Face Attendance System

Abstract

well-organized and real-time face discovery has been made possible by using the technique of Local Binary
Pattern since Viola and Jones’ work. The software first captures an image of all the authorized persons and stores the
information into database. Proposed work deals with automated system to detect and classify the Faces using
Probabilistic neural network algorithm. The methodology comprised of three phases, first face Detection from images,
second apply Local Binary Pattern algorithm for the purpose of feature extraction. The most useful and unique features
of the face image are extracted in the feature extraction phase. In the classification the face image is compared with the
images from the database. In our research work, we empirically evaluate face recognition which considers both shape
and texture information to represent face images based on Local Binary Patterns for person independent face recognition.
The features area is first divided into small region from which Local Binary Patterns (LBP), histograms are extract and
concatenated into a single feature vector. This feature vector forms an efficient representation of the face and is used to
measure similarities between images in third phase and probabilistic neural network has been created and trained
according to the features extracted from the image. Trained classifier classifies the types of hematoma according to their
features