Anupa Sinha
Assistant Professor , Dept. of CS & IT ,Kalinga University , New Raipur
anupa.sinha@kalingauniversity.ac.in
Using of real features alike to face, thumbprints,ears etc. of a human for individual identity
is kown as Biometrics. Among all Biometrics recognization Face recognition is wide and
interesting investigation region . Some of the resaons behind these are :
It requirs no physical intractionof user .
It is the only biometric recogntion that aloow us to perform one to many recogntion
like idenitfying a criminal in any partiular area .
Its accuracy is very high so there are high enrollment and high verification .
It can use any existing hardware for capturing the image.
It does not require any expert for interprting and analysis of result.
Face recognition is a subfield of computer vision or pattern recognition We can define face
recognition as computer application that can be used for identifying or verifying an individual
using their faces. This is a method of identifying or veryifying an individual identity based on
the face .This system uses photos , video or any real time system for identifyication .
For any face recogntion we reqire two types of comaparision :
Face Verification / Authentication : Here the system comapares any image to any
particular individual that means we are doing one to one comaprision .Based on that
we decide that this image belongs to that person or not .
Face Indentification /Recognition : Here the system comapares any image to allany
particular image that is already stored in enrolled data base that means we are doing
one to many comaprision. Based on that we decide that this image belongs to our
enrolled data base or not .
A simple face recognition system diagram is shown in fig1.1 . Here at first we input an image
after that face region is detected in that image . After that we preprocess the image so image
quality is improved for better recognition. After that we create a template of that image by
using feature extraction then based on that template we recognize that face by using our
classifier
Input Image : Here an image is input image can be still or digital still image will be
converted into digital image .
Finding Face Area : The first step for face recognition is face detection where an face area is
detected in any image that can be used for face recognition .
Pre- Processing : We crop , reduce noise and increase brightness in this sage for better face
recognition .
Feature Extraction : Here an template like face feature is created which are unique for any
person .
Stored Feature : Here all feature extraction template are stored that will be used for feature
matching.
Feature Matching : It compares the user input image all the stored database . Based on that
we authenticate or disauthenticate any person .
Face
Recognition
Input
Image Finding Face Area Pre – Processing
Feature Matching Feature Extraction
Stored Feature
Kalinga Plus is an initiative by Kalinga University, Raipur. The main objective of this to disseminate knowledge and guide students & working professionals.
This platform will guide pre – post university level students.
Pre University Level – IX –XII grade students when they decide streams and choose their career
Post University level – when A student joins corporate & needs to handle the workplace challenges effectively.
We are hopeful that you will find lot of knowledgeable & interesting information here.
Happy surfing!!