Advances in Optical Character Recognition for Figure Processing: A Review from 2014 to 2020

Soni

Advances in Optical Character Recognition for Figure Processing: A Review from 2014 to 2020

Authors: Soni

Published: 2025-02-21 19:23:09.735

Abstract

This research discusses the developments of Optical Character Recognition (OCR) methods for figure processing between 2014 and 2020. The study covered five sub-research questions on text detection, extraction, segmentation methods, state-of-the-art techniques, and their effectiveness in bridging existing research gaps. This is a quantitative method in which electronic data was analyzed systematically, based on independent variables like detection, extraction, and segmentation methods, along with dependent variables like accuracy, efficiency, and applicability. The key findings in this paper include the importance of deep learning to enhance the accuracy of text detection and segmentation, hybrid techniques that can improve text extraction efficiency, and integrated OCR frameworks for processing figures. The outcomes reveal recent trends, gaps in literature, and potential future directions that could further fuel innovation in OCR technology.

Keywords

Optical Character Recognition (OCR), Figure Processing, Text Detection, Text Extraction

References

Smith, R. (2007). An Overview of the Tesseract OCR Engine. Document Analysis and Recognition, ICDAR 2007.
Chen, H., Zhang, S., Xiao, B., & Hu, W. (2016). Text Detection and Recognition for Natural Scene Images via Fully Convolutional Networks. IEEE Transactions on Image Processing.
Long, J., Shelhamer, E., & Darrell, T. (2015). Fully Convolutional Networks for Semantic Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
Lyu, P., Liao, M., Yao, C., Wu, W., & Bai, X. (2018). Mask Text Spotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes. Proceedings of the European Conference on Computer Vision (ECCV).
Roy, A., & Kaushik, S. (2019). Hybrid Models for Optical Character Recognition: A Review. International Journal of Computer Vision.
Xu, Y., Wu, T., & Wang, J. (2020). Advancements in Figure Segmentation using Deep Learning Techniques. Neural Computing and Applications.
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Download PDF

How to Cite

Soni, (2025-02-21 19:23:09.735). Advances in Optical Character Recognition for Figure Processing: A Review from 2014 to 2020. Abhi International Journal of Applied Science, Volume zoZTzAC2cvXq8ipTGOd6, Issue 1.

ISSN: XXXX-XXXX

Abhi International Journal of
Applied Science ( AIJAS )