Fuzzy encoding with hybrid pooling for visual dictionary in food recognition

Tremendous number of f food images in the social media services can be exploited by using food recognition for healthcare benefits and food industry marketing. The main challenges in food recognition are the large variability of food appearance that often generates a highly diverse and ambiguous des...

Full description

Bibliographic Details
Main Authors: Razali, Mohd Norhisham, Manshor, Noridayu, Abdul Halin, Alfian, Mustapha, Norwati, Yaakob, Razali
Format: Article
Language:English
Published: Institute of Advanced Engineering and Science (IAES) 2021
Online Access:http://psasir.upm.edu.my/id/eprint/97413/
http://psasir.upm.edu.my/id/eprint/97413/1/ABSTRACT.pdf
_version_ 1848862592803536896
author Razali, Mohd Norhisham
Manshor, Noridayu
Abdul Halin, Alfian
Mustapha, Norwati
Yaakob, Razali
author_facet Razali, Mohd Norhisham
Manshor, Noridayu
Abdul Halin, Alfian
Mustapha, Norwati
Yaakob, Razali
author_sort Razali, Mohd Norhisham
building UPM Institutional Repository
collection Online Access
description Tremendous number of f food images in the social media services can be exploited by using food recognition for healthcare benefits and food industry marketing. The main challenges in food recognition are the large variability of food appearance that often generates a highly diverse and ambiguous descriptions of local feature. Ironically, the ambiguous descriptions of local feature have triggered information loss in visual dictionary constructions from the hard assignment practices. The current method based on hard assignment and Fisher vector approach to construct visual dictionary have unexpectedly cause errors from the uncertainty problem during visual word assignation. This research proposes a method of combination in soft assignment technique by using fuzzy encoding approach and maximum pooling technique to aggregate the features to produce a highly discriminative and robust visual dictionary across various local features and machine learning classifiers. The local features by using MSER detector with SURF descriptor was encoded by using fuzzy encoding approach. Support vector machine (SVM) with linear kernel was employed to evaluate the effect of fuzzy encoding. The results of the experiments have demonstrated a noteworthy classification performance of fuzzy encoding approach compared to the traditional approach based on hard assignment and Fisher vector technique. The effects of uncertainty and plausibility were minimized along with more discriminative and compact visual dictionary representation.
first_indexed 2025-11-15T13:19:29Z
format Article
id upm-97413
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T13:19:29Z
publishDate 2021
publisher Institute of Advanced Engineering and Science (IAES)
recordtype eprints
repository_type Digital Repository
spelling upm-974132022-08-26T08:47:18Z http://psasir.upm.edu.my/id/eprint/97413/ Fuzzy encoding with hybrid pooling for visual dictionary in food recognition Razali, Mohd Norhisham Manshor, Noridayu Abdul Halin, Alfian Mustapha, Norwati Yaakob, Razali Tremendous number of f food images in the social media services can be exploited by using food recognition for healthcare benefits and food industry marketing. The main challenges in food recognition are the large variability of food appearance that often generates a highly diverse and ambiguous descriptions of local feature. Ironically, the ambiguous descriptions of local feature have triggered information loss in visual dictionary constructions from the hard assignment practices. The current method based on hard assignment and Fisher vector approach to construct visual dictionary have unexpectedly cause errors from the uncertainty problem during visual word assignation. This research proposes a method of combination in soft assignment technique by using fuzzy encoding approach and maximum pooling technique to aggregate the features to produce a highly discriminative and robust visual dictionary across various local features and machine learning classifiers. The local features by using MSER detector with SURF descriptor was encoded by using fuzzy encoding approach. Support vector machine (SVM) with linear kernel was employed to evaluate the effect of fuzzy encoding. The results of the experiments have demonstrated a noteworthy classification performance of fuzzy encoding approach compared to the traditional approach based on hard assignment and Fisher vector technique. The effects of uncertainty and plausibility were minimized along with more discriminative and compact visual dictionary representation. Institute of Advanced Engineering and Science (IAES) 2021 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/97413/1/ABSTRACT.pdf Razali, Mohd Norhisham and Manshor, Noridayu and Abdul Halin, Alfian and Mustapha, Norwati and Yaakob, Razali (2021) Fuzzy encoding with hybrid pooling for visual dictionary in food recognition. Indonesian Journal of Electrical Engineering and Computer Science, 21 (1). 179 - 195. ISSN 2502-4752 https://ijeecs.iaescore.com/index.php/IJEECS/article/view/21679 10.11591/ijeecs.v21.i1.pp179-195
spellingShingle Razali, Mohd Norhisham
Manshor, Noridayu
Abdul Halin, Alfian
Mustapha, Norwati
Yaakob, Razali
Fuzzy encoding with hybrid pooling for visual dictionary in food recognition
title Fuzzy encoding with hybrid pooling for visual dictionary in food recognition
title_full Fuzzy encoding with hybrid pooling for visual dictionary in food recognition
title_fullStr Fuzzy encoding with hybrid pooling for visual dictionary in food recognition
title_full_unstemmed Fuzzy encoding with hybrid pooling for visual dictionary in food recognition
title_short Fuzzy encoding with hybrid pooling for visual dictionary in food recognition
title_sort fuzzy encoding with hybrid pooling for visual dictionary in food recognition
url http://psasir.upm.edu.my/id/eprint/97413/
http://psasir.upm.edu.my/id/eprint/97413/
http://psasir.upm.edu.my/id/eprint/97413/
http://psasir.upm.edu.my/id/eprint/97413/1/ABSTRACT.pdf