Classification of Invoice Images By Using Convolutional Neural Networks

Uymaz, Sait Ali; Arslan, Ömer

Classification of Invoice Images By Using Convolutional Neural Networks

Ömer Arslan, (Kuveyt Türk Katılım Bankası A.Ş., Konya Araştırma ve Geliştirme (Ar-Ge) Merkezi, Konya, Türkiye)

Sait Ali Uymaz (Bilgisayar Mühendisliği Bölümü, Mühendislik ve Doğa Bilimleri Fakültesi, Konya Teknik Üniversitesi, Konya, Türkiye)

Journal of advanced research in natural and applied sciences (Online)

16 3

Yıl: 2022 Cilt: 8 Sayı: 1 Sayfa Aralığı: 8 - 25 Metin Dili: İngilizce İndeks Tarihi: 14-09-2022

Classification of Invoice Images By Using Convolutional Neural Networks

Öz:

Abstract − Today, as the companies grow, the number of personnel working within the company and the number of supplier companies that the company works with are also increasing. In parallel with this increase, the amount of expenditure made on behalf of the company increases, and more invoi- ces are created. Since the in-voices must be kept for legal reasons, physical invoices are transferred to the digital environment. Since large companies have large numbers of invoices, labor demand is higher in digitalizing invoices. In addition, as the number of invoices to be transferred to digital media increases, the number of possible errors during entry becomes more. This paper aims to automate the transfer of invoices to the digital environment. In this study, invoices be-longing to four different templates were used. Invoice images taken from a bank system were used for the first time in this study, and the original invoice dataset was prepared. Furthermore, two more datasets were obtained by applying preprocessing methods (Zero-Padding, Brightness Augmentation) on the original dataset. The Invoice classification system developed using Convolutional Neural Networks (CNN) archite- ctures named LeNet-5, VGG-19, and MobileNetV2 was trained on three different data sets. Data preprocessing techniques such as correcting the curvature and aspect ratio of the invoices and image augmentation with variable brightness ratio were applied to create the data sets. The datasets created with preprocessing techniques have increased the classification success of the proposed models. With this proposed model, invoice images were automatically classified according to their templates using CNN architectures. In experimental studies, a classification success rate of 99.83% was achieved in training performed on the data set produced by the data augmentation method.

Anahtar Kelime:

Belge Türü: Makale Makale Türü: Araştırma Makalesi Erişim Türü: Erişime Açık

Afzal, M. Z., Capobianco, S., Malik, M. I., Marinai, S., Breuel, T. M., Dengel, A., & Liwicki, M. (2015).
Deepdocclassifier: Document classification with deep convolutional neural network. Paper presented at the 2015 13th international conference on document analysis and recognition (ICDAR). DOI: https:// doi.org/10.1109/ICDAR.2015.7333933
Aloysius, N., & Geetha, M. (2017). A review on deep convolutional neural networks. Paper presented at the 2017 International Conference on Communication and Signal Processing (ICCSP). DOI: https://doi. org/10.1109/ICCSP.2017.8286426
Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32. DOI: https://doi. org/10.1023/A:1010933404324
Brown, J. M. (2017). Predicting math test scores using k-nearest neighbor. Paper presented at the 2017 IEEE Integrated STEM Education Conference (ISEC). DOI: https://doi.org/10.1109/ISECon.2017.7910221
Carvalho, T., De Rezende, E. R., Alves, M. T., Balieiro, F. K., & Sovat, R. B. (2017). Exposing computer generated images by eye’s region classification via transfer learning of VGG19 CNN. Paper presented at the 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA). DOI: https://doi.org/10.1109/ICMLA.2017.00-47
Casey, R., Ferguson, D., Mohiuddin, K., & Walach, E. (1992). Intelligent forms processing system. Ma- chine Vision and Applications, 5(3), 143-155. DOI: https://doi.org/10.1007/BF02626994
Chunhavittayatera, S., Chitsobhuk, O., & Tongprasert, K. (2006). Image registration using Hough trans- form and phase correlation. Paper presented at the 2006 8th International Conference Advanced Com- munication Technology. DOI: https://doi.org/10.1109/ICACT.2006.206134
Duda, R. O., & Hart, P. E. (1972). Use of the Hough transformation to detect lines and curves in pictures. Communications of the ACM, 15(1), 11-15. DOI: https://doi.org/10.1145/361237.361242
Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Cai, J. (2018). Recent advances in convolutional neural networks. Pattern Recognition, 77, 354-377. DOI: https://doi.org/10.1016/j.patcog.2017.10.013
Ha, P. S., & Shakeri, M. (2016). License Plate Automatic Recognition based on edge detection. Paper presented at the 2016 Artificial Intelligence and Robotics (IRANOPEN). DOI: https://doi.org/10.1109/ RIOS.2016.7529509
Kang, L., Kumar, J., Ye, P., Li, Y., & Doermann, D. (2014). Convolutional neural networks for document image classification. Paper presented at the 2014 22nd International Conference on Pattern Recognition. DOI: https://doi.org/10.1109/ICPR.2014.546
Khan, M., & Mufti, N. (2016). Comparison of various edge detection filters for ANPR. Paper presented at the 2016 Sixth International Conference on Innovative Computing Technology (INTECH). DOI: https:// doi.org/10.1109/INTECH.2016.7845061
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neu- ral networks. Paper presented at the Advances in neural information processing systems. DOI: https:// doi.org/10.1145/3065386
LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document rec- ognition. Proceedings of the IEEE, 86(11), 2278-2324. DOI: https://doi.org/10.1109/5.726791
Liu, T., Fang, S., Zhao, Y., Wang, P., & Zhang, J. (2015). Implementation of training convolutional neural networks. Retrieved from: https://arxiv.org/abs/1506.01195
Nguyen, A.-D., Choi, S., Kim, W., Ahn, S., Kim, J., & Lee, S. (2019). Distribution Padding in Convolution- al Neural Networks. Paper presented at the 2019 IEEE International Conference on Image Processing (ICIP). DOI: https://doi.org/10.1109/ICIP.2019.8803537
O’Shea, K., & Nash, R. (2015). An introduction to convolutional neural networks. Retrieved from: https:// arxiv.org/abs/1511.08458
Rawat, W., & Wang, Z. (2017). Deep convolutional neural networks for image classification: A compre- hensive review. Neural computation, 29(9), 2352-2449. DOI: https://doi.org/10.1162/NECO_a_00990
Reghunath, A., Nair, S. V., & Shah, J. (2019). Deep learning based Customized Model for Features Extrac- tion. Paper presented at the 2019 International Conference on Communication and Electronics Systems (ICCES). DOI: https://doi.org/10.1109/ICCES45898.2019.9002299
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition. DOI: https://doi.org/10.1109/CVPR.2018.00474
Saxen, F., Werner, P., Handrich, S., Othman, E., Dinges, L., & Al-Hamadi, A. (2019). Face attribute detec- tion with mobilenetv2 and nasnet-mobile. Paper presented at the 2019 11th International Symposium on Image and Signal Processing and Analysis (ISPA). DOI: https://doi.org/10.1109/ISPA.2019.8868585
Shaha, M., & Pawar, M. (2018). Transfer learning for image classification. Paper presented at the 2018 Second International Conference on Electronics, Communication and Aerospace Technology (ICECA). DOI: https://doi.org/10.1109/ICECA.2018.8474802
Sidhwa, H., Kulshrestha, S., Malhotra, S., & Virmani, S. (2018). Text extraction from bills and invoices. Pa- per presented at the 2018 International Conference on Advances in Computing, Communication Control and Networking (ICACCCN). DOI: https://doi.org/10.1109/ICACCCN.2018.8748309
Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recogni- tion. Retrieved from: https://arxiv.org/abs/1409.1556
Tang, Y. Y., Suen, C. Y., De Yan, C., & Cheriet, M. (1995). Financial document processing based on staff line and description language. IEEE transactions on systems, man, and cybernetics, 25(5), 738-754. DOI: https://doi.org/10.1109/21.376488
Tarawneh, A. S., Hassanat, A. B., Chetverikov, D., Lendak, I., & Verma, C. (2019). Invoice classification using deep features and machine learning techniques. Paper presented at the 2019 IEEE Jordan Interna- tional Joint Conference on Electrical Engineering and Information Technology (JEEIT). DOI: https:// doi.org/10.1109/JEEIT.2019.8717504
Toğaçar, M., Cömert, Z., & Ergen, B. (2021). Intelligent skin cancer detection applying autoencoder, Mo- bileNetV2 and spiking neural networks. Chaos, Solitons & Fractals, 144, 110714. DOI: https://doi. org/10.1016/j.chaos.2021.110714
Wang, G., & Gong, J. (2019). Facial expression recognition based on improved LeNet-5 CNN. Paper pre- sented at the 2019 Chinese Control And Decision Conference (CCDC). DOI: https://doi.org/10.1109/ CCDC.2019.8832535
Xia, Y., Cai, M., Ni, C., Wang, C., Shiping, E., & Li, H. (2019). A Switch State Recognition Method based on Improved VGG19 network. Paper presented at the 2019 IEEE 4th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC). DOI:https://doi.org/10.1109/ IAEAC47372.2019.8998029
Zou, Y., Zhao, L., Qin, S., Pan, M., & Li, Z. (2020). Ship target detection and identification based on SSD_MobilenetV2. Paper presented at the 2020 IEEE 5th Information Technology and Mechatronics Engineering Conference (ITOEC). DOI: https://doi.org/10.1109/ITOEC49072.2020.9141734

APA	Arslan Ö, Uymaz S (2022). Classification of Invoice Images By Using Convolutional Neural Networks. , 8 - 25.
Chicago	Arslan Ömer,Uymaz Sait Ali Classification of Invoice Images By Using Convolutional Neural Networks. (2022): 8 - 25.
MLA	Arslan Ömer,Uymaz Sait Ali Classification of Invoice Images By Using Convolutional Neural Networks. , 2022, ss.8 - 25.
AMA	Arslan Ö,Uymaz S Classification of Invoice Images By Using Convolutional Neural Networks. . 2022; 8 - 25.
Vancouver	Arslan Ö,Uymaz S Classification of Invoice Images By Using Convolutional Neural Networks. . 2022; 8 - 25.
IEEE	Arslan Ö,Uymaz S "Classification of Invoice Images By Using Convolutional Neural Networks." , ss.8 - 25, 2022.
ISNAD	Arslan, Ömer - Uymaz, Sait Ali. "Classification of Invoice Images By Using Convolutional Neural Networks". (2022), 8-25.

APA	Arslan Ö, Uymaz S (2022). Classification of Invoice Images By Using Convolutional Neural Networks. Journal of advanced research in natural and applied sciences (Online), 8(1), 8 - 25.
Chicago	Arslan Ömer,Uymaz Sait Ali Classification of Invoice Images By Using Convolutional Neural Networks. Journal of advanced research in natural and applied sciences (Online) 8, no.1 (2022): 8 - 25.
MLA	Arslan Ömer,Uymaz Sait Ali Classification of Invoice Images By Using Convolutional Neural Networks. Journal of advanced research in natural and applied sciences (Online), vol.8, no.1, 2022, ss.8 - 25.
AMA	Arslan Ö,Uymaz S Classification of Invoice Images By Using Convolutional Neural Networks. Journal of advanced research in natural and applied sciences (Online). 2022; 8(1): 8 - 25.
Vancouver	Arslan Ö,Uymaz S Classification of Invoice Images By Using Convolutional Neural Networks. Journal of advanced research in natural and applied sciences (Online). 2022; 8(1): 8 - 25.
IEEE	Arslan Ö,Uymaz S "Classification of Invoice Images By Using Convolutional Neural Networks." Journal of advanced research in natural and applied sciences (Online), 8, ss.8 - 25, 2022.
ISNAD	Arslan, Ömer - Uymaz, Sait Ali. "Classification of Invoice Images By Using Convolutional Neural Networks". Journal of advanced research in natural and applied sciences (Online) 8/1 (2022), 8-25.