Professional Documents
Culture Documents
Tuan V. Pham
Center of Excellence
University of Technology, University of Danang
Danang, Vietnam
pvtuan@dut.udn.vn
I. INTRODUCTION
Image processing techniques have been applied widely
from civil device to specialized equipment. The use of image
processing for license plate recognition will contribute to
solving a part of the problem traffic congestion and automate
some tasks related to the management of cars. Now,
management of transport and general manager automobiles and
motorcycles in particular is extremely complex, as well as the
work of detecting and sanctioning traffic violations, theft... will
spend a lot of time and effort. And then, the demand of
building automation system identification and manage
motorized means of traffic are also born. This system will
reduce the pressure on human resources in management and
control these transport. Through this theme, also create the
premise for develop solutions such as: license plate
recognition, documents recognition.
License Plate Recognition (LPR) is a technology to extract
license number from vehicle image capturing by a single or
multiple cameras. It has various applications in traffic control,
vehicle theft prevention, vehicle surveillance, parking lot
access control, etc. A LPR system typically consists of three
steps: plate extraction, character segmentation and character
recognition.
Preprocessing
Plate
Localization
Character
Segmentation
Recognition
43A 03246
II. PREPROCESSING
A. Convert RGB image or colormap to grayscale
In Number Plate Detection, the image of a car plate may
not always contain the same brightness and shades. Therefore,
the given image has to be converted from RGB to Gray form.
Converts RGB values to Gray scale values by forming a
weighted sum of the R, G, and B components.
B. Noise filter and dilate an image
However, during this conversion from RGB to Gray form,
certain important parameters like difference in color, lighter
edges of object, etc. may get lost [6]. The process of dilation
will help to nullify such losses. Dilation is a process of
improvising given image by filling holes in an image, sharpen
the edges of objects in an image, and join the broken lines and
increase the brightness of an image. Using dilation, the noise
within an image can also be removed. By making the edges
sharper, the difference of gray value between neighboring
pixels at the edge of an object can be increased. The process of
dilation will help to nullify such losses.
We can use a periodical convolution of the function f with
specific types of matrices m to noise filter and dilate an image:
(
)
)
(
,
)-
Preprocessing
(1)
( )
As:
( )
(3)
Convolution
matrix
x1
x2
x3
m1 m2 m3
x4
x5
m4
x6
x7
x8
m6 m7 m8
m5
A. Preprocessing
* (
(
(
(
)+
)
)
b.
(4)
}
(5)
a.
B. Segmentation
The purpose of this step is to find the individual characters
on the plate. Pixel connectivity and projection profiles are two
popular features for segmenting license plate characters [11].
In the proposed approach, pixel connectivity feature was used
because it is more robust to rotation than projection profiles.
Fig. 7 shows the algorithm of segmentation stage.
a.
b.
c.
d.
B. Feature Extraction
Each character image has large dimension preventing it
from being use as the input feature. However, we can
use dimension reduction techniques to map data to a
lower dimensional space such that uninformative
variance in the data is discarded. There are many
dimension reduction techniques such as principal
components analysis (PCA), projection pursuit (PP),
principal curves (PC), self-organizing maps (SM). In the paper
proposed a hybrid method of principal components analysis
and local binary pattern (LBP). Firstly, PCA extracted the
global grayscale feature of the whole facial expression image
and reduced the data size at the same time. And LBP extracted
local neighbor texture feature of the mouth area, which
contributes most to facial expression recognition. Fusing the
global and local feature will be more effective for facial
expression recognition.
Step 1: Give
sampled images:
are
a.
Segment character
b. Skeletonized character
Fig.10 Segmented character is skeletonized
) (
)
.(
Local Binary Pattern
Intersection
b. end-point c. closed-area
Fig. 11 Three feature points
Where
( ) defined
( )
(
(
)
}
)
)
(
( )||
||
Step 3: For
set
()
(
is the number of pixels in
()
()
()
VI.
[(
[(
()
()
()
)]
EVALUATION
A. Classification measure
In this paper, performance of the proposed recognition
algorithm is assessed via the true positive rate (TPR) and false
positive rate (FPR) which are defined as follow:
,
Fig13. Type1: 62-50-25 NNET Type2: 62-50-8 NNET
Type3: 60-50-2 NNET.
