Face Detection Using Combinations of Classifiers

Ramirez, Geovany A.; Fuentes, Olac

doi:10.1109/crv.2005.40

Cited by 6 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, Detection rate False Positives Jesorsky et al [5] 91.80% Not reported Kirchberg et al [6] 92.80% Not reported Hamouz et al [4] 91.30% Not reported Fröba and Ernst [3] 97.75% 25 Ramirez and Fuentes [14] 93.23% 2236 our system test 3 93.68% 432 we created our own multi-pose test set. Our test set consists of 45 color images with 60 profile faces and 101 frontal faces.…”

Section: Resultsmentioning

confidence: 99%

Multi-Pose Face Detection with Asymmetric Haar Features

Ramirez

Fuentes

2008

2008 IEEE Workshop on Applications of Computer Vision

View full text Add to dashboard Cite

In this paper we present a system for multi-pose face detection. Our system presents three main contributions. First, we introduce the use of asymmetric Haar features. Asymmetric Haar features provide a rich feature space, which allows to build classifiers that are accurate and much simpler than those obtained with other features. The second contribution is the use of a genetic algorithm to search efficiently in the extremely large parameter space of potential features. Using this genetic algorithm, we generate a feature set that allows to exploit the expressive advantage of asymmetric Haar features and is small enough to permit exhaustive evaluation. The third contribution is the application of a skin color-segmentation scheme to reduce the search space. Our system uses specialized detectors in different face poses that are built using AdaBoost and the C4.5 rule induction algorithm. Experimental results using the CMU profile test set and BioID frontal faces test set, in addition to our own multi-pose face test set, show that our system is competitive with other systems presented recently in the literature.

show abstract

Section: Resultsmentioning

confidence: 99%

Multi-Pose Face Detection with Asymmetric Haar Features

Ramirez

Fuentes

2008

2008 IEEE Workshop on Applications of Computer Vision

View full text Add to dashboard Cite

show abstract

“…Ramirez and Fuentes [46] propose combinations of different classifiers including: Na¨ve Bayes (NB), support vector machine (SVM), C4.5 rule induction and feedforward artificial neural network (ANN) to vote for the best face candidate. This complex system ended with high detection rate on BioID database of 95.13% but coupled with 7075 false positive face instances.…”

Section: Other Face Detection/recognition Systemsmentioning

confidence: 99%

Exploiting Voronoi diagram properties in face segmentation and feature extraction

Cheddad

Mohamad

Manaf

2008

Pattern Recognition

View full text Add to dashboard Cite

“…Proposed methodology use C4.5 classifier which is a decision tree algorithm [18]. It is used to classify the foreground and background image pixels of input multi-face image.…”

Section: Classificationmentioning

confidence: 99%

Efficient Face Detection Method using Modified Hausdorff Distance Method with C4.5 Classifier and Canny Edge Detection

Singh¹,

Pawar²,

Jain³

2015

IJCA

View full text Add to dashboard Cite

With the rapid growth of population and technology, security problems become a major issue due to abnormal human behaviors. Recently researches have been motivated towards automatic human face detection from still image or from moving image. Present human face detection system leads computation inaccuracies i.e. higher degree of false negative rate. In this paper, a multilevel hybrid model has been proposed for face detection. In the proposed work, we initially use C4.5 classifier so that foreground and background images can be differentiated, as a result of which search space can be reduced. After that skin color model has been applied to detect the skin region which is followed by canny edge detection to detect the edges of skin region. In the last step, we use the Modified Hausdorff Distance Method which matches the pixel values and detects the faces with lower false negative rate.

show abstract

Face Detection Using Combinations of Classifiers

Cited by 6 publications

References 7 publications

Multi-Pose Face Detection with Asymmetric Haar Features

Multi-Pose Face Detection with Asymmetric Haar Features

Exploiting Voronoi diagram properties in face segmentation and feature extraction

Efficient Face Detection Method using Modified Hausdorff Distance Method with C4.5 Classifier and Canny Edge Detection

Contact Info

Product

Resources

About