Limitations of existing algorithms. Objective. Project selection. Algorithm and its flow. Implementation. Applications. Future Enhancement.

The existing face recognition algorithms use the

whole face to recognize wherein number of computations are more .

Power consumption .
Computation time.

Limitations of existing algorithms. Objective. Project selection. Algorithm and its flow. Implementation. Applications. Future Enhancement.

 According to the statistics, the faces of 85-90% of the people exhibit reflectional symmetry about a bilateral symmetry axis.

The use of the average half face in face recognition research has shown a potential

increase in accuracy and decrease in storage and computation time .

The project aims to authenticate the face by applying algorithm only for half face thereby reducing the number of computations and power consumption.

Limitations of existing algorithms. Objective. Project selection. Algorithm and its flow. Implementation. Applications. Future Enhancement.

Algorithm: MATLAB implementation of face recognition

profile matching Database: MATLAB development of file system Data Acquisition: Multimedia Lab video camera or digital camera

Limitations of existing algorithms. Objective. Project selection. Algorithm and its flow. Implementation. Applications. Future Enhancement.

I. Centre and orient the face in the image. II. Partition the image into two equal left and right halves, lh and rh. III. Reverse of the ordering of(or mirror) the

columns of one of the images producing rh1. IV. Average the resulting mirror right half image(rh1) with the left half image(lh) to produce the average-half-face. V. The average half face is then in used in place of the full face image for face recognition.

 Eigen faces are used because of its simplicity and it

highlights the difference in face recognition accuracy between using the full face and the average half face.
Eigen faces is based on the principal components analysis

(PCA) .
PCA captures as much of the variance in the data as possible

in as few principal components as possible

START
IMAGE ACQUISITION

FACE DETECTION

COMPUTATION OF AVERAGE-HALF-FACE

COMPARISION WITH DATABASE

DECISION MAKING
END

Limitations of existing algorithms. Objective. Project selection. Algorithm and its flow. Implementation. Applications. Future Enhancement.

 The 2D image for which the computation is to be done is

opened using MATLAB application.

Facial part of the subject is extracted. Average half face of image is obtained. Using PCA algorithm the average half face is compared

against the 2D images present in the database.

Later decision is made.

Limitations of existing algorithms. Objective. Project selection. Algorithm and its flow. Implementation. Applications. Future Enhancement.

We will collect it from internet)

(

Limitations of existing algorithms. Objective. Project selection. Algorithm and its flow. Implementation. Applications. Future Enhancement.

 We will use symmetry scores to compare most

symmetric and least symmetric sub-groups.

Future work will include introducing additional

symmetry measures as well as extending this analysis to more databases of 2D and 3D faces.
The ultimate goal would be to create a correlation

between the symmetry of the face and face recognition that could be used to improve the overall face recognition accuracy.

Limitations of existing algorithms. Objective. Project selection. Algorithm and its flow. Implementation. Applications. Future Enhancement.