本文着重介绍了基于学习的人脸图像超分辨率算法。
Then, we propose a new learning-based super-resolution algorithm for face images.
图像超分辨率充分利用了各帧图像间相似而又不同的信息。
Super-resolution makes full use of the similar but not the same information among each observation.
提出一种基于区域自适应学习的人脸图像超分辨率复原算法。
A novel region adaptive learning-based super resolution algorithm for human face images is proposed, which divides a face image into flat regions and detailed regions.
图像超分辨率复原的目的是从一个低分辨率图像序列中提取一幅高分辨率图像。
The goal of Super-resolution restoration is to draw a high-resolution image from a low-resolution ratio image array.
图像超分辨率技术是指利用若干幅低分辨率图像作为输入，通过一系列信号处理的手段融合出具有更多高频细节信息的高分辨率图像的方法的总称。
Image super resolution technology is a method that takes a series of low resolution images as input, and USES signal processing technology to obtain high resolution image.
光学遥感依赖于利用多光谱和超光谱图像具有较高的光谱分辨率和空间分辨率来对所观测场景进行辨别。
Optical remote sensing relies on the use of panchromatic, multispectral and hyperspectral images with a high spectral resolution and spatial resolution to distinguish the observed scene.
在加权最小二乘的基础上，结合PDE正则化，提出了一种视频图像序列超分辨率重建的自适应滤波方法。
An adaptive filter for video image sequence super resolution reconstruction is proposed on the basis of the weighted least square and PDE regularization in this paper.
为了改善超分辨率重建图像的效果，提出了一种基于线过程模型的凸集投影方法。
In order to improve the superresolution reconstruction of image, a method of projections onto convex sets (POCS) based on the line process modeling is proposed.
针对无源毫米波成像中图像分辨率低的问题，提出了一种改进的最大后验(MAP)超分辨算法。
To solve the problem of poor resolution in passive millimeter wave (PMMW) imaging, we present an improved maximum a posteriori (MAP) super-resolution algorithm.
超分辨率图像重建技术就是人们获取高分辨率图像的一种很重要的方法。
The technology for rebuilding high resolution image is an important method for getting high resolution images.
在传统的空间域正则化图像复原或超分辨率图像复原方法中，是用向量2-范数度量数据逼近项和正则项。
In traditional approach, people use l_2 -norm to measure data approximation item and regularization item in regularized image restoration and super-restoration in spatial domain.
为了解决单幅低分辨率人脸图像重构问题，提出了基于线性物体类理论重构超分辨率人脸图像的新方法。
A new super-resolution face image reconstruction method based on linear object-class theory is proposed to deal with the problem of low-resolution face images.
从实验结果看，这种超分辨算法显著提高了图像分辨率。
The results of experiments show that the higher resolution may be obtained by super resolution algorithm.
所提出的算法用于实际的图像序列，取得了满意的超分辨率效果。
The proposed algorithms are applied in synthetic and real image sequences, and the experimental results are prospective and satisfied.
实验证明，考虑运动模糊的改进POCS超分辨率重建算法能够有效地克服振荡效应，提高图像分辨率。
Experimental results prove that the improved POCS algorithm considering the motion blurs can effectually reduce the oscillation effect and advance the image spatial resolution.
超分辨率技术是一种利用同一场景的有相对位移的多帧低分辨率图像之间的混叠信息，来重建出比原始图像分辨率更高的超级分辨率图像的技术。
It uses the aliased information of multiple LR images with a different motion of the same scene to reconstruct the "super" resolution image which has even higher resolution than the original one.
基于重建的超分辨率（SR）方法中，图像求解是典型的高维病态问题，需借助有效的正则来稳定求解。
Image super-resolution restoration and enhancement (SR) based on reconstruction is a typically ill-posed and high-dimensional problem, which needs effective regularization to stable the solution.
但是，由于超分辨率图像重构本身是一个病态求逆过程，在重构图像中所产生的边缘振荡效应往往很难在重构过程中予以消除。
However, due to the ill-posed nature of the super-resolution image reconstruction, the ringing artifacts can not be easily removed in the reconstruction process.
多帧图像的超分辨率重建技术已被证明是一种行之有效的解决上述问题的方法。
Multiframe super-resolution reconstruction is an active topic in image processing which is urgently needed in many military and civilian applications as well as theoretical interests.
最后，将全局脸图像和局部细节信息相结合，得到最终的人脸超分辨率结果。
Finally, the global face image and local details are combined to the final face super-resolution results.
在最近几年中，由于彩色数码相机的迅猛发展，超分辨率技术的研究对象已从几年前的灰度图像进展到彩色图像。
In the recent few years, thanks to the boom of color digital camera, the research target of super resolution has shifted from grey images to color images.
实验结果表明，该算法在有效消除边缘振荡效应的同时，极大地提高了超分辨率图像重构的速度。
Experimental results show that the proposed algorithm has got a significant increase of efficiency while reducing the ringing artifacts effectively.
提出一种实时帧迭代反向投影算法实现对图像序列的超分辨率处理。
A real-time frame iterative back-projection algorithm for image sequences superresolution is proposed.
对工业自动化中拍摄的CFA低分辨率图像的实验结果表明，我们改进后的算法能鲁棒、精确、高效地对彩色图像进行超分辨率重建。
The experimental results regarding to the LR CFA images captured in factory automation show that our improved algorithm can produce color SR images robustly, accurately and efficiently.
该方法有效地保持了边缘特性，改善了超分辨率图像重建质量。
The experimental results show that the edges kept very well, and the performance of the reconstructed images is improved.
通过迭代求解法和高斯金字塔模型，快速精确地估计得到配准参数，采用凸集投影（POCS）算法对图像序列进行了超分辨率重建。
Based on the set theoretic formulation, a projection onto convex sets (POCS) algorithm is applied to find the solution to face image reconstruction.
图像配准的精确性直接影响超分辨率重建的效果。
The result of the SR reconstruction will be affected by the accuracy of the registration directly.
本文提出了一种基于支撑向量机的盲超分辨率图像复原算法。
In this paper we propose a blind super-resolution image restoration algorithm based on Support Vector Machines (SVM).
本文提出了一种基于支撑向量机的盲超分辨率图像复原算法。
In this paper we propose a blind super-resolution image restoration algorithm based on Support Vector Machines (SVM).
应用推荐