Content based image retrieval using various distance metrics

Authors:
Sanjay Patil;Sanjay Talbar
Affiliations:
Department of Electronics Engg. Padmabhushan Vasantdada Patil Pratisthan's College Of Engg., Sion-Chunabhatti, Mumbai, India;Shri Guru Gobind Singhji College of Engineering and Technology, Nanded, India
Venue:
ICDEM'10 Proceedings of the Second international conference on Data Engineering and Management
Year:
2010

Citing 4
Cited 1

Color indexing

International Journal of Computer Vision
Texture classification using QMF bank-based subband decomposition

CVGIP: Graphical Models and Image Processing
Content-Based Image Retrieval Systems

Computer
Colour and Texture Features for Content Based Image Retrieval

CGIV '06 Proceedings of the International Conference on Computer Graphics, Imaging and Visualisation

Figure Based Biomedical Document Retrieval System using Structural Image Features

International Journal of Knowledge Discovery in Bioinformatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Content based image retrieval (CBIR) provides an effective way to search the images from the databases. The feature extraction and similarity measures are the two key parameters for retrieval performance. A similarity measure plays an important role in image retrieval. This paper compares six different distance metrics such as Euclidean, Manhattan, Canberra, Bray-Curtis, Square chord, Square chi-squared distances to find the best similarity measure for image retrieval. Using pyramid structured wavelet decomposition, energy levels are calculated. These energy levels are compared by calculating distance between query image and database images using above mentioned seven different similarity metrics. A large image database from Brodatz album is used for retrieval purpose. Experimental results shows the superiority of Canberra, Bray-Curtis, Square chord, and Square Chi-squared distances over the conventional Euclidean and Manhattan distances.