A Binary Descriptor Invariant to Rotation and Robust to Noise (BIRRN) for Floor Recognition.
J. A. de Jesús Osuna-CoutiñoJosé Martínez-CarranzaPublished in: MCPR (2019)
Keyphrases
- image transformations
- affine distortion
- object recognition
- image matching
- invariant features
- geometric transformations
- geometric distortions
- noisy environments
- recognition rate
- rotation invariant
- keypoints
- recognition accuracy
- affine transformation
- action recognition
- image noise
- feature extraction
- partial occlusion
- highly discriminative
- feature points
- affine transform
- feature descriptors
- robust recognition
- noise level
- rotation invariance
- discriminatory power
- illumination change
- illumination invariance
- texture descriptors
- illumination variations
- affine invariant
- recognition algorithm
- shape recognition
- scale invariant feature transform
- fourier domain
- image structure
- shape descriptors
- signal to noise ratio
- preserving transformations
- tchebichef moments
- d objects
- salt pepper
- feature vectors