Face Recognition using new neural network architecture presentation
Loading...
Loading...
2,291
Loading...
Uploader Comments (kyoussef321)
see all
All Comments (4)
-
@kyoussef321 thanks, but let's make it simple, what is the best resolution for a B/W image to be processed?
Loading...
7:49
Intro to Neural Networksby bracksux10,091 views- 2:39
Pattern Recognition using Artificial Neural Networkby SymbolsBlog2,589 views
- 2:07
Mario AI Trained Neural Network running through test setby aruggles2,170 views
- 0:30
Face recognition demoby yxccumt14,428 views
- 9:35
Neural Network Types for Encogby HeatonResearch1,792 views
- 9:30
Encog Neural Network Framework Architectureby HeatonResearch2,450 views
- 2:02
Neural Network and Genetic Algorithm Simulationby ReandeBlog2,087 views
- 0:47
KeyLemon Presentationby KeyLemonSoftware2,314 views
- 14:25
Neural Network Calculation (Part 1): Feedforward Structureby HeatonResearch3,876 views
- 9:28
Introduction to Neural Networks for C# (Class 11/16, Part 1/5) predict stock marketby HeatonResearch2,438 views
- 3:09
HTS (Hand Tracking System)by ShayTuber1,221 views
- 3:39
Facebook based face recognition (Presentation)by helenahalowy1,502 views
- 2:09
Object Recognition (playing card & $10 bill)by Tsvetnikov1,353 views
- 9:11
Video results: Using Neural Networks and the Genetic Algorithm for Multi-Agent System Controlby tjosgood2,710 views
- 3:09
Face Recognition Systemby ExecodeOrg507 views
- 1:10
AAM Face Trackingby kotayamaguchi19846,707 views
- 1:10
Image Processing GUI with MATLABby qcthegreat12,975 views
- 0:52
Face recognition GUIby rajiv0877,388 views
- 0:37
2D Neural Network Solving Problem in Excelby cybercab10,297 views
- 9:58
Introduction to Neural Networks for Java(Class 3/16, Part 1/5) - hopfieldby HeatonResearch4,749 views
I'm approaching the study of the neural networks applied to image processing. My first experiments showed the needs of a very large input layer with a conseguent memory overflow. So i considered "downsampling" my input but i can't figure out a "fast" and "robust" image ratio.
For example assume a simple computer webcam with a capture resolution of 320x240 how much scale?
AlxEyesoul 1 year ago
@AlxEyesoul Scaling down the image alone is not a good solution for reducing the input size, especially in the case of face recognition. The minimum image scale I would recommend for face recognition would be 160 X 120. Anything below that would greatly reduce the recognition accuracy. But even with these values (160X120) you are still stuck with a very large input size (in this case 160x120 = 19200). "continued..."
kyoussef321 1 year ago
@AlxEyesoul So what I recommend to solve your problem is that you consider feature extraction and compression techniques. For example, instead of using the entire face, use only certain regions that are unique for different people such as eyes and lips. Use features such as skin texture, distance between eyes and nose…, or a combination of those. Typical input length consisting of a feature vector is in the range between few hundreds to a couple of thousands.
kyoussef321 1 year ago