Face recognition through learned boundary characteristics

L. Spacek, Miroslav Kubat, D. Flotzinger

Research output: Contribution to journalArticle

Abstract

This paper present a new approach to face recognition, combining the techniques of computer vision and machine learning. A steady improvement in recognition performance is demonstrated. It is achieved by learning individual faces in terms of the local shapes of image boundaries. High-level facial features, such as nose, are not explicitly used in this scheme. Several machine learning methods are tested and compared. The overall objectives are formulated as follows: Classify the different tasks of 'face recognition' and suggest an orderly terminology to distinguish between them. Design a set of easily and reliable and reliably obtainable descriptors and their automatic extraction from the images. Compare plausible machine learning methods: tailor them to this domain. Design experiments that would best reflect the needs of real world applications, and suggest a general methodology for further research. Perform the experiments and compare the performance.

Original languageEnglish
Pages (from-to)149-164
Number of pages16
JournalApplied Artificial Intelligence
Volume8
Issue number1
StatePublished - Jan 1 1994
Externally publishedYes

Fingerprint

Face recognition
Learning systems
Terminology
Computer vision
Experiments

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Face recognition through learned boundary characteristics. / Spacek, L.; Kubat, Miroslav; Flotzinger, D.

In: Applied Artificial Intelligence, Vol. 8, No. 1, 01.01.1994, p. 149-164.

Research output: Contribution to journalArticle

Spacek, L. ; Kubat, Miroslav ; Flotzinger, D. / Face recognition through learned boundary characteristics. In: Applied Artificial Intelligence. 1994 ; Vol. 8, No. 1. pp. 149-164.
@article{5e3debe6fe3a4233ad8da937b1817251,
title = "Face recognition through learned boundary characteristics",
abstract = "This paper present a new approach to face recognition, combining the techniques of computer vision and machine learning. A steady improvement in recognition performance is demonstrated. It is achieved by learning individual faces in terms of the local shapes of image boundaries. High-level facial features, such as nose, are not explicitly used in this scheme. Several machine learning methods are tested and compared. The overall objectives are formulated as follows: Classify the different tasks of 'face recognition' and suggest an orderly terminology to distinguish between them. Design a set of easily and reliable and reliably obtainable descriptors and their automatic extraction from the images. Compare plausible machine learning methods: tailor them to this domain. Design experiments that would best reflect the needs of real world applications, and suggest a general methodology for further research. Perform the experiments and compare the performance.",
author = "L. Spacek and Miroslav Kubat and D. Flotzinger",
year = "1994",
month = "1",
day = "1",
language = "English",
volume = "8",
pages = "149--164",
journal = "Applied Artificial Intelligence",
issn = "0883-9514",
publisher = "Taylor and Francis Ltd.",
number = "1",

}

TY - JOUR

T1 - Face recognition through learned boundary characteristics

AU - Spacek, L.

AU - Kubat, Miroslav

AU - Flotzinger, D.

PY - 1994/1/1

Y1 - 1994/1/1

N2 - This paper present a new approach to face recognition, combining the techniques of computer vision and machine learning. A steady improvement in recognition performance is demonstrated. It is achieved by learning individual faces in terms of the local shapes of image boundaries. High-level facial features, such as nose, are not explicitly used in this scheme. Several machine learning methods are tested and compared. The overall objectives are formulated as follows: Classify the different tasks of 'face recognition' and suggest an orderly terminology to distinguish between them. Design a set of easily and reliable and reliably obtainable descriptors and their automatic extraction from the images. Compare plausible machine learning methods: tailor them to this domain. Design experiments that would best reflect the needs of real world applications, and suggest a general methodology for further research. Perform the experiments and compare the performance.

AB - This paper present a new approach to face recognition, combining the techniques of computer vision and machine learning. A steady improvement in recognition performance is demonstrated. It is achieved by learning individual faces in terms of the local shapes of image boundaries. High-level facial features, such as nose, are not explicitly used in this scheme. Several machine learning methods are tested and compared. The overall objectives are formulated as follows: Classify the different tasks of 'face recognition' and suggest an orderly terminology to distinguish between them. Design a set of easily and reliable and reliably obtainable descriptors and their automatic extraction from the images. Compare plausible machine learning methods: tailor them to this domain. Design experiments that would best reflect the needs of real world applications, and suggest a general methodology for further research. Perform the experiments and compare the performance.

UR - http://www.scopus.com/inward/record.url?scp=0028261360&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028261360&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0028261360

VL - 8

SP - 149

EP - 164

JO - Applied Artificial Intelligence

JF - Applied Artificial Intelligence

SN - 0883-9514

IS - 1

ER -