O. A. Slavin Object Descriptors for Linking Structural Elements of Noisy Document Images
O. A. Slavin Object Descriptors for Linking Structural Elements of Noisy Document Images

The problem of extracting filling elements (fields) from a recognized image of a document with the help of descriptors - descriptions of one or more structural elements is considered. Structural elements can be words of static text and scribble lines used to shape the design of a document. Business documents with a simplified structure and a limited vocabulary are considered. Flexible business documents that allow significant modifications to the page design are considered. Descriptors are created taking into account a significant number of possible errors in document page recognition. Combined descriptors consisting of several terms and line segments are described. A binding algorithm based on descriptors is given. It is experimentally shown that the extraction of combined descriptors improves the accuracy of recognition of document fields during recognition by 17%, and the accuracy of extracting information from the document image by 16%. The SDK Smart Document Engine was used as OCR in the experiment.


virtual reality, augmented reality, virtual reality helmet, immersiveness, virtual object, heptic technologies, content.

pp. 13-24.

DOI 10.14357/20718632220402

1. Bashkatova, A. Cifrovaya ekonomika plodit vse bol'she bumag: Rossiyane ne skoro perestanut nosit' v organizacii spravki // Nezavisimaya Gazeta. – 2019 – 14 ноя. (accessed September 22, 2022).
2. Rusiñol M., Frinken V., Karatzas, D., Bagdanov, A. D., Lladós, J.: Multimodal page classification inadministrative document image streams. In: IJDAR. Vol. 17(4), pp. 331 Image Classification by Mixed Finite Element Method and Orthogonal Legendre Moments 341. (2014).
3. Jain, R., Wigington, C.: Multimodal Document Image Classification. pp. 71–77. (2019).
4. Qasim, S. Rukh., Mahmood, H., Shafait, F.: Rethinking Table Recognition using Graph Neural Networks. pp. 142–147. (2019).
5. Marchenko A.E., Ershov E.I., Gladilin S.A. Sistema razbora dokumenta, zadannogo atributami strukturnykh elementov i otnosheniyami mezhdu strukturnymi elementami [The system for parsing a document specified by attributes of structural elements and the relations between structural elements] / Trudy ISA RAN, Vol 67, No 4, pp. 87-97. (2017).
6. Postnikov V. V.: Identification and Recognition of Documents with a Predefined Structure // Pattern Recognition and Image Analysis. Vol. 13. № 2. pp. 332–334. (2003).
7. Smart Document Engine – automatic analysis and data extraction from business documents for desktop, server and mobile platforms / (accessed September 22, 2022).
8. Bellavia, F.: SIFT Matching by Context Exposed. IEEE Transactions on Pattern Analysis and Machine Intelligence. (2022).
9. Bay, H., Tuytelaars, T., Van Gool, Luc.: SURF: Speeded Up Robust Features. Computer Vision and Image Understanding - CVIU. Vol. 110. No. 3, pp. 404–417. (2006).
10. Slavin, O., Andreeva, E., Paramonov, N.: Matching Digital Copies of Documents Based on OCR, 2019 XXI International Conference Complex Systems: Control and Modeling Problems (CSCMP), pp. 177–181, (2019).
11. Slavin, O., Arlazarov, V., Tarkhanov, I.: Models and Methods Flexible Documents Matching Based on the Recognized Words. Cyber-Physical Systems: Advances in Design & Modelling. Springer Nature Switzerland AG. Vol. 350, pp. 173–184 (2021).
12. Matas, J., Galambos, C., Kittler, J.: Robust Detection of Lines Using the Progressive Probabilistic Hough Transform, Computer Vision and Image Understanding, Vol. 78, Issue 1, pp. 119–137, (2000).
13. Grompone von Gioi, R., Jakubowicz, J., Morel, JM. et al.: On Straight Line Segment Detection. J Math Imaging Vis. Vol. 32, pp. 313–347. (2008).
14. Grompone von Gioi R., Jakubowicz J., Morel J.-M., Randall G.: LSD: A Fast Line Segment Detector with a False Detection Control / IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 32, Issue 4. pp. 722–732. (2010).
15. Emaletdinova, L. & Nazarov, M.: Construction of a Fuzzy Model for Contour Selection. Construction of a Fuzzy Model for Contour Selection. In: Kravets, A.G., Bolshakov, A.A., Shcherbakov, M. (eds) Cyber-Physical Systems: Intelligent Models and Algorithms. Studies in Systems, Decision and Control, Vol. 417. pp. 243–246.
16. Zlobin, P., Chernyshova, Y., Sheshkus A., Arlazarov V. V.: Character sequence prediction method for training data creation in the task of text recognition. Proc. SPIE 12084, Fourteenth International Conference on Machine Vision (ICMV 2021), 120840R. (2022).
17. Matalov, D., Usilin, S., Arlazarov, V.V.: About Viola-Jones image classifier structure in the problem of stamp detection in document images. Proc. SPIE 11605, Thirteenth International Conference on Machine Vision,
116050V (2021).
18. Arlazarov, V., Voysyat, Ju. S., Matalov, D., Nikolaev, D., Usilin, S.A.: Evolution of the Viola-Jones Object Detection Method: A Survey. Vol. 14. pp. 52–23. (2021).

2024 / 02
2024 / 01
2023 / 04
2023 / 03

© ФИЦ ИУ РАН 2008-2018. Создание сайта "РосИнтернет технологии".