Multi-view Cooperative Deep Convolutional Network for Facial Recognition with Small Samples Learning

Alfakih, Amani; Yang, Shuyuan; Hu, T.

doi:10.1007/978-3-030-23887-2_24

Cited by 5 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However when looking at overall accuracy (Ma et al, 2018) remain with the lowest achieved accuracy with their InceptionV3 model, but the next three positions are taken by (Alfakih et al, 2020) with 72.27%, (Ma et al, 2018) with 72.52% and (Zeng et al, 2018a) with 74.00%. (Alfakih et al, 2020) have evaluated their model on two datasets, achieving a lower accuracy on FER2013, and a higher accuracy of 83.08% on RAF. They presented results with and without facial expressions and used a DCNN which may be more suitable for training and testing on larger datasets to achieve better results.…”

Section: 60%mentioning

confidence: 99%

“…They use MTCNN for landmark detection with a pre-existing CNN architecture consisting of 64 convolutional layers based on residual units. (Alfakih et al, 2020) present a multi-view DCNN to recognize faces and facial expressions while a very small number of samples. (Yao, 2020) present a DCNN that was adopted from the Caffe (Convolutional Architecture for Fast Feature Embedding) project.…”

Section: 60%mentioning

confidence: 99%

See 1 more Smart Citation

Convolutional Neural Networks for Face Recognition: A Systematic Literature Review

Barcic¹,

Grd²,

Tomičić³

2023

Preprint

View full text Add to dashboard Cite

This paper presents a comprehensive overview of Convolutional Neural Networks (CNNs) in the context of face recognition. By analyzing 150 research papers, we investigate major publication channels, temporal trends, prevalent CNN models, primary data sets, accuracy levels, primary research focuses, and future prospects for improving CNN-based facial recognition. A major focus is placed on identifying prevalent CNN architectures, techniques used for facial recognition and shedding light on the evolving landscape of CNN designs. Furthermore, we examine the datasets used for training and testing CNNs, and evaluate the accuracy levels achieved by these models. Lastly, we discuss future directions for enhancing CNN-based facial recognition, including addressing bias and fairness, improving robustness to environmental variations, privacy preservation, and exploring transfer learning and multimodal fusion. This paper serves as a valuable resource, summarizing major trends in CNN-based face recognition. It provides insights for researchers and practitioners, guiding future advancements in this rapidly evolving field.

show abstract

Section: 60%mentioning

confidence: 99%

Section: 60%mentioning

confidence: 99%

Convolutional Neural Networks for Face Recognition: A Systematic Literature Review

Barcic¹,

Grd²,

Tomičić³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The proposed ResNet101 approach achieved 92% accuracy. DOG+CNN technique in author (Shin et al, 2016) attained 83.72%, Fused CNN technique in author (Alif et al, 2018) attained 83.72% of accuracy, Raw+CNN technique in author (Shin et al, 2016) attained 62.2% of accuracy, Gender+CNN technique in author (Dar et al, 2020) attained 94% of accuracy, CNN+kernel size and number of filters technique in author (Agrawal & Mittal, 2020) attained 65%, DCT+CNN technique in author (Shin et al, 2016) attained 56.09% of accuracy, multi-view DCNN technique in author (Alfakih et al, 2020) attained 72.27% of accuracy, Is+CNN technique in author (Shin et al, 2016) attained 62.16% of accuracy, CNN+preprocessing technique in author (Lopes et al, 2017) attained 82.10% of accuracy and Hist+CNN technique in author (Shin et al, 2016) When compared to other techniques used for human facial emotion recognition, the proposed ResNet-101 model achieved better accuracy, underscoring the effectiveness of the detection model.…”

Section: Dataset Descriptionmentioning

confidence: 99%

A Deep Learning Approach for Human Facial Expression Recognition using Residual Network – 101

Kumari,

Wasim

2023

JCST

View full text Add to dashboard Cite

Emotion recognition is a dynamic process that focuses on a person's emotional state, which implies that the emotions associated with each individual's activities are unique. Human emotion analysis and recognition have been popular study areas among computer vision researchers. High dimensionality, execution time, and cost are the main difficulties in human emotion detection. To deal with these issues, the proposed model aims to design a human emotion recognition model using Residual Networks-101 (ResNet-101). A Convolutional Neural Network (CNN) design called ResNet-101 solves the vanishing gradient issue and makes it possible to build networks with thousands of convolutional layers that outperform networks with fewer layers. An image dataset was used for this emotion recognition. Then, this image dataset was subjected to preprocessing to resize the image and eliminate the noise contents present in the images. After preprocessing, the image was given to the classifier to recognize the emotions effectively. Here, ResNet-101 was used for the classification of six classes. The experimental results demonstrate that ResNet-101 models outperform the most recent techniques for emotion recognition. The proposed model was executed in MATLAB software and carried out several performance metrics. The proposed architecture attained better performance in terms of accuracy 92% and error with 0.08 and other performances like 92% of precision, 85% of specificity and 98% of sensitivity so on, and this shows the effectiveness of the proposed model to existing approaches such as LeNet, AlexNet and VGG. In comparison to current techniques, the suggested model provides improved recognition accuracy for low intensity or mild emotional expressions.

show abstract

Face feature extraction for emotion recognition using statistical parameters from subband selective multilevel stationary biorthogonal wavelet transform

Kumar¹,

Sundaram²,

Arumugam³

et al. 2021

Soft Comput

View full text Add to dashboard Cite

Multi-view Cooperative Deep Convolutional Network for Facial Recognition with Small Samples Learning

Cited by 5 publications

References 14 publications

Convolutional Neural Networks for Face Recognition: A Systematic Literature Review

Convolutional Neural Networks for Face Recognition: A Systematic Literature Review

A Deep Learning Approach for Human Facial Expression Recognition using Residual Network – 101

Face feature extraction for emotion recognition using statistical parameters from subband selective multilevel stationary biorthogonal wavelet transform

Contact Info

Product

Resources

About