Improved algorithm of ID card detection by a priori knowledge of the document aspect ratio

In this work, we consider a problem of quadrilateral document borders detection in images captured by a mobile device’s camera. State-of-the-art algorithms for the quadrilateral document borders detection are not designed for cases when one of the document borders is either completely out of the frame, obscured, or of low contrast. We propose the algorithm which correctly processes the image in such cases. It is built on the classical contour-based algorithm. We modify the latter using the document’s aspect ratio which is known a priori. We demonstrate that this modification reduces the number of incorrect detections by 34% on an open dataset MIDV-500.

[1]  Mickaël Coustaty,et al.  ICDAR2015 competition on smartphone document capture and OCR (SmartDoc) , 2015, 2015 13th International Conference on Document Analysis and Recognition (ICDAR).

[2]  Dieter Schmalstieg,et al.  Real-time Detection and Recognition of Machine-Readable Zones with Mobile Devices , 2015, VISAPP.

[3]  Dmitry P. Nikolaev,et al.  Real time rectangular document detection on mobile devices , 2015, Other Conferences.

[4]  Dmitry P. Nikolaev,et al.  Acceleration of Summation Over Segments Using the Fast Hough Transformation Pyramid , 2020 .

[5]  Woo-Jin Song,et al.  Removing chromatic aberration by digital image processing , 2010 .

[6]  Joachim Denzler,et al.  From corners to rectangles — Directional road sign detection using learned corner representations , 2017, 2017 IEEE Intelligent Vehicles Symposium (IV).

[7]  Andrey Savchenko,et al.  Detection of Sensitive Textual Information in User Photo Albums on Mobile Devices , 2019, 2019 International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON).

[8]  Timofey S. Chernov,et al.  Segments Graph-Based Approach for Document Capture in a Smartphone Video Stream , 2017, 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR).

[9]  Chen Zhang,et al.  Coarse-to-fine document localization in natural scene image with regional attention and recursive corner refinement , 2019, International Journal on Document Analysis and Recognition (IJDAR).

[10]  Dmitry P. Nikolaev,et al.  Blind radial distortion compensation from video using fast Hough transform , 2017, International Conference on Machine Vision.

[11]  David C. Howell,et al.  Chi-Square Test: Analysis of Contingency Tables , 2011, International Encyclopedia of Statistical Science.

[12]  Timofey S. Chernov,et al.  MIDV-500: A Dataset for Identity Documents Analysis and Recognition on Mobile Devices in Video Stream , 2018, Computer Optics.

[13]  Vladimir L. Arlazarov,et al.  Fast Method of ID Documents Location and Type Identification for Mobile and Server Application , 2019, 2019 International Conference on Document Analysis and Recognition (ICDAR).

[14]  Thierry Géraud,et al.  Document Detection in Videos Captured by Smartphones using a Saliency-Based Method , 2019, 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW).

[15]  Dmitry P. Nikolaev,et al.  Smart IDReader: Document Recognition in Video Stream , 2017, 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR).

[16]  Vladimir V. Arlazarov,et al.  Two-Step CNN Framework for Text Line Recognition in Camera-Captured Images , 2020, IEEE Access.

[17]  Zhengyou Zhang,et al.  Whiteboard scanning and image enhancement , 2007, Digit. Signal Process..

[18]  Dmitry P. Nikolaev,et al.  Approach for document detection by contours and contrasts , 2020, ArXiv.

[19]  Martin L. Brady,et al.  A Fast Discrete Approximation Algorithm for the Radon Transform , 1998, SIAM J. Comput..

[20]  Ronan Sicre,et al.  Complex Document Classification and Localization Application on Identity Document Images , 2017, 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR).