Original approach for the localization of objects in images

R. Vaillant, C. Monrocq, Yann LeCun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The detection and localization of faces in an image has many applications in various domains: surveillance, TV audience polling, etc. We propose a new method for this task. The main idea of our method is to train a neural network to detect the presence or absence of a face in its input window, and to scan this network over at all possible locations in the image. Because of the nature of the neural network architecture we used, this process can be done very efficiently without requiring to actually recompute the entire network state at each location. The scanning is performed on several versions of the image at various scales, resulting in an efficient, scale independent detector and locator.

Original languageEnglish (US)
Title of host publicationIEE Conference Publication
PublisherPubl by IEE
Pages26-29
Number of pages4
Edition372
StatePublished - 1993
Event3rd International Conference on Artificial Neural Networks - Brighton, England
Duration: May 25 1993May 27 1993

Other

Other3rd International Conference on Artificial Neural Networks
CityBrighton, England
Period5/25/935/27/93

Fingerprint

Neural networks
Network architecture
Detectors
Scanning

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Vaillant, R., Monrocq, C., & LeCun, Y. (1993). Original approach for the localization of objects in images. In IEE Conference Publication (372 ed., pp. 26-29). Publ by IEE.

Original approach for the localization of objects in images. / Vaillant, R.; Monrocq, C.; LeCun, Yann.

IEE Conference Publication. 372. ed. Publ by IEE, 1993. p. 26-29.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Vaillant, R, Monrocq, C & LeCun, Y 1993, Original approach for the localization of objects in images. in IEE Conference Publication. 372 edn, Publ by IEE, pp. 26-29, 3rd International Conference on Artificial Neural Networks, Brighton, England, 5/25/93.
Vaillant R, Monrocq C, LeCun Y. Original approach for the localization of objects in images. In IEE Conference Publication. 372 ed. Publ by IEE. 1993. p. 26-29
Vaillant, R. ; Monrocq, C. ; LeCun, Yann. / Original approach for the localization of objects in images. IEE Conference Publication. 372. ed. Publ by IEE, 1993. pp. 26-29
@inproceedings{e94f1845d85b45419ed9b90515e1c0c3,
title = "Original approach for the localization of objects in images",
abstract = "The detection and localization of faces in an image has many applications in various domains: surveillance, TV audience polling, etc. We propose a new method for this task. The main idea of our method is to train a neural network to detect the presence or absence of a face in its input window, and to scan this network over at all possible locations in the image. Because of the nature of the neural network architecture we used, this process can be done very efficiently without requiring to actually recompute the entire network state at each location. The scanning is performed on several versions of the image at various scales, resulting in an efficient, scale independent detector and locator.",
author = "R. Vaillant and C. Monrocq and Yann LeCun",
year = "1993",
language = "English (US)",
pages = "26--29",
booktitle = "IEE Conference Publication",
publisher = "Publ by IEE",
edition = "372",

}

TY - GEN

T1 - Original approach for the localization of objects in images

AU - Vaillant, R.

AU - Monrocq, C.

AU - LeCun, Yann

PY - 1993

Y1 - 1993

N2 - The detection and localization of faces in an image has many applications in various domains: surveillance, TV audience polling, etc. We propose a new method for this task. The main idea of our method is to train a neural network to detect the presence or absence of a face in its input window, and to scan this network over at all possible locations in the image. Because of the nature of the neural network architecture we used, this process can be done very efficiently without requiring to actually recompute the entire network state at each location. The scanning is performed on several versions of the image at various scales, resulting in an efficient, scale independent detector and locator.

AB - The detection and localization of faces in an image has many applications in various domains: surveillance, TV audience polling, etc. We propose a new method for this task. The main idea of our method is to train a neural network to detect the presence or absence of a face in its input window, and to scan this network over at all possible locations in the image. Because of the nature of the neural network architecture we used, this process can be done very efficiently without requiring to actually recompute the entire network state at each location. The scanning is performed on several versions of the image at various scales, resulting in an efficient, scale independent detector and locator.

UR - http://www.scopus.com/inward/record.url?scp=0027266148&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027266148&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0027266148

SP - 26

EP - 29

BT - IEE Conference Publication

PB - Publ by IEE

ER -