Automatic image annotation by ensemble of visual descriptors

Download

index.pdf

Date

2006

Author

Akbaş, Emre

Metadata

Show full item record

Item Usage Stats

192
views

138
downloads

Automatic image annotation is the process of automatically producing words to de- scribe the content for a given image. It provides us with a natural means of semantic indexing for content based image retrieval. In this thesis, two novel automatic image annotation systems targeting dierent types of annotated data are proposed. The rst system, called Supervised Ensemble of Visual Descriptors (SEVD), is trained on a set of annotated images with predened class labels. Then, the system auto- matically annotates an unknown sample depending on the classication results. The second system, called Unsupervised Ensemble of Visual Descriptors (UEVD), assumes no class labels. Therefore, the annotation of an unknown sample is accomplished by unsupervised learning based on the visual similarity of images. The available auto- matic annotation systems in the literature mostly use a single set of features to train a single learning architecture. On the other hand, the proposed annotation systems utilize a novel model of image representation in which an image is represented with a variety of feature sets, spanning an almost complete visual information comprising color, shape, and texture characteristics. In both systems, a separate learning entity is trained for each feature set and these entities are gathered under an ensemble learning approach. Empirical results show that both SEVD and UEVD outperform some of the state-of-the-art automatic image annotation systems in equivalent experimental setups.

Subject Keywords

Computer Science.

URI

http://etd.lib.metu.edu.tr/upload/3/12607443/index.pdf
https://hdl.handle.net/11511/16027

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Automatic Definition of Optimal Default Parameters of Models: Image Matting Application Ravve, Elena V.; Volkovich, Zeev; Weber, Gerhard Wilhelm (2015-09-24) As a general rule, each user must provide the tool applied with particular values of its input parameters. An inexperienced user may hardly figure out their values and the tool developer must define the default values in order to help her/him. We present an approach to solve the problem with the help of multi-criteria optimization that is new in this formulation. We demonstrate our approach in closer details using an example from the automatic definition of optimal default parameters for real-time merging o...
Hanolistic : a hierarchical automatic image annotation system using holistic approach Öztimur, Özge; Yarman Vural, Fatoş Tunay; Department of Computer Engineering (2008) Automatic image annotation is the process of assigning keywords to digital images depending on the content information. In one sense, it is a mapping from the visual content information to the semantic context information. In this thesis, we propose a novel approach for automatic image annotation problem, where the annotation is formulated as a multivariate mapping from a set of independent descriptor spaces, representing a whole image, to a set of words, representing class labels. For this purpose, a hiera...
Automatic image annotation by ensemble of visual descriptors Akbaş, Emre (2007-06-22) Automatic image annotation systems available in the literature concatenate color, texture and/or shape features in a single feature vector to learn a set of high level semantic categories using a single learning machine. This approach is quite naive to map the visual features to high level semantic information concerning the categories. Concatenation of many features with different visual properties and wide dynamical ranges may result in curse of dimensionality and redundancy problems. Additionally, it usu...
Image annotation with semi-supervised clustering Sayar, Ahmet; Yarman Vural, Fatoş Tunay; Department of Computer Engineering (2009) Image annotation is defined as generating a set of textual words for a given image, learning from the available training data consisting of visual image content and annotation words. Methods developed for image annotation usually make use of region clustering algorithms to quantize the visual information. Visual codebooks are generated from the region clusters of low level visual features. These codebooks are then, matched with the words of the text document related to the image, in various ways. In this th...
Selective word encoding for effective text representation Ozkan, Savas; Ozkan, Akin (The Scientific and Technological Research Council of Turkey, 2019-01-01) Determining the category of a text document from its semantic content is highly motivated in the literature and it has been extensively studied in various applications. Also, the compact representation of the text is a fundamental step in achieving precise results for the applications and the studies are generously concentrated to improve its performance. In particular, the studies which exploit the aggregation of word-level representations are the mainstream techniques used in the problem. In this paper, w...

Citation Formats

E. Akbaş, “Automatic image annotation by ensemble of visual descriptors,” M.S. - Master of Science, Middle East Technical University, 2006.