Automatic face recognition system based on the SIFT features

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F15%3A43926858" target="_blank" >RIV/49777513:23520/15:43926858 - isvavai.cz</a>

Result on the web

<a href="http://dx.doi.org/10.1016/j.compeleceng.2015.01.014" target="_blank" >http://dx.doi.org/10.1016/j.compeleceng.2015.01.014</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.compeleceng.2015.01.014" target="_blank" >10.1016/j.compeleceng.2015.01.014</a>

Result language

angličtina

Original language name

Automatic face recognition system based on the SIFT features

Original language description

The paper introduces an experimental fully automatic face recognition system which will be used to annotate photographs during insertion into the database. It processes photos of a great number of different individuals photographed in a totally uncontrolled environment. It uses our previously proposed SIFT based Kepenekci approach for face recognition. There is also proposed a new corpus creation algorithm. We show that this algorithm is beneficial in the preprocessing step of our system in order to create good quality face models. We further compare the performance of our SIFT based Kepenekci approach with the original Kepenekci method on the created corpus and our approach significantly outperforms the original one. The last contribution is proposition of two novel supervised confidence measure methods based on the posterior class probability and a multi-layer perceptron. We experimentally show that the proposed confidence measures are very efficient and thus suitable for our system.

Czech name

—

Czech description

—

Type

J_x - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)

CEP classification

JD - Use of computers, robotics and its application

OECD FORD branch

—

Project

<a href="/en/project/ED1.1.00%2F02.0090" target="_blank" >ED1.1.00/02.0090: NTIS - New Technologies for Information Society</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Publication year

2015

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Computers &amp; Electrical Engineering

ISSN

0045-7906

e-ISSN

—

Volume of the periodical

46

Issue of the periodical within the volume

1

Country of publishing house

GB - UNITED KINGDOM

Number of pages

17

Pages from-to

256-272

UT code for WoS article

000367122800021

EID of the result in the Scopus database

—