1 / 17

Segmentation of Images By Color

Segmentation of Images By Color. Using K-means Clustring Algorithm. Presentation by Aviv Peled Ofir Nijinsky Introduction to Computational and Biological Vision 2012 Ben Gurion University of The Negev. Your Text Here. Segmentation. Segmentation is ill-defined.

hye
Télécharger la présentation

Segmentation of Images By Color

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. Segmentation of Images By Color Using K-means Clustring Algorithm Presentation by Aviv Peled Ofir Nijinsky Introduction to Computational and Biological Vision 2012 Ben Gurion University of The Negev Your Text Here

  2. Segmentation Segmentation is ill-defined In specific cases segmentation can be easy and useful

  3. Example of a Restricted World Segmentation by colors is very effective A good segmentation is a crucial step in a Fruit Ninja Solver

  4. Goals and Ideas • Using k-means clustering algorithm to get a segmentation by color of an image from fruit ninja • Trying to get a good segmentation • Minimizing human interaction

  5. K-Means Clustering of Pixel Colors Mapping pixels to the RGB color space The “actual” k should be known in advance

  6. Segmentation Example The result could be better… 

  7. Estimating The K Parameter Too big k parameter decreases the minimal distance between centers

  8. Running The Algorithm The estimation of k is pretty close! But the problem from the previous slide persists

  9. Importance of Representations

  10. לֹColor Representation What would be a good representation for our needs?

  11. Running the Algorithm in HSV Original Optimal Result

  12. Running the Algorithm in RGB Original Optimal Result

  13. Running the Algorithm in HSV Original Optimal Result

  14. Running the Algorithm in RGB Original Optimal Result

  15. Running the Algorithm in RGB Original Optimal Result

  16. Why Use RGB? Is HSV the ultimate answer?

  17. Why Use RGB? RGB HSV

More Related