Face Recognition Using the SR-CNN Model

Autor: Chang Wen, Sheng Guanqun, Fangqing Wen, Kai Xie, Tang Xingong, Yu-Xin Yang
Rok vydání: 2018
Předmět:
Databases
Factual
Computer science
Graphics processing unit
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Scale-invariant feature transform
02 engineering and technology
lcsh:Chemical technology
rotation-invariant texture feature (RITF)
Biochemistry
Convolutional neural network
Facial recognition system
Article
Analytical Chemistry
Position (vector)
graphic processing unit (GPU)
0202 electrical engineering
electronic engineering
information engineering
Image Processing
Computer-Assisted
Humans
scale-invariant feature transform (SIFT)
lcsh:TP1-1185
face matching
Electrical and Electronic Engineering
Instrumentation
business.industry
parallel computing
020206 networking & telecommunications
Pattern recognition
Atomic and Molecular Physics
and Optics
convolution neural network (CNN)
Face (geometry)
Biometric Identification
Face
020201 artificial intelligence & image processing
Artificial intelligence
Neural Networks
Computer
business
Facial Recognition
Algorithms
Zdroj: Sensors (Basel, Switzerland)
Sensors, Vol 18, Iss 12, p 4237 (2018)
Sensors
Volume 18
Issue 12
ISSN: 1424-8220
Popis: In order to solve the problem of face recognition in complex environments being vulnerable to illumination change, object rotation, occlusion, and so on, which leads to the imprecision of target position, a face recognition algorithm with multi-feature fusion is proposed. This study presents a new robust face-matching method named SR-CNN, combining the rotation-invariant texture feature (RITF) vector, the scale-invariant feature transform (SIFT) vector, and the convolution neural network (CNN). Furthermore, a graphics processing unit (GPU) is used to parallelize the model for an optimal computational performance. The Labeled Faces in the Wild (LFW) database and self-collection face database were selected for experiments. It turns out that the true positive rate is improved by 10.97&ndash
13.24% and the acceleration ratio (the ratio between central processing unit (CPU) operation time and GPU time) is 5&ndash
6 times for the LFW face database. For the self-collection, the true positive rate increased by 12.65&ndash
15.31%, and the acceleration ratio improved by a factor of 6&ndash
7.
Databáze: OpenAIRE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje