International Journal of Engineering Research & Technology (IJERT)

ISSN: 2278-0181
Vol. 1 Issue 9, November- 2012

Vehicle License Plate Detection From Video Using Edge Detection And
Morphological Operators

Harpreet Kaur Manvi Balwinder Singh

Lala Lajpat Rai Institute Lala Lajpat Rai Institute Govt. Multipurpose Sec. School
of Engineering & Technology, of Engineering & Technology, (Passi Road )
Moga – 142001 (Punjab) Moga – 142001 (Punjab) Patiala -147001

Abstract - Road discipline is must due to growing components that are useful in representation and
number of vehicles and traffic violators on roads. In description of the object shape. It is mathematical in the
order to enhance discipline upon roads, this paper sense that analysis is based upon set theory, topology,
describes an instant and real time mobile vehicle lattice algebra, function etc.
license plate recognition system in an open
environment. License plate recognition system plays 2. Present Work
a major role in monitoring traffic rules and
maintaining law enforcement on public roads. Using The central idea of this paper is to detect
a fixed camera installed at red lights, toll plaza, vehicle number plate from video. The proposed system
border crossing, and petrol station and in parking has four modules: In first module, camera captures
areas, system capture the videos of the vehicles. video of the vehicle. In second module, video get
Using canny edge detection algorithm and converted into frames by using MATLAB operations.
morphological operators, system detects vehicle In third module, frames are converted into images.
RRTT
number plate. Experiment shows that system can Finally, in last module by using canny edge detection
effectively capture the vehicle video and detect the and morphological operator‟s vehicle number plate is
license plate whether it has been taken at day time, extracted. The main advantage of this technique is that
IIJJEE

night time or under complicated environments and from 10 sec (24fps) video, 240 frames or images are
show accuracy up to 90%. extracted. Therefore, algorithms are implemented upon
240 images one by one automatically by the system.
Keywords: LPR (License Plate Recognition), So, this work needs more computation as compared to
morphological operators, canny edge detector, video. previous work.

1. Introduction Capture Vehicle Video

Vehicle License plate identification is an
essential stage in intelligent traffic system. It is a video
processing technology used to identify vehicles by their
license plates. Real time LPR (License plate Video into frame conversion
recognition) play a major role in automatic monitoring
of traffic rules and maintaining law enforcement on
public roads. In previous work, there are different
techniques such as sobel edge detector [2], canny edge Frame into image conversion
detection and morphological operators [1] [10], skew
correction [11], color model [5] are used to detect
vehicle number plate. One similarity between
techniques discussed above is that they are
implemented on single image and at day time only. License Plate extracted
While this paper work uses canny edge detection and
morphological operators to detect vehicle number plate
from the videos of the vehicles in different illumination Figure 1.1: Block diagram of License Plate Detection
environments. Canny edge detector [1] is an edge
detection operator that uses a multi-stage algorithm to
detect wide range of edges in images. Mathematical
morphology [1] [10] is used as a tools to extract image

www.ijert.org 1
 International Journal of Engineering Research & Technology (IJERT)
ISSN: 2278-0181
Vol. 1 Issue 9, November- 2012

Step 1 produce 240 images. These images are stored in any

Capture Vehicle Video folder, in which the further processing will be done in
order to detect vehicle number plate.
To capture video of the vehicle, camera must
be placed at fixed location, at a minimum height of 3 Step 4
feet, so that camera faces vehicle number plate. The Number plate extraction
camera takes the video from either front or rear of the
vehicles. The video of the vehicle contains the license In order to extract vehicle number plate, image
plate. The camera feeds the input video to the system. processing has been done by using different
Camera can be installed at different locations. For algorithms. First of all canny edge detection algorithm
example: toll plaza, traffic lights, border crossings, and is applied in order to detect edges of the vehicle
petrol station etc. However, in this method, work has images. Then, morphological operators are applied to
been done upon 10 to 15 sec video clip. The 10 sec detect the vehicle number plate area. A morphological
video contains 240 frames/images (24fps), operations operator is applied to the image by specifying the
has been performed upon 240 images in order to extract plate location. A morphological operator is selected
vehicle number plate. This technique provides live that is sensitive to a specific shape in the input images.
monitoring and continuous reading. MATLAB In this system rectangular box is employed as a
operations are used to read the video of vehicle taken structural element to detect the car plates.
by camera positioned at fix location. Mmreader is able
to read AVI, WMV, MPEG, ASF files. It creates a Mathematical morphology - It is a topological
multimedia object for reading video files. Obj = and geometrical based approach for image analysis
mmreader(filename) constructs a multimedia reader which provides powerful tools for extracting
object, obj (object), that can read video data from a geometrical structures and representing shapes in
multimedia file. many applications. Using two basic operations of
morphology (erosion and dilation), opening and
RRTT
Step 2 closing of images has been done. The process of
Video into frame conversion dilation followed by erosion is called closing. It has
the effect of filling small and thin holes, connecting
IIJJEE

After reading video file, convert it into frames. nearby objects and smoothing the boundaries contours
Frame rate taken is 24 fps. This is universally of the objects. In closing operation dilation followed
accepted film frame rate. There are 3 types of frames: by erosion with the same SE (Structuring element).
I-frame, P-frame, B-frame. I-frame is an intra-frame, This operation removes black holes on white objects.
coded completely by itself. P-frame depend on the last The process of erosion followed by dilation is called
P-frame or I- frame (whichever is closer) also called opening. It has the effect of eliminating small and thin
“Anchor frame”. Therefore, P-frame is constructed by points and smoothing boundaries/contours of the
predicting the difference between the current frame objects. This operation can erase white holes on dark
and closest preceding I-frame or P- frame. A B-frame objects or can remove small white objects in a dark
is constructed from the two closest I-frames or P- background. So, rectangular box whose size is same as
frames. The B-frame must be positioned between number plate area will be taken as a structuring
these I-frames or P-frames. Camera captures video of element to detect number plate area. An object will be
different vehicles continuously and later on extracts erased if the SE does not fit within it. Hence, only
video of single vehicle. MATLAB provides a function vehicle number plate is detected and remaining
to extract the frames from video and process them. vehicle is erased.

a) Dilation
Step 3
(A⊕ B) (x,y) = max {A(x-s, y-t) + B(s,t)}
Frame into image conversion
b) Erosion
Frames can be obtained from a video and
(A Ө B)(x,y) = min {A(x+s, y+t) – B(s,t)}
converted into images. To convert a video frames into
images; the MATLAB function „frame2im‟ is used.
c) Opening
The necessity of this conversion arises because in
order to detect vehicle number plate different A o B = (A Ө B) ⊕ B
algorithms must be applied, these algorithms can only
be applied upon images. One 10 sec video may d) Closing

www.ijert.org 2
 International Journal of Engineering Research & Technology (IJERT)
ISSN: 2278-0181
Vol. 1 Issue 9, November- 2012

A ● B= (A ⊕ B) Ө B i) Probability of getting image accuracy is more as

video camera may not miss even a single
Here A(x,y) is the gray scale image and B(x,y) is the movement.
structuring element.
ii) If one image does not show result, then there are
Structuring Elements- In mathematical morphology number of images upon which operators have been
these are represented as matrices. Structuring applied to get the desired result.
element is a characteristic of certain structure and
features to measure the shape of an image and is For example: In 10 sec, video camera produces 240
used to carry out other image processing operations. frames/images, while photo camera captures
The shape and size of the structuring element plays approximately 6 images.
crucial role in extracting vehicle number plate. 3*5
structuring element is shown below used to detect Hence, Probability of detection of number plate
vehicle number plate. from video over images (PV) is:

PV= ((V-I) ÷ V) * 100

PV = ((240-6) ÷ 240) * 100 = 97.5%

V: denotes images extracted with video camera.

I: denotes images extracted with photo camera.

In video, among 240 images approximately

218 images can show the accurate number plate. In
Figure 1.2: Structuring Element
case of photo camera, among 6 images
RRTT
approximately 2 images can give accurate results.
These algorithms are applied on 240 images
one by one automatically by the system. Then
system shows extracted number plates results of all
3. Experimental Results
IIJJEE

images one by one automatically. Hence this is

Vehicle Video
main advantage of the system that it works upon
number of images not on a single one, as it is quite
easy to work upon single image.

Probability of detection of number plate

from Video over single image:

When any camera positioned at red lights

captures the images of the vehicles then following
problems may be faced:

i) Probability of image accuracy is less.

Figure 1.3: Video of car
ii) Corrupted or blurred image. Successfully extracted number plates from video

iii) Some movements of vehicles are missed by the

camera.

Hence, any software may be unable to detect

vehicle number plate if image is inaccurate,
corrupted or blurred.

So, to overcome above mentioned problems, the

need of video processing arises.

