An image retrieval system based on region classification

Download

index.pdf

Date

2004

Author

Özcanli-Özbay, Özge Can

Metadata

Show full item record

Item Usage Stats

238
views

147
downloads

In this thesis, a Content Based Image Retrieval (CBIR) system to query the objects in an image database is proposed. Images are represented as collections of regions after being segmented with Normalized Cuts algorithm. MPEG-7 content descriptors are used to encode regions in a 239-dimensional feature space. User of the proposed CBIR system decides which objects to query and labels exemplar regions to train the system using a graphical interface. Fuzzy ARTMAP algorithm is used to learn the mapping between feature vectors and binary coded class identification numbers. Preliminary recognition experiments prove the power of fuzzy ARTMAP as a region classifier. After training, features of all regions in the database are extracted and classified. Simple index files enabling fast access to all regions from a given class are prepared to be used in the querying phase. To retrieve images containing a particular object, user opens an image and selects a query region together with a label in the graphical interface of our system. Then the system ranks all regions in the indexed set of the query class with respect to their L2 (Euclidean) distance to the query region and displays resulting images. During retrieval experiments, comparable class precisions with respect to exhaustive searching of the database are maintained which demonstrates e ectiveness of the classifier in narrowing down the search space.

Subject Keywords

Electronic computers., Computer science.

URI

http://etd.lib.metu.edu.tr/upload/12605082/index.pdf
https://hdl.handle.net/11511/14249

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

An image retrieval system based on region classification Ozcanli, OC; Yarman-Vural, F (2004-01-01) In this study, a content based image retrieval (CBIR) system to query the objects in an image database is proposed. Images are represented as collections of regions after being segmented with Normalized Cuts algorithm. MPEG-7 content descriptors are used to encode regions in a 239-dimensional feature space. User of the proposed CBIR system decides which objects to query and labels exemplar regions to train the system using a graphical interface. Fuzzy ARTMAP algorithm is used to learn the mapping between fe...
Semantic service discovery with heuristic relevance calculation Özyönüm, Müge; Doğru, Ali Hikmet; Department of Computer Engineering (2010) In this thesis, a semantically aided web service and restful service search mechanism is presented that makes use of an ontology. The mechanism relates method names, input and output parameters for ontology guided matches and offers results with varying relevance corresponding to the matching degree. The mechanism is demonstrated using an experimental domain that is tourism and travel. An ontology is created to support a set of web services that exist in this domain.
An image encryption algorithm robust to post-encryption bitrate conversion Akdağ, Sadık Bahaettin; Candan, Çağatay; Department of Electrical and Electronics Engineering (2006) In this study, a new method is proposed to protect JPEG still images through encryption by employing integer-to-integer transforms and frequency domain scrambling in DCT channels. Different from existing methods in the literature, the encrypted image can be further compressed, i.e. transcoded, after the encryption. The method provides selective encryption/security level with the adjustment of its parameters. The encryption method is tested with various images and compared with the methods in the literature ...
A pattern classification approach boosted with genetic algorithms Yalabık, İsmet; Yarman Vural, Fatoş Tunay; Department of Computer Engineering (2007) Ensemble learning is a multiple-classier machine learning approach which combines, produces collections and ensembles statistical classiers to build up more accurate classier than the individual classiers. Bagging, boosting and voting methods are the basic examples of ensemble learning. In this thesis, a novel boosting technique targeting to solve partial problems of AdaBoost, a well-known boosting algorithm, is proposed. The proposed systems nd an elegant way of boosting a bunch of classiers successively t...
Design and implementation of a secure and searchable audit logging system İncebacak, Davut; Çetin, Yasemin; Department of Information Systems (2007) Logs are append-only time-stamped records to represent events in computers or network devices. Today, in many real-world networking applications, logging is a central service however it is a big challenge to satisfy the conflicting requirements when the security of log records is of concern. On one hand, being kept on mostly untrusted hosts, the logs should be preserved against unauthorized modifications and privacy breaches. On the other, serving as the primary evidence for digital crimes, logs are often n...

Citation Formats

Ö. C. Özcanli-Özbay, “An image retrieval system based on region classification,” M.S. - Master of Science, Middle East Technical University, 2004.