This paper presents a Weak Classifier that is extremely fast to compute, yet highly discriminant. This Weak Classifier may be used in, for example, a boosting framework and is the result of a novel way of organizing and evaluating Histograms of Oriented Gradients. The method requires only one access to main memory to evaluate each feature, in comparison with the more well-known Haar features which require somewhere between six and nine memory accesses to evaluate each feature. This low memory bandwidth makes the Weak Classifier especially ideal for use in small systems with little or no memory cache available. The presented Weak Classifier has been extensively tested in a boosted framework on data sets consisting of pedestrians and various road signs. The classifier yields detection results that are far superior than the results obtained from Haar features when tested on road signs and similar structures, whereas the detection results are comparable to those of Haar features when tested on pedestrians. In addition, the computational resources necessary for these results have been shown to be considerably smaller for the new weak classifier.
The histogram feature - a resource-efficient Weak Classifier
2008 IEEE Intelligent Vehicles Symposium ; 678-683
2008-06-01
940122 byte
Conference paper
Electronic Resource
English
The Histogram Feature - a Resource-Efficient Weak Classifier
British Library Conference Proceedings | 2008
|Efficient Color Histogram Indexing
British Library Conference Proceedings | 1994
|On the Importance of Accurate Weak Classifier Learning for Boosted Weak Classifiers
British Library Conference Proceedings | 2008
|A Gabor Feature Classifier for Face Recognition
British Library Conference Proceedings | 2001
|