Description: 超分辨率图像处理
从几幅图象中提取像素合成新的比较清晰的图像-super-resolution image processing images from pieces of pixels from the synthesis of new clearer images Platform: |
Size: 128000 |
Author:妮可莫 |
Hits:
Description: 仿真获取四幅互差半个像素的低分辨率图像，利用反演解析算法重建出一副高分辨率图像，属于亚像元技术或者超分辨率技术。-Simulation Interoperability poor access to four half-pixel low-resolution images, the use of inversion algorithm for the reconstruction of an analytic high-resolution images, belong to sub-pixel super-resolution technology or technology. Platform: |
Size: 5120 |
Author:周晓峰 |
Hits:
Description: 超分辨率图像处理从几幅图象中提取像素合成新的比较清晰的图像-Super-resolution image processing to extract images from a number of new synthetic pixel images clearer Platform: |
Size: 116736 |
Author:tlh |
Hits:
Description: 毫米波图像存在分辨率低的缺点，该程序在WRLA算法的基础上，进一步采用投影算法，能有效改善毫米波图像的分辨率-Images acquired from Passive Millimeter-Wave (PMMW) radiometer have poor resolution due to limited aperture dimension. Therefore, Super-Resolution Algorithm (SRA) is a key component for PMMW imager. SRA realizes spectrum extrapolation, however, spectrum in-band is deteriorated too. Wiener-Richardson-Lucy Algorithm (WRLA) recovers spectrum in-band by Wiener filter, and extrapolates spectrum out-of-band by Richardson-Lucy Algorithm (RLA). WRLA can avoid spectrum deterioration in passband, but its ability for spectrum extrapolation is limited also. We propose an improved algorithm to solve this problem. This algorithm, which has built constraints according to characteristics of PMMW imaging, uses Projection-Onto-Convex-Sets (POCS) technique to enhance the WRLA s performance, so it is termed as POCS-WRLA. Platform: |
Size: 19456 |
Author:姜正茂 |
Hits:
Description: 基于分块的人脸图像超分辨率学习算法实验平台，利用学习到的训练集图像信息对低分辨率图像超分辨率，并可以查看超分辨率后的图像块匹配结果（用鼠标双击结果显示窗口中的实验图像），可以设置实验参数。-Block-based face image super-resolution algorithm for the experimental platform to learn, learning to use the training set of low-resolution image information super-resolution images and can view the image super-resolution block-matching results (double-click with the mouse results display window of the experimental images), the experimental parameters can be set. Platform: |
Size: 2290688 |
Author:menchael |
Hits:
Description: 基于多帧图像插值（Interpolation）技术的方法是SR恢复技术当中最直观
的方法。这类方法首先估计各帧图像之间的相对运动信息，获得HR图像在非均
匀间距采样点上的象素值，接着通过非均匀插值得到HR栅格上的象素值，最后
采用图像恢复技术来去除模糊和降低噪声（运动估计!非均匀插值!去模糊和
噪声）。-In this paper, we propose a novel method for solv-
ing single-image super-resolution problems. Given a
low-resolution image as input, we recover its high-
resolution counterpart using a set of training exam-
ples. While this formulation resembles other learning-
based methods for super-resolution, our method has
been inspired by recent manifold learning methods, par-
ticularly locally linear embedding (LLE). Speci?cally,
small image patches in the low- and high-resolution
images form manifolds with similar local geometry in
two distinct feature spaces. As in LLE, local geometry
is characterized by how a feature vector correspond-
ing to a patch can be reconstructed by its neighbors
in the feature space. Besides using the training image
pairs to estimate the high-resolution embedding, we
also enforce local compatibility and smoothness con-
straints between patches in the target high-resolution
image through overlapping. Experiments show that our
method is very ?exible Platform: |
Size: 27595776 |
Author:qianyeyu |
Hits:
Description: 基于马尔科夫随机场的，例子学习超分辨率复原代码。-This is an implementation of the example-based super-resolution algorithm. Although the applications of MSFs have now extended beyond example-based super resolution and texture synthesis, it is still of great value to revisit this problem, especially to share the source code and examplar images with the research community. We hope that this software package can help to understand Markov random fields for low-level vision, and to create benchmark for super-resolution algorithms. Platform: |
Size: 37349376 |
Author:任伟彦 |
Hits:
Description: 多尺度图像非下采样轮廓波变换（NSCT）的工具箱，实现代码为Matlab版本。可用于图像的多尺度分析，如图像压缩、图像分割、图像融合和超分辨率等。-Multi-scale image nonsubsampled contourlet transform (NSCT) toolbox, code Matlab version. The images can be used for multi-scale analysis, such as image compression, image segmentation, image fusion and super-resolution. Platform: |
