A Multi-Scale Natural Scene Text Detection Method Based on Attention Feature Extraction and Cascade Feature Fusion

被引:0
|
作者
Li, Nianfeng [1 ]
Wang, Zhenyan [1 ]
Huang, Yongyuan [1 ]
Tian, Jia [1 ]
Li, Xinyuan [1 ]
Xiao, Zhiguo [1 ,2 ]
机构
[1] Changchun Univ, Coll Food Sci & Engn, 6543 Satellite Rd, Changchun 130022, Peoples R China
[2] Beijing Inst Technol, Sch Comp Sci, Beijing 100811, Peoples R China
关键词
text detection; attention mechanism; cascaded feature fusion; deep learning;
D O I
10.3390/s24123758
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Scene text detection is an important research field in computer vision, playing a crucial role in various application scenarios. However, existing scene text detection methods often fail to achieve satisfactory results when faced with text instances of different sizes, shapes, and complex backgrounds. To address the challenge of detecting diverse texts in natural scenes, this paper proposes a multi-scale natural scene text detection method based on attention feature extraction and cascaded feature fusion. This method combines global and local attention through an improved attention feature fusion module (DSAF) to capture text features of different scales, enhancing the network's perception of text regions and improving its feature extraction capabilities. Simultaneously, an improved cascaded feature fusion module (PFFM) is used to fully integrate the extracted feature maps, expanding the receptive field of features and enriching the expressive ability of the feature maps. Finally, to address the cascaded feature maps, a lightweight subspace attention module (SAM) is introduced to partition the concatenated feature maps into several sub-space feature maps, facilitating spatial information interaction among features of different scales. In this paper, comparative experiments are conducted on the ICDAR2015, Total-Text, and MSRA-TD500 datasets, and comparisons are made with some existing scene text detection methods. The results show that the proposed method achieves good performance in terms of accuracy, recall, and F-score, thus verifying its effectiveness and practicality.
引用
收藏
页数:18
相关论文
共 50 条
  • [1] Traffic sign detection based on multi-scale feature extraction and cascade feature fusion
    Zhang, Yongliang
    Lu, Yang
    Zhu, Wuqiang
    Wei, Xing
    Wei, Zhen
    [J]. JOURNAL OF SUPERCOMPUTING, 2023, 79 (02): : 2137 - 2152
  • [2] Traffic sign detection based on multi-scale feature extraction and cascade feature fusion
    Yongliang Zhang
    Yang Lu
    Wuqiang Zhu
    Xing Wei
    Zhen Wei
    [J]. The Journal of Supercomputing, 2023, 79 : 2137 - 2152
  • [3] Text Detection Algorithm Based on Multi-Scale Attention Feature Fusion
    She, Xiangyang
    Liu, Zhe
    Dong, Lihong
    [J]. Computer Engineering and Applications, 2024, 60 (01) : 198 - 206
  • [4] Pedestrian detection algorithm based on multi-scale feature extraction and attention feature fusion
    Xia, Hao
    Ma, Jun
    Ou, Jiayu
    Lv, Xinyao
    Bai, Chengjie
    [J]. DIGITAL SIGNAL PROCESSING, 2022, 121
  • [5] Hierarchical Feature Fusion With Text Attention For Multi-scale Text Detection
    Liu, Chao
    Zou, Yuexian
    Guan, Wenjie
    [J]. 2018 IEEE 23RD INTERNATIONAL CONFERENCE ON DIGITAL SIGNAL PROCESSING (DSP), 2018,
  • [6] UFNet: A Multi-scale Fusion Feature based Text Detection Method
    Chai, Zhengpeng
    Zhu, Rui
    Wang, Wei
    [J]. 2023 THE 6TH INTERNATIONAL CONFERENCE ON ROBOT SYSTEMS AND APPLICATIONS, ICRSA 2023, 2023, : 163 - 168
  • [7] Co-Saliency Detection Based on Multi-Scale Feature Extraction and Feature Fusion
    Zuo, Kuangji
    Liang, Huiqing
    Wang, Dechen
    Zhang, Dehua
    [J]. 2022 4TH INTERNATIONAL CONFERENCE ON CONTROL AND ROBOTICS, ICCR, 2022, : 364 - 368
  • [8] Salient Object Detection Based on Multi-scale Feature Extraction and Multi-level Feature Fusion
    Li, Lingli
    Meng, Lingbing
    Li, Jinbao
    [J]. Gongcheng Kexue Yu Jishu/Advanced Engineering Sciences, 2021, 53 (01): : 170 - 177
  • [9] Ship Detection in SAR Images Based on Multi-Scale Feature Extraction and Adaptive Feature Fusion
    Zhou, Kexue
    Zhang, Min
    Wang, Hai
    Tan, Jinlin
    [J]. REMOTE SENSING, 2022, 14 (03)
  • [10] Remote Sensing Object Detection Method Based on Attention Mechanism and Multi-scale Feature Fusion
    Liu, Yang
    Xiao, Yewei
    [J]. 2022 41ST CHINESE CONTROL CONFERENCE (CCC), 2022, : 7155 - 7160