Automatic image annotation by ensemble of visual descriptors

Date

2007-06-22

Author

Akbaş, Emre

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

204
views

0
downloads

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 usually requires normalization which may cause an undesirable distortion in the feature space. An elegant way of reducing the effects of these problems is to design a dedicated feature space for each image category, depending on its content, and learn a range of visual properties of the whole image from a variety of feature sets. For this purpose, a two-layer ensemble learning system, called Supervised Annotation by Descriptor Ensemble (SADE), is proposed. SADE, initially, extracts a variety of low-level visual descriptors from the image. Each descriptor is, then, fed to a separate learning machine in the first layer Finally, the meta-layer classifier is trained on the output of the first layer classifiers and the images are annotated by using the decision of the meta-layer classifier This approach not only avoids normalization, but also reduces the effects of dimensional curse and redundancy. The proposed system outperforms a state-of-the-art automatic image annotation system, in an equivalent experimental setup.

Subject Keywords

Photographic technology, Imaging science, Remote sensing, Computational biology, Computer science

URI

https://hdl.handle.net/11511/37659

DOI

https://doi.org/10.1109/cvpr.2007.383484

Collections

Department of Computer Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Automatic image annotation by ensemble of visual descriptors Akbaş, Emre; Yarman Vural, Fatoş Tunay; Department of Computer Engineering (2006) 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...
Selection of the best representative feature and membership assignment for content-based fuzzy image database Uysal, Mehmet Ali; Yarman-Vural, FT (2003-01-01) A major design issue in content-based image retrieval system is the selection of the feature set. This study attacks the problem of finding a discriminative feature for each class, which is optimal in some sense. The class-dependent feature is, then, used to calculate the membership value of each object class for content-based fuzzy image retrieval systems. The Best Representative Feature (BRF) for each class is identified in a training stage. Then, using the BRF of each object class, the segment groups in ...
Optimum design of grillage systems using harmony search algorithm Erdal, Ferhat; Saka, Mehmet Polat; Department of Engineering Sciences (2007) Harmony search method based optimum design algorithm is presented for the grillage systems. This numerical optimization technique imitates the musical performance process that takes place when a musician searches for a better state of harmony. For instance, jazz improvisation seeks to find musically pleasing harmony similar to the optimum design process which seeks to find the optimum solution. The design algorithm considers the displacement and strength constraints which are implemented from LRFD-AISC (Loa...
Computational representation of protein sequences for homology detection and classification Oğul, Hasan; Mumcuoğlu, Ünal Erkan; Department of Information Systems (2006) Machine learning techniques have been widely used for classification problems in computational biology. They require that the input must be a collection of fixedlength feature vectors. Since proteins are of varying lengths, there is a need for a means of representing protein sequences by a fixed-number of features. This thesis introduces three novel methods for this purpose: n-peptide compositions with reduced alphabets, pairwise similarity scores by maximal unique matches, and pairwise similarity scores by...
Implicit motif distribution based hybrid computational kernel for sequence classification Atalay, Mehmet Volkan (Oxford University Press (OUP), 2005-04-15) Motivation: We designed a general computational kernel for classification problems that require specific motif extraction and search from sequences. Instead of searching for explicit motifs, our approach finds the distribution of implicit motifs and uses as a feature for classification. Implicit motif distribution approach may be used as modus operandi for bioinformatics problems that require specific motif extraction and search, which is otherwise computationally prohibitive.

Citation Formats

E. Akbaş, “Automatic image annotation by ensemble of visual descriptors,” 2007, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/37659.