Chapter 5 1 5 1 Introduction 5



Download 0.6 Mb.
Page1/20
Date23.12.2017
Size0.6 Mb.
  1   2   3   4   5   6   7   8   9   ...   20

Neural Network-Based Face Recognition, using ARENA algorithm.

Abstract 4

Chapter 5

1 5

1.1 Introduction 5

1.2 Aims 6

Chapter 7

2 7

2.1 Face recognition 7

2.2 Why Face Recognition? 7

2.3 History of Face Recognition 8

2.4 The present 10

2.5 Face recognition and Face detection. 11

Chapter 14

3 14

3.1 Neural Networks 14

3.2 How Artificial Neural networks Work. 15

3.2.1 Input - Output 16



Output = Sum of Inputs * Weight 17

3.2.2 Functions 17



3.2.2.1 Activation Functions 18

OUT = 1 if INPUT > T 18

OUT = 0 otherwise 18

3.2.2.2 Threshold Functions 19

3.2.3 Associated Memory 20



3.3 Learning and Training 21

3.3.1 Learning Models 21



3.3.1.1 Supervised Learning 21

3.3.1.2 Unsupervised Learning 22

3.3.1.3 Learning Rules 23

3.3.2 Learning Rates and Training 23



3.4Back Propagation 23

3.4.1Architecture 24

In this section we want to present the architecture of the network which is most commonly used with the back propagation algorithm, the multilayer feedforward network. 24

3.4.1.1 Neuron Model 24

3.4.2Feedforward Network 25



Chapter 27

4 27

4.1 Databases 27

4.2Test and Train Sets 28

Chapter 30

5 30

5.1 Algorithms for face recognition 30

5.1.1 Principal Component Analysis 30



5.1.1.1 Algorithm 31

5.1.2 Eigenfaces 32

5.1.3 Euclidean distance 33

5.2 Arena Algorithm 33

5.2.1 The algorithm 34



Chapter 36

6 36

6.1 Coding 36

6.2 MATLAB 36

6.3 Implementing ARENA algorithm 37

Then we take the absolute value of the matrix elements and we take it to the power of p. after that we sum the columns of the matrix and we get a 1 by X vector of which the sum is the distance Lp. 39



6.4 Implementation of the Neural Networks 40

6.4.1 Training 40

After initialising the weights we give to the network the output distances of the training set, that we have from the arntrn.m program in order to train the network. 41

Output a for example, for p =1, by using five images with resolution 16x16 is 42

And the error 43

6.4.2Testing 43

The full implementation code, for all four programs, is in Appendix I. 44

Chapter 45

7 45

7.1 Results 45

7.2 ARENA 45

7.2.1 Train arena 45

7.2.2Test arena 49

For the first image we have 50

Similar results we have for resolution 32x32 51

Resolution = 32 51

For the first image 51

For the second image 51

For the first image 51

For the second image 51

For the first image 52

Resolution=32 52

Rez=32 52

For the first image 52

For the second image 54

For the second image 54

For the first image 55

For the second input image 55

For the first image 55

For the second input image 55



7.3 Neural networks 56

7.3.1 Train neural network 56

7.3.2 Testing Neural Network – Final Results. 65

For p=1, resolution 32x32, using test image1 (like above) we have 67



7.4 Accuracy 69

7.5 Complexity and Storage 70

Chapter 73

8 73

8.1 Further Work 73

8.1.2 Further work 73



8.1.2.1 Algorithm 73

8.1.2.2 Implementation 74

8.1.2.3 WEB 74

8.1.3 Future of Face Recognition 74



Conclusion 76

References 77

Bibliography 77



Papers 77

WEB 78

Other documentation 78

Appendix I

Appendix iI

Abstract

The purpose of that project is to implement a face recognition algorithm. The face recognition algorithm that is presented here is a memory based face recognition system. We show that an extremely simple, memory-based technique for view-based frontal face recognition can outperform more than sophisticated algorithms that use Principal Components Analysis (PCA) and neural networks. The goal of this report is to write about the most common methods that have been used till now for face recognition. Analyse these methods and give a general idea of the background of the algorithm, ARENA, which we are going. The capability of the face recognition is to find the exact mach of a face image from an image database project. The algorithm that is used in order to achieve that is called ARENA.

Chapter

1

1.1 Introduction

The objective of our system is to recognise and identify faces, not previously presented to or in some way processed by the system. There are many datasets involved in this project. Some of them are the ORL, MIT database which consisting of a large set of images of different people. The database has many variations in pose, scale, facial expression and details. Some of the images are used for training the system and some for testing. The test set is not involved in any part of training or configuration of the system, except for the weighted committees as described in a section later on.

The algorithm used for the face recognition, from the project is known as ARENA. Similar to several other approaches to face recognition and identification, which use Principal Component Analysis (PCA) as pre-processing, dimensionality reduction and feature extraction, of the input images. One of the main parts of the project is a neural network. The use of a neural network makes the algorithm perform better.

In chapters two and three we are going to analyse the background of the project. A literature background of face recognition and neural networks discussing also the methods that were used for the project. In the next chapter, four there is a description of the datasets that where used in order to test and train the algorithm and the neural network, the implementation of which is in chapter six. The code also is included in appendix 1. After that, in chapter seven there is a detailed analysis of the outputs we get from the programs and a comparison of the ARENA algorithm with other methods that have been used for face recognition, the theory of which is analysed in chapter five. Finally in chapter eight there is a discussion about the work that had been done and further improvement that could be done.


1.2 Aims

The purpose of face recognition algorithm is to examine a set of images and try to find the exact match of a given image. An advanced system would be a neural network face recognition algorithm. The system examines small windows of the image in order to calculate the distances of given points. That would be done from any algorithm but in a system where we use neural networks the system arbitrates between multiple networks in order to improve performance over a single network.

The goal of this ongoing project is to formulate paradigms for detection and recognition of human faces, and especially develop an algorithm, which is going to have high performance in complex backgrounds. One of the applications would be towards adding face-oriented queries to our image database project.

The fundamental principle, which we are exploiting for our face recognition algorithm, is Principal Component Analysis. Thought the algorithm is much simpler. One of the aims is to run tests in order to compare the algorithm with two PCA algorithm and also show that the calculation between two given point with the ARENA algorithm is efficient as much as if we had use the Euclidean distance.

Chapter

2






Share with your friends:
  1   2   3   4   5   6   7   8   9   ...   20


The database is protected by copyright ©dentisty.org 2019
send message

    Main page