International Journal of Scientific & Technology Research

Home About Us Scope Editorial Board Blog/Latest News Contact Us
10th percentile
Powered by  Scopus
Scopus coverage:
Nov 2018 to May 2020


IJSTR >> Volume 8 - Issue 4, April 2019 Edition

International Journal of Scientific & Technology Research  
International Journal of Scientific & Technology Research

Website: http://www.ijstr.org

ISSN 2277-8616

Analysis Of Hazy Images Based On K-Means Ground Truth And Quick Shift Segmentation

[Full Text]



Abdul Muqeet, Humera Tariq, Usman Amjad, Asia Samreen



dark channel, haze, superpixel, Edge Ratio, PSNR, UQI



Quick shift segmentation with optimal parameters claims for better edge visibility, improved color saturation and halo affects. The proposed method is based on grouping of hazy pixels such that it maximizes the similarity between a reference k-means and quick shift image. The objective of this paper is Qualitative and Quantative analysis of improved Quick shift segmentation based on super pixel segementation. Improved quick shift is based on super pixel based dark channel, K-Means based ground truth and having a fixed rectangular patch to determine dark channel image. The reference image helps in finding optimal quick shift parameters on fly instead of using fixed values for every image. Extensive quantitative (Mean Square Error, Structural similarity, Quality Index, Edge measurements) and qualitative evaluation were performed to show that the proposed method adheres the limitations of the state of the art fog removal methods.



[1]. H.Tariq, A.Samreen, U.Amjad, " Haze Removal Using Improved Automatic Quich Shift Segmentation," Advances and Applications in Discrete Mathematics, vol.20, no. 2, pp.295-304,2018.

[2]. S.-W. Noh, B. Ahn and I. S. Kweon, "Haze removal on superpixel domain," in International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), Jeju, 2013.

[3]. A. Vedaldi and S. Soatto, "Quick Shift and Kernel Methods for Mode Seeking," in Proceedings of the European Conference on Computer Vision, 2008.

[4]. M. Salem, A. Ibrahim and H. Ali, "Automatic quick-shift method for color image segmentation," in 8th International Conference on Computer Engineering & Systems (ICCES), 2013 , Cairo, 2013.

[5]. K. He, J. Sun and X. Tang, "Single image haze re-moval using dark channel prior," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 12, pp. 2341-2353, 2011.

[6]. K. He, J. Sun and X. Tang, "Guided Image Filtering," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 6, pp. 1397-1409, 2013.

[7]. T. Jacobs, "Underwater Image Haze Removal and Color Correction with an Underwater-ready Dark Channel Prior", July 2018.

[8]. L. Zhang, S. Wang and X.Wang, "Saliency-based dark channel prior model for single image haze re-moval," IET Image processing vol. 12, no. 6, p. 1049-1055, 2018.

[9]. R. Li, J. Pan, Z. Li and J. Tang, "Single Image Dehazing via Conditional Generative Adversarial Network," CVPR 2018.

[10]. C. Ancuti, O. Ancuti, R. Timofte, "NTIRE 2018 Chal-lenge on Image Dehazing: Methods and Results, " in CVPR workshop, p. 891-901,2018.
[11]. Q. Shu, C.Wu, Z. Xio and R.W. Liu, "Variational Regularized Transmission Refinement for Image Dehazing, arXiv preprint, CVPR 2019.

[12]. R. Fattal,"Dehazing using color-lines,". "ACM Trans. Graph.", vol 34, no. 1, 2014.

[13]. D. Berman, S. Avidan, et al, "Non-local image dehazing," In Proceedings of the IEEE conference on computer vision and pattern recognition, p. 1674–1682, 2016.

[14]. Q. Zhu, J. Mai, and L. Shao, “A fast single image haze removal algorithm using color attenuation prior,” Image Processing, IEEE Transactions on, vol. 24, no. 11, p. 3522–3533, 2015.

[15]. F. Yu, C. Qing, X. Xu and B. Cai, " Image and video dehazing using view-based cluster segmentation," The International Conference on Visual Communications and Image Processing (VCIP). 2016.

[16]. C. Qing, Y. Hu, X. Xu and W. Huang, “Image Haze Re-moval Using Depth-Based Cluster and Self-Adaptive Parameters”, IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), 2017.

[17]. R. T. Tan, “Visibility in bad weather from a single image,” in Proc. IEEE CVPR, p. 1–8, 2008.

[18]. R. Fattal, "Single image dehazing," in International Conference on Computer Graphics and Interactive Techniques, 2008.

[19]. S.M. Burney, H. Tariq, "K-Means Cluster Analysis for Image Segmentation," International Journal of Computer Applications, vol 96, p:1-8, 2014.

[20]. H. Xu, J. Guo, Q. Liu and L. Ye, "Fast image dehazing using improved dark channel prior," in Information Science and Technology (ICIST), 2012 International Conference on IEEE, 2012.

[21]. S. Fang, J. Zhan, Y. Cao and R. Rao, "Improved Single Image Dehazing Using Segmentation," in IEEE International Conference on Image Processing (ICIP), 2010.

[22]. A. V. a. B. Fulkerson, "VLFeat: An Open and Portable Library," 2008. [Online]. Available: http://www.vlfeat.org.