Sie sind auf Seite 1von 9

ARITRA KRISHNA BANIK 16MMT1005

VINOD HANDI 16MMT1003

RECOGNITION OF NUMBER PLATE IN CAR


PARKING SYSTEM

OBJECTIVE:
To develop a machine vision system for automated vehicle parking with the help
of image processing.

ABSTRACT:
Automatic number plate recognition is an image processing technology which
uses number plate to identify the vehicle. The vehicle plate recognition
automatically controls access to a secured area for authorized members which is
renewed on monthly basis of the frequently coming vehicles. This work proposes
a method for the detection and identification of vehicle number plate that will
help in the identifying authorized and unauthorized vehicles. This approach is
based on recognizing all the letters and numbers used in the number plate and real
time comparison with the number plates date fed into the system. Image
processing is processing of images using mathematical operations by using any
form of signal processing for which the input is an image or a series of images or
a video, the output of image processing may be either an image or a set of
characteristics or parameters related to the image. With the help of this system
we can automate the whole process of vehicle entry and exit hence reducing man
power and can also help in reducing the mal practices done by the gate keepers
which would compromise in the safety of the whole building and it would also
result in faster processing than manual checking of the entry slip.
Vehicle number plate recognition mainly consist of the five main parts-
 First step is pre-processing which will reduces the noise and make it more
clearly visible.
 Next will be crop the image and then the number plate edge extraction is
performed.
 Then it will segment the characters individually to recognise each character
of the number plate using algorithm which will recognize or interpret the
result.
SCOPE-
The above proposed system can be used in various places like Malls and
especially in the Urban cities where multilevel parking and being used for parking
of vehicles. Since these type of parking are open 24/7 recruiting a person to for
the whole time would be tedious and costly but with this system it would
eliminate the work of man and will work without fatigue.

METHODOLOGY-
IMAGE PROCESSING IN MATLAB-
An automated system is developed by using MATLAB in which image is
captured by a camera and converted into grey scale image for pre-processing.
After the image is converted into grey scale, the dilation process is applied and
horizontal and vertical edge processing is done and passed those histograms
through low pass filters. After filtering image segmentation and region of interest
is extracted and image is converted into binary form. Binary images are easily
processed as compared to colour images. Each alphanumeric character on the
number plate is extracted and then recognize with the help of template
matching.at the end of this process, data is stored in a file and the whole number
pate is extracted successfully.

IMAGE ACQUISITION-
This is the first step of image processing. In this steep the image is acquire by a
high resolution digital camera .Image should be taken from a fixed angle parallel
to horizon. Images are taken in different background, illumination conditions, and
at various distances from the camera to vehicle. Images are resized to (2931X
1359). Which is shown by the below fig2.

Fig3: original image taken by hardware

CONVERT INTO GRAY SCALE IMAGE-


This algorithms works on grey level image, for pre-processing and identifying
the required information. In this step colour image (Fig4) is converted into grey
scale image.
Fig4: gray scale image

CANDIDATE PLATE AREA SELECTION-


Morphological operations aim to remove unrelated objects in the image. Dilation
and erosion are used to extract candidate plate areas from the entire image.
Sometimes background areas may also get declared as candidate plate. Dilation
is a process for filling holes, sharpens edges of an object and maximize the
brightness connect the broken lines. With the help of this process we can remove
unwanted noise from captured image. This whole process can be done by signal
processing.

Fig 5: dilated image

PASSING HISTOGRAM THROUGH LOW PASS FILTER-


To minimize loss of information smooth out changes, Histogram values are
passed through low pass filter because values of histogram between consecutive
row and column changes drastically. This step is performed for both horizontal
and vertical histograms. All unwanted regions of an image are removed in this
step by filtering
SEGMENTATION OF REGION OF INTEREST-
In this step image has been segmented. segmentation sub divided an image into
its constituent region or objects .The level to which subdivision is carried depends
on the problem being solved .That is segmentation should stop when the object
of interest in an application have been isolated.

CHARACTER REGION ENHANCEMENT-


To enhance the character region, if histogram equalization or gray level scaling
is used, noise may also be enhanced. For the correct character segmentation, only
the character pixels need to be enhanced and the background pixels need to be
weakened.
Whole processes is shown by following figures.

Fig6. Segmentation of image

CONNECTED COMPONENT ANALYSIS-


To remove the noise, other than characters on the plate, connected component
analysis is used. Each labelled matrix of 8-connectivity pixels is evaluated based
on the area threshold. The result of connected component analysis and noise
removal is as shown in Fig
RECOGNISION OF INDIVIDUAL CHARACTER-
For Recognition of individual alphanumeric character, template based
Recognition method is used. In template based algorithm, segmented image is
compared with one image which is stored in database named as template image.
In both images best matched similarity is compared. This similarity is matched
with statistical method correlation. The image for which the correlation
coefficient for template image is maximum that image is best matched.
STORING IN FILE-
The OCR is mostly used method to recognize the character against the complete
alphanumeric database. For this particular project purpose template matching
algorithm is being used. After extracting the number from the number plate the
each and every individual number will be called by one MATLAB algorithm. The
extracted character will be comprised with the predefined characters those are
stored in one particular folder.
After template matching the particular images result is shown by figure

EXPERIMENTAL RESULT & ANALYSIS-


A database consists of different sized JPEG colored images. Images are resized
to 2931X 1351. Total 50 images are used to test the algorithm. The images are
taken with different background as well as illumination conditions. Experiments
show that the algorithm has good performance on number plate extraction, and
character segmentation work. It can deal the images correctly, with noise. This
work is implemented using MATLAB. Character recognition work is done on
10 digits (0 to 9) and 26 alphabets (A to Z).Some difficulties may arise for some
different font or some unrecognizable writing. The example is shown by the
figure 9

Fig 9: Defected number plate


CONCLUSION
Hence this projects presents a recognition method in which the plate image is
obtained by a digital camera and the image is processed to get the plate
information of the vehicle which is entering the parking system withoiut any
human interference.
REFERANCES:
 Automatic Vehicle Number Plate Recognition Using Morphological Edge
Detection and Segmentation Teena Singh Rajput
 RECOGNITION OF VEHICLE NUMBER PLATE USING MATLAB
Ragini Bhat1 , Bijender Mehandia
 Vehicle Number Plates Detection and Recognition using improved
Algorithms: A Review with Tanzanian Case study Cosmo H.Munuo1 , Dr.
Michael Kisangiri2

Das könnte Ihnen auch gefallen