| dc.contributor.author | Ochango, Vincent Mbandu | |
| dc.date.accessioned | 2025-03-13T14:26:59Z | |
| dc.date.available | 2025-03-13T14:26:59Z | |
| dc.date.issued | 2023 | |
| dc.identifier.issn | 2790-7945 | |
| dc.identifier.uri | http://repository.mut.ac.ke:8080/xmlui/handle/123456789/6520 | |
| dc.description.abstract | The use of a computer to recognize a person by the means of their face is what is known as face recognition in artificial intelligence. The term biometrics is an umbrella term that includes face recognition as well as signature, fingerprint, eye scanning, gait, and palm print recognition. The principal component analysis technique was used in this paper to extract distinctive features from the faces which are matched with other faces stored in the database and predictive results indicated which faces were recognized and the ones that were not recognized. The accuracy of these techniques was calculated and the principal component analysis technique was found to be 86.3636% accurate and it was concluded that the technique performs better when it comes to face recognition. | en_US |
| dc.language.iso | en | en_US |
| dc.publisher | International Journal of Formal Sciences: Current and Future Research Trends | en_US |
| dc.subject | Feature Descriptor; Covariance Matrix; Eigenface; eigenvector; Linear Algebra. | en_US |
| dc.title | A Model for Face Recognition using EigenFace Algorithm | en_US |
| dc.type | Article | en_US |
