Optic Character Recognition Using Image Processing Techniques

Abstract

In pattern recognition, the automatic identification of image-based input patterns by machine is an important problem. The need to convert images taken with tools such as cameras into formats usable by computers is increasing day by day. The output and efficiency of manual data entry processes are low and error rates are high. Outsourcing these processes to companies dealing with professional information entry is not preferred due to reasons such as security and lack of continuous service quality. For these and similar reasons, a system that enables automatic recognition of optical characters is aimed. With the help of this system, it is aimed to provide the opportunity to serve more people in a shorter time. In accordance with the stated objectives, a unique dataset has been created by performing identification card segmentation. This dataset was combined with the standard OCR dataset and classification was performed with ANN and proposed CNN methods on the extended dataset. The proposed CNN method, inspired by the Inception V3 model, is a deep learning model consisting of 15 layers. The ANN model uses features obtained from different wavelet types to increase discrimination. Competitive results were obtained from both ANN and proposed CNN models. In the proposed CNN model, in the extended version of the dataset, 99.49%, 98.87%, 99.48% and 99.50% values for F1 score, recall, precision, and accuracy metrics were obtained in the same order for training. Similarly, for validation, 99.13%, 98.43%, 99.21% and 99.27% values were obtained in the same order.

Keywords

• Digit Recognition
• Wavelet Transform
• OCR
• ANN
• CNN
• Deep learning

Ethical Statement

There is no conflict of interest between the authors.

References

1. X.-F. Wang, Z.-H. He, K. Wang, Y.-F. Wang, L. Zou, and Z.-Z. Wu, “A survey of text detection and recognition algorithms based on deep learning technology,” Neurocomputing, vol. 556, pp. 126702, 2023.
2. R. Mohapatra, B. Majhi, and S. Jena, “Printed Odia Digit Recognition Using Finite Automaton,” in Proc. 3rd Int. Conf. Adv. Comput. Netw. Informatics, 2016, pp. 643–650.
3. S. Ghosh, N. Das, M. Kundu, and M. Nasipuri, “Handwritten Oriya Digit Recognition Using Maximum Common Subgraph Based Similarity Measures,” in Inf. Syst. Des. Intell. Appl., 2016, pp. 165–173.
4. A. Ghahnavieh and A. Raie, “A New Hierarchical Architecture Based on SVM for Persian License Plate Character Recognition,” J. Adv. Comput. Res., vol. 7, no. 1, pp. 49–66, 2016.
5. S. Kaur, “An Automatic Number Plate Recognition System under Image Processing,” Int. J. Intell. Syst. Appl., vol. 8, no. 3, pp. 14, 2016.
6. S. Babu and Z. Masood, “Android Based Optical Character Recognition for Noisy Document Images,” Int. J. Comput. Sci. Inf. Secur., vol. 14, no. 1, pp. 34, 2016.
7. G. Joseph and T. Singh, “Registration Plate Recognition Using Dynamic Image Processing and Genetic Algorithm,” in Innovations in Computer Science and Engineering, 2016, pp. 37–43.
8. I. Ahmad, S. Mahmoud, and G. Fink, “Open-vocabulary recognition of machine-printed Arabic text using hidden Markov models,” Pattern Recognit., pp. 97–111, 2016.

