Combined descriptors and classifiers for automatic image annotation

Abstract

Due to the large amounts of multimedia data prevalent on the Web, researchers and industries are beginning to pay more attention to the Multimedia Semantic Web. Despite of decades of research, neither model based approaches can provide quality annotation to images. Many features extraction method and classifiers are used singly, with modest results, for automatic image annotation. The proposed approach is to select and combine together some efficient descriptors and classifiers. This document provides a semantic annotation system that combines some descriptors and classifiers in order to increase the accuracy of the annotation system. The color histograms, Texture, GIST and invariant moments, used as features extraction methods, are combined together with multiclass support vector machine, Bayesian networks, Neural networks and nearest neighbour classifiers, in order to annotate the image content with the appropriate keywords. The accuracy of the proposed approach is supported by the good experimental results obtained from ETH-80 databases.

Grouping K-Means Adjacent Regions for Semantic Image Annotation Using Bayesian Networks

“…With the rapid growth in data volumes, the manual annotation remains today prohibitively expensive and impractical. Therefore, the automatic image annotation becomes an important and unavoidable way to reduce the existing semantic gap between the high-level concepts that was been used by humans to describe images and the low-level visual content used by the machine to represent images [1][2]. In this paper, we focus on producing automated image annotation approaches that attempt to provide an answer to this problem that still persistent.…”