SMART RECOGNITION SYSTEM FOR THE ALPHANUMERIC
Content in Car License Plates
A. Akoum, B. Daya
Lebanese University, Institute of Technology, P.O.B. 813, Saida, Lebanon
P. Chauvet
Institut de Mathématiques Appliquées, UCO, CREAM/IRFA, 3, place André-Leroy
BP10808 – 49008 Angers - France
Keywords: License plate, Image processing, Segmentation, Extraction, Character recognition, Artificial neural network.
Abstract: A license plate recognition system is an automatic system that is able to recognize a license plate number,
extracted from an image device. Such system is useful in many fields and places: parking lots, private and
public entrances, border control, theft and vandalism control. In our paper we designed such a system. First
we separated each digit from the license plate using image processing tools. Then we built a classifier,
using a training set based on digits extracted from approximately 350 license plates. Our approach is
considered to identify vehicle through recognizing of its license plate using two different types of neural
networks: Hopfield and the multi layer perceptron "MLP". A comparative result has shown the ability to
recognize the license plate successfully.
1 INTRODUCTION
Optical character recognition has always been
investigated during the recent years, within the
context of pattern recognition (Swartz, 1999). The
broad interest lies mostly in the diversity and
multitude of the problems that may be solved (for
different language sets), and also to the ability to
integrate advanced machine intelligence techniques
for that purpose; thus, a number of applications has
appeared (Park, 2000; Omachi, 2000).
The steps involved in recognition of the license
plate are acquisition, candidate region extraction,
segmentation, and recognition. There is batch of
literature in this area. Some of the related work is as
follows: (Hontani, 2001) has proposed method heart
extracting characters without prior knowledge of
their position and size. (Cowell, 2002) has discussed
the recognition of individual Arabic and Latin
characters. Their approach identifies the characters
based on the number of black pixel rows and
columns of the character and comparison of those
values to a set of templates or signatures in the
database. (Yu, 2000) have used template matching.
In the proposed system high resolution digital
camera is used for heart acquisition.
The intelligent visual systems are requested more
and more in applications to industrial and deprived
calling: biometrics, ordering of robots, substitution
of a handicap, plays virtual, they make use of the
last scientific projections in vision by computer
(Daya, 2006), artificial training and pattern
recognition (Prevost, 2005).
The present work examines the recognition and
identification -in digital images- of the alphanumeric
content in car license plates. The images are
obtained from a base of abundant data, where
variations of the light intensity are common and
small translations and or rotations are permitted. Our
approach is considered to identify vehicle through
recognizing of it license plate using, two processes:
one to extract the block of license plate from the
initial image containing the vehicle, and the second
to extract characters from the licence plate image.
The last step is to recognize licence plate characters
and identify the vehicle. For this, we used two
different neural networks with 42x24 neurons as the
dimension of each character. The network must
memorize all the Training Data (36 characters). For
the validation of the network, we have built a
program that can read the sequence of characters,
565
Akoum A., Daya B. and Chauvet P. (2009).
SMART RECOGNITION SYSTEM FOR THE ALPHANUMERIC - Content in Car License Plates.
In Proceedings of the International Joint Conference on Computational Intelligence, pages 565-568
DOI: 10.5220/0002321805650568
Copyright
c
SciTePress
split each character, re-size it and finally display the
result on a Notepad editor.
The rest of the paper is organized as follows: In
Section 2, we present the real dataset used in our
experiment. We give in section 3 the description of
our algorithm which extracts the characters from the
license plate. Section 4 gives the experimental
results the recognizing of characters using two types
of neural networks architecture. Section 5 contains
our conclusion.
2 DATABASES
The database (Base Images with License) contains
images of good quality (high-resolution: 1280x960
pixels resizes to 120x180 pixels) of vehicles seen of
face, more or less near, parked either in the street or
in a car park, with a negligible slope.
The images employed have characteristics which
limit the use of certain methods. In addition, the
images are in level of gray, which eliminates the
methods using color spaces.
Figure 1 : Some examples from the database training.
3 LICENSE PLATE
CHARACTERS EXTRACTING
Our algorithm is based on the fact where an area of
text is characterized by its strong variation between
the levels of gray and this is due to the passage from
the text to the background and vice versa (see fig.
1.). Thus by locating all the segments marked by this
strong variation and while keeping those that are cut
by the axis of symmetry of the vehicle found in the
preceding stage, and by gathering them, one obtains
blocks to which we consider certain constraints
(surface, width, height, the width ratio/height,…) in
order to recover the areas of text candidates i.e. the
areas which can be the number plate of the vehicle
in the image.