9. H. Cecotti, “Active graph based semi-supervised learning using image matching: Application to handwritten digit recognition,” Pattern Recognit. Lett., pp. 76–82, 2016.
10. H. Sajedi, “Handwriting recognition of digits, signs, and numerical strings in Persian,” Comput. Electr. Eng., vol. 49, pp. 52–65, 2016.
11. S. Karthikeyan, A. G. S. de Herrera, F. Doctor, and A. Mirza, “An OCR Post-Correction Approach Using Deep Learning for Processing Medical Reports,” IEEE Trans. Circuits Syst. Video Technol., vol. 32, no. 5, pp. 2574–2581, 2022.
12. S. Naz, S. Ahmed, R. Ahmad, and M. Razzak, “Arabic Script based Digit Recognition Systems,” in Int. Conf. Recent Adv. Comput. Syst., 2016, pp. 67-73.
13. V. Aradhya, G. Kumar, and S. Noushath, “Robust unconstrained handwritten digit recognition using radon transform,” in Signal Process. Commun. Netw., 2007, pp. 626–629.
14. H. Boveiri, “Transformation-Invariant Classification of Persian Printed Digits,” Int. J. Signal Process. Image Process. Pattern Recognit., vol. 4, no. 3, pp. 153–164, 2011.
15. R. Azad, F. Davami, and H. Shayegh, “Recognition of Handwritten Persian/Arabic Numerals Based on Robust Feature Set and K-NN Classifier,” in 2013 First Int. Conf. Comput. Inf. Technol. Digit. Media (CITADIM Proceeding-Scientific), 2014.
16. M. Ghaleb, L. George, and F. Mohammed, “Printed and Handwritten Hindi/Arabic Numeral Recognition Using Centralized Moments,” Int. J. Sci. Eng. Res., vol. 5, no. 3, pp. 140–144, 2014.
17. C. Liu and C. Suen, “A new benchmark on the recognition of handwritten Bangla and Farsi numeral characters,” Pattern Recognit., vol. 42, no. 12, 2009.
18. I. Meymand, “Recognition of Handwritten Persian/Arabic Numerals Based on Robust Feature Set and K-NN Classifier,” Int. J. Comput. Inf. Technol., vol. 1, no. 3, pp. 220–230, 2013.
19. D. Sharma, G. Lehal, and P. Kathuria, “Digit extraction and recognition from machine printed Gurmukhi documents,” in Proc. Int. Work. Multiling. OCR, 2009.
20. S. Metlek and H. Çetiner, “ResUNet+: A New Convolutional and Attention Block-Based Approach for Brain Tumor Segmentation,” IEEE Access, vol. 11, pp. 69884–69902, 2023.
21. S. Metlek, “CellSegUNet: an improved deep segmentation model for the cell segmentation based on UNet++ and residual UNet models,” Neural Comput. Appl., vol. 36, pp. 5799-5825, 2024.
22. H. Çetiner and S. Metlek, “DenseUNet+: A novel hybrid segmentation approach based on multi-modality images for brain tumor segmentation,” J. King Saud Univ. - Comput. Inf. Sci., vol. 35, no. 8, pp. 101663, 2023.
23. S. Metlek, “A new proposal for the prediction of an aircraft engine fuel consumption: a novel CNN-BiLSTM deep neural network model,” Aircr. Eng. Aerosp. Technol., vol. 95, no. 5, pp. 838–848, Jan. 2023.
24. J. N. and S. K. A. M, “A Novel Text Recognition Using Deep Learning Technique,” in 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS), 2024, pp. 1–6.
25. L. Yang, D. Ergu, Y. Cai, F. Liu, and B. Ma, “A review of natural scene text detection methods,” Procedia Comput. Sci., vol. 199, pp. 1458–1465, 2022.
26. R. Krithiga, S. Varsini, R. G. Joshua, and C. U. O. Kumar, “Ancient Character Recognition: A Comprehensive Review,” IEEE Access, pp. 1, 2023.
27. P. Batra, N. Phalnikar, D. Kurmi, J. Tembhurne, P. Sahare, and T. Diwan, “OCR-MRD: performance analysis of different optical character recognition engines for medical report digitization,” Int. J. Inf. Technol., vol. 16, no. 1, pp. 447–455, 2024.
