Clustering of Features - matlab

I have multiview video dataset and I have extracted the features by using IDT (Improved Dense Trajectory Method). Dictionary of features is created using Vl_fisher method. Now, each row corresponds to a video and each column corresponds to a feature associated with each video. I want to apply clustering method to cluster the features but when I apply kmeans, spectral clustering I get the index of videos(rows) corresponding to each cluster but instead I want to know which feature corresponds to which cluster? Can anybody suggest any method. I am using Matlab for my work.

Related

how can i use surf feature in hierarchical clustering

First,Is it true to extract surf feature and use them in clustering? I want to cluster similar objects in images ?(each image contain one object)
If yes,how is it possible.
I extract features like this:
I = imread('cameraman.tif');
points = detectSURFFeatures(I);
[features, valid_points] = extractFeatures(I, points);
features is not a vector and is a matrix.Also number of points extracted by 'detectSURFFeatures' differ in different images.
how should features use?
First, you are detecting SURF features, not SIFT features (although they serve the same basic purpose). The reason you get multiple SURF features is that SURF is a local image feature, i.e. it describes only a small portion of the image. In general, multiple features will be detected in a single image. You probably want to find a way to combine these features into a single image descriptor before clustering.
A common method for combining these features is Bag-of-words.
Since it seems you are doing unsupervised learning, you will first need to learn a codebook. A popular method is to use k-means clustering on all the SURF features you extracted in all of your images.
Use these clusters to generate a k-dimensional image descriptor by creating a histogram of "codeword appearances" for each image. In this case there is one "codeword" per cluster. A codeword is said to "appear" each time a SURF feature belongs to its associated cluster.
The histogram of codewords will act as an image descriptor for each image. You can then apply clustering on the image descriptors to find similar images, I recommend either normalizing the image descriptors to have constant norm or using the cosine similarity metric (kmeans(X,k,'Distance','cosine') in MATLAB if you use k-means clustering).
That said, a solution which is likely to work better is to extract a deep feature using a convolutional neural network that was trained on a very large, diverse dataset (like ImageNet) then use those as image descriptors.

Incorporating new articles in tfidf vector for online clustering

I am building an Online news clustering system using Lucene and Mahout libraries in java. I intend to use vector space model and tfidf weights for Kmeans(or fuzzy/streamKmeans). My plan is : Cluster initial articles,assign new article to the cluster whose centroid is closest based on a small distance threshold. The leftover documents that aren’t associated with any old clusters form new data(new topics). Separately cluster them among themselves and add these temporary cluster centroids to the previous centroids. Less frequently, execute the full batch clustering to recluster the entire set of documents. The problem arises in comparing a new article to a centroid to assign it to an old cluster. The centroid dimension is number of distinct words in initial data. But the dimension of new article is different. I am following the book Mahout in Action. Is there any approach or some sort of feature extraction to handle this. The following similar links still remain unanswered:
https://stats.stackexchange.com/questions/41409/bag-of-words-in-an-online-configuration-for-classification-clustering
https://stats.stackexchange.com/questions/123830/vector-space-model-for-online-news-clustering
Thanks in advance
Increase the dimensionality as desired, using 0 as new values.
From a theoretical point of view, consider the vector space as infinite dimensional.

Time n-dimensional series clustering matlab

I have a set of time-sequences, every sequence is made of several frames, every frame is represented by an n-dimensional array of features.
I'd like to do DTW and K-means clustering on the set, I tried looking up for resources on the web with very little success. Do you have suggestions on how I could approach the problem or if there are already implemented algorithms available?

Interpreting the result of StreamingKMeans in mahout 0.8

What I want to achieve is simply find out which input points are included in a given cluster!?
I have a personal dataset which contains some documents that are grouped in 12 clusters manually.
I know how to interpret kmenas result in mahout .7 with using namedVector class and one of dumpers (like clusterdumper). after clustering using kmeans driver, a directory named clusteredPoints has created which contains clustering result and using clusterDumper, you can see the created clusters and the points that are in each one. in below link there is a good solution for this :
How to read Mahout clustering output
But, as I mentioned in title I want to have this capability to interpret Streaming Kmeans result which is a new feature in mahout .8.
In this feature, it uses a Centroid class for holding data points and each cluster seeds. The generated result of StreamingKMeans algorithm is only a sequence file which is constructed of centroid vectors + keys and weights of each cluster. And in this output there is no information of input data points to know the distribution of them between clusters. However, it is not possible to me to get a sense of accuracy of clustering.
by the way, How to get this information in clustering output ? It is not implemented or just I failed to find and use prepared soulution? How can I analysis the result of streamingKMeans?
thanks.

Ideas for extracting features of an object using keypoints of image

I'll be appreciated if you help me to create a feature vector of an simple object using keypoints. For now, I use ETH-80 dataset, objects have an almost blue background and pictures are took from different views. Like this:
After creating a feature vector, I want to train a neural network with this vector and use that neural network to recognize an input image of an object. I don't want make it complex, input images will be as simple as train images.
I asked similar questions before, some one suggested using average value of 20x20 neighborhood of keypoints. I tried it, It seems it's not working with ETH-80 images, because of different views of images. It's why I asked another question.
SURF or SIFT. Look for interest point detectors. A MATLAB SIFT implementation is freely available.
Update: Object Recognition from Local Scale-Invariant Features
SIFT and SURF features consist of two parts, the detector and the descriptor. The detector finds the point in some n-dimensional space (4D for SIFT), the descriptor is used to robustly describe the surroundings of said points. The latter is increasingly used for image categorization and identification in what is commonly known as the "bag of word" or "visual words" approach. In the most simple form, one can collect all data from all descriptors from all images and cluster them, for example using k-means. Every original image then has descriptors that contribute to a number of clusters. The centroids of these clusters, i.e. the visual words, can be used as a new descriptor for the image. The VLfeat website contains a nice demo of this approach, classifying the caltech 101 dataset:
http://www.vlfeat.org/applications/apps.html#apps.caltech-101