| Sun, Yu: Ph.D. student School of Computing, University of Utah |
|
|
|
|
|
|
|
|
|
|
|
Fingernail has a curly surface. So the analysis of the coloration changes in the fingernail has to be carried out in 3D. Currently there are many registration methods relying on naturally present features, such as edges, corners or texture. However, the fingernail is relative featureless and some features, related to color, change with force.
Pairing of those features with neighborhood correlation gives a great number of outliers (wrong pairs). We currently use RANSAC to find the inlier pairs and use those pairs to calculate the tranform matrix.
The 3D model of the fingernail is obtained with Bumblebee Stereo cameras from Point Grey Research.
|
|
The left is a new image and right is the normal image. The algorithm will register the new image to the normal image.
|
|
|
Use Harris feature point detection algorithm to automatically detect feature points in both source image and target image. The mapping pairs are identified with neightbor correlation.
|
|
|
Use RANSAC algorithm to eliminate the outliers.
|
|
|
The left image is the registration result. The left is the overlapping of registration result and the normal image.
|
| Journals | Conferences | Papers | Labs | Other Links |