Title: PCA-based home videos annotation system

Authors: Nashwa El-Bendary, Hossam M. Zawbaa, Aboul Ella Hassanien, Vaclav Snasel

Addresses: Arab Academy for Science, Technology, and Maritime Transport, Cairo, Egypt. ' Faculty of Computers and Information, Cairo University, Cairo, Egypt. ' Faculty of Computers and Information, Cairo University, Cairo, Egypt. ' Faculty of Electrical Engineering and Computer Science, VSB-Technical University of Ostrava, Ostrava Poruba, Czech Republic

Abstract: This paper presents a semi-automatic home videos annotation system that searches into video contents and retrieves video shots for a specific person. The proposed system is composed of four phases; namely (a) shot detection phase, (b) face detection and recognition phase using the Principal Component Analysis (PCA) feature extraction algorithm based on Haar-like features, (c) face clustering and annotation phase, and (d) retrieval phase. The proposed system is simple and provides a user-friendly interface. It greatly reduces workload and enhances the accuracy of annotating person’s faces in home videos.

Keywords: PCA; principal component analysis; face detection; face recognition; clustering; Haar-like features; video annotation; home videos; shot detection; feature extraction; face clustering; face annotation; image retrieval.

DOI: 10.1504/IJRIS.2011.042202

International Journal of Reasoning-based Intelligent Systems, 2011 Vol.3 No.2, pp.71 - 79

Received: 08 May 2021
Accepted: 12 May 2021

Published online: 31 Aug 2011 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article