|
Artificial Intelligence and Decision Making, 2016, Issue 2, Pages 60–69
(Mi iipr285)
|
|
|
|
This article is cited in 1 scientific paper (total in 1 paper)
Data mining
Usage of the intersection graph for camera-based document capture
V. V. Arlazarova, A. E. Zhukovskyb, V. E. Krivtsovb, V. V. Postnikova a Federal Research Center "Computer Science and Control" of Russian Academy of Sciences, Moscow
b Moscow Institute of Physics and Technology (National Research University), Dolgoprudny, Moscow Region
Abstract:
Document capture with a smartphone camera is already here to stay. Interactive applications for document capture and its enhancement have filled mobile application stores. However, discounting the predictions and judging only from the experience of using such applications, they are not yet ready to compete with stationary scanners when high quality and reliability is required. This paper is devoted to analysis of the problem of document detection in the image and evaluation of the quality of existing mobile applications. Based on this analysis we present a new reliable algorithm for document capture, based on the boundary segments detection and constructing an intersections graph to fit rectangular projective model. The algorithm achieves about 95% quality of document detection and outperforms all
of the reviewed algorithms, implemented in mobile applications.
Keywords:
document detection; segments detection; projective transform; mobile cameras.
Citation:
V. V. Arlazarov, A. E. Zhukovsky, V. E. Krivtsov, V. V. Postnikov, “Usage of the intersection graph for camera-based document capture”, Artificial Intelligence and Decision Making, 2016, no. 2, 60–69; Scientific and Technical Information Processing, 44:5 (2017), 365–372
Linking options:
https://www.mathnet.ru/eng/iipr285 https://www.mathnet.ru/eng/iipr/y2016/i2/p60
|
Statistics & downloads: |
Abstract page: | 18 | Full-text PDF : | 4 | References: | 1 |
|