In this paper, gives both face detection and
recognition techniques and developed algorithms for them.
Face detection and recognition is challenging due to the
Wide variety of faces and the complexity of noises and
image backgrounds. For face detection, we have used Viola
and Jones face detector based on the Haar-like
features.There are three key contributions. The first
contribution is a new a technique for computing a rich set of
image features using the integral image. The second is a
learning algorithm, based on AdaBoost, which selects a small
number of critical visual features and yields extremely
efficient classifiers. The third contribution is a method for
combining classifiers in a cascade which allows background
regions of the image to be quickly discarded while spending
more computation on promising object-like regions. Further
the algorithms that exist are very much specific to the kind
of images they would take as input and detect faces. To detect
faces we can put a number of simple rejection blocks in series,
until we get the faces. Deeper the rejection block, more
specifically it can be trained to eliminate non-faces.
Ms. Kanchan Wani : had completed her BE in E&TC and pursuing
M.E from J. T. Mahajan college of engineering Faizpur,
Maharashtra.
Mr. S. V. Patil : M.E (Control & Instrumentation) working as a Sr.
Lecturer in Dept. of E&TC. J. T. Mahajan College of Engineering,
Faizpur. Maharashtra.
SVM
PCA
PCA
RGB
Skin Color Segmentation
There are several methods for face detection, but we
have done it by two method. This are as Skin Color
Segmentation, Voilo-Jones method. In Skin Color
Segmentation some limitations such as background
should not be complex. Distance between face and
camera must be appropriate and there must be a single
face in input image. Hence, looked for another method
that is Voila-Jones method. It gives good result for Face
[1] Detection as compared to Skin Color Segmentation.
Advantages of Voila-Jones over the Skin Color
Segmentation are it detects the multiple faces, there is no
restriction on kind of background. It detects even small
face in an image because of these advantages we used this
methods for detection. For feature extraction we used
eigenface feature extraction methods. This is totally
mathematical method in which we first resize detected
face in square form then we calculate eigen values and
corresponding eigen vectors. [2] These eigen vectors are
used for further processing.
[1] H. Moon and P. J. Phillips. Analysis of PCA based
face recognition algorithms. In K W.Bowyer and P. J.
Phillips, editors, Empirical Evaluation Techniques in
Computer Vision. IEEE Computer Society Press, Los
Alamitos, CA. 1998.
[2] R. Chellappa, C. Wilson, and S. Sirohey, Human and
Machine Recognition of Faces: A Survey, Proc. IEEE,
vol. 83, no. 5, pp. 705- 740, 1995.
[3] Turk M. and Pentland A., Eigenfaces for Recognition,
Media Labs, M.I.T.
[4] Raphael Feraud, Olivier Bernier, Jean Emmanuael
Viallet, and Michel Collobert. A Fast and Accurate Face
Detector for Indexation of Face Images. In International
Conference on Face and Gesture Recognition. IEEE,
March 2000
[5] K. Sobottka and I. Pitas, Face localization and feature
extraction based on shape and color infor-mation, Proc.
IEEE Intl Conf. Image Processing, pp. 483-486, 1996.
