Name
Abstract | ||
|---|---|---|
Most successful object recognition systems are based on a visual alphabet of quantised gradient orientations. Here, we introduce two richer image feature alpha- bets for use in object recognition. The two alphabets are evaluated using the PASCAL VOC challenge 2007 dataset. The results show that both alphabets perform as well as or better than the 'standard' gradient orien- tation based one. |
Year | DOI | Venue |
|---|---|---|
2008 | 10.1109/ICPR.2008.4761173 | ICPR |
Keywords | Field | DocType |
feature extraction,gradient methods,object recognition,quantisation (signal),PASCAL VOC 2007 dataset,image feature alphabet,object recognition,quantised gradient orientation,visual alphabet | Histogram,Computer science,Artificial intelligence,Computer vision,Pattern recognition,Visualization,Feature extraction,Speech recognition,Mutual information,Quantization (signal processing),Alphabet,Encoding (memory),Cognitive neuroscience of visual object recognition | Conference |
ISSN | Citations | PageRank |
1051-4651 | 1 | 0.38 |
References | Authors | |
6 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Martin Lillholm | 1 | 256 | 21.72 |
| Lewis D. Griffin | 2 | 381 | 45.96 |