Feature Descriptors/Vectors
- Feature descriptors encode interesting information into a series of numbers and act as a sort of numerical “fingerprint” that can be used to differentiate one feature from another.
- Ideally this information would be invariant under image transformation, so we can find the feature again even if the image is transformed in some way.
BRISK descriptor – BRISK sampling pattern
BRISK descriptor – example of matching points using BRISK
Efficient Descriptors
DAISY
SURF (Speeded Up Robust Features)
U-SURF
Compact Binary Descriptors
LBP (Local Binary Patterns)
BRIEF
D-BRIEF
ORB (Oriented FAST and Rotated BRIEF)
BRISK (Binary Robust Invariant Scalable Keypoints)
FREAK (Fast Retina Keypoint)
CARD (Compact and Realtime Descriptor)
LDB (Local DIfference Binary)
More Robust Descriptors
LIOP (Local Intensity Order Pattern for Feature Descriptor)
Learned Descriptors
Winder & Brown
Descriptor Learning Using Convex Optimisation
Learning Spatial Pooling Regions
References:
- Modern features-part-2-descriptors
- “Introduction to Feature Descriptors in Vision: From Haar to SIFT,” A Presentation from Author Scott Krig
- What is a feature descriptor in image processing (algorithm or description)? – stack overflow
- A tutorial on binary descriptors – part 4 – The BRISK descriptor
- A tutorial on binary descriptors – part 2 – The BRIEF descriptor
- 776 Computer Vision Jan-Michael Frahm, Enrique Dunn Spring 2013.
- LDB: An Ultra-Fast Feature for Scalable Augmented Reality on Mobile Devices
- Local Intensity Order Pattern for Feature Description
Deep Learning KEYSCORE 