مجله ماشین بینایی و پردازش تصویر

مجله ماشین بینایی و پردازش تصویر

روشی کارآمد برای تخمین ابعاد هسته‌ی تاری در رفع تاری کور تصویر

نوع مقاله : مقاله پژوهشی

نویسندگان
1 دانشجوی دکتری مهندسی برق - الکترونیک، دانشکده مهندسی برق، دانشگاه صنعتی شاهرود، شاهرود، ایران
2 دانشکده مهندسی برق، دانشگاه صنعتی شاهرود، شاهرود، ایران
چکیده
در مسأله­ ی رفع تاری کور تصاویر، تخمین نادقیق ابعاد هسته‌ی تاری منجر به ایجاد اعوجاج­ شدید در تصویر رفع تاری شده می‌شود. در این مقاله، روشی برای تخمین ابعاد هسته‌ی تاری از یک تصویر تار ارائه شده است. در این روش، ویژگی‌های هیستوگرام گرادیان‌های جهت‌دار (HOG) تصاویر واضح از تصاویر تار متناظر یاد گرفته می­ شوند. برای این هدف، مدل‌های رگرسیون بردار پشتیبان (SVR) با استفاده از مجموعه‌ای از زوج تصاویر واضح و تار متناظر آموزش داده می­ شوند. این فرآیند در سطوح مختلف هرم تصویر انجام می‌شود. برخلاف روش‌های پیشین، بدون مفروض بودن شکل هسته‌ی تاری یک مدل رگرسیون آموزش داده می­ شود تا مستقیماً ابعاد هسته‌ی تاری را از ویژگی‌های HOG تخمین بزند. نتایج آزمایش‌های انجام شده نشان می‌دهد که این روش قادر است ابعاد هسته‌ی تاری را با دقت بیشتری نسبت به سایر روش ­های موجود از تصویر تار تخمین بزند. در نتیجه، به کمک روش پیشنهادی اعوجاج‌های ناشی از تخمین نادرست ابعاد هسته‌ی تاری در تصویر رفع تاری شده کاهش می‌یابد.
کلیدواژه‌ها

