Hi am kavitha i would like to get details on matlab code for number plate recognition using template matching

Object recognition in computer vision is the task of finding a
given object in an image or video sequence. Humans
recognize a large amount of objects in images with little
effort, regardless of the fact that the image of the objects
may differ somewhat in different viewpoints, in several
different sizes /scale or even when they are translated or
rotated . Objects can even be recognized when they are
partially obstructed from view. This task is still a challenge
for computer vision systems in general.
Object recognition can be observed as a learning problem.
To start with the system is trained on sample images of the
target object class and other objects, learning to differentiate
them. Subsequently, when new images are fed the system
can sense the presence of the target object class
The object recognition problem can be separated into two
basic blocks: low level and high level vision. The low level
vision task can be seen as to isolate objects and regions from
the given image and similarly extracting other characteristic
features from an image. The high level vision means the
interpretation of these objects or features in the frame of a
reference scene
Correlation is a measure of the degree to which two
variables agree, not necessary in actual value but in general
behavior. The two variables are the corresponding pixel
values in two images, template and source.
Template Matching: It is a Technique used to categorize
objects. A template is a small image (sub-image) .The goal
is to find occurrences of this template in a larger image that
is, you want to find matches of this template in the image.
Template matching techniques compare portions of images
against one another. Sample image may be used to recognize
similar objects in source image
Template matching has been a classical approach to the
problems of locating and recognizing of an object in an
image. Template matching technique, especially in two
dimensional cases, has many applications in object tracking,
image compression, stereo correspondence, and other
computer vision applications . Even now, it is a
fundamental technique to solve them. Among several
matching methods, Normalized Cross Correlation (NCC)
and square root of Sum of Square Differences ~SSD) have
been used as the measure for similarity. Moreover, many
other template matching techniques , such as Sum of
Absolute Differences (SAD) and Sequential Similarity
Detection Algorithm (SSDA) have been adopted in many
applications for pattern recognition, video compression and
so on. In addition, template matching has been extensively
used in various applications, for example, extraction of
container identity codes , image segmentation,and
so on.