DOI QR코드

DOI QR Code

A New Hybrid Weight Pooling Method for Object Image Quality Assessment with Luminance Adaptation Effect and Visual Saliency Effect

광적응 효과와 시각 집중 효과를 이용한 새로운 객관적 영상 화질 측정 용 하이브리드 가중치 풀링 기법

  • Shahab Uddin, A.F.M. (Dept. of Computer Science and Engineering, Kyung Hee University) ;
  • Kim, Donghyun (Agency for Defense Development) ;
  • Choi, Jeung Won (Agency for Defense Development) ;
  • Chung, TaeChoong (Dept. of Computer Science and Engineering, Kyung Hee University) ;
  • Bae, Sung-Ho (Dept. of Computer Science and Engineering, Kyung Hee University)
  • Received : 2019.05.31
  • Accepted : 2019.07.29
  • Published : 2019.09.30

Abstract

In the pooling stage of a full reference image quality assessment (FR-IQA) technique, the global perceived quality for any distorted image is usually measured from the quality of its local image patches. But all the image patches do not have equal contribution when estimating the overall visual quality since the degree of degradation on those patches depends on various considerations i.e., types of the patches, types of the distortions, distortion sensitivities of the patches, saliency score of the patches, etc. As a result, weighted pooling strategy comes into account and different weighting mechanisms are used by the existing FR-IQA methods. This paper performs a thorough analysis and proposes a novel weighting function by considering the luminance adaptation as well as the visual saliency effect to offer more appropriate local weights, which can be adopted in the existing FR-IQA frameworks to improve their prediction accuracy. The extended experimental results show the effectiveness of the proposed weighting function.

완전 참조 영상 화질(full-reference image quality assessment, FR-IQA)측정의 풀링 과정에 있어서, 한 영상의 전역 화질은 각 국부 패치의 측정된 화질값들로부터 측정된다. 그러나 한 영상의 전체 화질 값을 예측함에 있어서 국부 패치의 종류, 왜곡 타입, 왜곡의 인지 민감도, 국부 패치의 관심 집중(saliency) 정도에 따라 국부 패치가 전체 영상에 기여하는 왜곡의 정도가 다를 수 있다. 그 결과, 계산된 국부 패치 화질값에 대한 가중치 풀링 방법이 기존 FR-IQA 방법에서 고려되었다. 본 논문은 기존 FR-IQA 방법에서 고려되지 않은 시각인지시스템의 특성인, 광적응 효과 와 시각 관심 집중 효과를 고려한 새로운 가중치 풀링 방법을 제안한다. 실험 결과, 기존 FR-IQA 방법에 적용될 경우 예측 성능을 향상시킴을 확인하였으며, 이는 제안하는 가중치 풀링 방법은 사람의 시각인지 특성을 효과적으로 반영하기 때문으로 사료된다.

Keywords

References

  1. Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, "Image quality assessment: from error visibility to structural similarity," IEEE Trans. Image Process., vol. 13, no. 4, pp. 600-612, Apr. 2004, https://doi.org/10.1109/TIP.2003.819861.
  2. Bae, S.H., and Kim, M.: 'A novel image quality assessment with globally and locally consilient visual quality perception', IEEE Trans. Image Process., 2016, 25, (5), pp. 2392-2406, https://doi.org/10.1109/TIP.2016.2545863.
  3. T. Frese, C. A. Bouman, and J. P. Allebach, in Human Vision and Electronic Imaging II, Vol. 3016 (International Society for Optics and Photonics, 1997) pp. 472-484, https://doi.org/10.1117/12.274545.
  4. A. K. Jain, Fundamentals of digital image processing (Englewood Cliffs, NJ: Prentice Hall, 1989), ISBN. 0-13-336165-9.
  5. L. Itti, C. Koch, and E. Niebur, "A model of saliency-based visual attention for rapid scene analysis," IEEE Trans. Pattern Anal. Mach. Intell., vol. 20, no. 11, pp. 1254-1259, Nov. 1998, https://doi.org/10.1109/34.730558.
  6. X. Hou, J. Harel, and C. Koch, "Image signature: Highlighting sparse salient regions," IEEE Trans. Pattern Anal. Mach. Intell., vol. 34, no. 1, pp. 194-201, Jan. 2012, https://doi.org/10.1109/TPAMI.2011.146.
  7. X. Shen and Y. Wu, "A unified approach to salient object detection via low rank matrix recovery," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2012, pp. 853-860, https://doi.org/10.1109/CVPR.2012.6247758.
  8. L. Zhang, Z. Gu, and H. Li, "SDSP: A novel saliency detection method by combining simple priors," in Proc. IEEE Int. Conf. Image Process., Sep. 2013, pp. 171-175, https://doi.org/10.1109/ICIP.2013.6738036.
  9. Shen, L., Li, Y., Zhang, H.: 'VSI: A visual saliency-induced index for perceptual image quality assessment', IEEE Trans. Image Process., 2014, 23, (10), pp. 4270-4281, https://doi.org/10.1109/TIP.2014.2346028.
  10. Ponomarenko, N., Ieremeiev, O., Lukin, V., et al.: 'A new color image database TID2013: innovations and results', in Proc. Advanced Concepts for Intelligent Vision Systems (ACIVS), Poznan, Poland, 2013, pp. 402-413, https://doi.org/10.1007/978-3-319-02895-8_36.
  11. Ponomarenko, N., Battisti, F., Egiazarian, K., et al.: 'Metrics performance comparison for color image database'. Fourth Int. Workshop on Video Processing and Quality Metrics for Consumer Electronics, Scottsdale, Arizona, USA, 14-16 January 2009.
  12. E. C. Larson and D. M. Chandler, "Most apparent distortion: Full-reference image quality assessment and the role of strategy," J. Electron. Imag., vol. 19, no. 1, pp. 001006:1-001006:21, Jan. 2010, https://doi.org/10.1117/1.3267105.
  13. S. H. Bae, A. F. M. Shahab Uddin, Youmin Kim, Kang-Ho Lee and Jiyoung Jung, "A Novel Weight Pooling Method for Objective Image Quality Assessment with the Luminance Adaptation Effect in the Pixel Intensity Domain," Journal of Imaging Science and Technology, to be published in Vol. 64, no. 1, Jan. 2020, https://doi.org/10.2352/J.ImagingSci.Technol.2019.63.5.050502.