This is an image similarity comparison script, which uses SVM classification to find the closest image in terms of features. The idea is that you have a corpus of training data on which you train your machine, and given a new image, the script should be able to find the closest image on the basis on features I use the SURF (feature) detector to identify features in images which are quantified by a 128 dimension vector.
-
Notifications
You must be signed in to change notification settings - Fork 0
abhijaigarg/ImgCompare
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Find the closest image in training dataset to test image
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published