Please use this identifier to cite or link to this item:
https://scholarhub.balamand.edu.lb/handle/uob/3360
Title: | Face recognition using the SIFT most representative images | Authors: | Sallak, Nour El Hazim, Hani |
Advisors: | Dagher, Issam | Subjects: | Human face recognition (Computer science) | Issue Date: | 2013 | Abstract: | In this project, face recognition using the most SIFT representative images is presented. It is based on obtaining the SIFT features in different regions of each training image using the K-means algorithm. Based on these features, the most representative images of each face are obtained. A test image is recognized according to those representative images. The matching technique used is presented. This algorithm is compared to other algorithms for different database. |
Description: | Includes bibliographical references (p.27-28). Supervised by Dr. Issam Dagher. |
URI: | https://scholarhub.balamand.edu.lb/handle/uob/3360 | Rights: | This object is protected by copyright, and is made available here for research and educational purposes. Permission to reuse, publish, or reproduce the object beyond the personal and educational use exceptions must be obtained from the copyright holder | Ezproxy URL: | Link to full text | Type: | Project |
Appears in Collections: | UOB Theses and Projects |
Show full item record
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.