Identity recognition with the help of human face image processing in an intelligent way

Number of pages: 85 File Format: word File Code: 32562
Year: 2014 University Degree: Master's degree Category: Facilities - Mechanics
  • Part of the Content
  • Contents & Resources
  • Summary of Identity recognition with the help of human face image processing in an intelligent way

    Master's Thesis

    Applied design trend

    Abstract

    Facial recognition has received much attention in recent years in research fields related to biometrics, pattern recognition, and machine vision. Face recognition methods are also used in some commercial and security applications. These applications include people's security control, access control, identification of criminals, face reconstruction, and human-computer interfaces. Recognition with the help of facial images has received more attention because it requires little cooperation from people. In the meantime, face recognition methods try to increase the accuracy of tests on standard databases day by day by providing new solutions. In this research, a new method called the smart method has been introduced and investigated, the basis of which is based on the use of support vector machines that use an intelligent algorithm for data classification, although in part of the algorithm of the smart method, the methods that were presented in the first decade of the 21st century have been used. In this research, the ORL and YALE standard data banks were used to test the smart method. For the ORL data bank, only 2.45% error is observed in the average of all tests, while in the best case, the smart method showed 100% accuracy. For the YALE data bank, the average accuracy is 91.33% and in the best performance 96.67% accuracy has shown that very favorable results have been obtained for both data banks.

    Key words:

    Biometric; facial recognition; support vector machines; smart method; ORL Data Bank

     

    1-1- Introduction

    From the past times until now, humans have sought to protect themselves and their property, this need has evolved with the passage of time and the progress of humans and their abilities in such a way that the basic identity recognition systems from the end of the 20th century brought about a great evolution in improving security, but accidents Terrorist attacks in the early 21st century, especially September 11, 2001, made governments aware of many shortcomings in this field.

    Biometric technology has been the focus of the world's largest research institutions since then and is progressing with double growth. In the meantime, many technologies have been formed and evolved in identity recognition, including fingerprint recognition, face recognition, iris recognition, retina recognition, palm print recognition, hand geometry recognition, ear geometry recognition and several other methods. rtl;">Almost all facial recognition technologies require a series of voluntary operations from the user. For example, in identity recognition with the help of fingerprints and palms, the user must place his hand on the desired sensor to obtain the necessary scan, or in identity recognition by eyes, the person must place his eyes without moving in front of the camera lens, while in face recognition, a camera can transmit the person's image to the system for identification even from a distance. Simulating the action by a machine will be the ideal of science in identity recognition.

    Face recognition technology has many applications, including security systems, human-computer interface, automatic monitoring, bank verification systems, identity recognition by passports and various types of identification cards, etc.

    The face plays an essential role in identifying people and displaying their emotions in It has a community level. The ability of humans to recognize faces is remarkable. We can recognize thousands of faces taught throughout our lives and recognize familiar faces at a glance even after years of separation. This skill stands against changes in visual conditions such as facial expressions, age, and changes in glasses, beards, or hairstyles.This skill resists changes in visual conditions such as facial expressions, age, and also changes in glasses, beards, or hairstyles.

    Face recognition has become an important issue in applications such as security systems, credit card control, and criminal identification. For example, the ability to model a specific face and distinguish it from a large number of stored face models will greatly improve the ability to identify criminals.

    Although it is true that humans are capable of recognizing faces, the way in which faces are encoded and decoded in the human brain is not entirely clear. Human face recognition has been studied for more than twenty years. Developing a computational model for face recognition is quite difficult due to the complexity of faces and the multidimensional structure of vision. Therefore, face recognition is a high-level activity in computer vision and can include many basic vision techniques.

    The first step of human face recognition is extracting obvious features from face images. Here, a question arises as to how much facial features can be measured. Studies by researchers in the past several years indicate that certain features of the face are recognized by humans to identify faces.

  • Contents & References of Identity recognition with the help of human face image processing in an intelligent way

    List:

