Maximal Coordinate Discrepancy as Accuracy Criterion of Image Projective Normalization for Optical Recognition of Documents

Application of projective normalization (a special case of orthocorrection and perspective correction) to photographs of documents for their further optical recognition is generally accepted. In this case, inaccuracies of normalization can lead to recognition errors. To date, a number of normalization accuracy criteria are presented in the literature, but their conformity with recognition quality was not investigated. In this paper, for the case of a fixed structured document, we justify a uniform probabilistic model of recognition errors, according to which the probability of correct recognition of a character abruptly falls to zero with an increase in the coordinate discrepancy of this character. For this model, we prove that the image normalization accuracy criterion, which is equal to the maximal coordinate discrepancy in the text fields of a document, monotonously depends on the probability of correct recognition of the entire document. Also, we show that the problem on computing the maximal coordinate discrepancy is not reduced to the nearest known one, i.e. the linear-fractional programming problem. Finally, for the first time, we obtain an analytical solution to the problem on computing the maximal coordinate discrepancy on a union of polygons.

Keywords

orthocorrection; perspective correction; image projective normalization; optical character recognition; accuracy criteria; coordinate discrepancy; nonlinear programming.

References

1. Kunina I.A., Terekhin A.P., Gladilin S.A., Nikolaev D.P. Blind Radial Distortion Compensation from Video Using Fast Hough Transform. ICRMV 2016, SPIE, 2017, vol. 1025308, pp. 1-7. DOI: 10.1117/12.2254867
2. Shapiro L., Stokman D., Boguslavskiy A.A., Sokolov, S.M. Komp'yuternoe zrenie [Computer Vision]. Moscow, BINOM. Laboratoriya znaniy, 2013. (in Russian)
3. Putjatin E.P., Prokopenko D.O., Pechenaja E.M. [Image Normalization Issues in Projective Transformations]. Radiojelektronika i informatika [Electronics and Informatics], 1998, vol. 2, no. 3, pp. 82-86. (in Russian)
4. Zeynalov R., Velizhev A., Konushin A. [Recovering the Shape of a Page of Text for Correcting Geometric Distortions]. Proceedings of the 19 International Conference GraphiCon-2009, Moscow, 2009, pp. 125-128. (in Russian)
5. Zhukovsky A., Nikolaev D., Arlazarov V., Postnikov V., Polevoy D., Skoryukina N., Chernov T., Shemiakina J., Mukovozov A., Konovalenko I. Segments Graph-Based Approach for Document Capture in a Smartphone Video Stream. ICDAR 2017, IEEE Computer Society, 2017, vol. 1, pp. 337-342. DOI: 10.1109/ICDAR.2017.63
6. Bolotova J.A., Spicyn V.G., Osina P.M. [An Overview of the Algorithms for Detecting Text Areas in Images and Videos]. Komp'yuternaya optika [Computer Optics], 2017, vol. 41, no. 3, pp. 441-452. (in Russian)
7. Shemiakina J.A., Zhukovsky A.E., Faradjev I.A. [The Research of the Algorithms of a Projective Transformation Calculation in the Problem of Planar Object Targeting by Feature Points]. tIskusstvenny intellekt i prinyatie resheniy [Artificial Intelligence and Decision Making], 2017, vol. 2017, no. 1, pp. 43-49. (in Russian)
8. Skoryukina N., Shemiakina J., Arlazarov, V. L., Faradjev I. Document Localization Algorithms Based on Feature Points and Straight Lines. ICMV 2017, SPIE, 2018, vol. 106961H, pp. 1-8. DOI: 10.1117/12.2311478
9. Povolotskiy M.A., Kuznetsova E.G., Khanipov T.M. Russian License Plate Segmentation Based On Dynamic Time Warping. Proceedings ECMS 2017, 2017, pp. 285-291.
10. Skoryukina N.S, Chernov T.S, Bulatov K.B, Nikolaev D. P., Arlazarov V.L. Snapscreen: TV-Stream Frame Search with Projectively Distorted and Noisy Query. tICMV 2016, SPIE, 2017, vol. 103410Y, pp. 1-5. DOI: 10.1117/12.2268735
11. Youye Xie, Gongguo Tang, Hoff W. Geometry-Based Populated Chessboard Recognition. Tenth International Conference on Machine Vision (ICMV 2017): International Society for Optics and Photonics, 2018, vol. 1069603, pp. 1-5.