Figure 2: Selecting of license plate.
Figure 3: Extracting of license plate.
We digitize each block then we calculate the
relationship between the number of white pixels and
that of the black pixels (minimum/maximum). This
report/ratio corresponds to the proportion of the text
on background which must be higher than 0.15 (the
text occupies more than 15% of the block).
First, the block of the plate detected in gray will
be converted into binary code, and we construct a
matrix with the same size block detected. Then we
make a histogram that shows the variations of black
and white characters.
To filter the noise, we proceed as follows: we
calculate the sum of the matrix column by column,
then we calculate the min_sumbc and max_sumbc
representing the minimum and the maximum of the
black and white variations detected in the plaque.
All variations which are less than 0.08 * max_sumbc
will be considered as noises. These will be canceled
facilitating the cutting of characters.
Figure 4: Histogram to see the variation black and white of
the characters. The characters are separated by several
vertical lines by detecting the columns completely black.
To define each character, we detect areas with
minimum variation (equal to min_sumbc). The first
detection of a greater variation of the minimum
value will indicate the beginning of one character.
And when we find again another minimum of
IJCCI 2009 - International Joint Conference on Computational Intelligence
566
variation, this indicates the end of the character. So,
we construct a matrix for each character detected.
The Headers of the detected characters are
considered as noise and must be cut. Thus, we make
a 90 degree rotation for each character and then
perform the same work as before to remove these
white areas.
Figure 5: Extraction of one character.
A second filter can be done at this stage to
eliminate the small blocks through a process similar
to that of extraction by variations black white
column.
Finally, we make the rotation 3 times for each
image to return to its normal state. Then, we convert
the text in black and change the dimensions of each
extracted character to adapt it to our system of
recognition (Hopfield and MLP neural network).
4 RECOGNIZING OF
CHARACTERS USING OUR
APPROACH NEURAL
The character sequence of license plate uniquely
identifies the vehicle. It is proposed to use artificial
neural networks for recognizing of license plate
characters, taking into account their properties to be
as an associative memory. Using neural network has
advantage from existing correlation and statistics
template techniques (B. Kroese, 1996) that allow
being stable to noises and some position
modifications of characters on license plate.
Our approach is considered to identify vehicle
through recognizing its license plate using, Hopfield
networks with 42x24 neurons as the dimension of
each character. The network must memorize all the
Training Data (36 characters). For the validation of
the network we have built a program that reads the
sequence of characters, to cut each character and
resize it and put the result on a Notepad editor. A
comparison with an MLP network is very
appreciated to evaluate the performance of each
network.
For this analysis a special code has been
developed in MATLAB. Our Software is available
to do the following:
1) Load a validation pattern.
2) Choose architecture for solving the character
recognition problem, among these 6 architectures:
"HOP112": Hopfield architecture, for pictures
of 14x8 pixels (forming vector of length 112).
"HOP252": Hopfield, for 21x12 pixels.
"HOP1008": Hopfield, for 42x24 pixels.
"MLP112": Multi Layer Perceptron
architecture, for pictures of 14x8 pixels.
"MLP252": MLP, for 21x12 pixels.
"MLP1008": MLP, for 42x24 pixels.
3) Calculate time of processing of validation
(important for “real applications”).
Figure 6: The graphic interface which recognizes the plate
number and posts the result in text form.
For our study, we used 3 kinds of Hopfield
Networks and 3 kinds of MLP Networks, always
with one hidden layer. In the case of MLPs, we train
one MLP per character; it means that there are 36
MLPs for doing the recognition. In the case of
Hopfield there is only one network that memorizes
all the characters.
Table 1: The performance of each Neural Network
Architecture (multi layer perceptron and Hopfield).
Neural
Network
Number
of
neurons
Total
Symbols
Total
Errors
Perf
(%)
HOP 1008 1130 144 87 %
MLP 1008 1130 400 64 %
HOP 252 1130 207 84%
MLP 252 1130 255 80 %
HOP 112 1130 342 69 %
`MLP 112 1130 355 68 %
The table 1 shows the performance of each
neural architecture for the six different cases. Tables
2 and 3 “see appendix” shows all the recognitions
for all the patterns. First column corresponds to the
file's name of the plate number; second column the
plate number observed with (our eye) and from
SMART RECOGNITION SYSTEM FOR THE ALPHANUMERIC - Content in Car License Plates
567
columns 3 to 5 there is the plate number that each
architecture has recognized. The last row
corresponds to the average processing time that
takes for each network.
