FLOU IMAGES DECOLORATION VIA DEEP LEARNING.
- Assistant professor, Department of Computer Science and Engineering, S.A.Engineering College, India.
- Students, Department of Computer Science and Engineering, S.A.Engineering College, India.
- Abstract
- Keywords
- References
- Cite This Article as
- Corresponding Author
Image blur kernel calculation is critical to deblur a blind image. Many existing approaches describes blur features that are used only for identifying common blur across the images, which is impractical in real blind images because blur type is unknown. To avoid this problem, we have to identify the blur type for input image patch, and then the kernel parameter of the image This calculation can be done with the help of deep learning based pre-training method i.e., Deep neural network (DNN) which is used to find the blur type and a general regression neural network (GRNN), which is used to calculate its parameter. This method is very useful and easy to identify the different blur type in a mixed input of image blemish which contains various blurs and its parameters. The result of above method is more effectiveness and better compared to the Berkeley segmentation data set and the Pascal VOC 2007 data set.
- S. Cho, S. Paris, B. Horn, and W. Freeman. Blur kernel estimation using the radon transforms, in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Colorado Springs, CO, USA, in 2011.
- Levin, Y. Weiss, F. Durand, and W. Freeman, Efficient marginal likelihood optimization in blind deconvolution, in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Colorado Springs, CO, USA, 2011.
- Sun, S. Cho, J. Wang, and J. Hays,Eedge-based blur kernel estimation using patch priors, in Proc. IEEE Int. Conf. Computational Photography, Cambridge, MA, USA, Apr 2013.
- Xue, L. Zhang, X. Mou, Gradient magnitude similarity deviation: a highly efficient perceptual image quality index, in IEEE Trans. Image Process., vol. 23, no. 2, pp. 684?695, Dec 2014.
- Anat Levin, Yair Weiss, Fredo Durand, and William T. Freeman, Understanding and evaluating blind deconvolution algorithms, in IEEE Conf. Computer Vision and Pattern Recognition, Miami Beach, FL, USA, 2009.
- Neel Joshi Richard Szelis ki David J. Kriegman, PSF estimation using sharp edge prediction, in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Anchorage, AL, USA, 2008.
- Gu, G. Zhai, W. Lin, X. Yang and W.Zhang, No reference image sharpness assessment in autogressive parameter space, in IEEE Trans. on Image Process., vol. 24, no. 10, pp. 3218?3231, Oct.. 2015.
- Chen and J. Ma, ?An empirical identification method of gaussian blur parameter for image deblurring,? IEEE Trans. on Signal Process., vol. 57, no. 7, pp. 2467?2478, Mar. 2009.
- Jain and H. Seung, ?Natural image denoising with convolutional networks,? in Proc. Conf. Advances in Neural Information Processing Systems, Vancovour, Canada, 2008.
- Shan, J. Jia, and A. Agarwala, ?High-quality motion deblurring from a single image,? in ACM Trans. Graph., vol. 27, no. 3, pp. 721?730, Aug. 2008.
- Krishnan and R. Fergus, ?Fast image deconvolution using hyper-laplacian priors,? in Proc. Conf. Advances in Neural Information Processing Systems, Vancouver, BC, Canada, 2009.
- Liu, W. Lin, and M. Narwaria, Image quality assessment based on gradient similarity, in IEEE Trans. Image Process., vol. 21, no. 4, pp. 1500?1512, Mar. 2012.
- Gu, G. Zhai, X. Yang, and W. Zhang, Using free energy principle for blind image quality assessment, in IEEE Trans. on Multimedia, vol. 17, no. 1, pp. 50?63, Jan. 2015.
[K. Ramya Devi M. Tech, U. Nivetha and P. Saaketha. (2017); FLOU IMAGES DECOLORATION VIA DEEP LEARNING. Int. J. of Adv. Res. 5 (Feb). 1947-1952] (ISSN 2320-5407). www.journalijar.com
