Content based mammography images retrieval using Ripley's K function

Authors:
Leonardo S. Kury A. Mendes;Anselmo Cardoso de Paiva;Cláudio de Souza Baptista;Aristófanes Corrêa Silva
Affiliations:
Federal University of Maranhão - UFMA, São Luís, MA - Brazil;Federal University of Maranhão - UFMA, São Luís, MA - Brazil;University of Campina Grande - UFCG, Campina Grande, PB - Brazil;Federal University of Maranhão - UFMA, São Luís, MA - Brazil
Venue:
Proceedings of the 2nd International Conference on Interaction Sciences: Information Technology, Culture and Human
Year:
2009

Citing 7
Cited 0

VisualSEEk: a fully automated content-based image query system

MULTIMEDIA '96 Proceedings of the fourth ACM international conference on Multimedia
Performance evaluation in content-based image retrieval: overview and proposals

Pattern Recognition Letters - Special issue on image/video indexing and retrieval
Modern Information Retrieval

Modern Information Retrieval
Query by Image and Video Content: The QBIC System

Computer
A New Multiscale, Curvature-Based Shape Representation Technique for Image Retrieval Based on DSP Techniques

HIS '05 Proceedings of the Fifth International Conference on Hybrid Intelligent Systems
MultiWaveMed: a system for medical image retrieval through wavelets transformations

CBMS'03 Proceedings of the 16th IEEE conference on Computer-based medical systems
Retrieval by content of medical images using texture for tissue identification

CBMS'03 Proceedings of the 16th IEEE conference on Computer-based medical systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

The need for efficiently storing and retrieving digital images is increasing due to the raise in the availability of image acquisition devices, which are used in several domains, specially medical images. Many algorithms for Content-Based Image Retrieval (CBIR) have been proposed. These techniques extend the traditional search for images via descriptive text by including visual characteristics of these images. These characteristics can be obtained through extraction of features such as color, shape, texture and position of the objects. In this paper we present the use of Ripley's K function together with co-occurrence matrix as texture signature for content-based retrieval of mammographic images. Combining both techniques we reached precision of 80% with recall around 30%. Besides, we developed a database extension prototype for the Oracle 10g DBMS.