Title :
Novel image feature alphabets for object recognition
Author :
Lillholm, Martin ; Griffin, Lewis
Author_Institution :
Dept. of Comput. Sci., Univ. Coll. London, London, UK
Abstract :
Most successful object recognition systems are based on a visual alphabet of quantised gradient orientations. Here, we introduce two richer image feature alphabets 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 orientation based one.
Keywords :
feature extraction; gradient methods; object recognition; quantisation (signal); PASCAL VOC 2007 dataset; image feature alphabet; object recognition; quantised gradient orientation; visual alphabet; Computer science; Educational institutions; Encoding; Image edge detection; Labeling; Object recognition; Pipelines; Pixel; Quantization; Robustness;
Conference_Titel :
Pattern Recognition, 2008. ICPR 2008. 19th International Conference on
Conference_Location :
Tampa, FL
Print_ISBN :
978-1-4244-2174-9
Electronic_ISBN :
1051-4651
DOI :
10.1109/ICPR.2008.4761173
