Site icon Biyani Group of colleges

Face recognition using Neural Network


A face recognition system is a computer application for automatically identifying or verifying a person from a digital image or a video frame from a video source.
 Feature to be compared for face recognition:
1. Inter-ocular distance
2. distance between the lips and the nose
3. distance between the nose tip and the eyes
4. distance between the lips and the line joining the two eyes
5. eccentricity of the face
6. width of the lips
 A Neural Network is a system of programs and data structures that approximates the operation of the human brain.
 A neural network usually involves a large number of processors operating in parallel, each with its own small subject of information and access to data in its local memory.
 Typically, a neural network is initially “trained” or fed large amounts of data and rules about data relationships (for example, “A grandfather is older than a person’s father”).
A program can then tell the network how to behave in response to an external stimulus or can initiate activity on its own
EvolutionofFaceRecognition
 A formal method first proposed by Francis Galton in 1888.
 A growing interest since 1990.
 Research interest has grown :
* Availability of better hardware, allowing real- time.
* Increasing commercial opportunities applications.
* The increasing importance of surveillance-related applications.
* Great improvements have been made in the design of classifiers.
Face detection
 Face detection is the first step in automated face recognition.
 Face detection can be performed based on several cues:
 skin color
 motion
 facial/head shape
 facial appearance or
 A combination of these parameters.
 Most successful face detection algorithms are appearance-based without using other clues.


Why face recognition are used?
 Verification of credit card, personal ID, passport
 Bank or store security
 Crowd surveillance
 Access control
 Human-computer-interaction

Advantages
 When an element (Artificial neuron) of the neural network fails, it can continue without any problem by their parallel nature.
 A neural network learns and does not need to be reprogrammed.
 It can be implemented in any application.

Disadvantages
 They are black box – that is the knowledge of its internal working is never known
 Since applying neural network for human-related problems requires Time to be taken into consideration but it’s been noted that doing so is hard in neural networks
 They are just approximations of a desired solution and errors in them is inevitable.

Exit mobile version