Classification of Letter Images from Scanned Invoices using CNN
DOI:
https://doi.org/10.47839/ijc.22.3.3232Keywords:
CNN (Convolutional Neural Network), L 2 Regularization, Early stopping, OCR (optical character recognition)Abstract
Data analytics helps companies to analyze customer trends, make better business decisions and optimize their performances. Scanned document analysis is an important step in data analytics. Automatically extracting information from a scanned receipt has potential applications in industries. Both printed and handwritten letters are present in a receipt. Often these receipt documents are of low resolution due to paper damage and poor scanning quality. So, correctly recognizing each letter is a challenge. This work focuses on building an improved Convolutional Neural Network (CNN) model with regularization technique for classifying all English characters (both uppercase and lowercase) and numbers from 0 to 9. The training data contains about 60000 images of letters (English alphabets and numbers).This training data consists of letter images from windows true type (.ttf ) files and from different scanned receipts. We developed different CNN models for this 62 class classification problem, with different regularization and dropout techniques. Hyperparameters of Convolutional Neural Network are adjusted to obtain the optimum accuracy. Different optimization methods are considered to obtain better accuracy. Performance of each CNN model is analyzed in terms of accuracy, precision value, recall value, F1 score and confusion matrix to find out the best model. Prediction error of the model is calculated for Gaussian noise and impulse noise at different noise levels.
References
K. Y. Wong, R. G. Casey, F. M. Wahl, “Document analysis system,” IBM Journal of Research and Development, vol. 26, issue 6, pp. 647–656, 1982. https://doi.org/10.1147/rd.266.0647.
J. Memon, M. Sami, R. A. Khan, M. Uddin, “Handwritten optical character recognition (OCR): A comprehensive systematic literature review (SLR), IEEE Access, vol. 8, pp. 142642–142668, 2020. https://doi.org/10.1109/ACCESS.2020.3012542.
S. Mori, C. Suen, K. Yamamoto, “Historical review of OCR research and development,” Proceedings of the IEEE, vol. 80, issue 7, pp. 1029–1058, 1992. https://doi.org/10.1109/5.156468.
T. K. Ho, G. Nagy, “OCR with no shape training,” Proceedings of the 15th International Conference on Pattern Recognition. ICPR-2000, vol. 4, 2000, pp. 27–30. https://doi.org/10.1109/ICPR.2000.902858.
G. Nagy, “At the frontiers of OCR,” Proceedings of the IEEE, vol. 80, issue 7, pp. 1093–1100, 1992. https://doi.org/10.1109/5.156472.
V. Bharath, N. S. Rani, “A font style classification system for English OCR,” Proceedings of the 2017 IEEE International Conference on Intelligent Computing and Control (I2C2), 2017, pp. 1–5. https://doi.org/10.1109/I2C2.2017.8321962.
R. Hoch, “Using IR techniques for text classification in document analysis,” Proceedings of the SIGIR’94, Springer, 1994, pp. 31–40. https://doi.org/10.1007/978-1-4471-2099-5_4.
B. B. Chaudhuri, U. Pal, “A complete printed Bangla OCR system,” Pattern Recognition, vol. 31, issue 5, pp. 531–549, 1998. https://doi.org/10.1016/S0031-3203(97)00078-2.
A. Shrivastava, I. Jaggi, S. Gupta, D. Gupta, “Handwritten digit recognition using machine learning: A review,” Proceedings of the 2019 IEEE 2nd International Conference on Power Energy, Environment and Intelligent Control (PEEIC), 2019, pp. 322–326. https://doi.org/10.1109/PEEIC47157.2019.8976601.
C. Zhang, Z. Zhou, L. Lin, “Handwritten digit recognition based on convolutional neural network,” Proceedings of the 2020 IEEE Chinese Automation Congress (CAC), 2020, pp. 7384–7388. https://doi.org/10.1109/CAC51589.2020.9326781.
