SCENE TEXT RECOGNITION MODELS EXPLAINABILITY USING LOCAL FEATURES

被引:1
|
作者
Ty, Mark Vincent [1 ]
Atienza, Rowel [1 ,2 ]
机构
[1] Univ Philippines, Elect & Elect Engn Inst, Quezon City, Philippines
[2] Univ Philippines, AI Grad Program, Quezon City, Philippines
来源
2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP | 2023年
关键词
Computer Vision; Scene Text Recognition; Explainable AI;
D O I
10.1109/ICIP49359.2023.10222406
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Explainable AI (XAI) is the study on how humans can be able to understand the cause of a model's prediction. In this work, the problem of interest is Scene Text Recognition (STR) Explainability, using XAI to understand the cause of an STR model's prediction. Recent XAI literatures on STR only provide a simple analysis and do not fully explore other XAI methods. In this study, we specifically work on data explainability frameworks, called attribution-based methods, that explains the important parts of an input data in deep learning models. However, integrating them into STR produces inconsistent and ineffective explanations, because they only explain the model in the global context. To solve this problem, we propose a new method, STRExp, to take into consideration the local explanations, i.e. the individual character prediction explanations. This is then benchmarked across different attribution-based methods on different STR datasets and evaluated across different STR models.
引用
收藏
页码:645 / 649
页数:5
相关论文
共 50 条
  • [31] Review of Scene Text Detection and Recognition
    Han Lin
    Peng Yang
    Fanlong Zhang
    Archives of Computational Methods in Engineering, 2020, 27 : 433 - 454
  • [32] Scene text recognition: an Indic perspective
    Vijayan, Vasanthan P.
    Chanda, Sukalpa
    Doermann, David
    Krishnan, Narayanan C.
    INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION, 2024,
  • [33] Summary of Scene Text Detection and Recognition
    Qin, Yao
    Zhang, Zhi
    PROCEEDINGS OF THE 15TH IEEE CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS (ICIEA 2020), 2020, : 85 - 89
  • [34] Review network for scene text recognition
    Li, Shuohao
    Han, Anqi
    Chen, Xu
    Yin, Xiaoqing
    Zhang, Jun
    JOURNAL OF ELECTRONIC IMAGING, 2017, 26 (05)
  • [35] Edit Probability for Scene Text Recognition
    Bai, Fan
    Cheng, Zhanzhan
    Niu, Yi
    Pu, Shiliang
    Zhou, Shuigeng
    2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 1508 - 1516
  • [36] A New Model for Scene Text Recognition
    Wang M.-S.
    Jiang X.-S.
    Niu S.-Z.
    Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology, 2019, 39 (03): : 269 - 275
  • [37] Scene text detection and recognition: a survey
    Fatemeh Naiemi
    Vahid Ghods
    Hassan Khalesi
    Multimedia Tools and Applications, 2022, 81 : 20255 - 20290
  • [38] Data Augmentation for Scene Text Recognition
    Atienza, Rowel
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021), 2021, : 1561 - 1570
  • [39] Review of Scene Text Detection and Recognition
    Lin, Han
    Yang, Peng
    Zhang, Fanlong
    ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING, 2020, 27 (02) : 433 - 454
  • [40] Curriculum learning for scene text recognition
    Yan, Jingzhe
    Tao, Yuefeng
    Zhang, Wanjun
    JOURNAL OF ELECTRONIC IMAGING, 2021, 30 (04)