Content based image retrieval using hybrid features and various distance metric

https://doi.org/10.1016/j.jesit.2016.12.009Get rights and content
Under a Creative Commons license
open access

Abstract

In last decade, large database of images have grown rapidly and will continue in future. Retrieval and querying of these image in efficient way is needed in order to access the visual content from large database. Content based image retrieval (CBIR) provides the solution for efficient retrieval of image from these huge image database. In this article a hybrid feature based efficient CBIR system is proposed using various distance measure. Spatial domain features including color auto-correlogram, color moments, HSV histogram features, and frequency domain features like moments using SWT, features using Gabor wavelet transform are used. Further, to enhance precision binarized statistical image features, color and edge directivity descriptor features are employed for developing efficient CBIR system. Various distance metrics are used for retrieval.

The experiments are performed using WANG database which consists of 1000 images from 10 different classes. Experimental result shows that the proposed approach performs better in terms of precision compared to other existing systems.

Keywords

CBIR
DTCWT
SWT moments
Minkowski distance
Mahalanobis distance

Cited by (0)

Peer review under the responsibility of Electronics Research Institute (ERI).

  1. Download : Download high-res image (31KB)
  2. Download : Download full-size image
.