Title: Face Recognition Using Artificial Neural Network Group-based Adaptive Tolerance Trees
1Face Recognition Using Artificial Neural Network
Group-based Adaptive Tolerance Trees
- By Ming Zhang , John Fulcher
2ReviesGroup Theory
3ReviewNN Group Theory
4Translation-invariant face recognition system
5NN group-based tree node
6NN group-based tree node
7The Features of OR NN group
8Advantage
- No single neural network is capable of
approximating such a function comprising three
peaks and nonsmooth , noncontinuous points
9The Features of AND NN group
10Advantage
- No single neural network is capable of
approximating such a function comprising
sole-peak and nonsmooth , and /or noncontinuous
points
11- Both OR and AND NN groups were used as the nodes
for GAT tree, resulting in more accurate and
efficient face recognition .
12NN group-base adaptive tolerance tree.
13GAT tree model
14OPT
- Translation operator that can translate facial
image MI(I,j) into a center face, left face,
right face and so on --- shifts and rotates the
facial image in two dimensions.(but only during
training )
15OPA
- Adaptive node operator set that adds adaptive
connection and grows nodes in the GAT tree if the
parent node output is within tolerance.
16OPN
- Node operator set, which is a complex pattern
classifier.
17OPP
- Path operator set which sets the parent node
output to the input of the child node.
18OPL
- Label leaf operator set which indicates the
labeled person has been recognized.
19Face perspective classification using GAT tree
20Face perspective classification results
21Face perspective classification results
22Face perspective classification results
23Front glasses and beard face classification using
GAT tree.
24Front beard face and Front glasses face
classification
25Front beard face and Front glasses face
classification
26GAT tree for front face recognition
27Conclusion