Nowadays face detection and recognition has become an important tool for identification in industry, Educational institutes, verifying websites, hosting images and social networking site. Face Recognition is nothing but Features such as eyes, nose, lips etc. are extracted from a face, these features are processed and compared with similarly processed faces present in the database. If a face is recognized it is known or the system may show a similar face existing in a database else it is an unknown face. In proposed system, an input image can be taken as a static image or by capturing an image. The system is trying to improve efficiency. The system is using ANN (Artificial Neural Network) and Euclidean Distance Measure is working collaboratively for detection of the face. Over here, features are been marked using ELBP (Elliptical local binary pattern) using specific values. Facial features such as forehead, eyes, nose, lips and cheeks. The system basically converts RGB values of features to HSV (Hue saturation value) and stores this HSV values. These HSV values are compared with the feature values of HSV which are stored in databases and if these values are matched with the database face image values then the face is detected otherwise it is not detected. These features distances are calculated using Euclidean distance algorithm. For improving the efficiency OCA (Optimized comparison algorithm) plays an important role as in OCA two features are taken for comparison with the database image. Two features lips and cheeks are taken into consideration and it is compared with the all the database image. Whatever images have got is further compared with the optimized database and finally, face is recognized otherwise user not found message will be printed. Also for real time application live streaming is facilitated in the system for recognition and continuous processing is done. This way system facilitates to efficiently recognize the faces and also helps to improve the accuracy of the system.