Application of Binary Image Quality Assessment Methods to Predict the Quality of Optical Character Recognition Results
Source abstract
Abstract
One of the continuous challenges related to the growing popularity of mobile devices and embedded systems with limited memory and computational power is the development of relatively fast methods for real-time image and video analysis. One such example is Optical Character Recognition (OCR), which is usually too complex for such devices. Considering that images captured by cameras integrated into mobile devices may be acquired in uncontrolled lighting conditions, some quality issues related to non-uniform illumination may affect the image binarization results and further text recognition results. The solution proposed in this paper is related to a significant reduction in the computational burden, preventing the necessity of full text recognition. Conducting only the initial image binarization using various thresholding methods, the computation of the mutual similarities of binarization results is proposed, making it possible to build a simple model of binary image quality for a fast prediction of the OCR results’ quality. The experimental results provided in the paper obtained for the dataset of 1760 images, as well as the additional verification for a larger dataset, confirm the high correlation of the proposed quality model with text recognition results.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Image and Object Detection Techniques · Image Retrieval and Classification Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Signal Processing and Multimedia Engineering, West Pomeranian University of Technology in Szczecin, 70-313 Szczecin, Poland
References (31)
Show source-provided references
1. A Threshold Selection Method from Gray-Level Histograms10.1109/TSMC.1979.4310076 ↗
2. A method supporting fault-tolerant optical text recognition from video sequences recorded with handheld cameras10.1016/j.engappai.2023.106330 ↗
3. Ho, J., and Liu, M. (August, January 31). Research on Document Image Binarization: A Survey. Proceedings of the 2024 IEEE 7th International Conference on Electronic Information and Communication Technology (ICEICT), Xi’an, China.10.1109/ICEICT61637.2024.10671186 ↗
4. Improvement of the color text image binarization method using the minimum-distance classifier
5. Yang, Z., Zuo, S., Zhou, Y., He, J., and Shi, J. (2024). A Review of Document Binarization: Main Techniques, New Challenges, and Trends. Electronics, 13.10.3390/electronics13071394 ↗
6. No-reference image quality assessment algorithms: A survey10.1016/j.ijleo.2015.02.093 ↗
7. Distance-Reciprocal Distortion Measure for Binary Document Images10.1109/LSP.2003.821748 ↗
8. Young, D., and Ferryman, J. (2005, January 15–16). PETS Metrics: On-Line Performance Evaluation Service. Proceedings of the 2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, Beijing, China.
9. Similarity of Scenic Bilevel Images10.1109/TIP.2016.2598493 ↗
10. A simple quality evaluation method of binary images based on Border Distance10.1016/j.ijleo.2010.07.030 ↗
11. Michalak, H., and Okarma, K. (2020). Robust Combined Binarization Method of Non-Uniformly Illuminated Document Images for Alphanumerical Character Recognition. Sensors, 20.10.3390/s20102914 ↗
12. Bernsen, J. (1986, January 27–31). Dynamic Thresholding of Gray Level Image. Proceedings of the ICPR’86 Proceedings of International Conference on Pattern Recognition, Paris, France.
13. Adaptive Thresholding using the Integral Image10.1080/2151237X.2007.10129236 ↗
14. Contrast adaptive binarization of low quality document images10.1587/elex.1.501 ↗
15. Comparison of Niblack inspired binarization methods for ancient documents10.1117/12.805827 ↗
16. Niblack, W. (1990). An Introduction to Digital Image Processing, Prentice-Hall, Inc.
17. Adaptive document image binarization10.1016/S0031-3203(99)00055-2 ↗
18. Wolf, C., and Jolion, J.M. (2004). Extraction and recognition of artificial text in multimedia documents. Form. Pattern Anal. Appl., 6.10.1007/s10044-003-0197-7 ↗
19. Performance Evaluation Methodology for Historical Document Image Binarization10.1109/TIP.2012.2219550 ↗
20. A Hybrid Method for Objective Quality Assessment of Binary Images10.1109/ACCESS.2023.3289168 ↗
21. Combined image similarity index10.1007/s10043-012-0055-1 ↗
22. Rassool, R. (2017, January 7–9). VMAF reproducibility: Validating a perceptual practical video quality metric. Proceedings of the 2017 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB), Cagliari, Italy.10.1109/BMSB.2017.7986143 ↗
23. Okarma, K., Lech, P., and Lukin, V.V. (2021). Combined Full-Reference Image Quality Metrics for Objective Assessment of Multiply Distorted Images. Electronics, 10.10.3390/electronics10182256 ↗
24. Combining full-reference image visual quality metrics by neural network
25. Adaptive degraded document image binarization10.1016/j.patcog.2005.09.010 ↗
26. An adaptive local binarization method for document images based on a novel thresholding method and dynamic windows10.1016/j.patrec.2011.08.001 ↗
27. A New Local Adaptive Thresholding Technique in Binarization
28. Robust document image binarization technique for degraded document images10.1109/TIP.2012.2231089 ↗
29. Binarization of Document Image Using Optimum Threshold Modification10.1088/1742-6596/1019/1/012022 ↗
30. ISauvola: Improved Sauvola’s Algorithm for Document Image Binarization10.1007/978-3-319-41501-7_82 ↗
31. Nayef, N., Luqman, M.M., Prum, S., Eskenazi, S., Chazalon, J., and Ogier, J.M. (2015, January 23–26). SmartDoc-QA: A dataset for quality assessment of smartphone captured document images - single and multiple distortions. Proceedings of the 2015 13th International Conference on Document Analysis and Recognition (ICDAR). Institute of Electrical and Electronics Engineers (IEEE), Tunis, Tunisia.10.1109/ICDAR.2015.7333960 ↗