Keypoints class distribution based entropy for weighting scheme on image classification

In bag-of-visual words (BoVW), a weighting scheme is applied to improve the discriminative power of visual words, which affect the performance of image classification. However, the weighting schemes in the BoVW model did not utilize the information class of keypoints. In this paper, we propose an al...

Full description

Saved in:
Bibliographic Details
Main Authors: Pulung Nurtantio Andono, Catur Supriyanto
Format: Article
Language:English
Published: Springer 2022-11-01
Series:Journal of King Saud University: Computer and Information Sciences
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1319157822003019
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849325040550543360
author Pulung Nurtantio Andono
Catur Supriyanto
author_facet Pulung Nurtantio Andono
Catur Supriyanto
author_sort Pulung Nurtantio Andono
collection DOAJ
description In bag-of-visual words (BoVW), a weighting scheme is applied to improve the discriminative power of visual words, which affect the performance of image classification. However, the weighting schemes in the BoVW model did not utilize the information class of keypoints. In this paper, we propose an algorithm to measure the certainty of visual words which employ the information class of keypoints, called keypoints class distribution based entropy (KCDE). The algorithm is then combined with the existing weighting scheme namely term frequency-term distribution (TF-TD). The results show that the proposed weighting schemes give better classification results than the baseline weighting schemes.
format Article
id doaj-art-9da12449f55f4d92b3038a5aa0a34f13
institution Kabale University
issn 1319-1578
language English
publishDate 2022-11-01
publisher Springer
record_format Article
series Journal of King Saud University: Computer and Information Sciences
spelling doaj-art-9da12449f55f4d92b3038a5aa0a34f132025-08-20T03:48:31ZengSpringerJournal of King Saud University: Computer and Information Sciences1319-15782022-11-0134109028903810.1016/j.jksuci.2022.08.027Keypoints class distribution based entropy for weighting scheme on image classificationPulung Nurtantio Andono0Catur Supriyanto1Corresponding author.; Faculty of Computer Science, Universitas Dian Nuswantoro, Semarang, IndonesiaFaculty of Computer Science, Universitas Dian Nuswantoro, Semarang, IndonesiaIn bag-of-visual words (BoVW), a weighting scheme is applied to improve the discriminative power of visual words, which affect the performance of image classification. However, the weighting schemes in the BoVW model did not utilize the information class of keypoints. In this paper, we propose an algorithm to measure the certainty of visual words which employ the information class of keypoints, called keypoints class distribution based entropy (KCDE). The algorithm is then combined with the existing weighting scheme namely term frequency-term distribution (TF-TD). The results show that the proposed weighting schemes give better classification results than the baseline weighting schemes.http://www.sciencedirect.com/science/article/pii/S1319157822003019Bag-of-visual wordsWeighting schemesEntropyKeypoints class distributionImage classification
spellingShingle Pulung Nurtantio Andono
Catur Supriyanto
Keypoints class distribution based entropy for weighting scheme on image classification
Journal of King Saud University: Computer and Information Sciences
Bag-of-visual words
Weighting schemes
Entropy
Keypoints class distribution
Image classification
title Keypoints class distribution based entropy for weighting scheme on image classification
title_full Keypoints class distribution based entropy for weighting scheme on image classification
title_fullStr Keypoints class distribution based entropy for weighting scheme on image classification
title_full_unstemmed Keypoints class distribution based entropy for weighting scheme on image classification
title_short Keypoints class distribution based entropy for weighting scheme on image classification
title_sort keypoints class distribution based entropy for weighting scheme on image classification
topic Bag-of-visual words
Weighting schemes
Entropy
Keypoints class distribution
Image classification
url http://www.sciencedirect.com/science/article/pii/S1319157822003019
work_keys_str_mv AT pulungnurtantioandono keypointsclassdistributionbasedentropyforweightingschemeonimageclassification
AT catursupriyanto keypointsclassdistributionbasedentropyforweightingschemeonimageclassification