Feature Selection for Facial Emotion Recognition Using Cosine Similarity-Based Harmony Search Algorithm
Nowadays, researchers aim to enhance man-to-machine interactions by making advancements in several domains. Facial emotion recognition (FER) is one such domain in which researchers have made significant progresses. Features for FER can be extracted using several popular methods. However, there may b...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-04-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/10/8/2816 |
id |
doaj-bc5499bd0660461f8542323267c93754 |
---|---|
record_format |
Article |
spelling |
doaj-bc5499bd0660461f8542323267c937542020-11-25T02:34:45ZengMDPI AGApplied Sciences2076-34172020-04-01102816281610.3390/app10082816Feature Selection for Facial Emotion Recognition Using Cosine Similarity-Based Harmony Search AlgorithmSoumyajit Saha0Manosij Ghosh1Soulib Ghosh2Shibaprasad Sen3Pawan Kumar Singh4Zong Woo Geem5Ram Sarkar6Department of Computer Science and Engineering, Future Institute of Engineering and Management, Kolkata 700150, IndiaDepartment of Computer Science and Engineering, Jadavpur University, Kolkata 700032, IndiaDepartment of Computer Science and Engineering, Jadavpur University, Kolkata 700032, IndiaDepartment of Computer Science and Engineering, Future Institute of Engineering and Management, Kolkata 700150, IndiaDepartment of Information Technology, Jadavpur University, Kolkata 700106, IndiaDepartment of Energy IT, Gachon University, Seongnam 13120, KoreaDepartment of Computer Science and Engineering, Jadavpur University, Kolkata 700032, IndiaNowadays, researchers aim to enhance man-to-machine interactions by making advancements in several domains. Facial emotion recognition (FER) is one such domain in which researchers have made significant progresses. Features for FER can be extracted using several popular methods. However, there may be some redundant/irrelevant features in feature sets. In order to remove those redundant/irrelevant features that do not have any significant impact on classification process, we propose a feature selection (FS) technique called the supervised filter harmony search algorithm (SFHSA) based on cosine similarity and minimal-redundancy maximal-relevance (mRMR). Cosine similarity aims to remove similar features from feature vectors, whereas mRMR was used to determine the feasibility of the optimal feature subsets using Pearson’s correlation coefficient (PCC), which favors the features that have lower correlation values with other features—as well as higher correlation values with the facial expression classes. The algorithm was evaluated on two benchmark FER datasets, namely the Radboud faces database (RaFD) and the Japanese female facial expression (JAFFE). Five different state-of-the-art feature descriptors including uniform local binary pattern (uLBP), horizontal–vertical neighborhood local binary pattern (hvnLBP), Gabor filters, histogram of oriented gradients (HOG) and pyramidal HOG (PHOG) were considered for FS. Obtained results signify that our technique effectively optimized the feature vectors and made notable improvements in overall classification accuracy.https://www.mdpi.com/2076-3417/10/8/2816feature selectionfacial emotion recognitionharmony search algorithmcosine similarityPearson correlation coefficientlocal binary pattern (LBP) |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Soumyajit Saha Manosij Ghosh Soulib Ghosh Shibaprasad Sen Pawan Kumar Singh Zong Woo Geem Ram Sarkar |
spellingShingle |
Soumyajit Saha Manosij Ghosh Soulib Ghosh Shibaprasad Sen Pawan Kumar Singh Zong Woo Geem Ram Sarkar Feature Selection for Facial Emotion Recognition Using Cosine Similarity-Based Harmony Search Algorithm Applied Sciences feature selection facial emotion recognition harmony search algorithm cosine similarity Pearson correlation coefficient local binary pattern (LBP) |
author_facet |
Soumyajit Saha Manosij Ghosh Soulib Ghosh Shibaprasad Sen Pawan Kumar Singh Zong Woo Geem Ram Sarkar |
author_sort |
Soumyajit Saha |
title |
Feature Selection for Facial Emotion Recognition Using Cosine Similarity-Based Harmony Search Algorithm |
title_short |
Feature Selection for Facial Emotion Recognition Using Cosine Similarity-Based Harmony Search Algorithm |
title_full |
Feature Selection for Facial Emotion Recognition Using Cosine Similarity-Based Harmony Search Algorithm |
title_fullStr |
Feature Selection for Facial Emotion Recognition Using Cosine Similarity-Based Harmony Search Algorithm |
title_full_unstemmed |
Feature Selection for Facial Emotion Recognition Using Cosine Similarity-Based Harmony Search Algorithm |
title_sort |
feature selection for facial emotion recognition using cosine similarity-based harmony search algorithm |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2020-04-01 |
description |
Nowadays, researchers aim to enhance man-to-machine interactions by making advancements in several domains. Facial emotion recognition (FER) is one such domain in which researchers have made significant progresses. Features for FER can be extracted using several popular methods. However, there may be some redundant/irrelevant features in feature sets. In order to remove those redundant/irrelevant features that do not have any significant impact on classification process, we propose a feature selection (FS) technique called the supervised filter harmony search algorithm (SFHSA) based on cosine similarity and minimal-redundancy maximal-relevance (mRMR). Cosine similarity aims to remove similar features from feature vectors, whereas mRMR was used to determine the feasibility of the optimal feature subsets using Pearson’s correlation coefficient (PCC), which favors the features that have lower correlation values with other features—as well as higher correlation values with the facial expression classes. The algorithm was evaluated on two benchmark FER datasets, namely the Radboud faces database (RaFD) and the Japanese female facial expression (JAFFE). Five different state-of-the-art feature descriptors including uniform local binary pattern (uLBP), horizontal–vertical neighborhood local binary pattern (hvnLBP), Gabor filters, histogram of oriented gradients (HOG) and pyramidal HOG (PHOG) were considered for FS. Obtained results signify that our technique effectively optimized the feature vectors and made notable improvements in overall classification accuracy. |
topic |
feature selection facial emotion recognition harmony search algorithm cosine similarity Pearson correlation coefficient local binary pattern (LBP) |
url |
https://www.mdpi.com/2076-3417/10/8/2816 |
work_keys_str_mv |
AT soumyajitsaha featureselectionforfacialemotionrecognitionusingcosinesimilaritybasedharmonysearchalgorithm AT manosijghosh featureselectionforfacialemotionrecognitionusingcosinesimilaritybasedharmonysearchalgorithm AT soulibghosh featureselectionforfacialemotionrecognitionusingcosinesimilaritybasedharmonysearchalgorithm AT shibaprasadsen featureselectionforfacialemotionrecognitionusingcosinesimilaritybasedharmonysearchalgorithm AT pawankumarsingh featureselectionforfacialemotionrecognitionusingcosinesimilaritybasedharmonysearchalgorithm AT zongwoogeem featureselectionforfacialemotionrecognitionusingcosinesimilaritybasedharmonysearchalgorithm AT ramsarkar featureselectionforfacialemotionrecognitionusingcosinesimilaritybasedharmonysearchalgorithm |
_version_ |
1724806799148711936 |