Binary Representation for Face Detection and Recognition with Back Propagation Neural Network

DOI : 10.17577/IJERTV3IS111251

Download Full-Text PDF Cite this Publication

Text Only Version

Binary Representation for Face Detection and Recognition with Back Propagation Neural Network

Raviraj V. Mane CS Department SIT


Abstract – In this paper, an neural network is used to detect frontal views of faces. The recognition can be done by the Back propagation Neural Network (BPNN). Also, we reviewed some of the recent research works on face recognition algorithms. Issues with the previous face recognition techniques are recognition rate , time required is more for face recognition and database required to store the face images. To overcome these problems binary representation of face image technique can be used.

KEYWORDS – Binary Representation, Neural Networks, Feature Extraction,Nodal Points.


    The process of face detection involves the detection of face image of human being and face recognition involves comparing an image with a database


    Face detection methods are classified into following four different broad categories. They are:

    1. Knowledge based method

    2. Feature Invariant method

    3. Template matching method

    4. Appearance based method.

    Prof. Nisha Auti CS Department SIT


    of stored faces in order to identify the individual[20]. Face detection and recognition has attracted broad interests in the area of pattern recognition since from the past 20 years. Face recognition is quite easy for a human being, but for the computer it is a difficult task.So face recognition is a critical issue in todays world.

    Neural network is an interconnected group of artificial neurons and it uses a mathematical model for information processing. The difficulty level increases when two persons match the faces.In order to reduce the storage requirements for face images and to improve the performance of a neural network system the Binary Representation method is used. The basic idea of Binary Representation is to extract the essential features on a face. Therefore it helps in increasing the performance of face recognition and also reduces the storage requirements to store the captured faces[1].

    Our literature review indicates that problem of face recognition is still a critical issue and having some limitations. These are recognition rate, time required for face recognition time and storage requirements of the captured faces. Some of the important research papers studied and tabular overview is presented in next part of the paper.

    Literature survey on Previous face recognition methods

    Overview of issues with previous face recognition methods


    Based on

    Limitations/ongoing work

    1994 G. Yang ,

    T. S. Huang[8][9]

    Knowledge of face

    Difficulty in building appropriate

    set of rules

    1995, T.K. Leung,

    M.C. Burl,

    and P. Perona[10]

    Facial Features

    Cant achieve good results

    with variations in pose,shape

    1999, H. Wu, Q. Chen,

    M. Yachida[11][12]

    Multiple Features

    Detect faces with features such as beard and glasses

    1993, A. Tsukamoto, C.-W. Lee,and S.Tsuji[13][13][14]

    Predefined Templates

    Subtemplates used for future work

    1992,A. Yuille,

    P. Hallinan,

    and D. Cohen[15][16]

    Deformable Templates

    Deformable template must be initialized in the proximity

    2013, Jian Yang , Delin Chu[1]

    Feature Extraction

    Sparse representation of facial features

    2012, Stefanos Zafeiriou,

    Georgios Tzimiropoulos, Maria Petrou,

    Tania Stathaki[2]

    Eigen Analysis

    Face Recognition time is more

    2011, Yong Xu, Jian Yang,

    Jing-Yu Yang[3][5]

    Supervised Learning

    In the future, anyone can explore the applications of this two-phase

    classification framework on other methods

    2005, Jian Yang, Alejandro F.Frangi, Jing-yu Yang[6][7]

    Kernel Methods

    Difficulty in analyzing and recognizing patterns for classification

    2011,Mohammod Abul Kashem, Md. NasimAkhter,

    Shamim Ahmed[4]

    Creation of template

    Database size is more to store templates


    1. Nodal Points

      Nodal points are the Distinguishable landmarks on individual face. E.g. distance between the eyes, width of the nose, length of the jaw line[4].If nodal point is selected then white spot is shown, remaining spot is shown as black.

    2. New User Registration

      Face image is captured by using laptop camera and to register the new captured face image, user has to enter his details such as name,email id, contact etc.Now nodal points are selected for that captured face image and then face image is saved in database with the selected nodal points.

      Fig. 1: New User Registration

    3. Face Recognition of User

    Fig. 2: Face Recognition of User

    New user has to capture his face image by using camera and nodal points are selected. Back propagation neural network algorithm is used to match the two faces.BPNN algorithm is explained further.


    Fig.3:Input training set passed by using back propagation technique

    The backpropagation algorithm is used to train the Articial Neural Networks[17]. Backpropagation algorithm can be used for many practical applications. The BP algorithm used to calculate the weight changes of articial neural networks. Above picture shows three layer neural network with two inputs and one output. Training set of nodal points are passed as x1 and x2.Activation function is calculated with the help of nodal points and matched with the stored face images with selected nodal points. Activation function is recalculated by using back propagation to reduce the error and to improve the performance. If face image is matched greater than 70% then popup box is shown with the individual details which are saved at the time of registration, otherwise popup box shows face is not matched.


