Advanced search
1 file | 566.13 KB

No-reference blur estimation based on the average cone ratio in the wavelet domain

Author
Organization
Abstract
With extensive technological advancements in electronic imaging today, high image quality is becoming an imperative necessity in the modern imaging systems. An important part of quality assurance are techniques for measuring the level of image distortion. Recently, we proposed a wavelet based metric of blurriness in the digital images named CogACR. The metric is highly robust to noise and able to distinguish between a great range of blurriness. Also, it can be used either when the reference degradation-free image is available or when it is unknown. However, the metric is content sensitive and thus in a no-reference scenario it was not fully automated. In this paper, we further investigate this problem. First, we propose a method to classify images based on edge content similarity. Next, we use this method to automate the CogACR estimation of blur in a no-reference scenario. Our results indicate high accuracy of the method for a range of natural scene images distorted with the out-of-focus blur. Within the considered range of blur radius of 0 to 10 pixels, varied in steps of 0.25 pixels, the proposed method estimates the blur radius with an absolute error of up to 1 pixel in 80 to 90% of the images.
Keywords
image quality, wavelets, blur estimation, MODEL, EDGES, SINGULARITY DETECTION

Downloads

    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 566.13 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Platisa, Ljiljana, Aleksandra Pizurica, Ewout Vansteenkiste, and Wilfried Philips. 2011. “No-reference Blur Estimation Based on the Average Cone Ratio in the Wavelet Domain.” In Proceedings of Spie, the International Society for Optical Engineering, ed. D Akopian, R Creutzburg, CGM Snoek, N Sebe, and L Kennedy. Vol. 7881. Bellingham, WA, USA: SPIE.
APA
Platisa, L., Pizurica, A., Vansteenkiste, E., & Philips, W. (2011). No-reference blur estimation based on the average cone ratio in the wavelet domain. In D Akopian, R. Creutzburg, C. Snoek, N. Sebe, & L. Kennedy (Eds.), PROCEEDINGS OF SPIE, THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING (Vol. 7881). Presented at the Conference on Multimedia on Mobile Devices and Multimedia Content Access : Algorithms and Systems V, Bellingham, WA, USA: SPIE.
Vancouver
1.
Platisa L, Pizurica A, Vansteenkiste E, Philips W. No-reference blur estimation based on the average cone ratio in the wavelet domain. In: Akopian D, Creutzburg R, Snoek C, Sebe N, Kennedy L, editors. PROCEEDINGS OF SPIE, THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING. Bellingham, WA, USA: SPIE; 2011.
MLA
Platisa, Ljiljana, Aleksandra Pizurica, Ewout Vansteenkiste, et al. “No-reference Blur Estimation Based on the Average Cone Ratio in the Wavelet Domain.” Proceedings of Spie, the International Society for Optical Engineering. Ed. D Akopian et al. Vol. 7881. Bellingham, WA, USA: SPIE, 2011. Print.
@inproceedings{1924995,
  abstract     = {With extensive technological advancements in electronic imaging today, high image quality is becoming an imperative necessity in the modern imaging systems. An important part of quality assurance are techniques for measuring the level of image distortion. Recently, we proposed a wavelet based metric of blurriness in the digital images named CogACR. The metric is highly robust to noise and able to distinguish between a great range of blurriness. Also, it can be used either when the reference degradation-free image is available or when it is unknown. However, the metric is content sensitive and thus in a no-reference scenario it was not fully automated. In this paper, we further investigate this problem. First, we propose a method to classify images based on edge content similarity. Next, we use this method to automate the CogACR estimation of blur in a no-reference scenario. Our results indicate high accuracy of the method for a range of natural scene images distorted with the out-of-focus blur. Within the considered range of blur radius of 0 to 10 pixels, varied in steps of 0.25 pixels, the proposed method estimates the blur radius with an absolute error of up to 1 pixel in 80 to 90\% of the images.},
  articleno    = {78811D},
  author       = {Platisa, Ljiljana and Pizurica, Aleksandra and Vansteenkiste, Ewout and Philips, Wilfried},
  booktitle    = {PROCEEDINGS OF SPIE, THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING},
  editor       = {Akopian, D and Creutzburg, R and Snoek, CGM and Sebe, N and Kennedy, L},
  isbn         = {9780819484185},
  issn         = {0277-786X},
  keyword      = {image quality,wavelets,blur estimation,MODEL,EDGES,SINGULARITY DETECTION},
  language     = {eng},
  location     = {San Francisco, CA, USA},
  pages        = {12},
  publisher    = {SPIE},
  title        = {No-reference blur estimation based on the average cone ratio in the wavelet domain},
  url          = {http://dx.doi.org/10.1117/12.872836},
  volume       = {7881},
  year         = {2011},
}

Altmetric
View in Altmetric
Web of Science
Times cited: