Image deblurring aims to remove the blurring phenomenon caused by shaking, lighting and other reasons in the process of taking pictures, then obtain a clear image. In view of the lack of processing image details and edge information in deblurring with prior knowledge, we proposed a method combining Max-min prior and intensity prior. The algorithm extracted the prominent edges and details of the blurred image by intensity prior, used Max-min prior to suppress blur and noise interference, used a multi-scale strategy to obtain the blurred kernel, and used the estimated intermediate restored image and the blurred kernel to iterate repeatedly to obtain a clear image. Experimental results show that compared with the existing methods, the proposed method can estimate the blurred kernel more accurately, and the intermediate image contains clearer and sharper edge information, and the artifacts are also improved, and the performance evaluation indexes PSNR and SSIM are also improved. The PSNR value can be increased by dB, and the SSIM value can be increased by 4.69%. These results show that the proposed method has better deblurring performance than the existing methods in the direct sensory and numerical evaluation indexes of the obtained clear images.
ZHAOZongchen, LIUChunyu, XUMinglin, et al. Deblurring light field images based on local maximum gradient and minimum intensity priors[J]. Laser & Optoelectronics Progress, 2024, 61(18): 336-345. (in Chinese)
[6]
ZHAZ Y, YUANX, WENB H, et al. Group sparsity residual constraint with non-local priors for image restoration[J]. IEEE Transactions on Image Processing, 2020, 29: 8960-8975.
[7]
PANJ S, SUND Q, PFISTERH, et al. Blind image deblurring using dark channel prior[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2016: 1628-1636.
[8]
PANJ, HUZ, SUZ, et al. L0-regularized intensity and gradient prior for deblurring text images and beyond[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(2): 342-355.
[9]
CHENL, FANGF, WANGT, et al. Blind image deblurring with local maximum gradient prior[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019: 1742-1750.
[10]
XUZ H, CHENH S, LIZ H. Fast blind deconvolution using a deeper sparse patch-wise maximum gradient prior[J]. Signal Processing: Image Communication, 2021, 90: 116050.
[11]
EQTEDAEIA, AHMADYFARDA. Blind image deblurring using both L0 and L1 regularization of Max-min prior[J]. Neurocomputing, 2024, 592: 127727 .
[12]
NAH S, KIMT H, LEEK M. Deep multi-scale convolutional neural network for dynamic scene deblurring[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2017: 257-265.
[13]
XIAH, WUB, TANY, et al. MFC-Net: Multi-scale fusion coding network for image deblurring[J]. Applied Intelligence, 2022, 52(11): 13232-13249.
[14]
TAOX, GAOH, SHENX, et al. Scale-recurrent network for deep image deblurring[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018: 8174-8182.
[15]
ZHANGH, DAIY, LIH, et al. Deep stacked hierarchical multi-patch network for image deblurring[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR), 2019: 5971-5979.
[16]
TSAIF J, PENGY T, TSAIC C, et al. BANet: A blur-aware attention network for dynamic scene deblurring[J]. IEEE Transactions on Image Processing, 2022, 31: 6789-6799.
XUYu, LIUHui, SHANGZhenhong. A blind image deblurring method based on multiple priors[J]. Computer Engineering & Science, 2019, 41(8): 1466-1473. (in Chinese)
[19]
HUD D, TANJ Q, ZHANGL, et al. Salient edges combined with image structures for image deblurring[J]. Signal Processing: Image Communication, 2022, 107: 116787.
[20]
WENF, YINGR, LIUY, et al. A simple local minimal intensity prior and an improved algorithm for blind image deblurring[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2021, 31(8): 2923-2937.
[21]
CHENGZ Z, LUOB, XUL, et al. Blind image deblurring via content adaptive method[J]. Signal Processing: Image Communication, 2023, 113: 116924.
[22]
KRISHNAND, TAY T, FERGUSR. Blind deconvolution using a normalized sparsity measure[C]//CVPR 2011, 2011: 233-240.
[23]
YANY, RENW, GUOY, et al. Image deblurring via extreme channels prior[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017: 6978-6986.
[24]
CAOS F, HUH P, WANGW K. Blind image deblurring method based on l 1 / l 2 -norm regularization[J]. Journal of Measurement Science & Instrumentation, 2023, 14(2): 182-188.
HUXue, HUANGChengquan, FENGRun, et al. Blind image denoising and blurring by total variationa extreme channels prior[J]. Journal of Data Acquisition and Processing, 2022, 37(3): 643-656. (in Chinese)