Face Recognition Using Sf_3CNN With Higher Feature Discrimination

02/02/2021
by   Nayaneesh Kumar Mishra, et al.
0

With the advent of 2-dimensional Convolution Neural Networks (2D CNNs), the face recognition accuracy has reached above 99 still a challenge in real world conditions. A video, instead of an image, as an input can be more useful to solve the challenges of face recognition in real world conditions. This is because a video provides more features than an image. However, 2D CNNs cannot take advantage of the temporal features present in the video. We therefore, propose a framework called Sf_3CNN for face recognition in videos. The Sf_3CNN framework uses 3-dimensional Residual Network (3D Resnet) and A-Softmax loss for face recognition in videos. The use of 3D ResNet helps to capture both spatial and temporal features into one compact feature map. However, the 3D CNN features must be highly discriminative for efficient face recognition. The use of A-Softmax loss helps to extract highly discriminative features from the video for face recognition. Sf_3CNN framework gives an increased accuracy of 99.10 comparison to the previous 97

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/02/2021

Face Recognition using 3D CNNs

The area of face recognition is one of the most widely researched areas ...
research
01/23/2022

Basket-based Softmax

Softmax-based losses have achieved state-of-the-art performances on vari...
research
11/13/2017

Convolutional neural networks pretrained on large face recognition datasets for emotion classification from video

In this paper we describe a solution to our entry for the emotion recogn...
research
05/02/2018

Towards Interpretable Face Recognition

Deep CNNs have been pushing the frontier of visual recognition over past...
research
03/17/2018

SeqFace: Make full use of sequence information for face recognitio

Deep convolutional neural networks (CNNs) have greatly improved the Face...
research
08/24/2022

SubFace: Learning with Softmax Approximation for Face Recognition

The softmax-based loss functions and its variants (e.g., cosface, sphere...
research
05/30/2022

Median Pixel Difference Convolutional Network for Robust Face Recognition

Face recognition is one of the most active tasks in computer vision and ...

Please sign up or login with your details

Forgot password? Click here to reset