Mining Weakly Labeled Web Facial Images For Search-BasedFace Annotation
Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2015, Vol 17, Issue 4
Abstract
Abstract: This paper investigates a framework of search-based face annotation (SBFA) by mining weaklylabeled facial images that are freely available on the World Wide Web (WWW). One challenging problem forsearch-based face annotation scheme is how to effectively perform annotation by exploiting the list of mostsimilar facial images and their weak labels that are often noisy and incomplete. To tackle this problem, wepropose an effective unsupervised label refinement (ULR) approach for refining the labels of web facial imagesusing machine learning techniques. We formulate the learning problem as a convex optimization and developeffective optimization algorithms to solve the large-scale learning task efficiently. To further speed up theproposed scheme, we also propose a clustering-based approximation algorithm which can improve thescalability considerably. We have conducted an extensive set of empirical studies on a large-scale web facialimage testbed, in which encouraging results showed that the proposed ULR algorithms can significantly boostthe performance of the promising SBFA scheme.
Authors and Affiliations
Mr. Rohit D. Mane
Keywords
Related Articles
- EP ID EP148252
- DOI -
- Views 98
- Downloads 0
A New Approach to Compressed Image Steganography Using Wavelet Transform
Abstract : This paper proposes a novel steganographic technique that embeds compressed payload image within cover image. The pixel adjustment of the cover image is done optimally using Fourier Transform, so that visual c...
An effective citation metadata extraction process based on BibPro parser
There is a dramatic increase in academic publications and these publications are integrated to the digital libraries by making use of citation string. Any author can publish the journals conferences with the help...
Reducing location error in Wireless Sensor Networks
Abstract: Localization is the basic problem in the wireless sensor networks. All the result data get wasted if the node is placed in the wrong position. Range based and Range free algorithms are used for locating t...
Cloudburst Predetermination System
Abstract: Cloudburst is a devastating disaster that usually occurs during rainy seasons at Himalayan regions.The recent floods in the ‘Kedarnath’ area, Uttarakhand are a classic example of flash floods in the MandakiniRi...
Results for Web Graph Mining Base Recommender System forQuery, Image and Social Network using Query Suggestion Algorithm and Heat Diffusion Method
Abstract: In Previous paper, We have already discussed a general framework on Web graphs mining based recommender system for Query, Image and Social Network using Query Suggestion Algorithm and Heat Diffusion Method. In...