Recognition of Reconstructed Frontal Face Images Using FFT-PCA/SVD Algorithm
Face recognition has gained prominence among the various biometric-based methods (such as fingerprint and iris) due to its noninvasive characteristics. Modern face recognition modules/algorithms have been successful in many application areas (access control, entertainment/leisure, security system ba...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Journal of Applied Mathematics |
| Online Access: | http://dx.doi.org/10.1155/2020/9127465 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832567422922522624 |
|---|---|
| author | Louis Asiedu Felix O. Mettle Joseph A. Mensah |
| author_facet | Louis Asiedu Felix O. Mettle Joseph A. Mensah |
| author_sort | Louis Asiedu |
| collection | DOAJ |
| description | Face recognition has gained prominence among the various biometric-based methods (such as fingerprint and iris) due to its noninvasive characteristics. Modern face recognition modules/algorithms have been successful in many application areas (access control, entertainment/leisure, security system based on biometric data, and user-friendly human-machine interfaces). In spite of these achievements, the performance of current face recognition algorithms/modules is still inhibited by varying environmental constraints such as occlusions, expressions, varying poses, illumination, and ageing. This study assessed the performance of Principal Component Analysis with singular value decomposition using Fast Fourier Transform (FFT-PCA/SVD) for preprocessing the face recognition algorithm on left and right reconstructed face images. The study found that average recognition rates for the FFT-PCA/SVD algorithm were 95% and 90% when the left and right reconstructed face images are used as test images, respectively. The result of the paired sample t-test revealed that the average recognition distances for the left and right reconstructed face images are not significantly different when FFT-PCA/SVD is used for recognition. FFT-PCA/SVD is recommended as a viable algorithm for recognition of left and right reconstructed face images. |
| format | Article |
| id | doaj-art-0b2f8f32b5a74b2b9d86d8eadd3453b2 |
| institution | Kabale University |
| issn | 1110-757X 1687-0042 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Applied Mathematics |
| spelling | doaj-art-0b2f8f32b5a74b2b9d86d8eadd3453b22025-02-03T01:01:24ZengWileyJournal of Applied Mathematics1110-757X1687-00422020-01-01202010.1155/2020/91274659127465Recognition of Reconstructed Frontal Face Images Using FFT-PCA/SVD AlgorithmLouis Asiedu0Felix O. Mettle1Joseph A. Mensah2Department of Statistics & Actuarial Science, School of Physical and Mathematical Sciences, University of Ghana, Legon, Accra, GhanaDepartment of Statistics & Actuarial Science, School of Physical and Mathematical Sciences, University of Ghana, Legon, Accra, GhanaDepartment of Statistics & Actuarial Science, School of Physical and Mathematical Sciences, University of Ghana, Legon, Accra, GhanaFace recognition has gained prominence among the various biometric-based methods (such as fingerprint and iris) due to its noninvasive characteristics. Modern face recognition modules/algorithms have been successful in many application areas (access control, entertainment/leisure, security system based on biometric data, and user-friendly human-machine interfaces). In spite of these achievements, the performance of current face recognition algorithms/modules is still inhibited by varying environmental constraints such as occlusions, expressions, varying poses, illumination, and ageing. This study assessed the performance of Principal Component Analysis with singular value decomposition using Fast Fourier Transform (FFT-PCA/SVD) for preprocessing the face recognition algorithm on left and right reconstructed face images. The study found that average recognition rates for the FFT-PCA/SVD algorithm were 95% and 90% when the left and right reconstructed face images are used as test images, respectively. The result of the paired sample t-test revealed that the average recognition distances for the left and right reconstructed face images are not significantly different when FFT-PCA/SVD is used for recognition. FFT-PCA/SVD is recommended as a viable algorithm for recognition of left and right reconstructed face images.http://dx.doi.org/10.1155/2020/9127465 |
| spellingShingle | Louis Asiedu Felix O. Mettle Joseph A. Mensah Recognition of Reconstructed Frontal Face Images Using FFT-PCA/SVD Algorithm Journal of Applied Mathematics |
| title | Recognition of Reconstructed Frontal Face Images Using FFT-PCA/SVD Algorithm |
| title_full | Recognition of Reconstructed Frontal Face Images Using FFT-PCA/SVD Algorithm |
| title_fullStr | Recognition of Reconstructed Frontal Face Images Using FFT-PCA/SVD Algorithm |
| title_full_unstemmed | Recognition of Reconstructed Frontal Face Images Using FFT-PCA/SVD Algorithm |
| title_short | Recognition of Reconstructed Frontal Face Images Using FFT-PCA/SVD Algorithm |
| title_sort | recognition of reconstructed frontal face images using fft pca svd algorithm |
| url | http://dx.doi.org/10.1155/2020/9127465 |
| work_keys_str_mv | AT louisasiedu recognitionofreconstructedfrontalfaceimagesusingfftpcasvdalgorithm AT felixomettle recognitionofreconstructedfrontalfaceimagesusingfftpcasvdalgorithm AT josephamensah recognitionofreconstructedfrontalfaceimagesusingfftpcasvdalgorithm |