A design of apparent-age estimation system by the empirical mode decomposition

Hironobu Fukai, Hironori Takimoto, Yasue Mitsukura, Toshihisa Tanaka, Minoru Fukumi

Research output: Contribution to journalArticle

Abstract

Recently, the automation of the age estimation technique is hoped for in various fields. Therefore, we propose an apparent-age estimation system using empirical mode decomposition (EMD). Conventional study reported that the time-frequency features are important for age estimation. However, these cannot necessarily extract the time-frequency feature in detail, because the classical technique that have a relationship of trade-off between the time resolution and the frequency resolution are used. On the other hand, the EMD is the novel time-frequency analysis technique that do not have the relationship of trade-off between the time resolution and the frequency resolution. The EMD gives a time-frequency analysis decomposing a signal into several intrinsic mode functions (IMFs). The IMF together with their Hilbert transforms are called the HilbertHuang spectrum, which leads to instantaneous frequency and amplitude. We use these features effectively for extracting human's age perception. We estimate the age by a neural network that learns pairs of face image and the HilbertHuang spectrum. Furthermore, we compress the data for neural network by using the simple principal component analysis (SPCA). In order to show the effectiveness of the proposed method, computer simulations are done by the actual human data.

Original languageEnglish
Pages (from-to)1481-1492
Number of pages12
JournalJournal of Circuits, Systems and Computers
Volume18
Issue number8
DOIs
Publication statusPublished - 2009 Dec
Externally publishedYes

Fingerprint

Decomposition
Neural networks
Principal component analysis
Automation
Computer simulation

Keywords

  • Age estimation
  • Empirical mode decomposition (EMD)
  • Neural network (NN)
  • Simple principal component analysis (SPCA)

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Hardware and Architecture

Cite this

A design of apparent-age estimation system by the empirical mode decomposition. / Fukai, Hironobu; Takimoto, Hironori; Mitsukura, Yasue; Tanaka, Toshihisa; Fukumi, Minoru.

In: Journal of Circuits, Systems and Computers, Vol. 18, No. 8, 12.2009, p. 1481-1492.

Research output: Contribution to journalArticle

Fukai, Hironobu ; Takimoto, Hironori ; Mitsukura, Yasue ; Tanaka, Toshihisa ; Fukumi, Minoru. / A design of apparent-age estimation system by the empirical mode decomposition. In: Journal of Circuits, Systems and Computers. 2009 ; Vol. 18, No. 8. pp. 1481-1492.
@article{a0ca7c6927194db2af99a70f547d02b9,
title = "A design of apparent-age estimation system by the empirical mode decomposition",
abstract = "Recently, the automation of the age estimation technique is hoped for in various fields. Therefore, we propose an apparent-age estimation system using empirical mode decomposition (EMD). Conventional study reported that the time-frequency features are important for age estimation. However, these cannot necessarily extract the time-frequency feature in detail, because the classical technique that have a relationship of trade-off between the time resolution and the frequency resolution are used. On the other hand, the EMD is the novel time-frequency analysis technique that do not have the relationship of trade-off between the time resolution and the frequency resolution. The EMD gives a time-frequency analysis decomposing a signal into several intrinsic mode functions (IMFs). The IMF together with their Hilbert transforms are called the HilbertHuang spectrum, which leads to instantaneous frequency and amplitude. We use these features effectively for extracting human's age perception. We estimate the age by a neural network that learns pairs of face image and the HilbertHuang spectrum. Furthermore, we compress the data for neural network by using the simple principal component analysis (SPCA). In order to show the effectiveness of the proposed method, computer simulations are done by the actual human data.",
keywords = "Age estimation, Empirical mode decomposition (EMD), Neural network (NN), Simple principal component analysis (SPCA)",
author = "Hironobu Fukai and Hironori Takimoto and Yasue Mitsukura and Toshihisa Tanaka and Minoru Fukumi",
year = "2009",
month = "12",
doi = "10.1142/S0218126609005800",
language = "English",
volume = "18",
pages = "1481--1492",
journal = "Journal of Circuits, Systems and Computers",
issn = "0218-1266",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "8",

}

TY - JOUR

T1 - A design of apparent-age estimation system by the empirical mode decomposition

AU - Fukai, Hironobu

AU - Takimoto, Hironori

AU - Mitsukura, Yasue

AU - Tanaka, Toshihisa

AU - Fukumi, Minoru

PY - 2009/12

Y1 - 2009/12

N2 - Recently, the automation of the age estimation technique is hoped for in various fields. Therefore, we propose an apparent-age estimation system using empirical mode decomposition (EMD). Conventional study reported that the time-frequency features are important for age estimation. However, these cannot necessarily extract the time-frequency feature in detail, because the classical technique that have a relationship of trade-off between the time resolution and the frequency resolution are used. On the other hand, the EMD is the novel time-frequency analysis technique that do not have the relationship of trade-off between the time resolution and the frequency resolution. The EMD gives a time-frequency analysis decomposing a signal into several intrinsic mode functions (IMFs). The IMF together with their Hilbert transforms are called the HilbertHuang spectrum, which leads to instantaneous frequency and amplitude. We use these features effectively for extracting human's age perception. We estimate the age by a neural network that learns pairs of face image and the HilbertHuang spectrum. Furthermore, we compress the data for neural network by using the simple principal component analysis (SPCA). In order to show the effectiveness of the proposed method, computer simulations are done by the actual human data.

AB - Recently, the automation of the age estimation technique is hoped for in various fields. Therefore, we propose an apparent-age estimation system using empirical mode decomposition (EMD). Conventional study reported that the time-frequency features are important for age estimation. However, these cannot necessarily extract the time-frequency feature in detail, because the classical technique that have a relationship of trade-off between the time resolution and the frequency resolution are used. On the other hand, the EMD is the novel time-frequency analysis technique that do not have the relationship of trade-off between the time resolution and the frequency resolution. The EMD gives a time-frequency analysis decomposing a signal into several intrinsic mode functions (IMFs). The IMF together with their Hilbert transforms are called the HilbertHuang spectrum, which leads to instantaneous frequency and amplitude. We use these features effectively for extracting human's age perception. We estimate the age by a neural network that learns pairs of face image and the HilbertHuang spectrum. Furthermore, we compress the data for neural network by using the simple principal component analysis (SPCA). In order to show the effectiveness of the proposed method, computer simulations are done by the actual human data.

KW - Age estimation

KW - Empirical mode decomposition (EMD)

KW - Neural network (NN)

KW - Simple principal component analysis (SPCA)

UR - http://www.scopus.com/inward/record.url?scp=71749111159&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=71749111159&partnerID=8YFLogxK

U2 - 10.1142/S0218126609005800

DO - 10.1142/S0218126609005800

M3 - Article

VL - 18

SP - 1481

EP - 1492

JO - Journal of Circuits, Systems and Computers

JF - Journal of Circuits, Systems and Computers

SN - 0218-1266

IS - 8

ER -