Open AccessModified Bag of Visual Words Model for Image Classification
Author(s) -
Zainab N. Sultani,
Ban N. Dhannoon
Publication year - 2021
Publication title -
al-nahrain journal of science
Language(s) - English
Resource type - Journals
eISSN - 2663-5461
pISSN - 2663-5453
DOI - 10.22401/anjs.24.2.11
Subject(s) - scale invariant feature transform , bag of words model in computer vision , artificial intelligence , discriminative model , pattern recognition (psychology) , orb (optics) , computer science , bag of words model , contextual image classification , feature vector , feature (linguistics) , visual word , image retrieval , image (mathematics) , computer vision , feature detection (computer vision) , invariant (physics) , feature extraction , image processing , mathematics , linguistics , philosophy , mathematical physics
Image classification is acknowledged as one of the most critical and challenging tasks in computer vision. The bag of visual words (BoVW) model has proven to be very efficient for image classification tasks since it can effectively represent distinctive image features in vector space. In this paper, BoVW using Scale-Invariant Feature Transform (SIFT) and Oriented Fast and Rotated BRIEF(ORB) descriptors are adapted for image classification. We propose a novel image classification system using image local feature information obtained from both SIFT and ORB local feature descriptors. As a result, the constructed SO-BoVW model presents highly discriminative features, enhancing the classification performance. Experiments on Caltech-101 and flowers dataset prove the effectiveness of the proposed method.