Facial features extraction by accelerated implementation of circular hough transform and appearance evaluation

Hayato Iwasa; Wataru Oyama; Tetsushi Wakabayashi; Fumitaka Kimura

doi:10.1109/FCV.2015.7103709

Facial features extraction by accelerated implementation of circular hough transform and appearance evaluation

Hayato Iwasa, Wataru Oyama, Tetsushi Wakabayashi, Fumitaka Kimura

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

1 Citation (Scopus)

Abstract

Extraction of facial feature points is essential task for many kinds of applications of face images. The feasibility of facial features extraction is determined by not only its accuracy but processing time. Some applications require real-time detection of facial features. This research aims to propose a method of facial features extraction by an accelerated implementation of circular Hough transform with gradients and appearance evaluation by histogram of gradient features. The acceleration implementation employs General Purpose computing on Graphics Processing Unit. Experiment using FERET database shows that the proposed method successfully extracted eyes and nose for 98.44% and 99.50% of frontal face images in the dataset. And 96.5% of computational time was reduced by accelerated implementation employing GPGPU.

Original language	English
Title of host publication	2015 Frontiers of Computer Vision, FCV 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781479917204
DOIs	https://doi.org/10.1109/FCV.2015.7103709
Publication status	Published - Jan 1 2015
Externally published	Yes
Event	2015 21st Korea-Japan Joint Workshop on Frontiers of Computer Vision, FCV 2015 - Mokpo, Korea, Republic of Duration: Jan 28 2015 → Jan 30 2015

Other

Other	2015 21st Korea-Japan Joint Workshop on Frontiers of Computer Vision, FCV 2015
Country/Territory	Korea, Republic of
City	Mokpo
Period	1/28/15 → 1/30/15

All Science Journal Classification (ASJC) codes

Computer Vision and Pattern Recognition

Access to Document

10.1109/FCV.2015.7103709

Cite this

Facial features extraction by accelerated implementation of circular hough transform and appearance evaluation. / Iwasa, Hayato; Oyama, Wataru; Wakabayashi, Tetsushi et al.

2015 Frontiers of Computer Vision, FCV 2015. Institute of Electrical and Electronics Engineers Inc., 2015. 7103709.

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

Iwasa, H, Oyama, W, Wakabayashi, T & Kimura, F 2015, Facial features extraction by accelerated implementation of circular hough transform and appearance evaluation. in 2015 Frontiers of Computer Vision, FCV 2015., 7103709, Institute of Electrical and Electronics Engineers Inc., 2015 21st Korea-Japan Joint Workshop on Frontiers of Computer Vision, FCV 2015, Mokpo, Korea, Republic of, 1/28/15. https://doi.org/10.1109/FCV.2015.7103709

@inproceedings{8cc835cbc20e470786c23899a8b2835f,

title = "Facial features extraction by accelerated implementation of circular hough transform and appearance evaluation",

abstract = "Extraction of facial feature points is essential task for many kinds of applications of face images. The feasibility of facial features extraction is determined by not only its accuracy but processing time. Some applications require real-time detection of facial features. This research aims to propose a method of facial features extraction by an accelerated implementation of circular Hough transform with gradients and appearance evaluation by histogram of gradient features. The acceleration implementation employs General Purpose computing on Graphics Processing Unit. Experiment using FERET database shows that the proposed method successfully extracted eyes and nose for 98.44% and 99.50% of frontal face images in the dataset. And 96.5% of computational time was reduced by accelerated implementation employing GPGPU.",

author = "Hayato Iwasa and Wataru Oyama and Tetsushi Wakabayashi and Fumitaka Kimura",

year = "2015",

month = jan,

day = "1",

doi = "10.1109/FCV.2015.7103709",

language = "English",

booktitle = "2015 Frontiers of Computer Vision, FCV 2015",

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

address = "United States",

note = "2015 21st Korea-Japan Joint Workshop on Frontiers of Computer Vision, FCV 2015 ; Conference date: 28-01-2015 Through 30-01-2015",

}

TY - GEN

T1 - Facial features extraction by accelerated implementation of circular hough transform and appearance evaluation

AU - Iwasa, Hayato

AU - Oyama, Wataru

AU - Wakabayashi, Tetsushi

AU - Kimura, Fumitaka

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Extraction of facial feature points is essential task for many kinds of applications of face images. The feasibility of facial features extraction is determined by not only its accuracy but processing time. Some applications require real-time detection of facial features. This research aims to propose a method of facial features extraction by an accelerated implementation of circular Hough transform with gradients and appearance evaluation by histogram of gradient features. The acceleration implementation employs General Purpose computing on Graphics Processing Unit. Experiment using FERET database shows that the proposed method successfully extracted eyes and nose for 98.44% and 99.50% of frontal face images in the dataset. And 96.5% of computational time was reduced by accelerated implementation employing GPGPU.

AB - Extraction of facial feature points is essential task for many kinds of applications of face images. The feasibility of facial features extraction is determined by not only its accuracy but processing time. Some applications require real-time detection of facial features. This research aims to propose a method of facial features extraction by an accelerated implementation of circular Hough transform with gradients and appearance evaluation by histogram of gradient features. The acceleration implementation employs General Purpose computing on Graphics Processing Unit. Experiment using FERET database shows that the proposed method successfully extracted eyes and nose for 98.44% and 99.50% of frontal face images in the dataset. And 96.5% of computational time was reduced by accelerated implementation employing GPGPU.

UR - http://www.scopus.com/inward/record.url?scp=84937158603&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84937158603&partnerID=8YFLogxK

U2 - 10.1109/FCV.2015.7103709

DO - 10.1109/FCV.2015.7103709

M3 - Conference contribution

AN - SCOPUS:84937158603

BT - 2015 Frontiers of Computer Vision, FCV 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2015 21st Korea-Japan Joint Workshop on Frontiers of Computer Vision, FCV 2015

Y2 - 28 January 2015 through 30 January 2015

ER -

Facial features extraction by accelerated implementation of circular hough transform and appearance evaluation

Abstract

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this