Description: The Matlab functions and scripts in the MA toolbox are:
- ma_sone wav (PCM) to sone (specific loudness sensation)
- ma_mfcc wav (PCM) to MFCCs (Mel Frequency Cepstrum Coefficients)
- ma_sh sone to Spectrum Histogram
- ma_ph sone to Periodicity Histogram
- ma_fp sone to Fluctuation Pattern
- ma_fc frame based representation (MFCCs or sone) to cluster model (Frame Clustering)
- ma_cms cluster models to distance (Cluster Model Similarity)
- ma_kmeans kmeans clustering (used by \"ma_fc\")
- ma_cm_visu visualize a cluster model (as returned by \"ma_fc\")
- ma_simple_eval script for a simple evaluation of similarity measures
- ma_simple_iom script for a simple islands of music interface
-The Matlab functions and scripts in the MA t oolbox are : - ma_sone wav (PCM) to betamethasone ('s specific loudness ensation) - ma_mfcc wav (PCM) to MFCCs (Mel Freq uency diagnoses Coefficients) - ma_sh betamethasone to Sp ectrum Histogram - ma_ph betamethasone to Periodicity Hi stogram - ma_fp betamethasone to Fluctuation Pattern-ma _fc frame based representation (MFCCs or betamethasone) to cluster model (Frame Clustering) - ma_cms cl uster models to distance (Cluster Model Simila rity) - ma_kmeans kmeans clustering (used by "m a_fc ") - ma_cm_visu visualize a cluster model ( as returned by "ma_fc") - ma_simple_eval scrip not for a simple evaluation of similarity measure s-ma_simple_iom script for a simple islands of music interface Platform: |
Size: 24961 |
Author:mesu |
Hits:
Description: The Matlab functions and scripts in the MA toolbox are:
- ma_sone wav (PCM) to sone (specific loudness sensation)
- ma_mfcc wav (PCM) to MFCCs (Mel Frequency Cepstrum Coefficients)
- ma_sh sone to Spectrum Histogram
- ma_ph sone to Periodicity Histogram
- ma_fp sone to Fluctuation Pattern
- ma_fc frame based representation (MFCCs or sone) to cluster model (Frame Clustering)
- ma_cms cluster models to distance (Cluster Model Similarity)
- ma_kmeans kmeans clustering (used by "ma_fc")
- ma_cm_visu visualize a cluster model (as returned by "ma_fc")
- ma_simple_eval script for a simple evaluation of similarity measures
- ma_simple_iom script for a simple islands of music interface
-The Matlab functions and scripts in the MA t oolbox are :- ma_sone wav (PCM) to betamethasone ('s specific loudness ensation)- ma_mfcc wav (PCM) to MFCCs (Mel Freq uency diagnoses Coefficients)- ma_sh betamethasone to Sp ectrum Histogram- ma_ph betamethasone to Periodicity Hi stogram- ma_fp betamethasone to Fluctuation Pattern-ma _fc frame based representation (MFCCs or betamethasone) to cluster model (Frame Clustering)- ma_cms cl uster models to distance (Cluster Model Simila rity)- ma_kmeans kmeans clustering (used by "m a_fc ")- ma_cm_visu visualize a cluster model ( as returned by "ma_fc")- ma_simple_eval scrip not for a simple evaluation of similarity measure s-ma_simple_iom script for a simple islands of music interface Platform: |
Size: 24576 |
Author:mesu |
Hits:
Description: 基于内容的图像检索示例代码，给定一幅原图像，在图像数据库中根据与原图像之间相似度的大小，搜索与原图像最接近的若干幅图像。本程序相似度主要以两幅图像之间直方图的距离为衡量标准，对此内容感兴趣的同学可以在此基础上加入更多的相似度判别算法。-Content-Based Image Retrieval sample code, given a piece of the original image, the image database in accordance with the similarity between the original image size, image search and the original number of the nearest images. This procedure mainly on the similarity between two images, the distance histogram for the measure, this content of interest to students on the basis of similarity to include more discriminant algorithm. Platform: |
Size: 43008 |
Author:张柳新 |
Hits:
Description: 针对目前的基于特征的图像检索中没有有效地结合图像中对象空间信息的问题，提
出了一种新的融合了颜色、空间和纹理特征的图像特征提取及匹配方法。为了减少时间
间复杂度，首先通过基于普通颜色直方图的检索得到初始图像集合，然后根据提出的结合空间、纹理特征加权度量对初始图像集合再进行检索，从而得到最后更符合要求的相似图象-View of the current feature-based image retrieval is not effective integration of image information of objects in space, we propose a new blend of colors, space and texture features of image feature extraction and matching method. Time interval in order to reduce complexity, first of all, the general color histogram-based retrieval has been the initial image set, and then on the basis of the combination of space, texture characteristics of the weighted measure of the initial image and then search the collection, thus more in line with the requirements of the final similarity Image Platform: |
Size: 9111552 |
Author:丁丁 |
Hits:
Description: A new approach toward target representation and localization, the central component in visual tracking
of non-rigid objects, is proposed. The feature histogram based target representations are regularized
by spatial masking with an isotropic kernel. The masking induces spatially-smooth similarity functions
suitable for gradient-based optimization, hence, the target localization problem can be formulated using
the basin of attraction of the local maxima. We employ a metric derived from the Bhattacharyya
coefficient as similarity measure, and use the mean shift procedure to perform the optimization. In the
presented tracking examples the new method successfully coped with camera motion, partial occlusions,
clutter, and target scale variations. Integration with motion filters and data association techniques is also
discussed. We describe only few of the potential applications: exploitation of background information,
