A Novel Method of Image Quality Assessment

Abstract:

Image quality assessment (IQA) is one of the hot research areas in the field of image processing. For the reason that human being is the final receiver of the image, the image quality assessment should match the characteristics of human visual system. In this paper, we propose a novel method of image quality assessment which uses the visual selective attention of human visual system. For an image of a certain category, our method firstly detects the object in it and then calculate the saliency of the object. Lastly we use the combination of the detector’s score and the saliency as the image quality assessment. Experiments on some images of Pascal VOC dataset and INRIA dataset show that our method does well in image quality assessment.

• Periodical: Applied Mechanics and Materials (Volumes 556-562)
• Pages: 5064-5067
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.556-562.5064
• Online since: May 2014
• Authors: Ming Wei Guo*, Chen Bin Zhang, Zong Hai Chen
• Keywords: Deformable Part Model, Image Quality Assessment, Object Detection, Saliency Detection, Visual Selective Attention

References

[1] Yu Z., Wu H., and Winkler S, et al. Vision-model-based impairment metric to evaluate blocking artifact in digital video[J]. Proceeding of the IEEE, 2002, 90(1): 154-169.

DOI: 10.1109/5.982412

[2] Nill N. and Bouzas B., Objective image quality measure derived from digital image power spectra[J]. IEEE Signal Processing Letter, 2002, 9(3): 388-392.

[3] Wang Z, Alan C B, and Hamid R S. Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4): 600-612.

DOI: 10.1109/tip.2003.819861

[4] P. Felzenszwalb, R. Girshick, D. McAllester, D. Ramanan. Object detection with discriminatively trained part based models, Pattern Analysis and Machine Intelligence, vol. 32, no. 9, pp.1627-1645, (2009).

DOI: 10.1109/tpami.2009.167

[5] P. Felzenszwalb, D. McAllester, D. Ramanan. A Discriminatively Trained, Multiscale, Deformable Part Model, In Proc. IEEE Conf. Computer Vision and Pattern Recognition, IEEE, Anchorage, USA, pp.1-8, (2008).

DOI: 10.1109/cvpr.2008.4587597

[6] N. Dalal and B. Triggs. Histograms of Oriented Gradients for Human Detection[C]. Proc. IEEE Conf. Computer Vision and Pattern Recognition, San Diego: IEEE Press, 2005, 1: 886-893.

DOI: 10.1109/cvpr.2005.177

[7] Yan Q., Xu L., Shi J., Jia J., Hierarchical Saliency Detection[C]. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Oregen: IEEE Press, (2013).

DOI: 10.1109/cvpr.2013.153

[8] M. Everingham, L. Van Gool, C.K.I. Williams, J. Winn, and A. Zisserman, The PASCAL Visual Object Classes Challenge 2011 (VOC 2011) Results, http: /www. pascal-network. org/challenges/VOC/voc2011/, (2011).

DOI: 10.1007/s11263-009-0275-4

[9] Guo M, Zhao Y, Xiang J, Zhang C, Chen Z. Review of object detection methods based on SVM. Control and Decision, 2014, 29(2): 193-200.