Thesis: Some Results
Here are some results from current progress in my thesis at RIT. I have implemented the base boundary fragment model (Opelt 2006) and integrated it with graph cut segmentation (Boykov 2001). The graph cut segmentation’s energy function is based on:
- Boundary term:
- Distance from matching boundary fragments and image edges
- Region term:
- Matching of pixels to a color histogram of the individual object; the histogram is built from an initial estimate of the object’s region, e.g. from motion segmentation
Here are some images demonstrating the segmentations achieved. Note that the segmentation does use color information, even though these segmentation images are grayscale.
The image above shows two segmentations of a cow, using different parameterizations of the Canny edge detector. The left column shows the two segmentations. The upper right shows the image background, and the lower right shows the output of the Canny edge detector for the lower left segmentation.