Title :
Generic Feature Extraction for Image/Video Analysis
Author_Institution :
Philips Res. Labs., Eindhoven
Abstract :
This paper presents a generic algorithm for extracting invariant salient features from images and video sequences. The detected features/regions are invariant under viewpoint variations and illumination changes. Repeatability rate is used for evaluating the invariance of the feature detector. We also apply our feature detector on object recognition experiments. Experimental results show our proposed algorithm is very effective for recognizing objects in images/video with viewpoint changes and background variations
Keywords :
feature extraction; image sequences; object recognition; video signal processing; generic algorithm; image sequence; invariant salient feature extraction; object recognition; video sequence; Computer vision; Detectors; Entropy; Feature extraction; Image analysis; Neural networks; Object detection; Object recognition; Robustness; Sampling methods; Entropy; Feature Extraction; Repeatability; Salient Regions;
Conference_Titel :
Consumer Electronics, 2006. ISCE '06. 2006 IEEE Tenth International Symposium on
Conference_Location :
St. Petersburg
Print_ISBN :
1-4244-0216-6
DOI :
10.1109/ISCE.2006.1689407
