1 / 37

Computer Graphics and Image Processing (CIS-601)

Computer Graphics and Image Processing (CIS-601). Image Segmentation by Clustering (Using Mahalanobis Distance). - Manjit Chintapalli. What is Image Segmentation ?. To humans, an image is not just a random collection of pixels; it is a meaningful arrangement of regions and objects.

villagomeze
Download Presentation

Computer Graphics and Image Processing (CIS-601)

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Computer Graphics and Image Processing (CIS-601)

  2. Image Segmentation by Clustering (Using Mahalanobis Distance) - Manjit Chintapalli

  3. What is Image Segmentation ? • To humans, an image is not just a random collection of pixels; it is a meaningful arrangement of regions and objects. • There also exits a variety of images: natural scenes, paintings, etc. Despite the large variations of these images, humans have no problem to interpret them.

  4. Image Segmentation ? (Contd..) • Image segmentation is the first step in image analysis and pattern recognition. • It is a critical and essential component of image analysis system, is one of the most difficult tasks in image processing, and determines the quality of the final result of analysis.

  5. The Process… • Image segmentation is the process of dividing an image into different regions such that each region is homogeneous.

  6. Image Segmentation methods

  7. Image segmentation methods can be categorized as follows (this is not an exhaustive list): • Histogram thresholding • Edge-based approaches • Region-based approaches • Hybrid: consider both edges and regions.

  8. Continued… • Segmentation of texture by PCA • Segmentation of texture with moments

  9. Color Image Segmentation • Image segmentation based on color • We use clustering to segment an image according to color features

  10. Clustering ? • Clustering is a common step to get a segmentation • In the data space, clusters are regarded as regions of similar data points

  11. Clustering…. Similar data points grouped together into clusters.

  12. Clustering… Most popular clustering algorithms suffer from two major drawbacks • First, the number of clusters is predefined, which makes them inadequate for batch processing of huge image databases • Secondly, the clusters are represented by their centroid and built using an Euclidean distance therefore inducing generally an hyperspheric cluster shape, which makes them unable to capture the real structure of the data. • This is especially true in the case of color clustering where clusters are arbitrarily shaped

  13. Clustering Algorithms • K-means • K-medoids • Hierarchical Clustering • There are many other algorithms used for clustering.

  14. K-means Clustering Algorithm Step 1: Choose K cluster centers: c¹(1),c² (1),c³(1)….. Step 2: At the kth iterative step distribute the samples among the K cluster domains, using the relation for all x in S(j), if |x – Cj (k)| < |x – Cj (k)| Step 3: Compute the new cluster centers

  15. Algorithm continued … Step 4: If the algorithm has converged and the procedure is terminated. Otherwise go to Step 2 S(j): contains data points in RGB space x: is the data point in an iteration C(j): is the center of the cluster

  16. How the problem was approached ? • First the images are read from the directory. • Then each image is transformed into a 3-D RGB space. • K-means clustering using Mahanalobis distance and Euclidean distance was applied.

  17. Continued….. • Next, the mean color of each cluster is calculated. • Then it is transformed back from 3-D space. • Result : Segmented image

  18. Mahalanobis Distance • M.D. is a very useful way of determining the ”similarity” of a set of values from an ”unknown”: sample to a set of values measured from a collection of ”known” samples • Superior to Euclidean distance because it takes distribution of the points (correlations) into account • Traditionally to classify observations into different groups

  19. Mahalanobis vs. other classical statistical approaches • It takes into account not only the average value but also its variance and the covariance of the variables measured • It compensates for interactions (covariance) between variables • It is dimensionless

  20. Mahalanobis Distance • Dt(x) = (x – mt) S-1t (x – mt)` Mahalanobis Distance

  21. Euclidean Distance • The Euclidean distance is the straight-line distance between two pixels • Euc dist = √((x1 - x2)² + (y1 - y2)²) , where (x1,y1) & (x2,y2) are two pixel points or two data points

  22. After executing the program… Original Images

  23. More images…

  24. During execution… • The images are transformed into 3-D RGB space • K-means clustering is applied which groups data points with similar color into clusters Example:

  25. Continued… • The data points with minimum mahalanobis distance are grouped together into clusters. • After grouping into clusters, the mean color of the cluster is taken and mapped back into the image

  26. Continued… • The program was executed with different number of clusters • The same program was run with Euclidean distance for distance between data points

  27. Segmented Images

  28. Original Image Segmented with 4 clusters Segmented with 6 clusters

  29. 2 clusters Original Image 4 Clusters 6 Clusters

  30. Original Image 2 Clusters 4 Clusters 6 Clusters

  31. Mahalanobis vs. Euclidean

  32. Original Image 4 clusters Mahalanobis 4 clusters Euclidean

  33. Original Image 6 Clusters Mahalanobis 6 Clusters Euclidean

  34. Original Image 6 Clusters Mahalanobis 6 Clusters Euclidean

  35. Mahalanobis vs. Euclidean Result : Using Euclidean distance in the k-means clustering proved to be better than Mahalanobis distance.

  36. Conclusion • The program runs with all jpeg images and takes a lot of time to run for larger images • This is due to the calculation of the inverse of the covariance matrix for the mahalanobis distance • The results show that Image segmentation using Mahalanobis distance works but, not better than Euclidean distance

  37. The End

More Related