[1]
Y. Bai, G. Cheung, X. Liu and W. Gao, "Graph-Based Blind Image Deblurring From a Single Photograph," IEEE Transactions on Image Processing, vol. 28, no. 3, pp. 1404-1418, March 2019, https://doi.org/10.1109/TIP.2018.2874290.
[2]
C. Yang, W. Shao and L. Huang, "Boosting normalized sparsity regularization for blind image deconvolution," Signal, Image and Video Processing (SIViP), vol. 11, p. 681–688, 2017, https://doi.org/10.1007/s11760-016-1010-6.
[3]
D. Krishnan, T. Tay and R. Fergus, "Blind deconvolution using a normalized sparsity measure," in IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, CO, USA, 2011, https://doi.org/10.1109/CVPR.2011.5995521.
[4]
J. F. Cai, H. Ji, C. Liu and Z. Shen, "Framelet-based blind motion deblurring from a single image," IEEE Transactions on Image Processing, vol. 21, no. 2, pp. 562-572, February 2012, https://doi.org/10.1109/TIP.2011.2164413.
[5]
L. Sun, S. Cho, J. Wang and J. Hays, "Edge-based blur kernel estimation using patch priors," in IEEE International Conference on Computational Photography (ICCP), Cambridge, MA, USA, 2013, https://doi.org/10.1109/ICCPhot.2013.6528301.
[6]
J. Kotera, F. Sroubek and P. Milanfar, "Blind deconvolution using alternating maximum a posteriori estimation with heavy-tailed priors," in International Conference on Computer Analysis of Images and Patterns (CAIP), Berlin, Germany, 2013, https://doi.org/10.1007/978-3-642-40246-3_8.
[7]
W. Shao, H. Li and M. Elad, "Bi-L0-L2-norm regularization for blind motion deblurring," Journal of Visual Communication and Image Representation, vol. 33, pp. 42-59, November 2015, https://doi.org/10.1016/j.jvcir.2015.08.017.
[8]
W. Ren, X. Cao, J. Pan, X. Guo, W. Zuo and M. Yang, "Image deblurring via enhanced low-rank prior," IEEE Transactions on Image Processing, vol. 25, no. 7, pp. 3426-3437, July 2016, https://doi.org/10.1109/TIP.2016.2571062.
[9]
J. Pan, D. Sun, H. Pfister and M. Yang, "Blind image deblurring using dark channel prior," in IEEE conference on computer vision and pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, https://doi.org/10.1109/CVPR.2016.180.
[10]
J. Pan, Z. Hu, Z. Su and M. Yang, "L0-regularized intensity and gradient prior for deblurring text images and beyond," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 2, pp. 342-355, February 2017, https://doi.org/10.1109/TPAMI.2016.2551244.
[11]
J. Anger, G. Facciolo and M. Delbracio, "Blind Image Deblurring using the ℓ0 Gradient Prior," Image Processing On Line (IPOL), vol. 9, pp. 124-142, March 2019, https://doi.org/10.5201/ipol.2019.243.
[12]
D. Yang and X. Wu, "Dual-Channel Contrast Prior for Blind Image Deblurring," IEEE Access, vol. 8, pp. 227879-227893, 18 December 2020, https://doi.org/10.1109/ACCESS.2020.3045857.
[13]
X. Chen, Y. Zhu, W. Liu, J. Sun and Y. Zhang, "Blur kernel estimation of noisy-blurred image via dynamic structure prior," Neurocomputing, vol. 403, pp. 268-281, 2020, https://doi.org/10.1016/j.neucom.2020.03.067.
[14]
Y. Bai, H. Jia, M. Jiang, X. Liu, X. Xie and W. Gao, "Single Image Blind Deblurring Using Multi-Scale Latent Structure Prior," IEEE Transactions on Circuits and Systems for Video Technology, vol. 30, no. 7, pp. 2033-2045, July 2020, https://doi.org/10.1109/TCSVT.2019.2919159.
[15]
S. Liu, H. Wang, J. Wang, S. Cho and C. Pan, "Automatic blur-kernel-size estimation for motion deblurring," Visual Computer, vol. 31, pp. 733-746, May 2015, https://doi.org/10.1007/s00371-014-0998-2.
[16]
L. Si-Yao, D. Ren and Q. Yin, "Understanding Kernel Size in Blind Deconvolution," in IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA, 2019, https://doi.org/10.1109/WACV.2019.00224.
[17]
L. Pan, R. Hartley, M. Liu and Y. Dai, "Phase-only Image Based Kernel Estimation for Single Image Blind Deblurring," in Computer Vision and Pattern Recognition Conference (CVPR), Long Beach, CA, USA, 2019, https://doi.org/10.1109/CVPR.2019.00619.
[18]
S. Liu, H. Wang, J. Wang and C. Pan, "Blur-Kernel Bound Estimation from Pyramid Statistics," IEEE Transactions on Circuits and Systems for Video Technology, vol. 26, no. 5, pp. 1012-1016, May 2016, https://doi.org/10.1109/TCSVT.2015.2418585.
[19]
"Peak signal-to-noise ratio," Wikipedia, Aug. 11, 2025. [Online].
Available: https://en.wikipedia.org/wiki/Peak_signal-to-noise_ratio. [Accessed: Aug. 24, 2025].
[20]
Z. Wang, A. Bovik, H. Sheikh and E. Simoncelli, "Image quality assessment: From error visibility to structural similarity," IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600-612, April 2004, https://doi.org/10.1109/TIP.2003.819861.
[21]
D. Zoran and Y. Weiss, "From learning models of natural image patches to whole image restoration," in International Conference on Computer Vision, Barcelona, Spain, 2011, https://doi.org/10.1109/ICCV.2011.6126278.
[22]
A. Levin, Y. Weiss, F. Durand and W. T. Freeman, "Understanding and evaluating blind deconvolution algorithms," in IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, 2009, https://doi.org/10.1109/CVPR.2009.5206815.
[23]
W. Lai, J. Huang, Z. Hu, N. Ahuja and M. Yang, "A Comparative Study for Single Image Blind Deblurring," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, https://doi.org/10.1109/CVPR.2016.188.
[24]
E. Agustsson and R. Timofte, "NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study," in IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, USA, 2017, https://doi.org/10.1109/CVPRW.2017.150.
[25]
R. Kohler, M. Hirsch, B. Mohler, B. Scholkopf and S. Harmeling, "Recording and playback of camera shake: benchmarking blind deconvolution with a real-world database," in Proceedings of IEEE European Conference on Computer Vision (ECCV), 2012, https://doi.org/10.1007/978-3-642-33786-4_3.