• Home
  • Search
  • Implementation of early and late fusion methods for content-based image retrieval
  • Cite Icon9
  • https://doi.org/10.21833/ijaas.2021.07.012Copy DOI Icon

Implementation of early and late fusion methods for content-based image retrieval

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Content-Based Image Retrieval (CBIR) systems retrieve images from the image repository or database in which they are visually similar to the query image. CBIR plays an important role in various fields such as medical diagnosis, crime prevention, web-based searching, and architecture. CBIR consists mainly of two stages: The first is the extraction of features and the second is the matching of similarities. There are several ways to improve the efficiency and performance of CBIR, such as segmentation, relevance feedback, expansion of queries, and fusion-based methods. The literature has suggested several methods for combining and fusing various image descriptors. In general, fusion strategies are typically divided into two groups, namely early and late fusion strategies. Early fusion is the combination of image features from more than one descriptor into a single vector before the similarity computation, while late fusion refers either to the combination of outputs produced by various retrieval systems or to the combination of different rankings of similarity. In this study, a group of color and texture features is proposed to be used for both methods of fusion strategies. Firstly, an early combination of eighteen color features and twelve texture features are combined into a single vector representation and secondly, the late fusion of three of the most common distance measures are used in the late fusion stage. Our experimental results on two common image datasets show that our proposed method has good performance retrieval results compared to the traditional way of using single features descriptor and also has an acceptable retrieval performance compared to some of the state-of-the-art methods. The overall accuracy of our proposed method is 60.6% and 39.07% for Corel-1K and GHIM-10K ‎datasets, respectively.

Similar Papers
  • Research Article

Interpretability of a Deep Learning-Based Prediction Model for Mandibular Osteoradionecrosis.

  • Oct 01, 2023
  • International Journal of Radiation Oncology*Biology*Physics
  • L Humbert-Vidan +3
  • Conference Article
  • Citations10

Comparison of early and late fusion techniques for movie trailer genre labelling

  • Jul 01, 2020
  • J.H Mervitz +3
  • Research Article
  • Citations3

Clinical and health-related quality-of-life outcomes after early and late spinal fusion in pediatric patients with congenital scoliosis at 10-year follow-up.

  • Nov 23, 2020
  • Spine deformity
  • Noriaki Kawakami +6
  • Conference Article
  • Citations14

Combine Early and Late Fusion Together: A Hybrid Fusion Framework for Image-Text Matching

  • Jul 05, 2021
  • Yifan Wang +5
  • Research Article
  • Citations7

Advancing predictive maintenance: a deep learning approach to sensor and event-log data fusion

  • Jul 09, 2024
  • Sensor Review
  • Zengkun Liu +1
  • Research Article
  • Citations9

Short fusion with vertebrectomy during growth in congenital spinal deformity: is early surgical intervention recommended?

  • Feb 27, 2020
  • Spine Deformity
  • Hiroko Matsumoto +12
  • Book Chapter

Extension of the Rocchio Classification Method to Multi-modal Categorization of Documents in Social Media

  • Jan 01, 2012
  • Amin Mantrach +1
  • Research Article
  • Citations5

Early and Late Fusion for Multimodal Aggression Prediction in Dementia Patients: A Comparative Analysis

  • May 22, 2025
  • Applied Sciences
  • Ioannis Galanakis +5
  • 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
  • Citations9

Image retrieval: Benchmarking visual information indexing and retrieval systems

  • Feb 01, 2007
  • Bulletin of the American Society for Information Science and Technology
  • Abebe Rorissa
  • Research Article
  • Citations3

ExpertosLF: dynamic late fusion of CBIR systems using online learning with relevance feedback.

  • Aug 20, 2022
  • Multimedia Tools and Applications
  • Soraia M Alarcão +3
  • Conference Article
  • Citations15

Early and Late Fusion of Temporal Information for Classification of Surgical Actions in Laparoscopic Gynecology

  • Jun 01, 2018
  • Stefan Petscharnig +4
  • Research Article
  • Citations6

Enhanced Vision-Based Quality Inspection: A Multiview Artificial Intelligence Framework for Defect Detection.

  • Mar 10, 2025
  • Sensors (Basel, Switzerland)
  • Geethika Bhavanasi +5
  • Research Article
  • Citations10

Comprehensive Framework of Early and Late Fusion for Image–Sentence Retrieval

  • Jul 01, 2022
  • IEEE MultiMedia
  • Yifan Wang +5
  • Conference Article
  • Citations97

A novel log-based relevance feedback technique in content-based image retrieval

  • Oct 10, 2004
  • Chu-Hong Hoi +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.