2001-robust-real-time-face-detection.md

title	authors	fieldsOfStudy	meta_key	numCitedBy	reading_status	ref_count	tags	urls	venue	year
Robust Real-Time Face Detection	Paul A. Viola Michael Jones	Computer Science	2001-robust-real-time-face-detection	11305	TBD	39	detection gen-from-ref paper	https://www.semanticscholar.org/paper/Robust-Real-Time-Face-Detection-Viola-Jones/b09ec0b350f8352bce46a2f5bf7ae97c83a7b9ca?sort=total-citations	Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001	2001

semanticscholar url

Robust Real-Time Face Detection

Abstract

This paper describes a face detection framework that is capable of processing images extremely rapidly while achieving high detection rates. There are three key contributions. The first is the introduction of a new image representation called the “Integral Image” which allows the features used by our detector to be computed very quickly. The second is a simple and efficient classifier which is built using the AdaBoost learning algorithm (Freund and Schapire, 1995) to select a small number of critical visual features from a very large set of potential features. The third contribution is a method for combining classifiers in a “cascade” which allows background regions of the image to be quickly discarded while spending more computation on promising face-like regions. A set of experiments in the domain of face detection is presented. The system yields face detection performance comparable to the best previous systems (Sung and Poggio, 1998; Rowley et al., 1998; Schneiderman and Kanade, 2000; Roth et al., 2000). Implemented on a conventional desktop, face detection proceeds at 15 frames per second.

Paper References

1. A general framework for object detection
2. Neural Network-Based Face Detection
3. Example-Based Learning for View-Based Human Face Detection
4. A SNoW-Based Face Detector
5. Training support vector machines - an application to face detection
6. Boosting Image Retrieval
7. A Computational Model for Visual Selection
8. A statistical method for 3D object detection applied to faces and cars
9. Joint Induction of Shape Features and Tree Classifiers
10. Boxlets - A Fast Convolution Algorithm for Signal Processing and Neural Networks
11. Statistical Pattern Recognition
12. Modeling Visual Attention via Selective Tuning
13. Overcomplete steerable pyramid filters and rotation invariance
14. Summed-area tables for texture mapping
15. The Design and Use of Steerable Filters
16. Boosting the margin - A new explanation for the effectiveness of voting methods
17. A decision-theoretic generalization of on-line learning and an application to boosting
18. Irrelevant Features and the Subset Selection Problem