wang, Ying
Yang, Xin
Li, Jie
2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2021, : 2538 - 2542
[37] A Hierarchical Graph-Enhanced Transformer Network for Remote Sensing Scene Classification
Li, Ziwei
Xu, Weiming
Yang, Shiyu
Wang, Juan
Su, Hua
Huang, Zhanchao
Wu, Sheng
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2024, 17 : 20315 - 20330
[38] Transformer-based Scene Graph Generation Network With Relational Attention Module
Yamamoto, Takuma
Obinata, Yuya
Nakayama, Osafumi
2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2022, : 2034 - 2041
[39] BGT-Net: Bidirectional GRU Transformer Network for Scene Graph Generation
Dhingra, Naina
Ritter, Florian
Kunz, Andreas
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021, 2021, : 2150 - 2159
[40] Natural scene text detection based on multiscale connectionist text proposal network
Huang, Min
Lan, Chaohao
Huang, Wei
Tao, Yang
JOURNAL OF ENGINEERING-JOE, 2020, 2020 (13): : 326 - 329

← 1 2 3 4 5 →