Face recognition has received substantial attention from researches in biometrics, pattern recognition field and computer vision communities. Face recognition can be applied in Security measure at Air ports, Passport verification, Criminals list verification in police department, Visa processing, Verification of Electoral identification and Card Security measure at ATMs. In this paper, we reviewed some of the recent research works on face recognition .We classified face recognition approaches using knowledge based methods, feature invariant method, template based methods and appearance based methods.


  1. Jian Yang, Member, Lei Zhang, Yong Xu,Jingyu Yang, Sparse Representation Classifier Steered Discriminative Projection With Application to Face Recogniion, IEEE Transactions on Neural Networks and Learning Systems, Vol. 24, NO. 7, July 2013.

  2. S. Zafeiriou, G. Tzimiropoulos, M. Petrou, and T. Stathaki, Regularized kernel discriminant analysis with a robust kernel for face recognition and verification, IEEE Trans. Neural Netw. Learn. Syst., vol. 23, no. 3, pp. 526534, Mar. 2012.

  3. Y. Xu, D. Zhang, J. Yang, and J.-Y. Yang, A two-phase test sample sparse representation method for use with face recognition, IEEE Trans. Circuits Syst. Video Technol., vol. 21, no. 9, pp. 12551262, Sep. 2011.

  4. Mohammod Abul Kashem, Md. Nasim Akhter, Shamim Ahmed, and Md. Mahbub Alam, Face Recognition System Based on Principal Component Analysis (PCA) with Back Propagation Neural Networks (BPNN), Canadian Journal on Image Processing and Computer Vision Vol. 2, No. 4, April 2011.

  5. J. Mairal, F. Bach, J. Ponce, G. Sapiro, and A. Zisserman, Supervised dictionary learning, in Proc. Adv. NIPS, vol. 21. 2009.

  6. J. Yang, A. F. Frangi, Z. Jin, and J.-Y. Yang, Essence of kernel Fisher discriminant: KPCA plus LDA, Pattern Recognit., vol. 37, pp. 20972100, Oct. 2004.

  7. 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, IEEE Trans. Pattern Anal. Mach. Intell., vol. 27, no. 2, pp. 230244, Feb. 2005.

  8. G. Yang and T. S. Huang, Human Face Detection in Complex Background, Pattern Recognition, vol. 27, no. 1, pp. 53-63, 1994.

  9. C. Kotropoulos and I. Pitas, Rule-Based Face Detection in Frontal Views, Proc. Intl Conf. Acoustics, Speech and Signal Processing vol. 4, pp. 2537-2540, 1997

  10. T.K. Leung, M.C. Burl, and P. Perona, Finding Faces in Cluttered Scenes Using Random Labeled Graph Matching, Proc. Fifth IEEE Intl Conf. Computer Vision, pp. 637-644, 1995

  11. H. Wu, Q. Chen, and M. Yachida, Face Detection from Color Images Using a Fuzzy Pattern Matching Method, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 21, no. 6, pp. 557- 563,June 1999.

  12. H. Wu, T. Yokoyama, D. Pramadihanto, and M. Yachida, Face and Facial Feature Extraction from Color Image, Proc. Second Intl Conf. Automatic Face and Gesture Recognition, pp. 345-350, 1996.

  13. T. Sakai, M. Nagao, and S. Fujibayashi, Line Extraction and Pattern Detection in a Photograph, Pattern Recognition, vol. 1, pp. 233-248, 1969.

  14. Tsukamoto, C.-W. Lee, and S. Tsuji, Detection and Tracking of Human Face with Synthesized Templates, Proc. First Asian Conf.

    Computer Vision, pp. 183-186, 1993

  15. Lanitis, C.J. Taylor, and T.F. Cootes, An Automatic Face Identification System Using Flexible Appearance Models, Image and Vision Computing, vol. 13, no. 5, pp. 393-401, 1995.

  16. D. Donoho, Compressed sensing, IEEE Trans. Inf. Theory, vol. 52, no. 4, pp. 12891306, Apr.2006.

  17. Dr. Rama Kishore, Taranjit Kaur,Backpropagation Algorithm: An Artificial Neural Network Approach for Pattern Recognition, International Journal of Scientific & Engineering Research, Volume 3, Issue 6, June 2012.

  18. Sivasathya. M , Mary Joans. S," Image Feature Extraction Using Non Linear Principle Component Analysis", sciencedirect, vol 38,pp 911-917,2012.

  19. Chetan Ballur, Shylaja S S, Application of local binary pattern and principal component analysis for face recognition ,International Journal of Electrical, Electronics and Data Communication, Volume- 1, July- 2013.

  20. Raviraj Mane,Nisha Auti,Poorva Agrawal,Literature survey on sparse representation for neural network based face detection and recognition,Circuits and Systems: An International Journal (CSIJ), Vol. 1, No.2, April 2014.

Leave a Reply