Effect of hough forests parameters on face detection performance: An empirical analysis

M. Hassaballah; Mourad Ahmed; H. A. Alshazly

doi:10.1109/ICCES.2014.7030924

Effect of hough forests parameters on face detection performance: An empirical analysis

M. Hassaballah, Mourad Ahmed, H. A. Alshazly

South Valley University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Face detection as one of the most challenging tasks in computer vision has received a lot of attention in recent decades due to its wide range of use in face based image analysis. In this paper, we propose an efficient approach for face detection that efficiently combines generalized Hough transform within random decision forests framework. In this approach, we train random decision forests that directly maps the image patch appearance to the probabilistic vote about the possible location of the face centroid; the detection hypotheses then correspond to the maxima of the Hough image. The random decision forests construction and prediction abilities depend on setting some parameters, which in turns affects the performance of the method. Therefore, the impact of these parameters that most influence the behavior of the forest for detecting faces is studied through experiments on the widely used CMU+MIT database. Moreover, a comparison with some published methods is presented.

Original language	English
Title of host publication	Proceedings of 2014 9th IEEE International Conference on Computer Engineering and Systems, ICCES 2014
Editors	Ayman M. Wahba, M. Watheq El-Kharashi, Mohamed Taher, Ayman M. Bahaa El-Din, Ahmed M. Zaki
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	35-40
Number of pages	6
ISBN (Electronic)	9781479965946
DOIs	https://doi.org/10.1109/ICCES.2014.7030924
State	Published - 3 Feb 2014
Externally published	Yes
Event	2014 9th IEEE International Conference on Computer Engineering and Systems, ICCES 2014 - Cairo, Egypt Duration: 22 Dec 2014 → 23 Dec 2014

Publication series

Name	Proceedings of 2014 9th IEEE International Conference on Computer Engineering and Systems, ICCES 2014

Conference

Conference	2014 9th IEEE International Conference on Computer Engineering and Systems, ICCES 2014
Country/Territory	Egypt
City	Cairo
Period	22/12/14 → 23/12/14

Keywords

Face Detection
Parameters Setting
Random Hough Forests

Access to Document

10.1109/ICCES.2014.7030924

Cite this

Hassaballah, M., Ahmed, M., & Alshazly, H. A. (2014). Effect of hough forests parameters on face detection performance: An empirical analysis. In A. M. Wahba, M. W. El-Kharashi, M. Taher, A. M. Bahaa El-Din, & A. M. Zaki (Eds.), Proceedings of 2014 9th IEEE International Conference on Computer Engineering and Systems, ICCES 2014 (pp. 35-40). Article 7030924 (Proceedings of 2014 9th IEEE International Conference on Computer Engineering and Systems, ICCES 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCES.2014.7030924

Hassaballah, M. ; Ahmed, Mourad ; Alshazly, H. A. / Effect of hough forests parameters on face detection performance : An empirical analysis. Proceedings of 2014 9th IEEE International Conference on Computer Engineering and Systems, ICCES 2014. editor / Ayman M. Wahba ; M. Watheq El-Kharashi ; Mohamed Taher ; Ayman M. Bahaa El-Din ; Ahmed M. Zaki. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 35-40 (Proceedings of 2014 9th IEEE International Conference on Computer Engineering and Systems, ICCES 2014).

@inproceedings{c84aca36fbef474e8fc9e7a481c35d52,

title = "Effect of hough forests parameters on face detection performance: An empirical analysis",

abstract = "Face detection as one of the most challenging tasks in computer vision has received a lot of attention in recent decades due to its wide range of use in face based image analysis. In this paper, we propose an efficient approach for face detection that efficiently combines generalized Hough transform within random decision forests framework. In this approach, we train random decision forests that directly maps the image patch appearance to the probabilistic vote about the possible location of the face centroid; the detection hypotheses then correspond to the maxima of the Hough image. The random decision forests construction and prediction abilities depend on setting some parameters, which in turns affects the performance of the method. Therefore, the impact of these parameters that most influence the behavior of the forest for detecting faces is studied through experiments on the widely used CMU+MIT database. Moreover, a comparison with some published methods is presented.",

keywords = "Face Detection, Parameters Setting, Random Hough Forests",

author = "M. Hassaballah and Mourad Ahmed and Alshazly, \{H. A.\}",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 9th IEEE International Conference on Computer Engineering and Systems, ICCES 2014 ; Conference date: 22-12-2014 Through 23-12-2014",

year = "2014",

month = feb,

day = "3",

doi = "10.1109/ICCES.2014.7030924",

language = "English",

series = "Proceedings of 2014 9th IEEE International Conference on Computer Engineering and Systems, ICCES 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "35--40",