In the case of Hopfield recognition, when the
network doesn’t reach a known stable state it gives
the symbols “?”. Hopfield Networks have
demonstrated better performance 87% than MLPs
regarding OCR field. A negative point in the case of
Hopfield is the processing time, in the case of
pictures of 42x24 pixels (90 seconds average, versus
only 3 seconds in the case of pictures of 21x12
pixels). It can be observed also that cases
"HOP1008" and "HOP252" don’t present an
appreciable difference regarding performance.
5 CONCLUSIONS
The purpose of this paper is to investigate the
possibility of automatic recognition of vehicle
license plate.
Our algorithm of license plate recognition,
allows to extract the characters from the block of the
the plate, and then to identify them using artificial
neural network. The experimental results have
shown the ability of Hopfield Network to recognize
correctly characters on license plate with probability
of 87% more than MLP architecture which has a
weaker performance of 80%.
The proposed approach of license plate
recognition can be implemented by the police to
detect speed violators, parking areas, highways,
bridges or tunnels.
REFERENCES
J. Swartz, 1999. “Growing ‘Magic’ of Automatic
Identification”, IEEE Robotics & Automation
Magazine, 6(1), pp. 20-23.
Park et al, 2000. “OCR in a Hierarchical Feature Space”,
IEEE Transactions on Pattern Analysis and Machine
Intelligence, 22(4), pp. 400-407.
Omachi et al, 2000. Qualitative Adaptation of Subspace
Method for Character Recognition. Systems and
Computers in Japan, 31(12), pp. 1-10.
B. Kroese, 1996. An Introduction to Neural Networks,
Amsterdam, University of Amsterdam, 120 p.
J. Cowell, and F. Hussain, 2002. “A fast recognition
system for isolated Arabic characters”, Proceedings
Sixth International Conference on Information and
Visualisation, England, pp. 650-654.
H. Hontani, and T. Kogth, 2001. “Character extraction
method without prior knowledge on size and
information”, Proceedings of the IEEE lnternational
Vehicle Electronics Conference (IVEC’OI). pp. 67-72.
C. Nieuwoudt, and R. van Heerden, 1996. “Automatic
number plate segmentation and recognition”, In
Seventh annual South African workshop on Pattern
Recognition, l April, pp. 88-93.
M., Yu, and Y.D. Kim, 2000. ”An approach to Korean
license plate recognition based on vertical edge
matching”, IEEE International Conference on
Systems, Ma, and Cybernerics, vol. 4, pp. 2975-2980.
B. Daya & A. Ismail, 2006. A Neural Control System of a
Two Joints Robot for Visual conferencing. Neural
Processing Letters, Vol. 23, pp.289-303.
Prevost, L. and Oudot, L. and Moises, A. and Michel-
Sendis, C. and Milgram, M., 2005. Hybrid
generative/discriminative classifier for unconstrained
character recognition. Pattern Recognition Letters,
Special Issue on Artificial Neural Networks in Pattern
Recognition, pp. 1840-1848.
APPENDIX
Table 2: The recognition for some patterns with different
numbers of neurons (Hopfield Network).
Seq Real plate
number
(eye)
HOP1008 HOP252 HOP112
'p1' '9640RD9' '9640R094' '9640R09
4'
'9640R?94
'
'p2' '534DDW7
7'
'534DD?77' '534DD?7
7'
'534DD?7
7'
'p3' '326TZ94' '326TZ94' '326TZ94' '325TZ9?'
'p4' '6635YE93
'
'66J5YES?' 'B??5YE?
?'
'B???YE??
'
'p5' '3503RC94
'
'3503RC94' '35O3RC9
4'
'3503RC9
4'
'p6' '7874VT94
'
'7874VT94' '7874VT9
4'
'7874VT9
4'
Tim
e
-- 90 sec 3 sec 2 sec
Table 3: The recognition for all some patterns with
different numbers of neurons (MLP network).
Seq Real plate
number
(eye)
MLP1008 MLP252 MLP112
'p1' '9640RD9
4'
'964CR094' '56409D94' '2B40PD3
4'
'p2' '534DDW
77'
'53CZD677' '53CDD877
'
'53WDD9
77'
'p3' '326TZ94' '32SSZ8C' '326T794' '328TZ3C'
'p4' '6635YE9
3'
'8695YE8O' 'BE3SYE98
'
'E535YEB
3'
'p5' '3503RC9
4'
'35CO3C94' '5503RC94' '3503PC2
4'
'p6' '7874VT9
4'
'F674VT94' '7574V394' '7S74VT3
4'
Time -- 25 sec 3 sec 2 sec
IJCCI 2009 - International Joint Conference on Computational Intelligence
568