scholarly journals Feature super-resolution based Facial Expression Recognition for multi-scale low-resolution images

2021 ◽  
pp. 107678
Author(s):  
Fang Nan ◽  
Wei Jin ◽  
Feng Tian ◽  
Jizhong Zhang ◽  
Kuo-Ming Chao ◽  
...  
Keyword(s):  
Facial Expression ◽  
Facial Expression Recognition ◽  
Super Resolution ◽  
Expression Recognition ◽  
Low Resolution ◽  
Multi Scale ◽  
Low Resolution Images

scholarly journals Facial expression recognition for low resolution images using convolutional neural networks and denoising techniques

2021 ◽  
Vol 14 (12) ◽  
pp. 971-983
Author(s):  
Pavan Nageswar Reddy Bodavarapu ◽  
◽  
P V V S Srinivas
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Facial Expression ◽  
Convolutional Neural Network ◽  
Convolutional Neural Networks ◽  
Facial Expression Recognition ◽  
Research Work ◽  
Expression Recognition ◽  
Low Resolution ◽  
Low Resolution Images

Background/Objectives: There is only limited research work is going on in the field of facial expression recognition on low resolution images. Mostly, all the images in the real world will be in low resolution and might also contain noise, so this study is to design a novel convolutional neural network model (FERConvNet), which can perform better on low resolution images. Methods: We proposed a model and then compared with state-of-art models on FER2013 dataset. There is no publicly available dataset, which contains low resolution images for facial expression recognition (Anger, Sad, Disgust, Happy, Surprise, Neutral, Fear), so we created a Low Resolution Facial Expression (LRFE) dataset, which contains more than 6000 images of seven types of facial expressions. The existing FER2013 dataset and LRFE dataset were used. These datasets were divided in the ratio 80:20 for training and testing and validation purpose. A HDM is proposed, which is a combination of Gaussian Filter, Bilateral Filter and Non local means denoising Filter. This hybrid denoising method helps us to increase the performance of the convolutional neural network. The proposed model was then compared with VGG16 and VGG19 models. Findings: The experimental results show that the proposed FERConvNet_HDM approach is effective than VGG16 and VGG19 in facial expression recognition on both FER2013 and LRFE dataset. The proposed FERConvNet_HDM approach achieved 85% accuracy on Fer2013 dataset, outperforming the VGG16 and VGG19 models, whose accuracies are 60% and 53% on Fer2013 dataset respectively. The same FERConvNet_HDM approach when applied on LRFE dataset achieved 95% accuracy. After analyzing the results, our FERConvNet_HDM approach performs better than VGG16 and VGG19 on both Fer2013 and LRFE dataset. Novelty/Applications: HDM with convolutional neural networks, helps in increasing the performance of convolutional neural networks in Facial expression recognition. Keywords: Facial expression recognition; facial emotion; convolutional neural network; deep learning; computer vision

scholarly journals Caricaturing can improve facial expression recognition in low-resolution images and age-related macular degeneration

2019 ◽  
Vol 19 (6) ◽  
pp. 18 ◽  
Author(s):  
Jo Lane ◽  
Rachel A. Robbins ◽  
Emilie M. F. Rohan ◽  
Kate Crookes ◽  
Rohan W. Essex ◽  
...  
Keyword(s):  
Facial Expression ◽  
Macular Degeneration ◽  
Facial Expression Recognition ◽  
Age Related Macular Degeneration ◽  
Expression Recognition ◽  
Low Resolution ◽  
Age Related ◽  
Low Resolution Images

scholarly journals Framework for reliable, real-time facial expression recognition for low resolution images

2013 ◽  
Vol 34 (10) ◽  
pp. 1159-1168 ◽  
Author(s):  
Rizwan Ahmed Khan ◽  
Alexandre Meyer ◽  
Hubert Konik ◽  
Saïda Bouakaz
Keyword(s):  
Facial Expression ◽  
Real Time ◽  
Facial Expression Recognition ◽  
Expression Recognition ◽  
Low Resolution ◽  
Low Resolution Images

scholarly journals Pyramid With Super Resolution for In-the-Wild Facial Expression Recognition

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 131988-132001 ◽  
Author(s):  
Thanh-Hung Vo ◽  
Guee-Sang Lee ◽  
Hyung-Jeong Yang ◽  
Soo-Hyung Kim
Keyword(s):  
Facial Expression ◽  
Facial Expression Recognition ◽  
Super Resolution ◽  
Expression Recognition ◽  
In The Wild

scholarly journals Multi-Scale Gradient Image Super-Resolution for Preserving SIFT Key Points in Low-Resolution Images

2019 ◽  
Vol 78 ◽  
pp. 236-245 ◽  
Author(s):  
Dewan Fahim Noor ◽  
Yue Li ◽  
Zhu Li ◽  
Shuvra Bhattacharyya ◽  
George York
Keyword(s):  
Super Resolution ◽  
Low Resolution ◽  
Gradient Image ◽  
Multi Scale ◽  
Key Points ◽  
Image Super Resolution ◽  
Low Resolution Images

Low-resolution facial expression recognition: A filter learning perspective

2020 ◽  
Vol 169 ◽  
pp. 107370 ◽  
Author(s):  
Yan Yan ◽  
Zizhao Zhang ◽  
Si Chen ◽  
Hanzi Wang
Keyword(s):  
Facial Expression ◽  
Facial Expression Recognition ◽  
Expression Recognition ◽  
Low Resolution

Facial Expression Recognition Based on Monogenic Binary Coding

2014 ◽  
Vol 511-512 ◽  
pp. 437-440
Author(s):  
Xiao Xiao Xia ◽  
Zi Lu Ying ◽  
Wen Jin Chu
Keyword(s):  
Facial Expression ◽  
Facial Expression Recognition ◽  
Local Variation ◽  
Expression Recognition ◽  
Multi Scale ◽  
Linear Discrimination ◽  
Binary Coding ◽  
Japanese Female ◽  
Feature Based ◽  
Better Than

A new method based on Monogenic Binary Coding (MBC) is proposed for facial expression feature extraction and representation. Firstly, monogenic signal analysis is used to extract multi-scale magnitude, orientation and phase components. Secondly, Monogenic Binary Coding (MBC) is used to encode the monogenic local variation and intensity in local regions of each extracted component in each scale and local histograms are built. Then Blocked Fisher Linear Discrimination (BFLD) is used to reduce the dimensionality of histogram features and to enhance discrimination. Finally the three complementary components are fused for more effective facial expression recognition (FER). Experiment results on Japanese female expression database (JAFFE) show that the performance of the fusion method is even better than state-of-the-art local feature based FER methods such as Local Binary Pattern (LBP)+Sparse Representation (SRC), Local Phase Quantization (LPQ)+SRC ,etc.

Sign in / Sign up

Export Citation Format

Share Document