Learning object detection from a small number of examples: The importance of good features

Kobi Levi*, Yair Weiss

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

338 Scopus citations

Abstract

Face detection systems have recently achieved high detection ratesand real-time performance. However, these methods usually rely on a huge training database (around 5,000 positive examples for good performance). While such huge databases may be feasible for building a system that detects a single object, it is obviously problematic for scenarios where multiple objects (or multiple views of a single object) need to be detected. Indeed, even for multiview face detection the performance of existing systems is far from satisfactory. In this work we focus on the problem of learning to detect objects from a small training database. We show that performance depends crucially on the features that are used to represent the objects. Specifically, we show that using local edge orientation histograms (EOH) as features can significantly improve performance compared to the standard linear features used in existing systems. For frontal faces, local orientation histograms enable state of the an performance using only a few hundred training examples. For profile view faces, local orientation histograms enable learning a system that seems to outperform the state of the an in real-time systems even with a small number of training examples.

Original languageAmerican English
Pages (from-to)II53-II60
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2
StatePublished - 2004
EventProceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2004 - Washington, DC, United States
Duration: 27 Jun 20042 Jul 2004

Fingerprint

Dive into the research topics of 'Learning object detection from a small number of examples: The importance of good features'. Together they form a unique fingerprint.

Cite this