J. Li, G. Sun, L. Yi, Q. Cao, F. Liang, Y. Sun, “Handwritten digit recognition system based on convolutional neural network,” Proceedings of the 2020 IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA), 2020, pp. 739–742. https://doi.org/10.1109/AEECA49918.2020.9213619.
S. S. Rajput, Y. Choi, “Handwritten digit recognition using convolution neural networks,” Proceedings of the 2022 IEEE 12th Annual Computing and Communication Workshop and Conference (CCWC), 2022, pp. 0163–0168. https://doi.org/10.1109/CCWC54503.2022.9720854.
J. Hu, M. K. Brown, W. Turin, “HMM based online handwriting recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, issue 10, pp. 1039–1045, 1996. https://doi.org/10.1109/34.541414.
C. Bahlmann, B. Haasdonk, H. Burkhardt, “Online handwriting recognition with support vector machines – A kernel approach,” Proceedings of the Eighth IEEE International Workshop on Frontiers in Handwriting Recognition, 2002, pp. 49–54.
A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” Communications of the ACM, vol. 60, issue 6, pp. 84-90, 2017. https://doi.org/10.1145/3065386.
N. K. Manaswi, N. K. Manaswi, S. John, Deep Learning with Applications using Python, Springer, 2018. https://doi.org/10.1007/978-1-4842-3516-4.
K. A. Hamad, K. Mehmet, “A detailed analysis of optical character recognition technology,” International Journal of Applied Mathematics Electronics and Computers, vol. 4, Special Issue 1, pp. 244–249, 2016. https://doi.org/10.18100/ijamec.270374.
S. Khare, J. Singh, “Handwritten Devanagari character recognition system: A review,” International Journal of Computer Applications, vol. 121, pp. 9, 2015. https://doi.org/10.5120/21566-4600.
T. Ashwin, P. Sastry, “A font and size-independent OCR system for printed Kannada documents using support vector machines,” Sadhana, vol. 27, issue 1, pp. 35–58, 2002. https://doi.org/10.1007/BF02703311.
M. Avadesh, N. Goyal, “Optical character recognition for Sanskrit using convolution neural networks,” Proceedings of the 2018 13th IEEE IAPR International Workshop on Document Analysis Systems (DAS), 2018, pp. 447–452. https://doi.org/10.1109/DAS.2018.50.
S. Joshi, N. Khanna, “Single classifier-based passive system for source printer classification using local texture features,” IEEE Transactions on Information Forensics and Security, vol. 13, issue 7, pp. 1603–1614, 2018. https://doi.org/10.1109/TIFS.2017.2779441.
I. Goodfellow, Y. Bengio, A. Courville, Deep Learning, MIT Press, 2016.
C. Tensmeyer, T. Martinez, “Analysis of convolutional neural networks for document image classification,” Proceedings of the 2017 IEEE 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, 2017, pp. 388–393. https://doi.org/10.1109/ICDAR.2017.71.
C.-J. Lin, Y.-C. Liu, C.-L. Lee, “Automatic receipt recognition system based on artificial intelligence technology,” Applied Sciences, vol. 12, issue 2, 853, 2022. https://doi.org/10.3390/app12020853
L. Chen, S. Wang, W. Fan, J. Sun, S. Naoi, “Beyond human recognition: A CNN-based framework for handwritten character recognition,” Proceedings of the 2015 IEEE 3rd IAPR Asian Conference on Pattern Recognition (ACPR), 2015, pp. 695–699. https://doi.org/10.1109/ACPR.2015.7486592.
A. Yue, Automated Receipt Image Identification Cropping and Parsing, Princeton. Edu, 2020, pp 1-8.
P. Y. Simard, D. Steinkraus, J. C. Platt, et al., “Best practices for convolutional neural networks applied to visual document analysis,” ICDAR, vol. 3, pp. 122-132, 2003.
Downloads
Published
How to Cite
Issue
Section
License
International Journal of Computing is an open access journal. Authors who publish with this journal agree to the following terms:• Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
• Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
• Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
