• Manish Chauhan
• Dr. Maitreyee Dutta

Abstract- Face recognition can be realized as identification of a person from his facial features that can be accomplished by the application of various computational algorithms. Face recognition system is one of the most cost-effective methods for the use of computing resources in comparison to the authentication and identification. This work is done in two parts that is training and testing phase. In this paper, group image as taken as input image and face segmentation is done on the basis of skin color models and then preprocessed to remove the additional noise. The face detection is improved by using maximum likelihood function and features are extracted by using Principle Component Analysis method. This method also reduced the dimensionality and provides effective result. After this process testing phase is started in which captured image saved in the database and compared for detection. In this work the comparisons of different models like HSV +PCA, Binarized RGB +PCA and YCbCr +PCA is done and for validation of proposed method with ORL and Yale database. The accuracy and Hit rate of the proposed method represents the effectiveness and efficiency of the model.

Face Detection, Skin Color Models, PCA, ORL, Yale, Face Recognition.

"Face Recognition from a Group Photograph using Skin Color Models with PCA ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 7, page no.54-63, July-2018, Available :http://www.jetir.org/papers/JETIR1807611.pdf

"Face Recognition from a Group Photograph using Skin Color Models with PCA ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 7, page no. pp54-63, July-2018, Available at : http://www.jetir.org/papers/JETIR1807611.pdf