Super-resolution Facial Images from Single Input Images Based on Discrete Wavelet Transform

2014 ◽  
Author(s):  
Ali Mohammed Darvish ◽  
Haibo Li ◽  
Ulrik Soderstrom
Keyword(s):  
Wavelet Transform ◽  
Discrete Wavelet Transform ◽  
Super Resolution ◽  
Discrete Wavelet ◽  
Single Input ◽  
Facial Images

scholarly journals Global motion based video super-resolution reconstruction using discrete wavelet transform

2018 ◽  
Vol 77 (20) ◽  
pp. 27641-27660 ◽  
Author(s):  
Wasnaa Witwit ◽  
Yifan Zhao ◽  
Karl Jenkins ◽  
Sri Addepalli
Keyword(s):  
Wavelet Transform ◽  
Discrete Wavelet Transform ◽  
Super Resolution ◽  
Discrete Wavelet ◽  
Global Motion

scholarly journals Pengenalan Citra Wajah Dengan Menggunakan Transformasi Wavelet Diskrit dan Jaringan Saraf Tiruan Back-Propagation

2010 ◽  
Vol 1 (2) ◽  
pp. 691
Author(s):  
Suhendry Effendy
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Wavelet Transform ◽  
Discrete Wavelet Transform ◽  
Back Propagation ◽  
Input Image ◽  
Discrete Wavelet ◽  
Web Camera ◽  
Artificial Neural ◽  
Facial Images

This paper discusses the facial image recognition system using Discrete Wavelet Transform and back-propagation artificial neural network. Discrete Wavelet Transform processes the input image to obtain the essential features found on the face image. These features are then classified using an back-propagation artificial neural network for the input image to be identified. Testing the system using facial images in AT & T Database of Faces of 400 images comprising 40 facial images of individuals and web-camera catches as many as 100 images of 10 individuals. The accuracy of level of recognition on AT & T Database of Faces reaches 93.5%, while the accuracy of level of recognition on a web-camera capture images up to 96%. Testing is also done on image of AT & T Database of Faces with given noise. Apparently the noise in the image does not give meaningful effect on the level of recognition accuracy. 

Sign in / Sign up

Export Citation Format

Share Document