Radius based block LBP for facial expression recognition

Abdul Aziz K Abdul Hamid, Md. Jan Nordin

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper presents a 'significant facial region' in which the block size is extracted based on the radius length on the face area to improve the recognition performance and reduce size of feature vector. We introduces region selection using various critical point and report our result using benchmark database. The original LBP techniques focus in dividing the whole image into regions and for the proposed scheme, we focus on critical region, which gives more impact to the recognition performance. This technique is known as Radius Based Block Local Binary Pattern (RBB-LBP). We defined four critical point represent left eye, right eye, nose and mouth, from this four main point we derived the next nine point. We assessed on the face recognition problem using the Colorado State University Face Identification Evaluation System with images from the Japanese Female Facial Expression (JAFFE) database. Our experimental results clearly show that our approach outperforms the other methods. With RBB-LBP, the best facial expression recognition rate was achieved at 94.37% on hardest testing method - Leave One Out (LOO), which is an increase of 0.97% compared to linear programming algorithm and non-uniform LBP with usage of feature vector 1298 compared to 19456.

Original languageEnglish
Pages (from-to)4197-4202
Number of pages6
JournalInformation (Japan)
Volume19
Issue number9B
Publication statusPublished - 1 Sep 2016

Fingerprint

Face recognition
Linear programming
Testing

Keywords

  • Face recognition
  • JAFFE
  • Local Binary Pattern (LBP)
  • Radius based block Local Binary Pattern (RBB-LBP)
  • Significant facial region

ASJC Scopus subject areas

  • General

Cite this

Radius based block LBP for facial expression recognition. / Abdul Hamid, Abdul Aziz K; Nordin, Md. Jan.

In: Information (Japan), Vol. 19, No. 9B, 01.09.2016, p. 4197-4202.

Research output: Contribution to journalArticle

Abdul Hamid, AAK & Nordin, MJ 2016, 'Radius based block LBP for facial expression recognition', Information (Japan), vol. 19, no. 9B, pp. 4197-4202.
Abdul Hamid, Abdul Aziz K ; Nordin, Md. Jan. / Radius based block LBP for facial expression recognition. In: Information (Japan). 2016 ; Vol. 19, No. 9B. pp. 4197-4202.
@article{1a4a07b70ff045b0a9f8da7c9ef97b60,
title = "Radius based block LBP for facial expression recognition",
abstract = "This paper presents a 'significant facial region' in which the block size is extracted based on the radius length on the face area to improve the recognition performance and reduce size of feature vector. We introduces region selection using various critical point and report our result using benchmark database. The original LBP techniques focus in dividing the whole image into regions and for the proposed scheme, we focus on critical region, which gives more impact to the recognition performance. This technique is known as Radius Based Block Local Binary Pattern (RBB-LBP). We defined four critical point represent left eye, right eye, nose and mouth, from this four main point we derived the next nine point. We assessed on the face recognition problem using the Colorado State University Face Identification Evaluation System with images from the Japanese Female Facial Expression (JAFFE) database. Our experimental results clearly show that our approach outperforms the other methods. With RBB-LBP, the best facial expression recognition rate was achieved at 94.37{\%} on hardest testing method - Leave One Out (LOO), which is an increase of 0.97{\%} compared to linear programming algorithm and non-uniform LBP with usage of feature vector 1298 compared to 19456.",
keywords = "Face recognition, JAFFE, Local Binary Pattern (LBP), Radius based block Local Binary Pattern (RBB-LBP), Significant facial region",
author = "{Abdul Hamid}, {Abdul Aziz K} and Nordin, {Md. Jan}",
year = "2016",
month = "9",
day = "1",
language = "English",
volume = "19",
pages = "4197--4202",
journal = "Information (Japan)",
issn = "1343-4500",
publisher = "International Information Institute",
number = "9B",

}

TY - JOUR

T1 - Radius based block LBP for facial expression recognition

AU - Abdul Hamid, Abdul Aziz K

AU - Nordin, Md. Jan

PY - 2016/9/1

Y1 - 2016/9/1

N2 - This paper presents a 'significant facial region' in which the block size is extracted based on the radius length on the face area to improve the recognition performance and reduce size of feature vector. We introduces region selection using various critical point and report our result using benchmark database. The original LBP techniques focus in dividing the whole image into regions and for the proposed scheme, we focus on critical region, which gives more impact to the recognition performance. This technique is known as Radius Based Block Local Binary Pattern (RBB-LBP). We defined four critical point represent left eye, right eye, nose and mouth, from this four main point we derived the next nine point. We assessed on the face recognition problem using the Colorado State University Face Identification Evaluation System with images from the Japanese Female Facial Expression (JAFFE) database. Our experimental results clearly show that our approach outperforms the other methods. With RBB-LBP, the best facial expression recognition rate was achieved at 94.37% on hardest testing method - Leave One Out (LOO), which is an increase of 0.97% compared to linear programming algorithm and non-uniform LBP with usage of feature vector 1298 compared to 19456.

AB - This paper presents a 'significant facial region' in which the block size is extracted based on the radius length on the face area to improve the recognition performance and reduce size of feature vector. We introduces region selection using various critical point and report our result using benchmark database. The original LBP techniques focus in dividing the whole image into regions and for the proposed scheme, we focus on critical region, which gives more impact to the recognition performance. This technique is known as Radius Based Block Local Binary Pattern (RBB-LBP). We defined four critical point represent left eye, right eye, nose and mouth, from this four main point we derived the next nine point. We assessed on the face recognition problem using the Colorado State University Face Identification Evaluation System with images from the Japanese Female Facial Expression (JAFFE) database. Our experimental results clearly show that our approach outperforms the other methods. With RBB-LBP, the best facial expression recognition rate was achieved at 94.37% on hardest testing method - Leave One Out (LOO), which is an increase of 0.97% compared to linear programming algorithm and non-uniform LBP with usage of feature vector 1298 compared to 19456.

KW - Face recognition

KW - JAFFE

KW - Local Binary Pattern (LBP)

KW - Radius based block Local Binary Pattern (RBB-LBP)

KW - Significant facial region

UR - http://www.scopus.com/inward/record.url?scp=85003530609&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85003530609&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85003530609

VL - 19

SP - 4197

EP - 4202

JO - Information (Japan)

JF - Information (Japan)

SN - 1343-4500

IS - 9B

ER -