28. L. M. Low, F. H. M. Salleh, Y. F. Law, and N. Z. Zakaria, “Detecting and recognizing seven segment digits using a deep learning approach,” in ITM Web of Conferences, 2024, pp. 1007.
29. A. Singh, S. Jangra, and G. Aggarwal, “EnvisionText: Enhancing Text Recognition Accuracy through OCR Extraction and NLP-based Correction,” in 2024 14th International Conference on Cloud Computing, Data Science & Engineering (Confluence), 2024, pp. 47–52.
30. S. Gujjeti, M. S., and V. G., “A Systematic Investigation on Different Scene Text Detection and Recognition Method using Deep Learning Techniques,” in 2024 International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), 2024, pp. 1–5.
31. A. A. Chandio, M. Asikuzzaman, and M. R. Pickering, “Cursive character recognition in natural scene images using a multilevel convolutional neural network fusion,” IEEE Access, vol. 8, pp. 109054–109070, 2020.
32. R. Deore, B. Gawali, and S. Mehrotra, “Digit Recognition System Using EEG Signal,” in Brain-Computer Interfaces, Cham: Springer Int. Publ., 2015, pp. 375–416.
33. J. Park and Y.-B. Kwon, “An Embedded OCR: A Practical Case Study of Code Porting for a Mobile Platform,” in 2009 Chinese Conference on Pattern Recognition, 2009, pp. 1–5.
34. A. Canedo-Rodriguez, S. Kim, J. H. Kim, and Y. Blanco-Fernandez, “English to Spanish translation of signboard images from mobile phone camera,” in IEEE Southeastcon 2009, 2009, pp. 356–361.
35. M. Nava-Ortiz, W. Gómez, and A. Díaz-Pérez, “Digit recognition system for camera mobile phones,” in 8th International Conference on Electrical Engineering, Computing Science and Automatic Control, Merida City, Mexico, 2011, pp. 1-5.
36. R. Shah and T. Ratanpara, “A Mean-Based Thresholding Approach for Broken Character Segmentation from Printed Gujarati Documents,” in Proc. Second Int. Conf. Comput. Commun. Technol., 2016, pp. 487–496.
37. P. Singh, A. Verma, and N. Chaudhari, “Performance Evaluation of Classifier Combination Techniques for the Handwritten Devanagari Character Recognition,” Inf. Syst. Des. Intell. Appl., pp. 651–662, 2016.
38. P. Singh, R. Sarkar, and M. Nasipuri, “A Study of Moment Based Features on Handwritten Digit Recognition,” Appl. Comput. Intell. Soft Comput., vol. 2016, pp. 1-17, 2016.
39. G. C. Batista and W. L. S. Silva, “Application of support vector machines to recognize speech patterns of numeric digits,” in 2015 11th International Conference on Natural Computation (ICNC), 2015, pp. 831–836.
40. H. Çetiner, “Görüntü işleme teknikleri kullanarak optik karakter tanımlama.” Yüksek lisans tezi, Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği AnaBilim Dalı, Isparta, Türkiye, 2012.
41. A. Jaiswal, “Standard OCR Dataset,” Kaggle, 2021. [Online]. Available: https://www.kaggle.com/datasets/preatcher/standard-ocr-dataset. [Accessed: Jan. 1, 2024].
42. A. F. de Sousa Neto, B. L. D. Bezerra, G. C. D. de Moura, and A. H. Toselli, “Data Augmentation for Offline Handwritten Text Recognition: A Systematic Literature Review,” SN Comput. Sci., vol. 5, no. 2, pp. 258, 2024.
43. M. Misiti, Y. Misiti, G. Oppenheim, and J. Poggi, “Wavelet toolbox,” Matlab User’s Guid., 1997. [Online]. Available: https://feihu.eng.ua.edu/NSF_TUES/w7_1a.pdf.
44. S. G. Mallat, “A theory for multiresolution signal decomposition: the wavelet representation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 11, no. 7, pp. 674–693, Jul. 1989.
45. H. Çetiner and B. Cetişli, "Real time recognition of identification cards of Turkish Republic with wavelet transforms," in 2013 21st Signal Processing and Communications Applications Conference (SIU), Haspolat, Turkey, 2013, pp. 1-4.