An unsupervised method for clustering images based on their salient regions of interest.
Gustavo B. BorbaHumberto R. GambaOge MarquesLiam M. MayronPublished in: ACM Multimedia (2006)
Keyphrases
- region of interest
- clustering method
- unsupervised learning
- synthetic and real images
- segmentation method
- k means
- similarity metric
- image set
- fully automatic
- three dimensional
- unsupervised manner
- salient features
- dissimilarity measure
- segmentation algorithm
- input data
- ground truth
- similarity measure
- pairwise
- image classification
- edge detection
- denoising
- image matching
- test images
- image processing
- salient regions
- cluster validation
- unsupervised feature selection
- salient points
- unsupervised clustering
- pixel level
- image analysis
- image data
- pixel values
- principal components
- image features
- input image
- medical images