A Wrapper-Based Approach to Image Segmentation and Classification

1. A Wrapper-Based Approach to Image Segmentation and Classification Michael E. Farmer, Member, IEEE, and Anil K. Jain, Fellow, IEEE

2. 大綱 • Introduction • Overview of the approach • Experiment: Vision-Base airbag suppression application • Experimental result

3. Introduction

4. Traditional processing • The traditional processing flow for image-based pattern recognition consists of image segmentation followed by classification.

5. Three limitations of traditional processing • The object of interest “should be uniform and homogeneous with respect to some characteristic” and “adjacent regions should be differing significantly” • There are few metrics available for evaluating segmentation algorithms • Inability to adapt to real-world changes

6. The contributions in this paper • Developing a closed-loop framework for image segmentation to find the best segmentation for a given class of objects by using the shape of the object for classification of the segmented object • Using the probability of correct classification of the object to provide an “objective evaluation of segmented outputs” • The system can adapt to “real-world changes.”

7. Overview of the approach

8. Wrapper-Based Approach • Wrap the segmentation and the classification together, and use the classifier as the metric for selecting the best segmentation. • Using the classifier to intelligently re-assemble to solve over-segmented problem. • The classification is correct when the minimum distance between the classification of the candidate segmentation and one of the desired pattern classes < T

9. Traditional vs Wrapper-Base

10. Experiment: Vision-Base airbag suppression application

11. Problem Infant or Adult

12. Challenges • Nonuniform illumination • Poor image contrast • Shadows and highlights • Occlusions • Sensor noise • Background clutter

13. Variability for the infant class

14. Variability for the infant class

15. Proposed approach

16. Preliminary Segmentation • Reduce the number of blobs that must be processed. • Once the correlation value for each region is determined, an adaptive threshold is applied, and any region that falls below the threshold is considered a part of the foreground.

17. Preliminary Segmentation

18. Preliminary Segmentation

19. RegionLabeling • Using the EM algorithm with a fixed number of components, and then rely on the classification accuracy to determine if more components are required. • Merging the very small blobs by mode filter • Merging any regions that are smaller then 20 pixels in size with their larger neighbors

20. RegionLabeling Results

21. RegionLabeling Results

22. Blob Combiner • We have framed the blob combiner problem as one of blob selection, where there exists a subset of blobs that will provide the highest classification accuracy for a given pattern class • Forward selection mode • Backward selection mode

23. Blob Combiner( plus-L, minus-R algorithm )

24. Blob Combiner ( plus-L, minus-R algorithm )

25. Feature Extraction

26. Feature Extraction

27. Acceleration Methods for Feature Extraction: • Precompute the moments for each blob • Compute the moments using only the local neighborhood of each blob. • Attain over a ten thousand-fold reduction in processing for each moment calculated.

28. : class - A points : class - B points : point with unknown class Feature 2 Circle of 1 - nearest neighbor The point is class B via 1-NNR. Feature 1 Classification of Blob Combinations • Using the nearest neighbor classifier to compute classification distance

29. Proposed approach

30. Demonstrating

31. Demonstrating

32. Demonstrating

33. EXPERIMENTAL RESULTS

34. EXPERIMENTAL RESULTS

35. Correct segmentations

36. Incorrect segmentation