Face Anti-Spoofing Using Multi-Branch CNN

We propose a face classification system based on deep learning algorithm. This system is capable of distinguishing real and fake faces from RGB images taken by a normal camera. To do that, we have built a system composed of 4 parts: RGB image processing, HSV image processing, YCrCb image processing,...

Full description

Saved in:
Bibliographic Details
Main Authors: Tin, Nguyen Cong, Pham, Bach-Tung, Le, Thi Phuong, Tai, Tzu-Chiang, Wang, Jia-Ching
Format: Conference Proceeding
Language:English
Subjects:
Deep learning
Feature extraction
Image color analysis
Information processing
Neural networks
Training data
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose a face classification system based on deep learning algorithm. This system is capable of distinguishing real and fake faces from RGB images taken by a normal camera. To do that, we have built a system composed of 4 parts: RGB image processing, HSV image processing, YCrCb image processing, and classification. In order to achieve optimal processing performance, we include encoder and decoder structure models, which eliminate unnecessary components and help the model focus only on the components it gives. Most importantly, this structure helps reduce the complexity of the model. In addition, we have applied a number of special tweaks to the training data. Experimental results indicate that our system gives very good results on the public database.
ISSN:2640-0103