Multi-Oriented Scene Text Detection at Character Level

سال انتشار: 1402
نوع سند: مقاله ژورنالی
زبان: انگلیسی
مشاهده: 137

فایل این مقاله در 9 صفحه با فرمت PDF قابل دریافت می باشد

این مقاله در بخشهای موضوعی زیر دسته بندی شده است:

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

JR_IECO-6-3_006

تاریخ نمایه سازی: 10 آبان 1402

چکیده مقاله:

Recent scene text detection methods perform superior on benchmark datasets using deep-learning frameworks. In this paper, we re-implement the state-of-the-art text detection method, character region awareness for text detection (CRAFT), which can detect individual characters of scene text images. CRAFT is a character-based detection method with many advantages in detecting complex text by detecting character units and estimating the area between characters, capable of detecting texts of any shape. In the other words, we improve the detection performance of the baseline method, CRAFT, by some modifications in its architecture and proposing a training scheme that takes benefit of the advanced optimizer. The performance improvements of CRAFT are validated on three benchmark datasets: ICDAR۲۰۱۳, ICDAR۲۰۱۵, and COCO-Text. By applying the pre-trained models on COCO-Text, CRAFT shows that it cannot generalize without fine-tuning. We also improve the ICDAR۲۰۱۵ model and evaluate it on benchmark datasets. The evaluation results show improved precision performance compared to the original pre-trained model with fewer iterations and higher accuracy.

کلیدواژه ها:

نویسندگان

Mahdi Kazeminia

Velayat University

Hamed Shahraki

Velayat University

Mehran Tamjidi

Velayat University

مراجع و منابع این مقاله:

لیست زیر مراجع و منابع استفاده شده در این مقاله را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود مقاله لینک شده اند :
  • H. Lin, P. Yang, and F. Zhang, "Review of scene ...
  • S. Long, Y. Guan, B. Wang, K. Bian, and C. ...
  • T. Diep, "State-of-the-art in action: unconstrained text detection, " in ...
  • J. Matas, O. Chum, M. Urban, and T. Pajdla, "Robust ...
  • L. Neumann and J. Matas, "A method for text localization ...
  • B. Epshtein, E. Ofek, and Y. Wexler, "Detecting text in ...
  • W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, ...
  • J. Redmon, S. Divvala, R. Girshick, and A. Farhadi. "You ...
  • S. Ren, K. He, R. Girshick, and J. Sun. "Faster ...
  • J. Long, E. Shelhamer, and T. Darrell, "Fully convolutional networks ...
  • K. He, G. Gkioxari, P. Dollar, and R. Girshick, "Mask ...
  • Y. Baek, et al. "Character region awareness for text detection" ...
  • X. Zhou, C. Yao, H. Wen, Y. Wang, S. Zhou, ...
  • M. Liao, B. Shi, X. Bai, X. Wang, and W. ...
  • Y. Liu and L. Jin, "Deep matching prior network: Toward ...
  • M. Liao, B. Shi, and X. Bai, "Textboxes++: a single-shot ...
  • J. Ma, W. Shao, H. Ye, L. Wang, H. Wang, ...
  • X. Li, J. Liu, S. Zhang, and G. Zhang, "Learning ...
  • P. He, W. Huang, T. He, Q. Zhu, Y. Qiao, ...
  • D. Deng, H. Liu, X. Li, and D. Cai, "Pixellink: ...
  • S. Long, et al . "Textsnake: A flexible representation for ...
  • Z. Zhang, C. Zhang, W. Shen, C. Yao, W. Liu, ...
  • M. Liao, Z. Wan, C. Yao, K. Chen, and X. ...
  • X. Liu, D. Liang, S. Yan, D. Chen, Y. Qiao, ...
  • T. He, Z. Tian, W. Huang, C. Shen, Y. Qiao, ...
  • P. Lyu, M. Liao, C. Yao, W. Wu, and X. ...
  • Q. Wang, Y. Zheng, and M. Betke, "Sa-text: Simple but ...
  • H. Hu, C. Zhang, Y. Luo, Y. Wang, J. Han, ...
  • S. Zhang, M. Lin, T. Chen, L. Jin, and L. ...
  • C. Yao, X. Bai, N. Sang, X. Zhou, S. Zhou, ...
  • B. Shi, X. Bai, and S. Belongie, "Detecting oriented text ...
  • O. Ronneberger, P. Fischer, and T. Brox, "U-net: Convolutional networks ...
  • K. Simonyan and A. Zisserman, "Detecting oriented text in natural ...
  • C. Yao, X. Bai, W. Liu, Y. Ma, and Z. ...
  • D. Karatzas, et al. " Icdar ۲۰۱۳ robust reading competition, ...
  • D. Karatzas, et al. "Icdar ۲۰۱۵ competition on robust reading," ...
  • A. Gupta, A. Vedaldi, and A. Zisserman, "Synthetic data for ...
  • C.K. Ch'ng and C.S. Chan, "Total-text: A comprehensive dataset for ...
  • L. Yuliang, J. Lianwen, Z. Shuaitao, and Z. Sheng, "Detecting ...
  • M. Iwamura, N. Morimoto, K. Tainaka, D. Bazazian, L. Gomez, ...
  • T. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, ...
  • A. Veit, T. Matera, L. Neumann, J. Matas, and S. ...
  • Z. Raisi, M.A. Naiel, P. Fieguth, S. Wardell, and John ...
  • D.P. Kingma and J. Ba, "Adam: A method for stochastic ...
  • W. Wang, E. Xie, X. Li, W. Hou, T. Lu, ...
  • S.X. Zhang, et al. "Deep relational reasoning graph network for ...
  • Y. Su, Z. Shao, Y. Zhou, F. Meng, H. Zhu, ...
  • Z. Raisi, et al. "Smart Text Reader System for People ...
  • نمایش کامل مراجع