Assessment of time-lapse in visible and thermal face recognition
Although face recognition seems as an easy task for human, automatic face recognition is a much more challenging task due to variations in time, illumination and pose. In this paper, the influence of time-lapse on visible and thermal images is examined. Orthogonal moment invariants are used as a fea...
Main Authors: | , , , |
---|---|
Format: | Article |
Published: |
World Academy of Science, Engineering and Technology
2012
|
Subjects: |
_version_ | 1796856905269772288 |
---|---|
author | Farokhi, Sajad Shamsuddin, Siti Mariyam Jan, Flusse Ullah Sheikh, Usman |
author_facet | Farokhi, Sajad Shamsuddin, Siti Mariyam Jan, Flusse Ullah Sheikh, Usman |
author_sort | Farokhi, Sajad |
collection | ePrints |
description | Although face recognition seems as an easy task for human, automatic face recognition is a much more challenging task due to variations in time, illumination and pose. In this paper, the influence of time-lapse on visible and thermal images is examined. Orthogonal moment invariants are used as a feature extractor to analyze the effect of time-lapse on thermal and visible images and the results are compared with conventional Principal Component Analysis (PCA). A new triangle square ratio criterion is employed instead of Euclidean distance to enhance the performance of nearest neighbor classifier. The results of this study indicate that the ideal feature vectors can be represented with high discrimination power due to the global characteristic of orthogonal moment invariants. Moreover, the effect of time-lapse has been decreasing and enhancing the accuracy of face recognition considerably in comparison with PCA. Furthermore, our experimental results based on moment invariant and triangle square ratio criterion show that the proposed approach achieves on average 13.6% higher in recognition rate than PCA. |
first_indexed | 2024-03-05T18:49:48Z |
format | Article |
id | utm.eprints-31712 |
institution | Universiti Teknologi Malaysia - ePrints |
last_indexed | 2024-03-05T18:49:48Z |
publishDate | 2012 |
publisher | World Academy of Science, Engineering and Technology |
record_format | dspace |
spelling | utm.eprints-317122019-01-28T03:50:01Z http://eprints.utm.my/31712/ Assessment of time-lapse in visible and thermal face recognition Farokhi, Sajad Shamsuddin, Siti Mariyam Jan, Flusse Ullah Sheikh, Usman Q Science (General) Although face recognition seems as an easy task for human, automatic face recognition is a much more challenging task due to variations in time, illumination and pose. In this paper, the influence of time-lapse on visible and thermal images is examined. Orthogonal moment invariants are used as a feature extractor to analyze the effect of time-lapse on thermal and visible images and the results are compared with conventional Principal Component Analysis (PCA). A new triangle square ratio criterion is employed instead of Euclidean distance to enhance the performance of nearest neighbor classifier. The results of this study indicate that the ideal feature vectors can be represented with high discrimination power due to the global characteristic of orthogonal moment invariants. Moreover, the effect of time-lapse has been decreasing and enhancing the accuracy of face recognition considerably in comparison with PCA. Furthermore, our experimental results based on moment invariant and triangle square ratio criterion show that the proposed approach achieves on average 13.6% higher in recognition rate than PCA. World Academy of Science, Engineering and Technology 2012 Article PeerReviewed Farokhi, Sajad and Shamsuddin, Siti Mariyam and Jan, Flusse and Ullah Sheikh, Usman (2012) Assessment of time-lapse in visible and thermal face recognition. International Journal of Computer and Communication Engineering, 6 (2). pp. 181-186. ISSN 0950-4125 https://waset.org/Publications?p=62 |
spellingShingle | Q Science (General) Farokhi, Sajad Shamsuddin, Siti Mariyam Jan, Flusse Ullah Sheikh, Usman Assessment of time-lapse in visible and thermal face recognition |
title | Assessment of time-lapse in visible and thermal face recognition |
title_full | Assessment of time-lapse in visible and thermal face recognition |
title_fullStr | Assessment of time-lapse in visible and thermal face recognition |
title_full_unstemmed | Assessment of time-lapse in visible and thermal face recognition |
title_short | Assessment of time-lapse in visible and thermal face recognition |
title_sort | assessment of time lapse in visible and thermal face recognition |
topic | Q Science (General) |
work_keys_str_mv | AT farokhisajad assessmentoftimelapseinvisibleandthermalfacerecognition AT shamsuddinsitimariyam assessmentoftimelapseinvisibleandthermalfacerecognition AT janflusse assessmentoftimelapseinvisibleandthermalfacerecognition AT ullahsheikhusman assessmentoftimelapseinvisibleandthermalfacerecognition |