Shape-included label-consistent discriminative dictionary learning: An approach to detect and segment multi-class objects in images.
Mahdi MarsousiXingyu LiKonstantinos N. PlataniotisPublished in: ICIP (2016)
Keyphrases
- multi class
- dictionary learning
- object category recognition
- classifier training
- image classification
- sparse coding
- sparse representation
- support vector machine
- input image
- feature selection
- object detection
- pairwise
- keypoints
- linear classifiers
- probabilistic boosting tree
- test images
- image regions
- small number
- image annotation
- multi class classification
- object recognition
- bounding box
- image features
- discriminative power
- model selection
- natural images
- d objects
- object categories
- prior knowledge
- support vector
- data sets