Rapid object detection using a boosted cascade of simple features

@article{Viola2001RapidOD,
  title={Rapid object detection using a boosted cascade of simple features},
  author={Paul A. Viola and Michael J. Jones},
  journal={Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001},
  year={2001},
  volume={1},
  pages={I-I}
}
  • Paul A. Viola, Michael J. Jones
  • Published 8 December 2001
  • Computer Science
  • Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001
This paper describes a machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates. [] Key Method 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.

Figures from this paper

Learning object detection from a small number of examples: the importance of good features
  • K. Levi, Yair Weiss
  • Computer Science
    Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.
  • 2004
TLDR
This work shows that using local edge orientation histograms (EOH) as features can significantly improve performance compared to the standard linear features used in existing systems and enables learning a system that seems to outperform the state of the art in real-time systems even with a small number of training examples.
Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection
TLDR
A novel set of rotated haar-like features is introduced that significantly enrich the simple features of [6] and can also be calculated efficiently and present a through analysis of different boosting algorithms and weak classifiers on the detection performance and computational complexity.
Parts-based object detection using multiple views
TLDR
This thesis extends the approach of parts-based object detection to include support for multiple viewing angles, and uses Bayesian networks to integrate the parts detection of each view in a flexible manner.
Face Detection Using a Boosted Cascade of Features Using OpenCV
TLDR
This work proposes a learning algorithm, based on AdaBoost, which selects a small number of critical visual features from a larger set and yields extremely efficient classifiers which allows background regions of the image to be quickly discarded while spending more computation on promising face like regions.
The power of feature clustering: An application to object detection
TLDR
A fast rejection scheme that is based on image segments that is simple and fast to be learned, thus making it an excellent pre-processing step to accelerate standard machine learning classifiers, such as neural-networks, Bayes classifiers or SVM.
Receptive field cooccurrence histograms for object detection
  • S. Ekvall, D. Kragic
  • Computer Science
    2005 IEEE/RSJ International Conference on Intelligent Robots and Systems
  • 2005
TLDR
The specific goal in this paper is the development of an online learning scheme that is effective after just one training example but still has the ability to improve its performance with more time and new examples.
Low-Level Image Features for Real-Time Object Detection
TLDR
This chapter describes several image feature extractors used in real-time object detection and in detail discusses the novel features based on local ranks.
Contour-based learning for object detection
TLDR
The major contributions are the application of boosted local contour-based features for object detection in a partially supervised learning framework, and an efficient new boosting procedure for simultaneously selecting features and estimating per-feature parameters.
Face Detection and Recognition Using Recorded Video's
TLDR
The goal of paper is to described the recorded video face detection by manipulating the machine and image processing with learning, algorithm based on Paul Viola and Michael Jones, which is method for combining increasingly more complex classifiers in a "cascade" which allows background regions of the image to be quickly discarded while spending more computation on promising object-like regions.
Local Feature Detection using Neural Networks
TLDR
The bag-of-words model is used to implement an image retrieval application, in order to determine how the methods perform in practice, and shows that, in some cases, neural networks can outperform traditional methods.
...
...

References

SHOWING 1-10 OF 25 REFERENCES
A general framework for object detection
TLDR
A general trainable framework for object detection in static images of cluttered scenes based on a wavelet representation of an object class derived from a statistical analysis of the class instances and a motion-based extension to enhance the performance of the detection algorithm over video sequences is presented.
Training support vector machines: an application to face detection
  • E. Osuna, R. Freund, F. Girosi
  • Computer Science
    Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 1997
TLDR
A decomposition algorithm that guarantees global optimality, and can be used to train SVM's over very large data sets is presented, and the feasibility of the approach on a face detection problem that involves a data set of 50,000 data points is demonstrated.
A statistical method for 3D object detection applied to faces and cars
  • H. Schneiderman, T. Kanade
  • Computer Science
    Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662)
  • 2000
TLDR
Using this method, this work has developed the first algorithm that can reliably detect human faces with out-of-plane rotation and the first algorithms thatCan reliably detect passenger cars over a wide range of viewpoints.
Example-Based Learning for View-Based Human Face Detection
TLDR
An example-based learning approach for locating vertical frontal views of human faces in complex scenes and shows empirically that the distance metric adopted for computing difference feature vectors, and the "nonface" clusters included in the distribution-based model, are both critical for the success of the system.
Statistical Pattern Recognition
  • J. Davis
  • Computer Science
    Technometrics
  • 2003
This chapter introduces the subject of statistical pattern recognition (SPR). It starts by considering how features are defined and emphasizes that the nearest neighbor algorithm achieves error rates
Neural Network-Based Face Detection
TLDR
A neural network-based face detection system that arbitrates between multiple networks to improve performance over a single network using a bootstrap algorithm, which eliminates the difficult task of manually selecting non-face training examples.
Joint Induction of Shape Features and Tree Classifiers
TLDR
A very large family of binary features for two-dimensional shapes determined by inductive learning during the construction of classification trees is introduced, which makes it possible to narrow the search for informative ones at each node of the tree.
Summed-area tables for texture mapping
  • F. Crow
  • Environmental Science
    SIGGRAPH '84
  • 1984
TLDR
Texture-map computations can be made tractable through use of precalculated tables which allow computational costs independent of the texture density, and the cost and performance of the new technique is compared to previous techniques.
Pattern Recognition
...
...