(43-4) 15 * << * >> * Russian * English * Content * All Issues

Adaptive ANN-based method of constructing an interpolation formula for doubling the image size

S.E. Vaganov1

Ivanovo State University, Ivanovo, Russia

 PDF, 939 kB

DOI: 10.18287/2412-6179-2019-43-4-627-631

Pages: 627-631.

Full text of article: Russian language.

The architecture of an artificial neural network that solves the problem of constructing interpolation formulas for doubling the size of images is proposed. The trained model receives a 4×4 matrix as an argument. The result is an interpolation formula represented as a weight vector for 4 points.
A comparison of the main quality assessments of the proposed method with some well-known adaptive approaches is made. The results of the comparative analysis show that the proposed approach has a better interpolation quality than NEDI and DCCI methods.

interpolation, machine learning, artificial neural network, gradient descent, image quality

Vaganov S. Adaptive ANN-based method of constructing an interpolation formula for doubling the image size. Computer Optics 2019, 43(4): 627-631. DOI: 10.18287/2412-6179-2019-43-4-627-631.


  1. Vaganov SE, Khashin SI. Comparison of doubling the size of image algorithms [In Russian]. Modelirovanie i Analiz Informacionnyh Sistem 2016; 23(4): 382-400. DOI: 10.18255/1818-1015-2016-4-389-400.
  2. Zhou D, Shen X, Dong W. Image zooming using directional cubic convolution interpolation. IET Image Processing 2012; 6(6): 627-634. DOI: 10.1049/iet-ipr.2011.0534.
  3. Jing L, Zongliang G, Xiuchang Z. Directional bicubic interpolation – a new method of image super-resolution. In Book: Proceedings of 3rd International Conference on Multimedia Technology (ICMT-13). Atlantis Press; 2013: 470-477. DOI:10.2991/icmt-13.2013.57.
  4. Li X, Orchard MT. New edge-directed interpolation. IEEE Transactions on Image Processing 2001; 10(10): 1521-1527. DOI:10.1109/83.951537.
  5. Dong C, Loy CC, He K, Tang X. Image super-resolution using deep convolutional networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 2016; 38(2): 295-307. DOI: 10.1109/TPAMI.2015.2439281.
  6. Plaziac N. Image interpolation using neural networks. IEEE Transactions on Image Processing 1999; 8(11): 1647-1651. DOI: 10.1109/83.799893.
  7. Hu H, Holman PM, de Haan G. Image interpolation using classification-based neural networks. IEEE International Symposium on Consumer Electronics 2004: 133-137. DOI: 10.1109/ISCE.2004.
  8. Test bmp files [In Russian]. Source: <http://math.ivanovo.ac.ru/dalgebra/Khashin/bmp_ex/>.
  9. Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 2017. Source: <https://arxiv.org/abs/1412.6980>.
  10. TensorFlow (official site). Source: <http://tensorflow.org>.
  11. Nasonov AV, Krylov AS, Petrova X, Rychagov MN. Edge-directional interpolation algorithm using structure tensor. In Book: Agaian SS, Egiazarian KO, Gotchev AP, eds. Electronic Imaging, Image Processing: Algorithms and Systems XIV. Ingenta; 2016: 1-4. DOI: 10.2352/ISSN.2470-1173.2016.15.IPAS-026.
  12. Gashnikov M.V. Interpolation based on context modeling for hierarchical compression of multidimensional signals. Computer Optics 2018; 42(3): 468-475. DOI: 10.18287/2412-6179-2018-42-3-468-475.
  13. Implementation of an adaptive ANN-based image interpolation method. Source: <http://math.ivanovo.c.ru/dcompmath/Vaganov/Interp.html>.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: ko@smr.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20