10-04-2017, 08:09 PM
FACE RECOGNITION BASED ON OPENCV(USING PRINCIPAL COMPONENT ANALYSIS)
[attachment=684]
INTRODUCTION
It is one of the biometric technology..
Face Recognition is the process of identification of a person by their facial image.
Face recognition approaches for still images can be broadly categorized into holistic methods and feature based methods .
Holistic methods use the entire raw face image as an input, whereas feature based methods extract local facial features and use their geometric and appearance properties.
What we do(modules)
DataBase Preparation
Training
Testing
DataBase Preparation
We first store intended images in data base and from it,we calculate 15 to 20 different images in different expressions and viewing angles but in similar conditions ( such as lighting, background,distance from camera etc.).
Training
In this,we follow the procedure for each image to be trained:
1.Read all the faces of each person and normalize all the faces.
2. Find significant Eigenvectors of Reduced Covariance Matrix.
3. Hence calculate the Eigenvectors of Covariance Matrix.
4. Calculate Recognizing Pattern Vectors for each image and average RPV for each person
5. For each person calculate the maximum out of the distances of all his imageRPVs from average RPV of that person.
Testing
Testing is carried out by following steps:
Select an image which is to be tested.
Image is Read and normalize.
Calculate the RPV of image using Eigenvector of Covariance Matrix.
Find the distance of this input image RPV from average RPVs of all the persons.
Find the person from which the distance is minimum.
If this minimum distance is less than the maximum distance of that person calculated during training than the person is identified as this person.