• Home
  • Search
  • Pre-trained CNNs Models for Content based Image Retrieval
  • Cite Icon21
  • https://doi.org/10.14569/ijacsa.2021.0120723Copy DOI Icon

Pre-trained CNNs Models for Content based Image Retrieval

  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Content based image retrieval (CBIR) systems is a ‎common recent method for image retrieval and is ‎based mainly ‎on two pillars extracted features and similarity measures. Low ‎level image presentations, ‎based on colour, texture and shape ‎properties are the most common feature extraction methods used ‎by ‎traditional CBIR systems. Since these traditional handcrafted ‎features require good prior domain ‎knowledge, inaccurate ‎features used for this type of CBIR systems may widen the ‎semantic gap and ‎could lead to very poor performance retrieval ‎results. Hence, features extraction methods, which ‎are ‎independent of domain knowledge and have automatic ‎learning capabilities from input image are ‎highly useful. Recently, ‎pre-trained deep convolution neural networks (CNN) with ‎transfer learning ‎facilities have ability to generate and extract ‎accurate and expressive features from image data. Unlike ‎other ‎types of deep CNN models which require huge amount of data ‎and massive processing time ‎for training purposes, the pre-‎trained CNN models have already trained for thousands of ‎classes of large-scale data, including huge ‎images and their ‎information could be easily used and transferred. ResNet18 ‎and ‎SqueezeNet are successful and effective examples of pre-‎trained CNN models used recently in many ‎machine learning ‎applications, such as classification, clustering and object ‎recognition. In this ‎study, we have developed CBIR systems ‎based on features extracted using ResNet18 and SqueezeNet ‎pre-‎trained CNN models. Here, we have utilized these pre-trained ‎CNN models to extract two groups of features ‎that are stored ‎separately and then later are used for online image searching and ‎retrieval. Experimental ‎results on two popular image datasets ‎Core-1K and GHIM-10K show that ResNet18 features ‎based on ‎the CBIR method have overall accuracy of 95.5% and 93.9% for ‎the two datasets, respectively, which ‎greatly outperformed the ‎traditional handcraft features based on the CBIR method.‎

Loading PDF

Similar Papers
  • Research Article
  • Citations7

Pre-trained convolution neural networks models for content-based medical image retrieval

  • Dec 01, 2022
  • International Journal of ADVANCED AND APPLIED SCIENCES
  • Ali Ahmed +2
  • Research Article
  • Citations3

Content-based medical image retrieval method using multiple pre-trained convolutional neural networks feature extraction models

  • Jun 01, 2024
  • International Journal of ADVANCED AND APPLIED SCIENCES
  • Ahmad A Alzahrani +2
  • Conference Article
  • Citations18

Image Retrieval by Fusion of Features from Pre-trained Deep Convolution Neural Networks

  • Mar 01, 2019
  • Vijayakumar Bhandi +1
  • Supplementary Content

Texture Patterns for Object Recognition and Content-Based Color Image Retrieval

  • Dec 21, 2020
  • Griffith Research Online (Griffith University, Queensland, Australia)
  • Muhammad Asif
  • Research Article

Study and Analysis of User Desired Image Retrieval

  • Oct 01, 2021
  • Recent Advances in Computer Science and Communications
  • John Bosco P +1
  • Research Article
  • Citations66

An effective hybrid framework for content based image retrieval (CBIR)

  • May 12, 2021
  • Multimedia Tools and Applications
  • Umer Ali Khan +2
  • Research Article
  • Citations23

Content Based Image Retrieval System Using CNN based Deep Learning Models

  • Jan 01, 2024
  • Procedia Computer Science
  • Giriraj Gautam +1
  • Research Article
  • Citations37

Review of image low-level feature extraction methods for content-based image retrieval

  • Nov 18, 2019
  • Sensor Review
  • Shenlong Wang +2
  • Conference Article
  • Citations3

Content-based 3D image retrieval using point cloud library a novel approach for the retrieval of 3D images

  • Apr 01, 2017
  • G Aiswarya +5
  • Research Article
  • Citations4

Learning image representations for content-based image retrieval of radiotherapy treatment plans

  • May 03, 2023
  • Physics in Medicine & Biology
  • Charles Huang +9
  • Research Article
  • Citations3

Multi-Featured Content-Based Image Retrieval Using Color and Texture Features

  • Aug 01, 2016
  • Applied Mechanics and Materials
  • Mehmet Ayan +2
  • Conference Article
  • Citations22

Improving relevance feedback for content based medical image retrieval

  • Feb 01, 2014
  • T Rajalakshmi +1
  • Conference Article
  • Citations36

<title>A general framework for content-based medical image retrieval with its application to mammograms</title>

  • Apr 15, 2005
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Chia-Hung Wei +2
  • Research Article
  • Citations1

Content-Based Image Retrieval Using Discrete Wavelet Transform and Convolutional Neural Network

  • Apr 02, 2021
  • Journal of Contemporary Issues in Business and Government
  • S Mohandass +1
  • Research Article
  • Citations148

A Survey on Current Content based Image Retrieval Methods

  • May 01, 2002
  • IETE Journal of Research
  • Manesh Kokare +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.