3D human face recognition using sift descriptors of face’s feature regions

Nguyen Hong Quy, Nguyen Hoang Quoc, Nguyen Tran Lan Anh, Hyung Jeong Yang, Pham The Bao

Research output: Contribution to journalArticlepeer-review

Abstract

Many researches in 3D face recognition problem have been studied because of adverse effects of human’s age, emotions, and environmental conditions on 2D models. In this paper, we propose a novel method for recognizing 3D faces. First, a 3D human face is normalized and determined regions of interest (ROI). Second, SIFT algorithm is applied to these ROIs for detecting invariant feature points. Finally, this descriptor, extracted from a training image, will be stored and later used to identify the face in a test image. For performing reliable recognition, we also adjust parameters of SIFT algorithm to fit own characteristics of the template database. In our experiments, the proposed method produces promising performance up to 84.6% of accuracy when using 3D Notre Dame biometric data-TEC.

Original languageEnglish
Pages (from-to)117-126
Number of pages10
JournalStudies in Computational Intelligence
Volume572
DOIs
StatePublished - 2015

Keywords

  • 3D face recognition
  • Range images
  • SIFT descriptors

Fingerprint

Dive into the research topics of '3D human face recognition using sift descriptors of face’s feature regions'. Together they form a unique fingerprint.

Cite this