Skip to main navigation Skip to search Skip to main content

Automatic cheek detection in digital images

  • Silesian University of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

This paper deals with some problems of cheek detection in colour images. Authors reviewed the literature in this field and proposed a new effective method for cheek detection. A characteristic feature of the proposed method is the use of 13 essential face landmarks generated by a known face landmark detector. In the paper four methods from the literature and one’s own method are described in detail. All these methods have been tested experimentally using a suitable face image database PUT. Preliminary tests showed the advantages of our method. Additionally we investigated the impact of head movements on the location detected cheeks. A small number of false cheek pixels lying outside the face contour and a small colour error caused by movements of the head predetermines the proposed method for further research and applications.

Original languageEnglish
Title of host publicationComputational Vision and Medical Image Processing V - Proceedings of 5th Eccomas Thematic Conference on Computational Vision and Medical Image Processing, VipIMAGE 2015
EditorsJoao Manuel R.S. Tavares, R.M. Natal Jorge
PublisherCRC Press/Balkema
Pages49-56
Number of pages8
ISBN (Print)9781138029262
Publication statusPublished - 2016
Event5th Eccomas Thematic Conference on Computational Vision and Medical Image Processing, VipIMAGE 2015 - Tenerife, Spain
Duration: 19 Oct 201521 Oct 2015

Publication series

NameComputational Vision and Medical Image Processing V - Proceedings of 5th Eccomas Thematic Conference on Computational Vision and Medical Image Processing, VipIMAGE 2015

Conference

Conference5th Eccomas Thematic Conference on Computational Vision and Medical Image Processing, VipIMAGE 2015
Country/TerritorySpain
CityTenerife
Period19/10/1521/10/15

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Biomedical Engineering
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Automatic cheek detection in digital images'. Together they form a unique fingerprint.

Cite this