Search - entropy data

Search - entropy data - List

[Special Effects] kmean DL : 0: 包括K-均值聚类算法的思想介绍，kmeans的MATLAB代码，c语言代码、c++代码。-Including the K-means clustering algorithm introduced the idea, kmeans of MATLAB code, c language code, c++ code.-Entropy Based Subspace Clustering for Mining Data- ENCLUS- a new version of PROCLUS algorithm for clustering high dimensional data set.
Date : 2025-12-26 Size : 1.08mb User : 陈老师
[Special Effects] suanshubianma DL : 0: 算术编码算法，是图像压缩的主要算法之一。是一种无损数据压缩方法，也是一种熵编码的方法。-Arithmetic coding algorithm, image compression is one of the main algorithm. Is a lossless data compression method, but also a method of entropy coding.
Date : 2025-12-26 Size : 1kb User : 小明
[Special Effects] imjepg DL : 0: JPEG压缩编码的主要步骤有： 1.通过前向离散余弦变换减少图像数据相关性； 2.利用人眼的视觉特性队DCT系数进行量化； 3.使用查分脉冲编码调制对直流系数进行编码； 4.对交流系数进行Z形扫描，使用形成长度编码队交流系数进行编码； 5.熵编码器对上述描述符进行熵编码。-JPEG compression encoding of the main steps are: 1.forward discrete cosine transform to reduce the image data 2.Using human visual characteristics of the team DCT coefficients are quantized 3.check points pulse code modulation encoding the DC coefficient 4.coefficients of the Z-scan AC coefficient is encoded using the form length encoding team 5.the entropy encoder for entropy coding of the above descriptors.
Date : 2025-12-26 Size : 150kb User : 汪晨
[Special Effects] ImgProcess2009-05-14 DL : 0: 这是我读“图像识别与人工智能”研究生是，在实验室做图像处理与跟踪实验所用的框架程序。里面已经包含了如下函数模块：图像显示：单幅图像显示，连续文件名的序列图像显示，SRC（纯数据图像文件）序列图显示图像滤波、增强：均值滤波，灰度拉伸，图像减背景并拉伸图像分割：自适应门限阈值分割，基于梯度的分割，基于最大熵的分割，OTSU分割，图像加噪：图像加入随机噪声，序列图加噪声图像轮廓：轮廓提取（只能对0-255二值图），轮廓跟踪（只能对0-255二值图），其他：图像差分，腐蚀，膨胀说明：因为是实验室做实验用的，所以界面做的很简单，大家多多谅解。但内容还是听丰富的，既有师兄师姐们积累的成果，也有我的两年经验。各函数都有很详细的中文注释，希望能给大家带来帮助，少走弯路。-The software contains the following function modules: Image display: single image, the image sequence of consecutive file names SRC (pure data image files) sequence diagram showsImage filtering, enhancement: the mean filter, gray stretch, the image background subtraction and tensileImage Segmentation: Adaptive threshold threshold segmentation, gradient-based segmentation, segmentation based on maximum entropy, OTSU split,Image noise: images by adding random noise sequence diagram plus noiseImage contours: contour extraction (only 0-255 binary image), the contour tracking (only 0-255 binary diagram)Other: image difference, erosion and dilationDescription: laboratory experiments, so the interface to do the very simple, we a lot of understanding. Or listen to the rich, both brothers Shijie accumulated results of two years experience. Each function has a very detailed notes in Chinese, I hope we can bring help to avoid detours.
Date : 2025-12-26 Size : 3.8mb User : 罗蛟
[Special Effects] FAST-ICA DL : 0: 1、对观测数据进行中心化，； 2、使它的均值为0，对数据进行白化—>Z； 3、选择需要估计的分量的个数m，设置迭代次数p<-1 4、选择一个初始权矢量（随机的W，使其维数为Z的行向量个数）； 5、利用迭代W(i,p)=mean(z(i,:).*(tanh((temp) *z)))-(mean(1-(tanh((temp)) *z).^2)).*temp(i,1)来学习W （这个公式是用来逼近负熵的） 6、用对称正交法处理下W 7、归一化W(:,p)=W(:,p)/norm(W(:,p)) 8、若W不收敛，返回第5步 9、令p=p+1，若p小于等于m,返回第4步剩下的应该都能看懂了基本就是基于负熵最大的快速独立分量分析算法-1, on the center of the observation data, 2, making a mean of 0, the data to whitening-> Z 3, select the number of components to be estimated m, setting the number of iterations p < -1 4, select an initial weight vector (random W, so that the Z dimension of the row vectors of numbers) 5, the use of iteration W (i, p) = mean (z (i, :).* (tanh ((temp) ' * z)))- (mean (1- (tanh ((temp)) ' * z). ^ 2)).* temp (i, 1) to learn W (This formula is used to approximate the negative entropy) 6 with symmetric orthogonal treatments W 7, normalized W (:, p) = W (:, p)/norm (W (:, p)) 8, if W does not converge, return to step 5 9 , so that p = p+1, if p less than or equal m, return to step 4 should be able to read the rest of the basic is based on negative entropy of the largest fast independent component analysis algorithm
Date : 2025-12-26 Size : 1kb User : liu xp