Size: 114688 |
Author:王星 |
Hits:
Description: ：超分辨率(sR)重建技术是利用一幅或多幅低分辨率(LR)图像的信息重建出一幅高分辨率(HR)图像，同时能够
消除由成像器件引入的模糊、噪声。该技术应用领域广泛，已经成为国内外图像处理领域的研究热点之一。介绍了超分
辨率重建技术的基本原理，并分别以单帧和多帧、频域和空域为分类依据，分别阐述了超分辨率重建技术的经典方法，系
统地总结了各种方法的优缺点，提出了超分辨率重建技术可能的研究方向，从而为超分辨率重建相关技术的进一步研究
提供一定的理论基础-Abstract：Super—resolution image reconstruction technique produces a high—resolution image from seve~ low—resolution images，call al—
SO eliminate additive noise and the distinction Which has been come from limited detector of size and optical components．Therefore．it
has been a lot topic in the field of image processing．Introduces the basic principle of super—resolution reconstruction tec hnique，and classifies
the classical method based on single frame and multi frame．the frequency domain and airspace．Systematically summarizes the ad—
van tages an d disadvan tages of various methods and provide theoretical basis for the supe r—resolution reconstruction technique of further
research，and puts forward the research direction of super-resolution reconstruction technique Platform: |
Size: 355328 |
Author:liuzhao |
Hits:
Description: 本文提出，为第一次，一个统一的多图像超分辨率盲法（MISR或SR），单个图像模糊反卷积（二次发射离子束淀积），和多图像模糊反褶积（国际金业）的低分辨率（LR）图像退化通过线性空间不变（LSI）模糊，锯齿，加白高斯噪声（AWGN）。该方法是基于
交替最小化（AM）的一个新的成本函数
对于未知的高分辨率（HR）图像和模糊。
-This paper presents, for the first time, a unified
blind method for multi-image super-resolution (MISR or SR),
single-image blur deconvolution (SIBD), and multi-image blur
deconvolution (MIBD) of low-resolution (LR) images degraded
by linear space-invariant (LSI) blur, aliasing, and additive white
Gaussian noise (AWGN). The proposed approach is based on
alternating minimization (AM) of a new cost function with
respect to the unknown high-resolution (HR) image and blurs. Platform: |
Size: 2874368 |
Author:wangshuang |
Hits:
Description: 本文运用深度神经网络的方法克服姿态变量和图像分辨率的影响,提出了一种多姿态的人脸超分辨识别算法并在实验数据集上获得了良好的性能表现。另外本文利用深度信念网络探索正面人脸图像和侧面人脸图像的映射,方法放松了深度信念网络的输入也输出之间绝对相等,而只是保证其高层含义上的相等。实验表明了使用深度信念网络可以学习到侧面人脸图像到正面人脸图像的一个全局映射,但是丢失了个体细节差异。本文还提出了基于深度网络保持姿态邻域进行姿态分类的方法,在学习过程中,我们保证了同一个姿态下的人脸图像应该与同一姿态下的多张图像互为邻居。实验证明了,我们的方法在用于姿态分类具有非常良好的性能,但是也发现学习过程中,那些与区别个体的信息逐渐丢失了,这也导致了直接运用非线性近邻元分析的特征的人脸识别的性能不佳。-In this paper, the neural network approach to overcome the depth of variables that affect the attitude and image resolution , proposed a multi-pose face recognition algorithms and super-resolution experimental data set obtained in a good performance. Also this paper to explore the depth of belief network mapping frontal face image and profile face images , the method of absolute equality between the input relax depth of belief networks is also output , but only to ensure equal meaning on its top . Experimental results show that the use of deep belief networks can learn to face image to the side of the front face of a global image map , but lost the details of individual differences . This paper also proposes to maintain posture neighborhood depth network-based gesture classification methods in the learning process , we ensure that the face image under the same gesture with multiple images should be under the same attitude are neighbors . Experiment proves that our method for gesture cl Platform: |
Size: 9719808 |
Author:cen |
Hits:
Description: The low-resolution images have small translations and rotations the high-resolution reference image. The problem consists of constructing a model of linear transformations for each image, and then piecing together the images to form the high-resolution image. Super-resolution image -The low-resolution images have small translations and rotations the high-resolution reference image. The problem consists of constructing a model of linear transformations for each image, and then piecing together the images to form the high-resolution image. Super-resolution image Platform: |
Size: 256000 |
Author:haroon |
Hits:
Description: 用于对超分辨率重建后的重建影像进行无参考影像质量评价(the code is used for image quality measure without reference images) Platform: |
Size: 177152 |
Author:lilly
|
Hits:
Search - super resolution for images