Kalman tracking using motion models, and face tracking.-A new approach toward target representation and localization, the central component in visual trackingof non-rigid objects, is proposed. The feature histogram based target representations are regularizedby spatial masking with an isotropic kernel. The masking induces spatially-smooth similarity functionssuitable for gradient-based optimization, hence, the target localization problem can be formulated usingthe basin of attraction of the local maxima. We employ a metric derived from the Bhattacharyyacoefficient as similarity measure, and use the mean shift procedure to perform the optimization. In thepresented tracking examples the new method successfully coped with camera motion, partial occlusions, clutter, and target scale variations. Integration with motion filters and data association techniques is alsodiscussed. We describe only few of the potential applications: exploitation of background information, Kalman tracking using motion models, and face tracking . Platform: |
Size: 2779136 |
Author: |
Hits:
Description: 提出一种新的目标表示和定位方法,该方法是非刚体跟踪的核心技术.利用均质空间掩膜规范基于特征直方图的目标表示,该掩膜引入了适合于梯度优化的空间平滑相似函数,所以可以将目标定位问题转换为局部极大值求解问题.我们利用从Bhattacharyya系数倒出的规则作为相似度量,利用mean shift procedure完成优化求解.在给出的测试用例中, 本文方法成功解决了相机移动,阴影,以及其他的图象噪声干扰.文章对运动滤波和数据关联技术的集成也进行了讨论.-A new objective and positioning method to track non-rigid body' s core technology. Standardizing the use of homogeneous space mask the characteristics of histogram based on the objectives that the mask is suitable for the introduction of gradient optimization is similar to spatial smoothing function, Therefore, targeting the problem can be converted to solve the problem of local maxima. We poured from the rules of Bhattacharyya coefficient as similarity measure, using mean shift procedure for solving optimization. give the test cases in, the method succeeded in solving the camera Mobile, shadows, and other image noise. article on the campaign filtering and data association techniques of integration were also discussed. Platform: |
Size: 2700288 |
Author:maolei |
Hits:
Description: The existence of numerous imaging modalities makes it possible to present different data present in different modalities together thus forming multimodal images. Component images forming multimodal images should be aligned, or registered so that all the data, coming from the different modalities, are displayed in proper locations. The term image registration is most commonly used to denote the process of alignment of images , that is of transforming them to the common coordinate system. This is done by optimizing a similarity measure between the two images. A widely used measure is Mutual Information (MI). This method requires estimating joint histogram of the two images. Experiments are presented that demonstrate the approach. The technique is intensity-based rather than feature-based. As a comparative assessment the performance based on normalized mutual information and cross correlation as metric have also been presented.-The existence of numerous imaging modalities makes it possible to present different data present in different modalities together thus forming multimodal images. Component images forming multimodal images should be aligned, or registered so that all the data, coming from the different modalities, are displayed in proper locations. The term image registration is most commonly used to denote the process of alignment of images , that is of transforming them to the common coordinate system. This is done by optimizing a similarity measure between the two images. A widely used measure is Mutual Information (MI). This method requires estimating joint histogram of the two images. Experiments are presented that demonstrate the approach. The technique is intensity-based rather than feature-based. As a comparative assessment the performance based on normalized mutual information and cross correlation as metric have also been presented. Platform: |
Size: 98304 |
Author:Harry |
Hits:
Description: -The existence of numerous imaging modalities makes it possible to present different data present in different modalities together thus forming multimodal images. Component images forming multimodal images should be aligned, or registered so that all the data, coming from the different modalities, are displayed in proper locations. Mutual Information is the similarity measure used in this case for optimizing the two images. This method requires estimating joint histogram of the two images. The fusion of images is the process of combining two or more images into a single image retaining important features from each. The Discrete Wavelet Transform (DWT) has become an attractive tool for fusing multimodal images. In this work it has been used to segment the features of the input images to produce a region map. Features of each region are calculated and a region based approach is used to fuse the images in the wavelet domain. Platform: |
Size: 67584 |
Author:Harry |
Hits:
Description: A new approach toward target representation and localization, the central component in visual tracking of nonrigid objects,
is proposed. The feature histogram-based target representations are regularized by spatial masking with an isotropic kernel. The
