Combining Descriptors Extracted from Feature Maps of Deconvolutional Networks and SIFT Descriptors in Scene Image Classification.
Dung A. DoanNgoc-Trung TranDinh-Phong VoBac LeAtsuo YoshitakaPublished in: ICCSA (5) (2013)
Keyphrases
- sift descriptors
- image classification
- visual words
- feature maps
- bag of features
- densely sampled
- image features
- bag of words
- image search
- keypoints
- discriminative power
- image representation
- visual features
- image matching
- feature extraction
- video sequences
- feature vectors
- sparse coding
- object recognition
- saliency map
- computer vision
- feature space
- self organizing maps
- action recognition
- feature representation
- machine learning
- neural network
- texture classification
- kernel function
- input image
- low level
- keywords
- image sequences