Adaptive bag‐of‐visual word modelling using stacked‐autoencoder and particle swarm optimisation for the unsupervised categorisation of images. Issue 9 (26th May 2020)

• Record Type: Journal Article
• Authors: Olaode, Abass; Naghdy, Golshah
• Is Part Of: IET image processing. Volume 14:Issue 9(2020)
• Page Start: 1769
• Page End: 1776
• Publication Date: 2020-05-26
• Subjects: particle swarm optimisation -- vector quantisation -- image classification -- pattern clustering -- visual databases -- image representation -- feature extraction -- learning (artificial intelligence); bag‐of‐visual word modelling -- stacked‐autoencoder -- particle swarm optimisation -- unsupervised categorisation -- bag‐of‐visual words -- BOVWs -- effective mean -- image classification -- visual codebook -- handcrafted image feature extraction algorithms -- vector quantisation -- significant computational overhead -- poor classification accuracies -- adaptive BOVW modelling -- deep feature learning -- Caltech‐101 image dataset -- categorisation performance -- computational load; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2019.1160
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : The bag‐of‐visual words (BOVWs) have been recognised as an effective mean of representing images for image classification. However, its reliance on a visual codebook developed using handcrafted image feature extraction algorithms and vector quantisation via k ‐means clustering often results in significant computational overhead, and poor classification accuracies. Therefore, this study presents an adaptive BOVW modelling, in which image feature extraction is achieved using deep feature learning and the amount of computation required for the development of visual codebook is minimised using a batch implementation of particle swarm optimisation. The proposed method is tested using Caltech‐101 image dataset, and the results confirm the suitability of the proposed method in improving the categorisation performance while reducing the computational load.