搜索资源列表
基于OMP算法的信号稀疏分解（Gabor字典）
- 基于OMP算法的信号稀疏分解程序
k_svd
- k-svd算法m代码.用于形成冗余字典，对图像进行稀疏分解-m k-svd algorithm code used to create a redundant dictionaries, sparse decomposition of images
KSVD_Matlab_ToolBox
- KSVD原始算法：信号稀疏表示中的过完备字典的学习算法-KSVD original algorithm: Signal Sparse Representation of the learning algorithm over-complete dictionary
K-SVD工具箱
- 用于信号稀疏表示的K-SVD字典学习算法工具箱，有详细的Demo，方便理解。
imagematchingpursuitbasedonGabordictionatry
- 基于Gabor感知多成份字典，进而提出一种高效的基于匹配追踪的图像稀疏分解算法，很有参考价值！-An effective algorithm based on the matching pursuit method is posed to obtain sparse decomposition of image with Gabor dictionary!
ompbox9
- 稀疏分解工具包，采用OMP算法，可用于稀疏字典的构造，压缩感知等领域-Sparse decomposition tool kit, using OMP algorithm, can be used for the construction of sparse dictionary, compressed sensing and other areas
ksvdbox12
- 采用KSVD算法通过训练的方法来构造稀疏过完备字典，在使用时一定要确保已装有ompbox9。可用于语音，图像信号处理等的稀疏字典构造-KSVD algorithm using the method of training to construct the sparse over-complete dictionary, in use, make sure have been installed ompbox9. Can be used for the sparse dictionary cons
gabor_function.m
- 自己写的Gabor方程函数，可以用来产生过完备的稀疏表示字典。-Gabor write their own equation function, can be used to generate the sparse representation over-complete dictionary.
CSlearning
- CS理论里观测矩阵的优化算法以及训练稀疏字典的算法-optimization of measurement matrix and dictionary learning for sparse approximations
tree
- 目前比较流行的稀疏分解重构程序，可以用在人脸识别、字典构造等方面。-Currently popular sparse decomposition and reconstruction process, can be used in face recognition, dictionary structure and so on.
sgLasso
- 目前比较流行的稀疏分解重构程序，可以用在人脸识别、字典构造等方面。-Currently popular sparse decomposition and reconstruction process, can be used in face recognition, dictionary structure and so on.
Metaface_ICIP
- 利用稀疏表示一集字典学习的方法进行人脸自动识别的Matlab算法，是经典SRC方法的提高-That a sparse set of dictionary use of learning methods in Matlab automatic face recognition algorithms, is the classic method of improving SRC
dct-dft--dwt
- 基于Matlab的压缩感知DCT、DWT、DFT正交基及过完备字典稀疏分解信号及重构-Matlab-based compression perception DCT, DWT, DFT orthogonal basis and complete dictionary signal sparse decomposition and reconstruction
Image-Super-Resolution-Algorithms
- 前基于图像块稀疏表示的超分辨率重构算法对所有图像块都用同一字典表示，不能反映不同类型图 像块问的筹别．针对这一缺点，本文提出基于图像块分类稀疏表示的方法．该方法先利用图像局部特征将图像块分为 平滑、边缘和不规则结构三种类型，其中边缘块细分为多个方向．然后利用稀疏表示方法对边缘和不规则结构块分别 训练各自对应的低分辨率和-岛分辨率字典．重构时对平滑块利用简单双三次插值方法，边缘和不规则结构块由其对应 的高、低分辨率字典通过正交匹配追踪箅法重构．实验结果表明，与单字典稀疏表示算法相比
自己编写的稀疏去噪代码
- 先使用K-means聚类算法将图像分为几个类，然后针对每一类分别Ksvd字典训练和稀疏表示，进行去噪
稀疏分解图像去噪
- 基于稀疏字典和稀疏编码的图像去噪算法，基于低秩约束的高光谱条纹噪声去除，包含论文及代码(Based on sparse dictionary and sparse coding image denoising algorithm, based on low rank constraints of hyperspectral fringe noise removal, including papers and code)
SPAMS
- 先输入数据生成相应的字典，再输入检测信号后得到用字典稀疏表示的结果(First input data, generate the corresponding dictionary, and then input the detection signal to obtain sparse dictionary results)
稀疏融合
- 利用DCT字典对图形进行稀疏表示，实现两幅图像的融合(Using the DCT dictionary to sparse representation of the graphics to achieve the fusion of two images)
稀疏分解
- 信号稀疏表示的目的就是在给定的超完备字典中用尽可能少的原子来表示信号，可以获得信号更为简洁的表示方式，从而使我们更容易地获取信号中所蕴含的信息，更方便进一步对信号进行加工处理，如压缩、编码等(Signal sparse representation is to overcomplete dictionary given in as little as possible to represent atomic signal, signal can be more succinct represen
字典学习模型_算法及其应用研究进展_练秋生
- 这是一篇关于字典学习的国内最新版综述，详细的描述了不同字典学习模型下的典型算法，对于稀疏表示领域的同学有一定的参考价值和作用。(This is a domestic latest edition of dictionary learning, which describes in detail the typical algorithms under different dictionary learning models. It has a certain reference value an