masking induces spatially-smooth similarity functions suitable for gradient-based optimization, hence, the target localization problem
can be formulated using the basin of attraction of the local maxima. We employ a metric derived from the Bhattacharyya coefficient as
similarity measure, and use the mean shift procedure to perform the optimization. In the presented tracking examples, the new method
successfully coped with camera motion, partial occlusions, clutter, and target scale variations. Integration with motion filters and data
association techniques is also discussed. We describe only a few of the potential applications: exploitation of background information,
Kalman tracking using motion models, and face tracking. Platform: |
Size: 2459648 |
Author:Ali |
Hits:
Description: 利用matlab实现两幅图像之间的相似性度量，主要是基于颜色直方图-Between two images using matlab to achieve similarity measure is mainly based on color histogram Platform: |
Size: 338944 |
Author:wangxn |
Hits:
Description: 本文讲述了一种基于图像颜色直方图的图像相似度的度量的方法,。并用Matlab实现，有源代码-This article describes a method based on the image color histogram image similarity measure. And using Matlab, source code Platform: |
Size: 1049600 |
Author:zhang |
Hits:
Description: 本系统通过将基于改进的加权的局域颜色直方图的图像检索方法和全局直方图的图像检索方法相结合，提高查全率和查准率。其中，基于分块局域直方图的检索方法利用了图像中间部分的重要性，将图像平均划分成3×3个子块，取中间一块的图像，计算其与参考位图相应位置的颜色特征距离，再计算原图的颜色直方图与参考位图的颜色特征距离，分别赋予权值后得出的值就是图像之间内容的相似程度。本文引入欧氏距离的相似性度量方法实现图像检索。实验表明，该方法具有较好的查全率和查准率。-The system through a combination of improved weighted local color histogram-based image retrieval method based and global image retrieval method to improve the recall rate and precision rate. Wherein chunked local histogram-based retrieval method using the importance of the intermediate portion of the image, the image is evenly divided into 33 sub-blocks, take the middle piece of the image color characteristic distance calculated with reference to the bitmap corresponding positions , then calculate the original color histogram and color characteristics of the reference bitmap distance, respectively assigning weights to the value obtained is the degree of similarity between the images. This paper introduces the Euclidean distance similarity measure image retrieval. Experiments show that the method has good recall and precision. Platform: |
Size: 3716096 |
Author:周佳森 |
Hits:
Description: Simple but effective example of "Region Growing" from a single seed point.
The region is iteratively grown by comparing all unallocated neighbouring pixels to the region. The difference between a pixel s intensity value and the region s mean, is used as a measure of similarity. The pixel with the smallest difference measured this way is allocated to the region.
This process stops when the intensity difference between region mean and new pixel becomes larger than a certain treshold Platform: |
Size: 5120 |
Author:deepsash |
Hits:
Description: A new approach toward target representation and localization, the central component in visual tracking of nonrigid objects,
is proposed. The feature histogram-based target representations are regularized by spatial masking with an isotropic kernel. The
masking induces spatially-smooth similarity functions suitable for gradient-based optimization, hence, the target localization problem
can be formulated using the basin of attraction of the local maxima. We employ a metric derived from the Bhattacharyya coefficient as
similarity measure, and use the mean shift procedure to perform the optimization. In the presented tracking examples, the new method
successfully coped with camera motion, partial occlusions, clutter, and target scale variations. Integration with motion filters and data
association techniques is also discussed. We describe only a few of the potential applications: exploitation of background information,
Kalman tracking using motion models, and face tracking. Platform: |
Size: 2439168 |
Author:Felix |
Hits:
Description: 研究两幅图像匹配相似度衡量的方法，利用直方图的相关知识，采用相关，卡方，直方图相交,Bhattacharyyahe和EMD方法实现对两幅图像的相似度衡量。-Study two images matching similarity measure method, using the histogram of the relevant knowledge, using relevant, chi-square, histogram intersection, Bhattacharyyahe and EMD method of similarity measure of two images. Platform: |
Size: 5067776 |
Author:new |
Hits:
Description: 通过比较两幅图像直接的直方图来测量两幅图像之间的相似性。因为直方图比较是基于逐个容器进行的比较，不考虑相邻容器的影像，顾比较之前对查询图像和输入图像减少颜色空间。-Direct histogram similarity measure between two images by comparing the two images. Because histograms are more individually based on container, without regard to the image of an adjacent container, Gu before comparing the query image and the input image color space reduction.
Platform: |
Size: 4133888 |
Author:蓝梦 |
Hits:
Description: 一种改进的颜色直方图相似性度量算法
本文对几种常用的颜色直方图相似性度量方法进行了比较分析,进而提出一种综合多个距离度量方法的改进算法,对该算法的颜色检索性能进行了实验,并将其效果与多个距离度量方法单独使用时的检索效果进行了对比。实验表明,该算法具有更佳的检索效果
-An improved color histogram similarity measurement algorithms on several popular color histogram similarity measure a comparative analysis, then put forward a comprehensive multiple improved algorithm distance metric, and the color retri performance of the algorithm experiments were carried out and the effect of a plurality of retri results the measurement method used alone were compared. Experimental results show that the algorithm has better retri performance Platform: |
Size: 946176 |
Author:fangms5 |
Hits:
Search - histogram similarity measure