Classification and Segmentation

6. Classification and Segmentation

Images are pre-filtered by Perona-Malik’s method, and then segmented/classified by the fast marching method. The critical points are detected by the anisotropic vector diffusion, and classified by peak-searching of the histogram. All methods used for classification, filtering, and segmentation are developed at the CVC, The University of Texas at Austin.

2D Result

Original image: slice #00
Original image: slice #00
Classification
Classification
Segmentation
Segmentation
Hand-picking result
Hand-picking result
Original image: slice #10
Original image: slice #10
Classification
Classification
Segmentation
Segmentation
Hand-picking result
Hand-picking result
Original image: slice #20
Original image: slice #20
Classification
Classification
Segmentation
Segmentation
Hand-picking result
Hand-picking result
Original image: slice #30
Original image: slice #30
Classification
Classification
Segmentation
Segmentation
Hand-picking result
Hand-picking result
Original image: slice #40
Original image: slice #40
Classification
Classification
Segmentation
Segmentation
Hand-picking result
Hand-picking result
Original image: slice #50
Original image: slice #50
Classification
Classification
Segmentation
Segmentation
Hand-picking result
Hand-picking result
Original image: slice #60
Original image: slice #60
Classification
Classification
Segmentation
Segmentation
Hand-picking result
Hand-picking result

3D Result