摘要
为直观准确地消除离焦误差造成的图像模糊现象,提升数字图像处理精度,提出基于立体双目视觉的模糊图像视觉效果优化算法。将模糊图像优化问题变换成模糊核路径关系约束下优化估计问题,在模糊核路径对应基础上,构建立体双目图像模糊核路径对应关系模型。将模型作为收敛条件,获取模糊图像特征间的耦合关系与三维几何信息;使用方向滤波器剔除模糊图像噪声,运用Radon变换处理方向滤波在模糊函数估计中引发的误差,利用卷积操作去除模糊现象,通过梯度范数的变分泛函优化算法实现模糊图像视觉效果优化。实验结果表明,该方法可以很好地优化被噪声和模糊污染的图像,完整保留图像的纹理和细节信息,在迭代次数为7次时图像差异能量达到收敛,可高效率完成模糊图像视觉效果优化。
In order to intuitively and accurately eliminate the image blur phenomenon caused by the defocus error and improve the accuracy of digital image processing, a fuzzy image visual effect optimization algorithm based on stereo binocular vision is proposed. The fuzzy image optimization problem is transformed into an optimization estimation problem under the constraint of the fuzzy core path relationship. Based on the fuzzy core path correspondence, a stereo binocular image fuzzy core path corresponding relationship model is constructed, and the model is used as a convergence condition to obtain the coupling between the fuzzy image features relation and three-dimensional geometric information. Directional filter is used to remove fuzzy image noise, Radon transform is used to deal with the error caused by directional filter in fuzzy function estimation, convolution operation is used to remove blur phenomenon, through the gradient norm’s variational functional optimization algorithm. The visual effects of blurred images is optimized. The experimental results show that the proposed method can optimize the image contaminated by noise and blur, and retain the texture and detail information of the image completely. When the number of iterations is 7 times, the difference energy of the image reaches convergence, and the visual effect of the blurred image can be completed efficiently optimization.
作者
李艳
LI Yan(School of Art and Design,Lanzhou University of Arts and Science,Lanzhou 730000,China)
出处
《吉林大学学报(信息科学版)》
CAS
2021年第6期656-661,共6页
Journal of Jilin University(Information Science Edition)
基金
兰州文理学院校级教育改革基金资助项目(LY65927)。
关键词
立体双目视觉
模糊图像
视觉效果优化
特征分析
模糊函数估计
stereo binocular vision
blurred image
visual effect optimization
feature analysis
blur function estimation