April 2015
Intermediate to advanced
128 pages
3h 45m
English
1.1 Visualized example of a visual dictionary 10
2.1 Influences of different contextual and Mean Shift scales 23
2.2 Proposed descriptor for CASL detectors 24
2.3 Results of learning-based CASL detection 26
2.4 Examples from the UKBench retrieval benchmark database 28
2.5 Examples from the Caltech101 object categorization database 29
2.6 Repeatability comparison in detector repeatability sequence 32
2.7 CASL performance comparison in near-duplicated image retrieval 34
2.8 Categorization confusion matrix in 10 categories from Caltech101 (I) 36
2.9 Categorization confusion matrix in 10 categories from Caltech101 (II) 36
3.1 Visual word distribution in a 2-layer, 12-level vocabulary tree 43
3.2 Feature-Frequency statistics (the ...