Face is easy to understand. However, the process of

Face is the most prominent
feature used to recognize any person. It is tough task to identify human face
through facial expressions . Face recognition method using mathematic algorithm
is the most competent system for the security systems. It is a biometric
technology based concept with a purpose to prevent digital offences such as hacking
of ATM machines, avoid voter’s fraud, suspect’s identification, human’s digital
interaction with computer or other electronic machines, etc. Based on its
structural algorithm, facial biometric system used prominent facial features to
identification. Extorted facial features from face images are considerable for
face biometrics system performance.


Face recognition is arising hurdle
in the field of computer visualization and pictorial analysis as such has acknowledged
a great deal of consideration over the last decade because of its many
applications in several domains. It is the most hot topic since the late 80’s, delivering
solutions to several realistic troubles. Face recognition method should be accurate
to scan and identify face in images. when scanned result occur a recheck of
many faces in a database using the various features.  The environment conditions like lighting,
prospective view of a face, facial expressions and ageing. The similarity in
faces makes it hard to recognize the exact face from database. This involves
extraction of its features from the image and then recognizes it, regardless of
pose, expression, occlusion, lighting, ageing and illumination.

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!

order now


Face reorganization is not
that complex as it sounds, because it is easy to understand. However, the
process of recognition of faces used by the human

brain for
identification has many factors yet to discover. Human brain sees the faces on
daily bases and number of faces he sees is very large. Brain uses the same
process for every face. Brain extracts the features from the faces and store
that features in his database, next time when he sees the same face, brain try
to recognize the face by extracting the feature and compare it the stored
features in his database.After comparing both the face, human brain tells the
result. This task is easy for human brain. In modern era, digital security and
biometric based authority identification is in demand for banks, offices,
confidential research holds etc. Face Recognition Technology is used in
identity authentication, access control and other highly featured applications.
In present time, still there is more detailed research is conducting for
improvements and reducing flaws of biometric technology. Basically, face
recognition simply works with face scanned images, face viewpoint and other
pre-set expressions. Therefore, the functionality of the face recognition
system is always a matter of doubt.


In this thesis, two
algorithms are used I,e. Local Binary Pattern and Uniform Local Binary Pattern.
Local Binary Pattern (LBP) was first defined in 1994. It is a type of feature
used for the purpose of classification in computer vision. It has been observed
that LBP produces the best classifier of humans when it is combined with Histogram
of oriented gradients (HOG) classifier. Uniform Local binary pattern is said to
be uniform if upon traversing the bit pattern in a circular way, the binary
pattern contains at most two bitwise transitions from 0 to 1 or vice versa. These
patterns are used in the computation of LBP labels so that there is a separate
label for each uniform pattern and but a single label for all the non-uniform


In this proposed work, we
have studied the work on both i.e. face recognition and detection techniques
and developed algorithms for them. We have used a novel LBP-block wise face
recognition algorithm based on the features of local binary pattern and
uniforms local binary pattern. Two variants (each) of both the techniques are
used in this thesis work. One variant is applied to whole image as it is and in
other variant, first image is divided into 16 blocks of size 4 X 4 and then the
techniques are applied to each block and in the end the features of all the
blocks are appended together to form a combined feature vector for the whole
image. We have validated the proposed method on a set of classifiers computed
on a benchmarked ORL image database. It has been observed that the recognition
rate of the novel LBP-block wise method is better than the existing LBP method.






Place: Ferozepur                                                                                                                Nikhil Kumar


Date: January 11, 2018