Paper Details: Downloads: 562
Serial Number: P1151044324
Title: Web Image Mining Age Estimation Framework
Authors: Mohamed Y. Eldib and Hoda M. Onsi
Abstract: In this paper, we present an automatic web image mining engine that is capable of collecting images using human age related text queries from Flickr photo sharing website that has various ancestry groups and different image qualities, 37000 images were downloaded from this step. We use the Active Shape Model for robust face detection; it acts also as a removal step for non-face images. After that, we use the bio-inspired features (BIF) to extract the facial aging information. We introduce a universal labeler algorithm to label Flickr images automatically. Finally, we use the web image collection as a training dataset, and the standard databases as testing datasets showing the superiority of our proposed image web mining algorithm, over the state-of-the-art methods
Keywords: Human age estimation, Active Shape Model, Facial feature extraction.
Journal/Conference: International Journal of Graphics, Vision and Image Processing
Volume: 11
Issue: 1
Submission Date: 10/26/2010 12:00:00 AM
Review Date: 11/28/2010 12:00:00 AM
Publishing Date: 12/4/2010 12:00:00 AM
Article Downloads: 562
Download:

Facebook