|
Аннотация.
В данной работе подробно рассмотрены особенности входных данных (изображений документов, полученных путем сканирования, фотографий и видеопоследовательностей), используемых в современных системах распознавания удостоверяющих документов. Предложена классификация распознающих систем по виду обрабатываемых входных данных. Рассмотрены имеющиеся проблемы и особенности введенных 2D, 3D и 4D-распознаваний. Сформулированы концептуальные модели и подход к построению универсальной промышленной системы распознавания, способной одинаково обрабатывать входные данные, относящиеся к различным классам.
Ключевые слова: распознавание документов, идентификационные документы, искусственный интеллект, OCR, машинное обучение, обработка изображений.
Стр. 3-9.
DOI: 10.14357/20790279220301 Литература
1. Llados J., Lumbreras F., Chapaprieta V. and Queralt J. ICAR: Identity card automatic reader // Proceedings of Sixth Interna-tional Conference on Document Analysis and Recognition. 2001. P. 470–474. 2. Mollah A.F., Majumder N., Basu S. and Nasipuri M. Design of an optical character recognition system for camera-based handheld devices // International Journal of Computer Science Issues. 2011. Vol. 8. No. 4. P. 283–289. 3. Ryan M. and Hanafiah N. An examination of character recognition on id card using template matching approach // Procedia Computer Science. 2015. Vol. 59. P. 520–529. 4. Attivissimo F., Giaquinto N., Scarpetta M. and Spadavecchia M. An automatic reader of identity documents // 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC). 2019. P. 3525–3530. 5. Xu J. and Wu X. A system to localize and recognize texts in oriented id card images // 2018 IEEE International Conference on Progress in Informatics and Computing (PIC). 2018. P. 149–153. 6. Bulatov K., Matalov D. and Arlazarov V. MIDV-2019: challenges of the modern mobile-based document OCR // Twelfth International Conference on Machine Vision (ICMV 2019). 2020. Vol. 11433. P. 717–722. 7. Li X., Zhang B., Liao J. and Sander P.V. Document rectification and illumination correction using a patch-based CNN // ACM Trans. Graph. 2019. Vol. 38. No. 6. 8. Asad F., Ul-Hasan A., Shafait F. and Dengel A. High performance OCR for camera-captured blurred documents with LSTM networks // 2016 12th IAPR Workshop on Document Analysis Systems (DAS). 2016. P. 7–12. 9. Chernov T.S., Razumnuy N.P., Kozharinov A.S., Nikolaev D.P. and Arlazarov V.V. Image quality assessment for video stream recognition systems // ICMV 2017. 2018. Vol. 10696. No. 106961U. P. 1–8. 10. Nunnagoppula G., Deepak K.S., Harikrishna G., Rai N., Krishna P.R. and Vesdapunt N. Automatic blur detection in mobile captured document images: Towards quality check in mobile based document imaging applications // 2013 IEEE Second International Conference on Image Information Processing (ICIIP-2013). 2013. P. 299–304. 11. Miao L. and Peng S. Perspective rectification of document images based on morphology // 2006 International Conference on Computational Intelligence and Security. 2006. Vol. 2. P. 1805–1808. 12. Takezawa Y., Hasegawa M. and Tabbone S. Robust perspective rectification of camera-captured document images // 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). 2017. Vol 06. P. 27–32. 13. Kunina I., Gladilin S. and Nikolaev D. Blind radial distortion compensation in a single image using fast Hough transform // Computer Optics. 2016. Vol. 40. No. 3. P. 395–403. 14. Chazalon J., Gomez-Krämer P., Burie J., Coustaty M., Eskenazi S., Luqman M., Nayef N., Rusiñol M., Sidère N. and Ogier J. SmartDoc 2017 Video Capture: Mobile Document Acquisition in Video Mode // 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). 2017. Vol. 04. P. 11–16. 15. Skoryukina N., Arlazarov V. and Nikolaev D. Fast method of id documents location and type identification for mobile and server application // 2019 International Conference on Document Analysis and Recognition (ICDAR). 2019. P. 850–857. 16. Zhukovsky A., Nikolaev D., Arlazarov V., Postnikov V., Polevoy D., Skoryukina N., Chernov T., Shemiakina J., Mukovozov A., Konovalenko I. and Povolotsky M. Segments graph-based approach for document capture in a smartphone video stream // 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). 2017. Vol. 01. P. 337–342. 17. Haris M., Shakhnarovich G. and Ukita N. Recurrent back-projection network for video super-resolution // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2019. P. 3892–3901. 18. Petrova O., Bulatov K., Arlazarov V.V. and Arlazarov V.L. Weighted combination of perframe recognition results for text recognition in a video stream // Computer Optics. 2021. Vol. 45. No. 1. P. 77–89.
|
