Nokia Research Center Fast Interactive Image Segmentation by Discriminative Clustering Dingding Liu * Kari Pulli † Linda Shapiro * Yingen Xiong † † Nokia Research Center, Palo Alto, CA 94304, USA *Dept. Elect. Eng., University of Washington, WA 98095, USA 1
25
Embed
Fast Interactive Image Segmentation by Discriminative Clustering
Fast Interactive Image Segmentation by Discriminative Clustering. Dingding Liu * Kari Pulli † Linda Shapiro * Yingen Xiong † † Nokia Research Center, Palo Alto, CA 94304, USA *Dept. Elect. Eng., University of Washington, WA 98095, USA. Research Aim. - PowerPoint PPT Presentation
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Nokia Research Center
1
Fast Interactive Image Segmentation by Discriminative Clustering
Dingding Liu * Kari Pulli † Linda Shapiro * Yingen Xiong † † Nokia Research Center, Palo Alto, CA 94304, USA*Dept. Elect. Eng., University of Washington, WA 98095, USA
Nokia Research Center
2
Research Aim• Cut out an object from its background fast
• Computation time – so can quickly iterate• With as few strokes as possible
Nokia Research Center
3
Overview• Introduction
• Motivation • Related work
• Algorithm• Pre-segmentation by the Mean-Shift algorithm• Merge regions by discriminative clustering• Local neighborhood region classification and pruning
• Experiments and Results• Conclusions and Future Work
Nokia Research Center
4
Introduction• Motivation: Image editing on mobile devices
• Convenience• Anytime, anywhere
• Challenges• Limited computational resources• Smaller screens and imprecise input
Nokia Research Center
5
Related Work -Interactive Image Segmentation• Lazy Snapping
• Li et al., ACM Transactions on Graphics 2004
Nokia Research Center
6
Related Work -Interactive Image Segmentation• Interactive Image Segmentation by Maximal Similarity Based Region Merging
• Ning et al., Pattern Recognition 2010
Insufficient user inputs
Sufficient user inputs
Nokia Research Center
Algorithm: Summary
7
1. Pre-segmentation by the Mean-Shift algorithm2. Merge regions by discriminative clustering3. Local neighborhood region classification and
1. Choose a search window size2. Choose the initial location of the search window3. Compute the mean (centroid of the data) within the search window4. Center the search window at that mean location5. Repeat 3 and 4 until convergence
The mean shift algorithm seeks the“mode” or point of highest density of a data distribution
Nokia Research Center
Mean-Shift Segmentation
10
1. Convert the image into tokens (via color, gradients, texture measures, etc.)2. Choose initial search window locations uniformly in the data3. Compute the mean shift window location for each initial position4. Merge windows that end up on the same “peak” or mode5. Repeat 3 and 4 until convergence
Nokia Research Center
11
Mean-Shift Segmentation Results
Nokia Research Center
12
Algorithm: Pre-segmentation using Mean-Shift
• Three reasons for choosing the Mean-Shift algorithm:
Pre-segmentation can be done either before or after the user input
1. It preserves the boundaries better than other methods
2. Its speed has been improved significantly in recent years
3. Fewer parameters to tune
Nokia Research Center
13
Algorithm: Merge non-ambiguous regions
Create two kd-trees in CIELab color space• One for the marked foreground, another for the background regionsFor each unmarked region, find the color difference to• the most similar marked background db and foreground region df
Choice of dthresh :• Min difference of mean colors between the marked foreground and
background• that is higher than a minimum allowed distance (we chose 2)
Nokia Research Center
Algorithm: Assign ambiguous regions
14
Now use also location informationEach of the remaining ambiguous regions is assigned • the label of the neighboring region that has the most similar mean colorIf the most similar neighboring region is also an unmarked region• merge them to a new unmarked region, repeat the processIf there is a tie in the mean color for assignment to foreground and background• the label of the region that has the most similar color variance is used
Nokia Research Center
Algorithm: Prune / flip isolated regions
15
Find isolated foreground or background regions (use connected components)
Regions are changed to the opposite label when all of the following hold:
(a)The region is not marked by the user (b) The region is not the biggest region with that label (c) The region is smaller than its surrounding regions