[Special Effects] FAST-ICA11 DL : 0: 1、对观测数据进行中心化，； 2、使它的均值为0，对数据进行白化—>Z； 3、选择需要估计的分量的个数m，设置迭代次数p<-1 4、选择一个初始权矢量（随机的W，使其维数为Z的行向量个数）； 5、利用迭代W(i,p)=mean(z(i,:).*(tanh((temp) *z)))-(mean(1-(tanh((temp)) *z).^2)).*temp(i,1)来学习W （这个公式是用来逼近负熵的） 6、用对称正交法处理下W 7、归一化W(:,p)=W(:,p)/norm(W(:,p)) 8、若W不收敛，返回第5步 9、令p=p+1，若p小于等于m,返回第4步剩下的应该都能看懂了基本就是基于负熵最大的快速独立分量分析算法-1, on the center of the observation data, 2, making a mean of 0, the data to whitening-> Z 3, select the number of components to be estimated m, setting the number of iterations p < -1 4, select an initial weight vector (random W, so that the Z dimension of the row vectors of numbers) 5, the use of iteration W (i, p) = mean (z (i, :).* (tanh ((temp) ' * z)))- (mean (1- (tanh ((temp)) ' * z). ^ 2)).* temp (i, 1) to learn W (This formula is used to approximate the negative entropy) 6 with symmetric orthogonal treatments W 7, normalized W (:, p) = W (:, p)/norm (W (:, p)) 8, if W does not converge, return to step 5 9 , so that p = p+1, if p less than or equal m, return to step 4 should be able to read the rest of the basic is based on negative entropy of the largest fast independent component analysis algorithm
Date : 2025-12-26 Size : 1kb User : liu xp
[Special Effects] spectrum-estimation DL : 0: 功率谱估计是利用有限长的数据估计信号的功率谱，广泛应用于各个领域。功率谱估计主要分为经典谱估计与现代谱估计。常用的经典谱估计方法有周期图法，相关法，周期图的改进法，常用的现代谱估计方法有最大熵谱估计，AR模型，MA模型，ARMA模型。经典谱估计适用于长序列的信号，其主要缺陷是描述功率谱波动的数字特征方差性能差，频率分辨率低，现代谱估计适用于短序列的信号，旨在改善谱估计的分辨率，并将其应用于实际地震资料的谱分析。 -Power spectrum estimation is the use of a finite length data to estimate the power spectrum of the signal, widely used in various fields. Power spectrum estimation is divided into classic and modern spectral estimation spectral estimation. Commonly used methods of classical periodogram spectrum estimation method, the relevant law, the cycle graph Improvement Act, commonly used in modern spectral estimation methods have maximum entropy spectral estimation, AR model, MA model, ARMA model. Classical spectral estimation applied to signal a long sequence, its main drawback is the fluctuation power spectrum describing digital signature variance performance is poor, the frequency resolution is low, modern spectral estimation applied to signal short sequences designed to improve spectral estimation resolution, and The analysis applied to real seismic data spectrum.
Date : 2025-12-26 Size : 3kb User : 裴忠林
[Special Effects] iycet DL : 0: Can realize the two-dimensional data clustering, Rotating machinery 2-d holographic spectrum calculation, Based on negative entropy largest independent component analysis.
Date : 2025-12-26 Size : 4kb User : benhiefei
[Special Effects] nfuis DL : 0: Energy entropy calculation, Interpolation and fitting, solution of equations, data analysis, For lack of EMD.
Date : 2025-12-26 Size : 5kb User : sengqingsanpao
[Special Effects] dhbsc DL : 0: Can realize the two-dimensional data clustering, The commonly used digital signal modulation based on artificial neural network, Based on negative entropy largest independent component analysis.
Date : 2025-12-26 Size : 147kb User : lunnanghiupei
[Special Effects] E0-练习 DL : 0: 0-1、基本要求 1，显示一个灰度图象p0-01和彩色图象p0-02； 2，观察灰度图象和彩色图象的数据矩阵和文件内容； 3，熟悉灰度图象、二值图象、彩色图象和索引图象之间的变换。 0-2、计算图象的统计参数 1，对灰度图象计算其灰度均值、方差和熵; 2，对灰度图象计算其灰度的直方图; 3，对灰度图象实施直方图均衡化。(0-1. Basic requirements 1. Display a grayscale image p0-01 and color image p0-02; 2. Observe the data matrix and file contents of gray image and color image; 3. Familiar with the transformation between grayscale image, binary image, color image and index image. 0-2. Statistical parameters of computed image 1. The grayscale image is calculated with the mean, variance and entropy. 2. The histogram of grayscale image is calculated. 3. The histogram equalization of grayscale image is implemented.)
Date : 2025-12-26 Size : 840kb User : LIMBO2K
[Special Effects] automatic_image_segement DL : 0: 本文以k-means算法为背景，引入信息熵相关知识，从而实现全自动分割图像。然而在利用混合高斯模型对图像进行数据分析时，会发生一定的过拟合现象，导致我们得不到预期的聚类数目。本文设计合理的合并准则，令模型简化，有效地消除过拟合现象，使得最后得到的聚类数目与预期符合。，设计合理的准则改进了图像的全自动分割方法，使得分割结果更加优化(In this paper, k-means algorithm is used as the background, and information entropy related knowledge is introduced to realize full-automatic image segmentation. However, when the Gaussian mixture model is used to analyze the image data, there will be some over-fitting phenomenon, resulting in that we cannot get the expected number of clusters. In this paper, a reasonable merging criterion is designed to simplify the model and effectively eliminate the over-fitting phenomenon, so that the final clustering number is in line with the expectation. A reasonable criterion is designed to improve the automatic image segmentation method and make the segmentation result more optimized.)
Date : 2025-12-26 Size : 1kb User : xiaoxiaofish