In this paper,we propose a shear high-order gradient(SHOG)operator by combining the shear operator and high-order gradient(HOG)operator.Compared with the HOG operator,the proposed SHOG operator can incorporate more di...In this paper,we propose a shear high-order gradient(SHOG)operator by combining the shear operator and high-order gradient(HOG)operator.Compared with the HOG operator,the proposed SHOG operator can incorporate more directionality and detect more abundant edge information.Based on the SHOG operator,we extend the total variation(TV)norm to shear high-order total variation(SHOTV),and then propose a SHOTV deblurring model.We also study some properties of the SHOG operator,and show that the SHOG matrices are Block Circulant with Circulant Blocks(BCCB)when the shear angle isπ/4.The proposed model is solved efficiently by the alternating direction method of multipliers(ADMM).Experimental results demonstrate that the proposed method outperforms some state-of-the-art non-blind deblurring methods in both objective and perceptual quality.展开更多
为了提高现有块压缩感知重构算法的性能,提出了基于全变分和混合变分模型的块压缩感知(简称BCS-TV和BCS-MV)算法。该方法以块为单位进行图像采样,以自然图像正则项的稀疏性为先验条件,通过变型的增广拉格朗日交替方向乘子法(ALM-ADMM),...为了提高现有块压缩感知重构算法的性能,提出了基于全变分和混合变分模型的块压缩感知(简称BCS-TV和BCS-MV)算法。该方法以块为单位进行图像采样,以自然图像正则项的稀疏性为先验条件,通过变型的增广拉格朗日交替方向乘子法(ALM-ADMM),在整幅图像范围内逼近目标函数来重构原始图像。与以前基于一致性块采样的压缩感知工作对比,该算法的PSNR约提高1.5 d B,SSIM约提高0.05,运行速度较稳定,特别适合具有固定传输时延的多媒体数据处理场合。展开更多
In this paper, we propose a novel shear gradient operator by combining the shear and gradient operators. The shear gradient operator performs well to capture diverse directional information in the image gradient domai...In this paper, we propose a novel shear gradient operator by combining the shear and gradient operators. The shear gradient operator performs well to capture diverse directional information in the image gradient domain. Based on the shear gradient operator, we extend the total variation(TV) norm to the shear total variation(STV) norm by adding two shear gradient terms. Subsequently, we introduce a shear total variation deblurring model. Experimental results are provided to validate the ability of the STV norm to capture the detailed information. Leveraging the Block Circulant with Circulant Blocks(BCCB) structure of the shear gradient matrices, the alternating direction method of multipliers(ADMM) algorithm can be used to solve the proposed model efficiently. Numerous experiments are presented to verify the performance of our algorithm for non-blind image deblurring.展开更多
基金Supported by the National Natural Science Foundation of China(61701004)Outstanding Young Talents Support Program of Anhui Province(gxyq2021178)+1 种基金Open Fund of Key Laboratory of Anhui Higher Education Institutes(CS2021-07)Program of University Mathematics Teaching Research and Development Center(CMC20200301)。
文摘In this paper,we propose a shear high-order gradient(SHOG)operator by combining the shear operator and high-order gradient(HOG)operator.Compared with the HOG operator,the proposed SHOG operator can incorporate more directionality and detect more abundant edge information.Based on the SHOG operator,we extend the total variation(TV)norm to shear high-order total variation(SHOTV),and then propose a SHOTV deblurring model.We also study some properties of the SHOG operator,and show that the SHOG matrices are Block Circulant with Circulant Blocks(BCCB)when the shear angle isπ/4.The proposed model is solved efficiently by the alternating direction method of multipliers(ADMM).Experimental results demonstrate that the proposed method outperforms some state-of-the-art non-blind deblurring methods in both objective and perceptual quality.
文摘为了提高现有块压缩感知重构算法的性能,提出了基于全变分和混合变分模型的块压缩感知(简称BCS-TV和BCS-MV)算法。该方法以块为单位进行图像采样,以自然图像正则项的稀疏性为先验条件,通过变型的增广拉格朗日交替方向乘子法(ALM-ADMM),在整幅图像范围内逼近目标函数来重构原始图像。与以前基于一致性块采样的压缩感知工作对比,该算法的PSNR约提高1.5 d B,SSIM约提高0.05,运行速度较稳定,特别适合具有固定传输时延的多媒体数据处理场合。
基金Supported by Open Fund of Key Laboratory of Anhui Higher Education Institutes (CS2021-07)the National Natural Science Foundation of China (61701004)Outstanding Young Talents Support Program of Anhui Province (gxyq2021178)。
文摘In this paper, we propose a novel shear gradient operator by combining the shear and gradient operators. The shear gradient operator performs well to capture diverse directional information in the image gradient domain. Based on the shear gradient operator, we extend the total variation(TV) norm to the shear total variation(STV) norm by adding two shear gradient terms. Subsequently, we introduce a shear total variation deblurring model. Experimental results are provided to validate the ability of the STV norm to capture the detailed information. Leveraging the Block Circulant with Circulant Blocks(BCCB) structure of the shear gradient matrices, the alternating direction method of multipliers(ADMM) algorithm can be used to solve the proposed model efficiently. Numerous experiments are presented to verify the performance of our algorithm for non-blind image deblurring.