editor = "Wahba, \{Ayman M.\} and El-Kharashi, \{M. Watheq\} and Mohamed Taher and \{Bahaa El-Din\}, \{Ayman M.\} and Zaki, \{Ahmed M.\}",

booktitle = "Proceedings of 2014 9th IEEE International Conference on Computer Engineering and Systems, ICCES 2014",

address = "United States",

}

Hassaballah, M, Ahmed, M & Alshazly, HA 2014, Effect of hough forests parameters on face detection performance: An empirical analysis. in AM Wahba, MW El-Kharashi, M Taher, AM Bahaa El-Din & AM Zaki (eds), Proceedings of 2014 9th IEEE International Conference on Computer Engineering and Systems, ICCES 2014., 7030924, Proceedings of 2014 9th IEEE International Conference on Computer Engineering and Systems, ICCES 2014, Institute of Electrical and Electronics Engineers Inc., pp. 35-40, 2014 9th IEEE International Conference on Computer Engineering and Systems, ICCES 2014, Cairo, Egypt, 22/12/14. https://doi.org/10.1109/ICCES.2014.7030924

Effect of hough forests parameters on face detection performance: An empirical analysis. / Hassaballah, M.; Ahmed, Mourad; Alshazly, H. A.
Proceedings of 2014 9th IEEE International Conference on Computer Engineering and Systems, ICCES 2014. ed. / Ayman M. Wahba; M. Watheq El-Kharashi; Mohamed Taher; Ayman M. Bahaa El-Din; Ahmed M. Zaki. Institute of Electrical and Electronics Engineers Inc., 2014. p. 35-40 7030924 (Proceedings of 2014 9th IEEE International Conference on Computer Engineering and Systems, ICCES 2014).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Effect of hough forests parameters on face detection performance

T2 - 2014 9th IEEE International Conference on Computer Engineering and Systems, ICCES 2014

AU - Hassaballah, M.

AU - Ahmed, Mourad

AU - Alshazly, H. A.

PY - 2014/2/3

Y1 - 2014/2/3

N2 - Face detection as one of the most challenging tasks in computer vision has received a lot of attention in recent decades due to its wide range of use in face based image analysis. In this paper, we propose an efficient approach for face detection that efficiently combines generalized Hough transform within random decision forests framework. In this approach, we train random decision forests that directly maps the image patch appearance to the probabilistic vote about the possible location of the face centroid; the detection hypotheses then correspond to the maxima of the Hough image. The random decision forests construction and prediction abilities depend on setting some parameters, which in turns affects the performance of the method. Therefore, the impact of these parameters that most influence the behavior of the forest for detecting faces is studied through experiments on the widely used CMU+MIT database. Moreover, a comparison with some published methods is presented.

AB - Face detection as one of the most challenging tasks in computer vision has received a lot of attention in recent decades due to its wide range of use in face based image analysis. In this paper, we propose an efficient approach for face detection that efficiently combines generalized Hough transform within random decision forests framework. In this approach, we train random decision forests that directly maps the image patch appearance to the probabilistic vote about the possible location of the face centroid; the detection hypotheses then correspond to the maxima of the Hough image. The random decision forests construction and prediction abilities depend on setting some parameters, which in turns affects the performance of the method. Therefore, the impact of these parameters that most influence the behavior of the forest for detecting faces is studied through experiments on the widely used CMU+MIT database. Moreover, a comparison with some published methods is presented.

KW - Face Detection

KW - Parameters Setting

KW - Random Hough Forests

UR - http://www.scopus.com/inward/record.url?scp=84946690038&partnerID=8YFLogxK

U2 - 10.1109/ICCES.2014.7030924

DO - 10.1109/ICCES.2014.7030924

M3 - Conference contribution

AN - SCOPUS:84946690038

T3 - Proceedings of 2014 9th IEEE International Conference on Computer Engineering and Systems, ICCES 2014

SP - 35

EP - 40

BT - Proceedings of 2014 9th IEEE International Conference on Computer Engineering and Systems, ICCES 2014

A2 - Wahba, Ayman M.

A2 - El-Kharashi, M. Watheq

A2 - Taher, Mohamed

A2 - Bahaa El-Din, Ayman M.

A2 - Zaki, Ahmed M.

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 22 December 2014 through 23 December 2014

ER -

Hassaballah M, Ahmed M, Alshazly HA. Effect of hough forests parameters on face detection performance: An empirical analysis. In Wahba AM, El-Kharashi MW, Taher M, Bahaa El-Din AM, Zaki AM, editors, Proceedings of 2014 9th IEEE International Conference on Computer Engineering and Systems, ICCES 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 35-40. 7030924. (Proceedings of 2014 9th IEEE International Conference on Computer Engineering and Systems, ICCES 2014). doi: 10.1109/ICCES.2014.7030924

Effect of hough forests parameters on face detection performance: An empirical analysis

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this