(46-1) 15 * << * >> * Russian * English * Content * All Issues

A method for assessing photorealistic image quality with high resolution
S.V. Sai 1

1 Pacific National University, Khabarovsk, Russia

 PDF, 1197 kB

DOI: 10.18287/2412-6179-CO-899

Pages: 121-129.

Full text of article: Russian language.

Abstract:
The article proposes a method for assessing photorealistic image quality based on a comparison of the detail coefficients in the original and distorted images. An algorithm for identifying fine structures of the original image uses operations of active pixels segmentation, which include point objects, thin lines and texture fragments. The number of active pixels is estimated by the value of a fine detail factor (FDF), which is determined by the ratio of active pixels to the total number of image pixels. The same algorithm is used to calculate the FDF of the distorted image and, further, the image quality deterioration is estimated by comparing the obtained values. Special features of the method include the fact that the identification of small structures and the segmentation of active pixels are performed in the normalized system N-CIELAB. The algorithm also takes into account the influence of false microstructures on the results of the restored image estimating. Features of the construction of neural networks SRCNN in the tasks of a qualitative increase in the image resolution with the restoration of fine structures are considered. Results of the analysis of the quality of enlarged images by the traditional metrics PSNR and SSIM, as well as by the proposed method are also presented.

Keywords:
image analysis, super resolution, fine structures, distortion metric.

Citation:
Sai SV. A method for assessing photorealistic image quality with high resolution. Computer Optics 2022; 46(1): 121-129. DOI: 10.18287/2412-6179-CO-899.

References:
  1. Sai SV, Kamensky AV, Kuryachy MI. Modern methods of analyzing and improving the digital images quality. Khabarovsk: Publishing house of the Pacific State University; 2020.
  2. Wang Z, Chen J, Hoi Steven CH. Deep learning for image super-resolution: A survey. IEEE Trans Pattern Anal Mach Intell 2021; 43: 3365-3387.
  3. Lin W, Jay Kuo C-C. Perceptual visual quality metrics: A survey. J Vis Commun Image Represent 2011; 22(4): 297-312.
  4. Wang Z, Bovik AC, Sheikh HR, Simoncelli EP. Image quality assessment: From error visibility to structural similarity. IEEE Trans Image Process 2004; 13(4): 600-612.
  5. Top 15 Best Image Enlarger Review 2021. Source: <https://topten.ai/image-enlargers-review/>.
  6. Barten PGJ. Contrast sensitivity of the human eye and its effects on image quality. Knegsel: HV Press; 1999.
  7. Dvorkovich VP, Dvorkovich AV. Measurements in video information systems (theory and practice). Moscow: "Technosphere" Publisher; 2015.
  8. ISO 12233:2017. Photography – Electronic still picture imaging – Resolution and spatial frequency responses. Source: <https://www.iso.org/standard/71696.html>.
  9. Born M, Wolf E. Principles of optics: Electromagnetic theory of propagation, interference and diffraction of light. 7th ed. Cambridge: Cambridge University Press; 2019.
  10. Burns PD, Williams D. Sampling efficiency in digital camera performance standards. Proc SPIE 2008; 6808: 680805.
  11. Williams D, et al. A pilot study of digital camera resolution metrology protocols proposed under ISO 12233, edition 2. Proc SPIE 2008; 6808: 680804.
  12. Gonzalez RC, Woods RE. Digital image processing. 3rd ed. Prentice Hall; 2008.
  13. High resolution test patterns. Source: <http://www.bealecorner.org/red/test-patterns/>.
  14. Imatest. Source: <https://www.imatest.com/>.
  15. Sai SV. Metric of fine structures distortions of compressed images. Computer Optics 2018; 42(5): 829-837. DOI: 10.18287/2412-6179-2018-42-5-829-837.
  16. Pennebaker WB, Mitchel JL. JPEG still image data compression standard. New York, USA: Springer; 1992.
  17. Bovik A, Mittal A. No-reference image quality assessment in the spatial domain. IEEE Trans Image Process 2012; 21(12): 4695-4708.
  18. Dong C, Loy CC, He K, Tang X. Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 2016; 38(2): 295-307.
  19. Ledig C, Theis L, Huszar F, et al. Photo-realistic single image super-resolution using a generative adversarial network. arXiv Preprint 2017. Source: <https://arxiv.org/abs/1609.04802>.
  20. Yang C, Lu X, Lin Z, et al. High-resolution imageinpainting using multi-scale neural patch. Proc IEEE Conf on Computer Vision and Pattern Recognition 2017: 6721-6729.
  21. Sheikh HR, Wang Z, Cormack L and Bovik AC. LIVE image quality assessment database. Source: <http://live.ece.utexas.edu/research/quality>.

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