Research on Face Recognition Based on Small Samples of CNN

Peng, Xin; Ma, Jia; Liu, Yantao; He, Jiqiang; Wang, Wenxia; Wang, Ying

doi:10.1109/edssc.2019.8754183

Cited by 2 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is important to notice that the second most largest category goes to private datasets with 34 papers (Zhou et al, 2018;Ara et al, 2017;Phankokkruad, 2018;Gilani and Mian, 2018;Khan et al, 2019b;Qin et al, 2019;Liu et al, 2019;Peng et al, 2019;Mangal et al, 2020;Lv et al, 2020;Perti et al, 2020;Kim et al, 2017;Irjanto and Surantha, 2020;Arafah et al, 2020;Prasetyo et al, 2021;Moon et al, 2017;Chandran et al, 2018;Yang et al, 2018;Son et al, 2020;Alhanaee et al, 2021;Khan et al, 2020;Nakajima et al, 2021;Talahua et al, 2021;He and Ding, 2023;Karlupia et al, 2023;Bussey et al, 2017;Li et al, 2022;Filippidou and Papakostas, 2020;Bussey et al, 2017;Singh et al, 2022;Setio Aji et al, 2022;Wang et al, 2022;Lestari et al, 2021) creating their own datasets for testing. There are advantages and disadvantages to developing and utilizing private face image datasets for CNN-based face recognition.…”

Section: Assessment Of Q3: What Type Of Cnn Model Is Most Commonly Us...mentioning

confidence: 99%

“…Another important trend that was discovered, specifically in recent papers is data augmentation. Some examples of data augmentation can be found in (Peng et al, 2019) where the authors use a siamese NN in combination with an augmented small sample dataset. To enhance their network the authors used a combination of ReLU and MFM activation functions as well as contrastive and sigmoid loss functions.…”

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: Assessment Of Q3: What Type Of Cnn Model Is Most Commonly Us...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

“…X. Peng et al [22] analyzes the e↵ects of di↵erent activation on face recognition rate. Majorly they focused on experimenting with small samples of CNN.…”

Section: Literature Surveymentioning

confidence: 99%

Supervisory framework for threat detection withmultilayer processing in CNN

Mule¹,

Pandit²,

Karmakar³

et al. 2022

ITM Web Conf.

View full text Add to dashboard Cite

Face recognition has received huge acknowledgement due to its various uses in Internet communication, security, access control, surveillance, PC entertainment and law enforcement. Conventional methods of recognition based on the ownerships of identity-cards or full knowledge such as a security number or password are not totally solid. Physical ID cards can be lost or forged, passwords can be hacked or forgotten but a face is undoubtedly connected to its owner. It cannot be stolen, borrowed or easily forged. Our current system has a lot of weaknesses wherever it is simply taken and merged. The focus of this paper is to help users for development of the security by utilizing face identification and recognition. The proposed framework principally comprises of subsystems specifically picture capture, face identification and detection, email alerts and metal detection. Furthermore, the improvement in Computer Vision through Deep Learning algorithms has been an impressive achievement, especially with the Convolutional Neural Network algorithm. A convolutional neural network is a feed-forward neural network that is by and large used to break down visual pictures by using grid-like topology. It is also called as ConvNet. The objects in a picture are distinguished and arranged using convolutional neural network. CNN detects various simple complex patterns in images and data in its different layers of Convolution Layer, Max Polling Layer and Fully Connected Layer .This field intends to allow and configure machines to see the world as people do, and utilize the information for doing tasks (such as Image Analysis, Image Recognition and Classification, etc).

show abstract

Research on Face Recognition Based on Small Samples of CNN

Cited by 2 publications

References 7 publications

Convolutional Neural Networks for Face Recognition: A Systematic Literature Review

Convolutional Neural Networks for Face Recognition: A Systematic Literature Review

Supervisory framework for threat detection withmultilayer processing in CNN

Contact Info

Product

Resources

About