12. Arvind C.S., Mishra R., Vishal K., Gundimeda V. Vision Based Speed Breaker Detection for Autonomous Vehicle. Tenth International Conference on Machine Vision (ICMV 2017), 2018, vol. 106960E, pp. 1-9. DOI: 10.1117/12.2311315
13. Dubuisson M.P., Jain A.K. A Modified Hausdorff Distance for Object Matching. Proceedings of 12th International Conference on Pattern Recognition, 1994, vol. 1, pp. 566-568. DOI: 10.1109/ICPR.1994.576361
14. Sim D.G., Kwon O.K., Park R.H. Object Matching Algorithms Using Robust Hausdorff Distance Measures. IEEE Transactions on Image Processing, 1999, vol. 8, no. 3, pp. 425-429. DOI: 10.1109/83.748897
15. Orrite C., Herrero J.E. Shape Matching of Partially Occluded Curves Invariant Under Projective Transformation. Computer Vision and Image Understanding, 2004, vol. 93, no. 1, pp. 34-64. DOI: 10.1016/j.cviu.2003.09.005
16. Nikolayev P.P. [Projectively Invariant Description of Non-Planar Smooth Figures. 1. Preliminary Analysis of the Problem]. Sensornye sistemy [Sensor System], 2016, vol. 30, no. 4, pp. 290-311. (in Russian)
17. Balickiy A.M., Savchik A.V., Gafarov R.F., Konovalenko I.A. [About Design-Invariant Points of an Oval with a Distinguished External Line]. Problemy peredachi informacii [Information Transfer Issues], 2017, vol. 53, no. 3, pp. 84-89. (in Russian)
18. Savchik A.V., Nikolaev P.P. [Projective Matching Method for Ovals with Two Marked Points]. Informacionnye tehnologii i vychislitel'nye sistemy [Information Technology and Computing Systems], 2018, vol. 2018, no. 1, pp. 60-67. (in Russian)
19. Katamanov S.N. [MTSAT-1R Automatic Geostationary Satellite Image Linking]. Sovremennye problemy distancionnogo zondirovanija Zemli iz kosmosa [Modern Problems of Remote Sensing of the Earth from Space], 2007, vol. 1, no. 4, pp. 63-68. (in Russian)
20. Karpenko S., Konovalenko I., Miller A., Miller B., Nikolaev D. UAV Control on the Basis of 3D Landmark Bearing-Only Observations. Sensors, 2015, vol. 15, no. 12, pp. 29802-29820. DOI: 10.3390/s151229768
21. Holopov I.S. [Projection Distortion Correction Algorithm for Low-Altitude Shooting]. Komp'yuternaja optika [Computer Optics], 2017, vol. 41, no. 2, pp. 284-290. (in Russian)
22. Legge G.E., Pelli D.G., Rubin G.S., Schleske M.M. Psychophysics of Reading-I. Normal Vision. Vision Research, 1985, vol. 25, no. 2, pp. 239-252. DOI: 10.1016/0042-6989(85)90117-8
23. Kunina I.A., Gladilin S.A., Nikolaev D.P. [Blind Radial Distortion Compensation in a Single Image Using Fast Hough Transform]. Komp'yuternaja optika [Computer Optics], 2016, vol. 40, no. 3, pp. 395-403. (in Russian) DOI: 10.18287/2412-6179-2016-40-3-395-403
24. Arlazarov V.V., Slavin O.A.E., Uskov A.V.E., Janiszewskinn I.M. Modelling the Flow of Character Recognition Results in Video Stream. Bulletin of the South Ural State University. Series: Mathematical Modelling, Programming and Computer Software, 2018, vol. 11. no. 2, pp. 14-28. DOI: 10.14529/mmp180202
25. Avriel, M. tNonlinear Programming: Analysis and Methods. North Chelmsford, Courier Corporation, 2003.
26. Charnes A., Cooper, W.W. Programming with Linear Fractional Functionals. Naval Research Logistics Quarterly, 1962, vol. 9, no. 3-4, pp. 181-186. DOI: 10.1002/nav.3800090303
27. Boyd, L. tConvex Optimization. Cambridge, Cambridge University Press, 2004. DOI: 10.1017/CBO9780511804441
28. Biswas A., Verma S., Ojha, D.B. Optimality and Convexity Theorems for Linear Fractional Programming Problem. International Journal of Computational and Applied Mathematics, 2017, vol. 12, no. 3, pp. 911-916.
29. Judin D.B. Matematicheskie metody upravlenija v uslovijah nepolnoj informacii [Mathematical Control Methods in Conditions of Incomplete Information]. Moscow, Izdatel'skaya gruppa URSS, 2010. (in Russian)
30. Rokafellar R. Vypuklyj analiz [Convex Analysis]. Moscow, Mir, 1973. (in Russian)