The Type 1 NNET receives a 62x1 vector in the form of
Fig13. It passes through the first log-sigmoid hidden layer
with contains 50 neurons and finally it enter the output logsigmoid layer which contains 25 neurons, leading to vector .
The output 25x1 vector values correspond to the sequence of
Type1 and are between 0 and 1(due to the log-sigmoid
function). It can be said that each value represent the
probability that the input signature is classified to a specific
Type1. The final result is provided through a competitive
transfer function which returns the index with the optimum
value.
The Type2 and Type3 NNET work identically to the
Type1 network, except that it use 8, 2 neurons in the output
layer.
Back-propagation algorithm.
Five steps of training MLP network use back-gropagation
algorithm as following:
Step 1: Perform a feedforward pass, computing the activation
for layers
, and so on up to the output layer
:
(
)
(
() ()
)
DETAILS OF RESULT
()
( ( ))
Step 2: For each output unit i in layer (the output layer), set:
Test
database
Amount
Segmentation
TPR
FPR
Total
Contrast
Low
High
Weather
Rainy
Cloudy
Sunny
Position/ Angle
Straight
Rotation
Projection
Quantity
High
Low
View
Front
Back
Background
Simple
Complex
127
107
84.25
15.75
35
95
27
79
77.14
85.87
22.86
14.13
32
93
25
31
78
23
96.88
83.87
92
3.13
16.13
8
60
39
17
55
32
11
91.67
82.05
64.71
8.33
17.95
35.29
101
15
83
12
82.18
64.52
17.82
20
95
31
86
20
90.53
64.52
9.47
35.48
40
28
34
20
85
71.43
15
28.57
TABLE III.
Set1
Set2
Set3
TABLE II.
Test
database
Set1
Set2
Set3
Quantity
Description
183
67
91
Evaluation
Total plate
183
67
91
Segmentation
176
51
56
Ratio
96.17%
76.12%
61.54%
C. Segmentation evaluation
Train
(samples/character)
Clear
Noisy
Clean
model
Noisy
model
Test
(samples/character)
WM MM HM ALL
50
20
20
20
60
50
30
10
10
10
30
2) Evaluation
The test sets consist of WM, MM, HM and ALL
(WM+MM+HM) are used for testing in both training models.
At first, closed-area feature is used for categorizing the type of
characters. The categorizing results of three subsets are shown
in Table 4 (clean model) and Table 5 (noisy model).
a) Clean model
The test set contains of test WM (700 chars), test MM (700
chars), test HM (700 chars) and test ALL (2100 chars) are
used for evaluation the clean model.
TABLE V.
Clean
model
WM
MM
HM
ALL
T1 T2 T3 T1 T2 T3 T1 T2 T3 T1 T2 T3
Type1
498 2 0 499 1 0 499 1 0 1496 4 0
(T1)
Type2
2 158 0 4 155 1 6 150 4 12 463 5
(T2)
Type3
0 0 40 0 0 40 1 0 39 1
0 119
(T3)
b) Noisy model
The test set contains of test WM (350 chars), test MM (350
chars), test HM (350 chars) and test ALL (1050 chars) are
used for evaluation the noisy model.
TABLE VI.
WM
MM
HM
ALL
Noisy
model T1 T2 T3 T1 T2 T3 T1 T2 T3 T1 T2 T3
Type1
250 0 0 249 1 0 249 1 0 748 2 0
(T1)
Type2
2 78 0 1 79 0 1 78 1 4 235 1
(T2)
Type3
0 0 20 0 0 20 0 0 20 0 0 60
(T3)
HM
ALL
VII. CONCLUSION
ACKNOWLEDGMENT
We would like to give a special thank to Mr. Tuan M.
Nguyen
and
Mr
Anh
Nguyen,
Electronic
&
Telecommunication Engineering Department, Danang
University of Technology, The University of Danang.
REFERENCES
1) Clean model
[3]
[2]
Clean model
Total
TPR
FPR
[4]
WM
MM
HM
ALL
700
700
700
2100
99.43%
93.98%
85.12%
92.84%
0.018%
0.187%
0.458%
0.221%
[5]
2) Noisy model
RESULT OF TESTING CHARACTER RECOGNITION FOR NOISY
MODEL
Noisy
model
WM
MM
Total
TPR
FPR
350
350
99.43%
98.29%
0.018%
0.054%
0.249%
0.107%
[1]
TABLE VIII.
92.00%
96.57%
350
1050
[6]
[7]