Enhanced independent spectral histogram representations in face recognition

Ying Han Pang, Andrew Beng Jin Teoh, Shih Yin Ooi, Cheng Yaw Low

Research output: Contribution to journalArticle

Abstract

A spectral histogram descriptor computes a set of marginal distributions based on the filter bank’s responses, and further encodes them into the images. The encoding process for local image structure takes place during the filtering stage, whereas the encoding process of global image feature is conducted during the histogram stage. One drawback of spectral histogram descriptors is their performances will be greatly deteriorated when the filter bank’s responses are not stochastically independent. To tackle this problem, a computational technique named Enhanced Independent Spectral Histogram Feature (EISHF) is proposed. EISHF is composed of four working modules: (1) unsupervised independent filter bank responses computation, (2) binary hashing, (3) XOR bitwise operation and feature encoding, and lastly, (4) block-wise histogramming. To ensure the performance of ordinary spectral histogram descriptors, an XOR operation has been delicately adopted to increase the independency of the filter responses. Tested on three public face databases, the experimental results have substantiated the performance of EISHF in handling different kinds of facial expressions, illuminations, time spans as well as facial makeup effects.

Original languageEnglish
Pages (from-to)14259-14284
Number of pages26
JournalMultimedia Tools and Applications
Volume77
Issue number11
DOIs
Publication statusPublished - 2018 Jun 1

Fingerprint

Filter banks
Face recognition
Lighting

All Science Journal Classification (ASJC) codes

  • Software
  • Media Technology
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

Pang, Ying Han ; Teoh, Andrew Beng Jin ; Ooi, Shih Yin ; Low, Cheng Yaw. / Enhanced independent spectral histogram representations in face recognition. In: Multimedia Tools and Applications. 2018 ; Vol. 77, No. 11. pp. 14259-14284.
@article{0ebbdfd9f44143bdbec444f4f6edf4a4,
title = "Enhanced independent spectral histogram representations in face recognition",
abstract = "A spectral histogram descriptor computes a set of marginal distributions based on the filter bank’s responses, and further encodes them into the images. The encoding process for local image structure takes place during the filtering stage, whereas the encoding process of global image feature is conducted during the histogram stage. One drawback of spectral histogram descriptors is their performances will be greatly deteriorated when the filter bank’s responses are not stochastically independent. To tackle this problem, a computational technique named Enhanced Independent Spectral Histogram Feature (EISHF) is proposed. EISHF is composed of four working modules: (1) unsupervised independent filter bank responses computation, (2) binary hashing, (3) XOR bitwise operation and feature encoding, and lastly, (4) block-wise histogramming. To ensure the performance of ordinary spectral histogram descriptors, an XOR operation has been delicately adopted to increase the independency of the filter responses. Tested on three public face databases, the experimental results have substantiated the performance of EISHF in handling different kinds of facial expressions, illuminations, time spans as well as facial makeup effects.",
author = "Pang, {Ying Han} and Teoh, {Andrew Beng Jin} and Ooi, {Shih Yin} and Low, {Cheng Yaw}",
year = "2018",
month = "6",
day = "1",
doi = "10.1007/s11042-017-5028-8",
language = "English",
volume = "77",
pages = "14259--14284",
journal = "Multimedia Tools and Applications",
issn = "1380-7501",
publisher = "Springer Netherlands",
number = "11",

}

Enhanced independent spectral histogram representations in face recognition. / Pang, Ying Han; Teoh, Andrew Beng Jin; Ooi, Shih Yin; Low, Cheng Yaw.

In: Multimedia Tools and Applications, Vol. 77, No. 11, 01.06.2018, p. 14259-14284.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Enhanced independent spectral histogram representations in face recognition

AU - Pang, Ying Han

AU - Teoh, Andrew Beng Jin

AU - Ooi, Shih Yin

AU - Low, Cheng Yaw

PY - 2018/6/1

Y1 - 2018/6/1

N2 - A spectral histogram descriptor computes a set of marginal distributions based on the filter bank’s responses, and further encodes them into the images. The encoding process for local image structure takes place during the filtering stage, whereas the encoding process of global image feature is conducted during the histogram stage. One drawback of spectral histogram descriptors is their performances will be greatly deteriorated when the filter bank’s responses are not stochastically independent. To tackle this problem, a computational technique named Enhanced Independent Spectral Histogram Feature (EISHF) is proposed. EISHF is composed of four working modules: (1) unsupervised independent filter bank responses computation, (2) binary hashing, (3) XOR bitwise operation and feature encoding, and lastly, (4) block-wise histogramming. To ensure the performance of ordinary spectral histogram descriptors, an XOR operation has been delicately adopted to increase the independency of the filter responses. Tested on three public face databases, the experimental results have substantiated the performance of EISHF in handling different kinds of facial expressions, illuminations, time spans as well as facial makeup effects.

AB - A spectral histogram descriptor computes a set of marginal distributions based on the filter bank’s responses, and further encodes them into the images. The encoding process for local image structure takes place during the filtering stage, whereas the encoding process of global image feature is conducted during the histogram stage. One drawback of spectral histogram descriptors is their performances will be greatly deteriorated when the filter bank’s responses are not stochastically independent. To tackle this problem, a computational technique named Enhanced Independent Spectral Histogram Feature (EISHF) is proposed. EISHF is composed of four working modules: (1) unsupervised independent filter bank responses computation, (2) binary hashing, (3) XOR bitwise operation and feature encoding, and lastly, (4) block-wise histogramming. To ensure the performance of ordinary spectral histogram descriptors, an XOR operation has been delicately adopted to increase the independency of the filter responses. Tested on three public face databases, the experimental results have substantiated the performance of EISHF in handling different kinds of facial expressions, illuminations, time spans as well as facial makeup effects.

UR - http://www.scopus.com/inward/record.url?scp=85026454690&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85026454690&partnerID=8YFLogxK

U2 - 10.1007/s11042-017-5028-8

DO - 10.1007/s11042-017-5028-8

M3 - Article

VL - 77

SP - 14259

EP - 14284

JO - Multimedia Tools and Applications

JF - Multimedia Tools and Applications

SN - 1380-7501

IS - 11

ER -