|
D.V. Tropin, D.P. Nikolaev, D.G. Slugin The method of image alignment based on sharpness maximization |
|
Abstract. This paper describes an image alignment method based on sharpness maximization of average image. The proposed algorithm is substantiated for global-shift model of optical flow using an efficient way of calculation with Fast Fourier Transformation. For projective model is proposed an approach of image alignment by comparison separate fragments and using RANSAC to obtain the final transform. The experimental results of solution the problem of restoring document’s image in a video stream showing increase in quality of output images are presented. Keywords: image analysis, image alignment, optical flow, FFT, RANSAC. PP. 134-141. DOI: 10.14357/20790279180515 References 1. Bulatov K., Arlazarov V.V., Chernov T., Slavin O. and Nikolaev D. “Smart IDReader: Document Recognition in Video Stream,” 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Kyoto, 2017, pp. 39-44. doi: 10.1109/ICDAR.2017.347 2. Lucas B.D., Kanade, T. An iterative image registration technique with an application in stereo vision // Seventh International Joint Conference on Artificial Intelligence (IJCAI-81). – Vancouver, 1981. − P. 674-679. 3. Horn B.K.P., Schunck B.G. Determining optical flow. Artificial Intelligence // Artificial Intelligence. – Cambridge, 1981. – P. 185–203. 4. Lowe D.G. Distinctive image features from scale-invariant keypoints // International Journal of Computer Vision. – 2004. − № 56. 5. Nanne van Noord, Eric Postma. Learning scale-variant and scale-invariant features for deep image classification Pattern Recognition. Pattern Recognition. Volume 61, January 2017, Pages 583-592 6. Kuglin C.D. and Hines D.C. The phase correlation image alignment method. International Conference of Cybernetic Society. Proc IEEE 1975. New York. PP 163-165. 7. Szeliski Richard. Image Alignment and Stitching: A Tutorial. Foundations and Trends in Computer Graphics and Vision Vol. 2, No 1 (2006) 1–104 8. Arlasarov V.V., Zhukovsky A.E., Krivtsov V.E., Nikolaev D.P., Polevoy D.V. Analysis of features of the use of fixed and mobile small-sized digital video camera for OCR. // Information Technologies and Computing Systems − 2016. − №2, −P. 71-81. 9. Fischler M.A., Bolles R.C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography // Communications of the ACM. – 1981. − №24. – P. 381-395. 10. Smartphone Document Capture Competition http://smartdoc.univ-lr.fr/task/ 11. Natalya Skoryukina, Julia Shemiakina, Vladimir L. Arlazarov, Igor Faradjev. Document localization algorithms based on feature points and straight lines. Proceedings Volume 10696, Tenth International Conference on Machine Vision (ICMV 2017); doi: 10.1117/12.2311478
|