Advantages of video processing are:

www.ijert.org 3
 International Journal of Engineering Research & Technology (IJERT)
ISSN: 2278-0181
Vol. 1 Issue 9, November- 2012

I1: denotes number of images per video, e.g. 15 sec

video produces 360 frames/images.

Table 1.2: Accuracy calculation of vehicle number

plate
Frames Images No. Plate Accuracy=
per video per video extracted (S/I1)* 100
(approx.) (approx.) (S)
(I1)

240 240 218 90.8%

200 200 180 90.0%

Figure 1.4: Extracted number plates from video 4. Conclusion and Future work
Vehicle number plate This technique is very efficient in detecting
vehicle number plate from videos of the vehicles using
edge detector and morphological operators. It is highly
effective in security areas like border crossing, red
lights, toll plaza and petrol station etc. It shows number
plate extracted from all images one by one
automatically. Accuracy of showing vehicle number
plate from number of images in a single video is 85%
to 90%. While getting desired result of number plate
RRTT
from overall video is 99%. For example: among 240
images there is a single image present which shows the
correct and accurate result. Future work of this
Figure 1.5: Vehicle number plate
technique is to select single result automatically which
IIJJEE

is best one among multiple number plates. Hence, to

Table 1 shows Experimental environment, vehicles
successfully extract single number plate from multiple
to be observed, video clips taken in different
number plates is the challenging future scope.
environments and length of video.

Table 1.1: Experimental videos References

Experiment Vehicles Experiment Length
[1] Chetan Sharma, Amandeep Kaur, “Indian vehicle license
environment used videos of plate extraction and segmentation”, IJCSE, International
video Journal of Computer Science and Communication, Dept.of
CSE, Patiala, Jul-Dec 2011, Vol 2 no.2, 593-599.
Day Car 20 clips 5 to 15
sec [2] Dr. P.K.Suri, Dr. Ekta walia, Dr. Amit verma, “Vehicle
number plate detection using sobel edge detection technique”,
Night Motorbike 10 clips 5 to 15
UCST, Vol 1, Issue 2, Dec 2010, 178-182.
sec
[3] Ehsan Nadersinajeb, Sara Sharifzada , Hamid Hassanpur,
Accuracy of the above experimental videos is “edge detection techniques evaluations and comparisons”,
calculated in Table 2 shown below: IJCST, 2008, 1507-1520.

[4] Kaushik Deb, Andreyvevilin,”Projection and least square

Formula for calculating Accuracy is:
fitting with perpendicular offsets based vehicle license plate
tilt correction” SICE Annual Conference, 2010, 3291-3298.
Accuracy= (S ÷ I1)*100
[5] Kaushik Deb and Kang Hyun Jo,”Segmenting the
Here, License plate region using color model”, University of Ulsan
south Korea, 2009, 401-418.
S: denotes the probability of finding number plate
from the video clip.

www.ijert.org 4
 International Journal of Engineering Research & Technology (IJERT)
ISSN: 2278-0181
Vol. 1 Issue 9, November- 2012

[6] Kou-Ming Hung, Ching-Tang Hseih,”A Real- time

Mobile Vehicle License Plate Detection and Recognition”
Tam Kang Journal of Science and Engineering, 2010, 433-
442.

[7] Raphael Labayrade and Didier Aubert,“In-Vehicle

obstacles detection and characterization by stereovision” ESV
2003 Proceedings, Nagoya, Japan, 19-22 May 2003.

[8] R.C.Gonzalez and R.E.Woods, “Digital Image

Processing”, 2nd ed. Prentice Hall, 2002.

[9] Rong Lia, Musa Yassin Fortb, and Georgios C.

Anagnostopoulos,“Multi-stage Automatic License Plate
Location and Recognition”, IEEE International Conference
on Image Processing, 2002, 502-511.

[10] Shriram K.Vasudevan, Dharmendra T, Sivaraman R,”

Automotive Image Processing Technique using Canny‟s Edge
Detector” IJEST, 2010, 2632-2644.

[11] Varun Manchikalapudi, “Skew Correction and

Localisation of Number Plate Using Hough Transform”
UCST, 2011, 472-476.

[12] Wing Teng Ho, Wooi Hen Yap, Yong Haur Tay,
“Learning based License Plate Detection on Edge Features”,
IEEE International Conference on Image Processing,
RRTT
Sept.2004, 900-903.
IIJJEE

www.ijert.org 5