A general framework for object detection
C. Papageorgiou, M. Oren, Tomaso Poggio · International Conference on Computer Vision · 2002
This paper presents a general trainable framework for object detection in static images of cluttered scenes. The detection technique we develop is based on a wavelet representation of an object class derived from a statistical analysis of the class instances. By learning an object class in terms of a subset of an overcomplete dictionary of wavelet basis functions, we derive a compact representation of an object class which is used as an input to a support vector machine classifier. This representation overcomes both the problem of in-class variability and provides a low false detection rate in unconstrained environments. We demonstrate the capabilities of the technique in two domains whose inherent information content differs significantly. The first system is face detection and the second is the domain of people which, in contrast to faces, vary greatly in color, texture, and patterns. Unlike previous approaches, this system learns from examples and does not rely on any a priori (hand-crafted) models or motion-based segmentation. The paper also presents a motion-based extension to enhance the performance of the detection algorithm over video sequences. The results presented here suggest that this architecture may well be quite general.
Cited by 1,438 works. doi:10.1109/iccv.1998.710772
Authors
References
- The Nature of Statistical Learning Theory
- A theory for multiresolution signal decomposition: the wavelet representation
- A training algorithm for optimal margin classifiers
- Training support vector machines: an application to face detection
- Original approach for the localisation of objects in images
- Probabilistic visual learning for object detection
- Feature extraction from faces using deformable templates
- Example Based Learning for View-Based Human Face Detection.
- Model-based vision: a program to see a walking person
- Human Face Detection in Visual Scenes