Retracted : A Novel Study on Localization in Scene Text Detection


Pravinkumar Sonsare
Rushabh Jain
Rutuj Runwal
Kunal Dave
Ashutosh Banode


Scene text detection has been one of the most important topics for research in computer vision. With constant development and rise in deep learning, computer vision technology has undergone an impactful transformation. In the era before deep learning, there existed algorithms and technologies for scene text detection, but the performance was mediocre. In recent years, deep learning technology has remarkably transformed scene text detection. Researchers have witnessed notable advancements in the approach, methodology, and overall performance of the newly discovered techniques. In this paper, the predominant focus is on summarizing and analysing the significant progress in scene text detection through deep learning. This paper covers an introduction to scene text detection, steps to perform scene text recognition and detection, technique before deep-learning, recent techniques and their insights, some results, and an overview by comparing the algorithms. We will also emphasize the criteria that make a search algorithm a good choice for performing scene text detection and recognition, the notable differences incorporated by deep learning, and analyse the drawbacks of the techniques used before deep learning. This paper would be helpful to understand the key differences that have changed this field and also some remaining challenges.


How to Cite
Sonsare, P., Jain, R., Runwal, R., Dave, K. ., & Banode, A. (2023). Retracted : A Novel Study on Localization in Scene Text Detection. International Journal of Next-Generation Computing, 14(1).


  1. Baek, Y., Lee, B., Han, D., Yun, S., and Lee, H. 2019. Character region awareness for text detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 9365–9374. DOI:
  2. Sonsare, P., Pardhi, P., and Khedgaonkar, R. 2021. Leaf infection detection using fuzzy support vector machine. International Journal of Next-Generation Computing 12, 5
  3. Sonsare, P. M. and Gunavathi, C. 2021. Cascading 1d-convnet bidirectional long short term memory network with modified cocob optimizer: A novel approach for protein secondary structure prediction. Chaos, Solitons & Fractals 153, 111446. DOI:
  4. Tian, S., Pan, Y., Huang, C., Lu, S., Yu, K., and Tan, C. L. 2015. Text flow: A unified text detection system in natural scene images. In Proceedings of the IEEE international conference on computer vision. 4651–4659. DOI:
  5. Zhang, Z., Zhang, C., Shen, W., Yao, C., Liu, W., and Bai, X. 2016. Multi-oriented text detection with fully convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4159–4167. DOI:
  6. Zhou, X., Yao, C., Wen, H., Wang, Y., Zhou, S., He, W., and Liang, J. 2017. East: an efficient and accurate scene text detector. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 5551–5560. DOI: