Study on handwritten invoice recognition system
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In recent years, the growing preference for contactless services has resulted in an increased demand for kiosk-based reception systems. Although several kiosks have been activated for product orders, the reception services that entail more intricate procedures and require extensive information, such as those in postal and logistics services, have not been adequately embraced. Furthermore, the conventional paper-based reception systems fail to suffice the modern requirements. Therefore, this study proposes an innovative system for automatically processing handwritten invoices. The proposed system accurately extracts invoice details from parcel images and automatically digitizes the sender and receiver information by employing a visual document understanding model. In particular, this study presents the essential construction of an optimal training dataset that is required during the fine-tuning process of neural network-based models. It is anticipated that this will dramatically enhance the performance and accuracy of systems that handle hand-written invoices, paving the way for innovative advancements in the forthcoming years.
Abstract
In recent years, the growing preference for contactless services has resulted in an increased demand for kiosk-based reception systems. Although several kiosks have been activated for product orders, the reception services that entail more intricate procedures and require extensive information, such as those in postal and logistics services, have not been adequately embraced. Furthermore, the conventional paper-based reception systems fail to suffice the modern requirements. Therefore, this study proposes an innovative system for automatically processing handwritten invoices. The proposed system accurately extracts invoice details from parcel images and automatically digitizes the sender and receiver information by employing a visual document understanding model. In particular, this study presents the essential construction of an optimal training dataset that is required during the fine-tuning process of neural network-based models. It is anticipated that this will dramatically enhance the performance and accuracy of systems that handle hand-written invoices, paving the way for innovative advancements in the forthcoming years.
참고문헌 (24)
- C. W. Chen, "Automatic telephone in-terview survey system", 2021 9th International Conference on Orange Technology, pp.1~4 (2021), IEEE
- S. Saiki, "A study of practical education program on ai, big data, and cloud computing through development of automatic ordering system", 2018 IEEE International Conference on Big Data, Cloud Computing, Data Science & Engineering, pp.31~36 (2018), IEEE
- F. Gao, "Omnichannel service operations with online and offline self-order technologies", Management Science, 64(8), pp.3595~3608 (2018)
- M. Chung, "Smart ordering application for assigning sequence numbers to customers at offline sites", ITM Web of Conferences, EDP Sciences, 24 (2019)
- T. Y. Wen, "Human and technology interaction: Consumer perception toward the touch screen ordering kiosk in fast food restaurant", Research in Management of Technology and Business, 3(2), pp.328~343 (2022)
- J. Memon, "Handwritten optical character recognition(OCR) : A comprehensive systematic literature review(SLR)", IEEE Access, 8, pp.142642~142668 (2020)
- S. D. Connell, "Template-based online character recognition", Pattern Recognition, 34(1), pp.1~14 (2001)
- I. K. Pathan, "Recognition of offline handwritten isolated Urdu character", Advances in Computational Research, 4(1), pp.117~121 (2012)
- M. T. Parvez, "Offline Arabic handwritten text recognition: A survey", ACM Computing Surveys, 45(2), pp.1~35 (2013)
- Y. Xu, "LayoutLM: Pre-training of text and layout for document image understanding", Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp.1192~1200 (2020)
- Y. Xu, "LayoutLMv2: Multi-modal pre-training for visually-rich document understanding", Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 1, pp.2579~2591 (2020)
- Y. Huang, "LayoutLMv3: Pre-training for document AI with unified text and image masking", Proceedings of the 30th ACM International Conference on Multimedia, pp.4083~4091 (2022)
- S. Appalaraju, "Docformer: End-to-end transformer for document understanding", Proceedings of the IEEE, 2021, 993~983
- S. Appalaraju, "DocFormerv2: Local features for document understanding", ~ (2023)
- K. Lee, "Pix2struct: Screenshot parsing as pretraining for visual language understanding", International Conference on Machine Learning, pp.18893~18912 (2023)
- Z. Tang, "Unifying vision, text, and layout for universal document processing", Proceedings of the IEEE, 2023, 19254~19264
- G. Kim, "OCR-free document understanding transformer", European Conference on Computer Vision, pp.498~517 (2022)
- Y. B. Hamdan, "Construction of statistical SVM based recognition model for handwritten character recognition", Journal of Information Technology and Digital World, 3(2), pp.92~107 (2021)
- A. Gupta, "Synthetic data for text localisation in natural images", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.2315~2324 (2016)
- T. Q. Phan, "Recognizing text with perspective distortion in natural scenes", Proceedings of the IEEE International Conference on Computer Vision, pp.569~576 (2013)
- Z. Zhang, "Multi-oriented text detection with fully convolutional networks", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.4159~4167 (2016)
- F. Borisyuk, "Rosetta: Large scale system for text detection and recognition in images", Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp.71~79 (2018)
- Z. Liu, "Swin transformer: Hierarchical vision transformer using shifted windows", Proceedings of the IEEE, 2021, 9992~10002
- M. Lewis, "Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension", Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp.7871~7880 (2020)