    Chapter 1 - Introduction. 1

    1-1- Introduction. 2

    Chapter 2 - An overview of the research background. 5

    2-1- Introduction. 6

    Face recognition using special faces 6

    2-3- General system. 10

    2-3-1- Face database shaping phase 10

    2-3-2- Training phase. 11

    2-3-3- Recognition and learning phase. 11

    2-4- Calculation of features 13

    2-5- Principal components analysis method (PCA) 17

    2-6- LDA linear resolution analysis method. 21

    2-7- ICA independent component analysis method. 23

    Chapter 3 - The main concepts of face recognition. 28

    3-1- Introduction. 29

    3-2- The main concepts of pattern and face recognition 29

    3-2-1- Overview 29

    3-2-2- Recognition of real items. 29

    3-2-3- Identifying abstract items. 29

    3-3- Patterns and classes of patterns 30

    3-4- Basic issues in the design of pattern recognition system. 31

    3-5- Learning and practicing. 32

    3-6 supervised and unsupervised pattern recognition. 33

    3-7- Generalities of a pattern recognition system. 33

    3-8- Generalities of a general face recognition system. 35

    3-8-2- Receiving module. 35

    3-8-3- Preprocessing module. 36

    3-8-4- feature extraction module. 37

    3-8-5- Classification module. 37

    3-8-6- exercise set. 38

    3-8-7- Face database 38

    Chapter 4 - Proposed model and method. 39

    4-1- Introduction. 40

    4-2- Linear discriminant analysis for image matrix (2D-LDA) 40

    4-3- Support vector machine (SVM) 46

    4-4- Intelligent method. 52

    4-4-1- Introduction ..52

    4-4-2- Using support vector machines (2D-LDA-SVM method) 52

    4-4-3- Using both image dimensions for more complete training (2D-2D-LDA-SVM) 53

    Chapter 5 - Results 55

    5-1- Introduction of used data bank 56

    5-1-1- ORL data bank. 56

    5-1-2- YALE data bank. 57

    5-2- The results of the implementation of experiments in MATLAB software. 58

    5-3- Results of 2D-LDA-SVM method. 58

    5-3-1- Implementation on the ORL database. 58

    5-3-2- Comparison of 2D-LDA-SVM method with 2D-LDA method. 62

    5-3-3- Implementation on the YALE database. 63

    5-4- Results of 2D-2D-LDA-SVM method. 65

    5-4-1- Implementation on the ORL database. 65

    5-4-2- Comparison of 2D-2D-LDA-SVM method with 2D-LDA method. 67

    5-4-3- Implementation on the YALE database. 68

    5-5- Comparison of 2D-2D-LDA-SVM methods with 2D-LDA-SVM. 70

    5-5-1- ORL data bank. 70

    5-5-2- YALE data bank. 71 5-6- Conclusions and suggestions. 72 References 75 Source: [1] M. Kirby and L. Sirovich, "Application of the Karhunen-Loeve procedure for the characterization of human faces," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 12, pp. 103-108, 1990.

    [2]        L. Sirovich and M. Kirby, "Low-dimensional procedure for the characterization of human faces," JOSA A, vol. 4, pp. 519-524, 1987.

    [3] M. Turk and A. Pentland, "Eigenfaces for recognition," Journal of cognitive neuroscience, vol. 3, pp. 71-86, 1991.

    [4]        A. Pentland, B. Moghaddam, and T. Starner, "View-based and modular eigenspaces for face recognition," in Computer Vision and Pattern Recognition, 1994. Proceedings CVPR'94., 1994 IEEE Computer Society Conference on, 1994, pp. 84-91.

    [5] S. Akamatsu, T. Sasaki, H. Fukamachi, and Y. Suenaga, "Robust face identification scheme: KL expansion of an invariant feature space," in Intelligent Robots and Computer Vision X: Algorithms and Techniques, 1992, pp. 71-84. [6] K.-C. Chung, S. C. Kee, and S. R. Kim, "Face recognition using principal component analysis of Gabor filter responses," in Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems, 1999. Proceedings. International Workshop on, 1999, pp. 53-57.

    [7]        P. N. Belhumeur, J. P. Hespanha, and D. Kriegman, "Eigenfaces vs. fisherfaces: Recognition using class specific linear projection," Pattern Analysis and. fisherfaces: Recognition using class specific linear projection," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 19, pp. 711-720, 1997.

    [8] H. Yu and J. Yang, "A direct LDA algorithm for high-dimensional data—with application to face recognition," Pattern recognition, vol. 34, pp. 2067-2070, 2001.

    [9] C., M.-T. 1326-1726, 2000.

    [10] J. Lu, K. N. Plataniotis, and A. N. Venetsanopoulos, "Face recognition using LDA-based algorithms," IEEE Transactions on, vol. 195-200, 2003. 623-627, 2000.

    [12] J. Lu, K. N. Plataniotis, and A. N. Venetsanopoulos, "Regularization studies of linear discriminant analysis in small sample size scenarios with application to face recognition," Pattern Recognition Letters, vol. 26, pp. 181-191, 2005.

    [13]      J. J. Atick and A. N. Redlich, "What does the retina know about natural scenes?," Neural computation, vol. 4, pp. 196-210, 1992.

    [14] Z. Chen, S. Haykin, J. J. Eggermont, and S. Becker, "Discussion," Correlative Learning: A Basis for Brain and Adaptive Systems, pp. 356-362, 2007.

    [15] M. S. Bartlett, J. R. Movellan, and T. J. Sejnowski, "Face recognition by independent component analysis," Neural Networks, IEEE Transactions on, vol. 13, pp. 1450-1464, 2002.

    [16] K. Baek, B. A. Draper, J. R. Beveridge, and K. She, "PCA vs. ICA: A Comparison on the FERET Data Set," in JCIS, 2002, pp. 824-827.

    [17]      K. Delac, M. Grgic, and S. Grgic, "Independent comparative study of PCA, ICA, and LDA on the FERET data set," International Journal of Imaging Systems and Technology, vol. 15, pp. 252-260, 2005. [18] J. Yang, A. F. Frangi, J.-y. Yang, D. Zhang, and Z. Jin, "KPCA plus LDA: a complete kernel Fisher discriminant framework for feature extraction and recognition," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 27, pp. 230-244, 2005.

    [19] C. Liu and H. Wechsler, "Independent component analysis of Gabor features for face recognition," Neural Networks, IEEE Transactions on, vol. 14, pp. 919-928, 2003.

    [20] Internet resources

    [21] Li, M. and B. Yuan (2005).

Identity recognition with the help of human face image processing in an intelligent way