A novel approach to automatic detection of interest points in multiple facial images
The human face includes different colors and forms due to its complexity. Therefore, facial image processing comprises even more problems than image processing of other objects. Interest point detection is one of the important problems in computer vision, which is the key aspect of solving problem...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IJEGEO
2017-05-01
|
Series: | International Journal of Environment and Geoinformatics |
Subjects: | |
Online Access: | http://dergipark.gov.tr/download/article-file/302653 |
_version_ | 1797913564897345536 |
---|---|
author | Bülent Bayram G. Çiğdem Çavdaroğlu Dursun Zafer Şeker Sıtkı Külür |
author_facet | Bülent Bayram G. Çiğdem Çavdaroğlu Dursun Zafer Şeker Sıtkı Külür |
author_sort | Bülent Bayram |
collection | DOAJ |
description | The human face includes different colors and forms due to its complexity. Therefore, facial image processing
comprises even more problems than image processing of other objects. Interest point detection is one of the
important problems in computer vision, which is the key aspect of solving problems such as facial expression
analysis, age analysis, sex defining, facial recognition, and three-dimensional face modelling in augmented
reality. To accomplish these tasks, facial interest points need automatic definition. A hybrid algorithm was
developed to detect automatically interest regions and points in multiple images in the resented study. The
study used processed facial images from an authorized image database with a resolution of 1600 x 1200, taken
in standardized illumination conditions by using an InSpeck Mega Capturor II optical 3D structured light
digitizer and 1000-W halogen lamp. The presented study integrated skin color analysis with the Haar
classification method, processing 11 male and 25 female facial images with the developed algorithm. The
average accuracy of facial interest point detection was 0.68 mm after testing all images. |
first_indexed | 2024-04-10T12:13:38Z |
format | Article |
id | doaj.art-88028d7082c142118ea7a2ef8c5c533d |
institution | Directory Open Access Journal |
issn | 2148-9173 2148-9173 |
language | English |
last_indexed | 2024-04-10T12:13:38Z |
publishDate | 2017-05-01 |
publisher | IJEGEO |
record_format | Article |
series | International Journal of Environment and Geoinformatics |
spelling | doaj.art-88028d7082c142118ea7a2ef8c5c533d2023-02-15T16:15:51ZengIJEGEOInternational Journal of Environment and Geoinformatics2148-91732148-91732017-05-014211612710.30897/ijegeo.312635A novel approach to automatic detection of interest points in multiple facial imagesBülent Bayram0G. Çiğdem Çavdaroğlu1Dursun Zafer Şeker2 Sıtkı Külür3 Yıldız Technical University, Department of Geomatic Engineering, Division of Photogrammetry, Davutpasa Campus, Esenler, 34210, Istanbul,TR IDEGIS Technology, Information and Software Ltd. Company, Yıldız Technical University Davutpasa Campus, Technopark, Davutpasa Str, K-118, 34210 Esenler-/Istanbul-TR Istanbul Technical University, Department of Geomatics Engineering, 34469 Maslak Istanbul, Turkey Istanbul Technical University, Department of Geomatics Engineering, 34469 Maslak Istanbul, Turkey The human face includes different colors and forms due to its complexity. Therefore, facial image processing comprises even more problems than image processing of other objects. Interest point detection is one of the important problems in computer vision, which is the key aspect of solving problems such as facial expression analysis, age analysis, sex defining, facial recognition, and three-dimensional face modelling in augmented reality. To accomplish these tasks, facial interest points need automatic definition. A hybrid algorithm was developed to detect automatically interest regions and points in multiple images in the resented study. The study used processed facial images from an authorized image database with a resolution of 1600 x 1200, taken in standardized illumination conditions by using an InSpeck Mega Capturor II optical 3D structured light digitizer and 1000-W halogen lamp. The presented study integrated skin color analysis with the Haar classification method, processing 11 male and 25 female facial images with the developed algorithm. The average accuracy of facial interest point detection was 0.68 mm after testing all images.http://dergipark.gov.tr/download/article-file/302653Close-range photogrammetryface recognition and facial interest pointsimage matching and processing |
spellingShingle | Bülent Bayram G. Çiğdem Çavdaroğlu Dursun Zafer Şeker Sıtkı Külür A novel approach to automatic detection of interest points in multiple facial images International Journal of Environment and Geoinformatics Close-range photogrammetry face recognition and facial interest points image matching and processing |
title | A novel approach to automatic detection of interest points in multiple facial images |
title_full | A novel approach to automatic detection of interest points in multiple facial images |
title_fullStr | A novel approach to automatic detection of interest points in multiple facial images |
title_full_unstemmed | A novel approach to automatic detection of interest points in multiple facial images |
title_short | A novel approach to automatic detection of interest points in multiple facial images |
title_sort | novel approach to automatic detection of interest points in multiple facial images |
topic | Close-range photogrammetry face recognition and facial interest points image matching and processing |
url | http://dergipark.gov.tr/download/article-file/302653 |
work_keys_str_mv | AT bulentbayram anovelapproachtoautomaticdetectionofinterestpointsinmultiplefacialimages AT gcigdemcavdaroglu anovelapproachtoautomaticdetectionofinterestpointsinmultiplefacialimages AT dursunzaferseker anovelapproachtoautomaticdetectionofinterestpointsinmultiplefacialimages AT sıtkıkulur anovelapproachtoautomaticdetectionofinterestpointsinmultiplefacialimages AT bulentbayram novelapproachtoautomaticdetectionofinterestpointsinmultiplefacialimages AT gcigdemcavdaroglu novelapproachtoautomaticdetectionofinterestpointsinmultiplefacialimages AT dursunzaferseker novelapproachtoautomaticdetectionofinterestpointsinmultiplefacialimages AT sıtkıkulur novelapproachtoautomaticdetectionofinterestpointsinmultiplefacialimages |