Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

BPDO:Boundary Points Dynamic Optimization for Arbitrary Shape Scene Text Detection (2401.09997v1)

Published 18 Jan 2024 in cs.CV

Abstract: Arbitrary shape scene text detection is of great importance in scene understanding tasks. Due to the complexity and diversity of text in natural scenes, existing scene text algorithms have limited accuracy for detecting arbitrary shape text. In this paper, we propose a novel arbitrary shape scene text detector through boundary points dynamic optimization(BPDO). The proposed model is designed with a text aware module (TAM) and a boundary point dynamic optimization module (DOM). Specifically, the model designs a text aware module based on segmentation to obtain boundary points describing the central region of the text by extracting a priori information about the text region. Then, based on the idea of deformable attention, it proposes a dynamic optimization model for boundary points, which gradually optimizes the exact position of the boundary points based on the information of the adjacent region of each boundary point. Experiments on CTW-1500, Total-Text, and MSRA-TD500 datasets show that the model proposed in this paper achieves a performance that is better than or comparable to the state-of-the-art algorithm, proving the effectiveness of the model.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (28)
  1. “Real-time scene text detection with differentiable binarization,” in AAAI, 2020, pp. 11474–11481.
  2. “Cmfn: Cross-modal fusion network for irregular scene text recognition,” in ICONIP, 2024, pp. 421–433.
  3. L. Zhang and H. Fan, “Visual object tracking: Progress, challenge, and future,” The Innovation, vol. 4, 2023.
  4. “Artificial intelligence: A powerful paradigm for scientific research,” The Innovation, vol. 2, no. 4, pp. 100179, 2021.
  5. “Learning shape-aware embedding for scene text detection,” in CVPR, 2019, pp. 4229–4238.
  6. “Shape robust text detection with progressive scale expansion network,” in CVPR, 2019, pp. 9328–9337.
  7. “Adaptive boundary proposal network for arbitrary shape text detection,” in ICCV, 2021, pp. 1285–1294.
  8. “Real-time scene text detection with differentiable binarization and adaptive scale fusion,” TPAMI, vol. 45, no. 1, pp. 919–931, 2023.
  9. “Arbitrary shape text detection via boundary transformer,” TMM, pp. 1–14, 2023.
  10. “Dptext-detr: Towards better scene text detection with dynamic points in transformer,” in AAAI, 2023, pp. 3241–3249.
  11. “Novel approach to nonlinear/non-gaussian bayesian state estimation,” IEE Proceedings F - Radar and Signal Processing, vol. 140, no. 2, pp. 107–113, 2002.
  12. “Deformable detr: Deformable transformers for end-to-end object detection,” ICLR, 2021.
  13. “Deformable convnets v2: More deformable, better results,” in CVPR, 2019, pp. 9300–9308.
  14. “Synthetic data for text localisation in natural images,” in CVPR, 2016.
  15. C. Ch’ng and C. Chan, “Total-text: A comprehensive dataset for scene text detection and recognition,” in ICDAR, 2017, vol. 01, pp. 935–942.
  16. “Curved scene text detection via transverse and longitudinal sequence connection,” Pattern Recognition, vol. 90, pp. 337–345, 2019.
  17. “Detecting texts of arbitrary orientations in natural images,” in CVPR, 2012, pp. 1083–1090.
  18. “Ms-rocanet: Multi-scale residual orthogonal-channel attention network for scene text detection,” in ICASSP, 2022, pp. 2200–2204.
  19. “Character region awareness for text detection,” in CVPR, 2019, pp. 9357–9366.
  20. “Efficient and accurate arbitrary-shaped text detection with pixel aggregation network,” in ICCV, October 2019.
  21. “Deep relational reasoning graph network for arbitrary shape text detection,” in CVPR, 2020, pp. 9696–9705.
  22. “Contournet: Taking a further step toward accurate arbitrary-shaped scene text detection,” in CVPR, June 2020.
  23. “Fourier contour embedding for arbitrary-shaped text detection,” in CVPR, 2021, pp. 3122–3130.
  24. “Progressive contour regression for arbitrary-shape scene text detection,” in CVPR, 2021, pp. 7389–7398.
  25. “I3cl: Intra- and inter-instance collaborative learning for arbitrary-shaped scene text detection,” IJCV, vol. 130, pp. 1961–1977, 2022.
  26. “Few could be better than all: Feature sampling and grouping for scene text detection,” in CVPR, 2022, pp. 4563–4572.
  27. “Turning a clip model into a scene text detector,” in CVPR, 2023, pp. 6978–6988.
  28. “Arbitrary shape text detection via segmentation with probability maps,” TPAMI, vol. 45, no. 3, pp. 2736–2750, 2023.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Jinzhi Zheng (3 papers)
  2. Libo Zhang (105 papers)
  3. Yanjun Wu (26 papers)
  4. Chen Zhao (249 papers)
Citations (1)
View on Semantic Scholar