Журнал «Труды Института системного анализа Российской академии наук» - D.V. Tropin, D.P. Nikolaev, D.G. Slugin The method of image alignment based on sharpness maximization

Просматривается номер 2018-S1

Data mining and image recognition

N.S. Skoryukina, A.N. Milovzorov, D.V. Polevoy, V.V. Arlazarov Paintings recognition in uncontrolled conditions using one-shot learning

A.E. Zhukovsky Methods for interframe integration of document detection results in a video stream of a mobile device

I.A. Kunina, E. I. Panfilova, M.A. Povolotskiy Zebra-crossing detection on road images using dynamic time warping

O.A. Slavin, V.L. Arlazarov Method for classifying recognized pages of administrative documents on the basis of text key points

O.O. Petrova, K.B. Bulatov Methods of machine-readable zone recognition results post-processing

A.E. Marchenko, E.I. Ershov, D.A. Shepelev, D.S. Sidorchuk, V.P. Bozhkova, D.P. Nikolaev Designing of language of description of observable properties of recognized objects in the absence of samples

Intellectual systems and technologies

E.E. Limonova, N.L. Rzhenev, A.V. Uskov, M.I. Neiman-zade Fast implementation of Hamming distance on VLIW-architectures on the example of Elbrus platform

V.V. Arlazarov, K.B. Bulatov, A.V. Uskov A model of object recognition system in video stream of a mobile device

A.A. Ivanova, S.A. Gladilin, A.E. Zhukovsky, E.L. Pliskin Database for the administrative accounting of scientific publications

A.S. Ingacheva, A.V. Sheshkus, T. S. Chernov, E.E. Limonova, V.V. Arlazarov X-ray computed tomography scanner – a new tool in recognition

N.O. Beshaposhnikov, A.G. Kushnirenko, A.A. Levin A method for auto-calibration of the educational robot control parameters using computer vision library OpenCV

Image and signal processing

A.E. Zhukovsky, E.E. Limonova, D.P. Nikolaev Exact implementation of common image processing algorithms using fully convolutional networks

V.E. Prun Reducing the influence of high-absorbing inclusions on CT reconstructions using algebraic reconstruction technique

B.I. Savelyev, I.B. Mamay, D.P. Nikolaev, V.L. Arlazarov, K.B. Bulatov, N.S. Skoryukina A method of projective transformations graph adjustment for panorama stitching problem for images of planar objects

D.V. Tropin, D.P. Nikolaev, D.G. Slugin The method of image alignment based on sharpness maximization

J.A. Shemiakina, A.E. Zhukovsky, I.A. Konovalenko, D.P. Nikolaev Algorithm for automatic framing of digital images under projective transformation

MACHINE LEARNING

A.V. Gayer, A.V. Sheshkus, Y.S. Chernyshova Augmentation on the fly for the neural networks learning

V.V. Arlazarov, D.P. Matalov, S.A. Usilin Localization of the seal on the identity document image using machine learning approach

A.E. Lynchenko, A.V.Sheshkus, V.L.Arlazarov Identity document classifiaction algorithm based on similarity metric robust to projective distortions

V.A. Malykh, V.A. Lyalin On Classification of Noisy Texts

Y.S. Chernyshova, M.A. Aliev, A.V. Sheshkus Optical font recognition of images captured with mobile devices and its application for detecting identity documents forgery

D.A. Ilin Fast words boundaries localization in text fields for low quality document images

D.E. Ivanov, D.V. Polevoy, D.L. Sholomov Selection of informative elements for the training of a lightweight convolutional neural network classifier in the conditions of a strong imbalance of the training sample


	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

2024-74-1

2023-73-4

2023-73-3

2023-73-2