Computer Vision: Difference between revisions
Created page with "Notes from the [https://www.udacity.com/course/introduction-to-computer-vision--ud810 Udacity Computer Vision Course] taught by Georgia Tech professors. ==Segmentation== ===M..." |
|||
Line 3: | Line 3: | ||
==Segmentation== | ==Segmentation== | ||
===Mean Shift Segmentation=== | ===Mean Shift Segmentation=== | ||
# For every pixel (or a sample of pixels) in the image calculate some features such as (u,v)-color or (x,y, u, v) where xy are coordinates and uv are chroma. | |||
# For each sampled pixel, or region of interest, calculate the new ''center-of-mass'', or weighted-mean. The weights are typically Gaussian based on distance to the center. Repeat until convergence. | |||
# The regions will cluster into modes. All regions which cluster to the same position are in the same ''attraction basin''. | |||
Attraction basin: the region for which all trajectories lead to the same mode. | |||
;Pros | |||
* Automatically finds basin of attraction. | |||
* Only one parameter: Window size for region of interest. | |||
* Does not assume any shape on cluster. | |||
;Cons | |||
* Need to pick a window size. | |||
* Doesn't scale well for high dimensions. |
Revision as of 14:13, 16 September 2020
Notes from the Udacity Computer Vision Course taught by Georgia Tech professors.
Segmentation
Mean Shift Segmentation
- For every pixel (or a sample of pixels) in the image calculate some features such as (u,v)-color or (x,y, u, v) where xy are coordinates and uv are chroma.
- For each sampled pixel, or region of interest, calculate the new center-of-mass, or weighted-mean. The weights are typically Gaussian based on distance to the center. Repeat until convergence.
- The regions will cluster into modes. All regions which cluster to the same position are in the same attraction basin.
Attraction basin: the region for which all trajectories lead to the same mode.
- Pros
- Automatically finds basin of attraction.
- Only one parameter: Window size for region of interest.
- Does not assume any shape on cluster.
- Cons
- Need to pick a window size.
- Doesn't scale well for high dimensions.