Title: Hybrid approach for content-based image retrieval

Authors: S. Theetchenya; Somula Ramasubbareddy; S. Sankar; Syed Muzamil Basha

Addresses: Department of CSE, Sona College of Technology, Salem, 636005, Tamilnadu, India ' Department of Information Technology, VNRVJIET, Hyderabad, 500016, India ' Department of CSE, Sona College of Technology, Salem, 636005, Tamilnadu, India ' School of Computing and Information Technology, Reva University, Bangalore, 560064, Karnataka, India

Abstract: Content-based image retrieval (CBIR) is one of the vital research areas in image processing. The CBIR, also known as query by image content, i.e., the problem searching for similar digital images in a large database. The existing CBIR system used to retrieve the relevant images lack inaccuracy. To improve the accuracy level of CBIR, the proposed system introduces an unsupervised Hybrid Approach. The proposed system gets the input images as colour image. The pre-processing is performed using the median filter. This system is extracted the feature such as colour, texture, brightness distribution, Euclidean distance from hybrid approach. While the user gives the query on this system, the real time comparison is made with feature stored database. Finally the proposed system retrieves the related image from database. The proposed system compared with various dataset Corel 10000, IMAGENET1M and also increased the accuracy level by 5%.

Keywords: CBIR; content-based image retrieval; query by image content; colour histogram; texture detection algorithm; brightness distribution algorithm.

DOI: 10.1504/IJDS.2021.117467

International Journal of Data Science, 2021 Vol.6 No.1, pp.45 - 56

Received: 07 Jul 2020
Accepted: 05 Nov 2020
Published online: 07 Sep 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article