Beruflich Dokumente
Kultur Dokumente
747
Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing October 20-22,2004 Hong Kong
in a certain image and locate the position of license plate didate is verified by using a number of evaluation algo
images. The third approach was texture-based one [2]. rithms (see 3.2.2). However, the main limitation of this
According to this approach, a VLP was considered as an approach is the time required since the Hough transform
object with different textures and frames. The texture is applied to a usually great number of pixels. Espe
window frames of different sizes were used to detect cially, the larger image is, the slower the algorithm is.
plate-candidates. These candidates were passed to a The speed of the algorithm may be improved by thin
classifier to confirm whether they are plates or not. This ning image before applying the l'lough transform. How
approach was commonly used in finding text in image ever, the thinning algorithm is also slow. The limitation
tasks. In addition, there have been a number of other of processing speed makes this approach unsuitable for
methods related to this problem but focusing on detect real time traffic management systems.
ing VLP in video data (objects appear in a cha in of se
The method we present in this paper is the combination
quent images)[5][6].
of the two approaches above which produces higher
accuracy and faster speed so that it can be applied to real
time systems.
3. THE PROPOSED ALGORITHM
3.2.1. Comhille lIough Tramform allli Contollr Algo
3.1. Preprocessing
rithmfor Detectillg VLP
Images taken from camera were processed by the pre
OUf approach is as follows: from the extracted edging
processing module. The purpose of this module was to
image, we use the contour algorithm to detect closed
enrich the edge features. This will improve the success
boundaries of objects. These contour lines are
ful rate of the VLP detection module. The algorithms
transformed to Hough coordinate to find two interacted
sequentially used in this module are graying, normaliz
parallel lines (one of two parallel lines hold back the
ing and histogram equalization. After having obtained a
other 2-parallel lines and establishes an parallelogram
grey-scale image, we use Sobel filters to extract the edg
form object) that are considered as a plate-candidate.
ing image, then thresholding the image to a binary one.
Since there are quite few (blac k ) pixels in the contour
The resulted images are used as inputs for the VLP de
lines, the transformation these points to Hough
tection module.
coordinate required much less computation. Hence, the
3.2. Vehicles' License-Plates Detect Algorithm speed of the algorithm is improved significantly without
the loss of accuracy (see Fig 5).
In order to detect regions of plate-candidate image, we
firstly apply contour algorithm for detecting closed
boundary objects. A number of candidate evaluation
plate
algorithms are applied on contour images obtained from
candidate
the contour algorithm to separate plate objects.
-----�--.
= :=;.
3
'b=l.�t{:1�£dC:: p[ate
.....
-.-.---�...
./ candidates
Fig 5. Two case successful case when use combination of
of using Contour algorithm only
Contour algorithm and Hough transformation
C--'����
___
Failed
detection
However, there may be images that have other objects
such as wear glasses, headlights, decorated things, etc.
Fig 4. A failed case of using Contour algorithm only These objects may also have the shape of two interacted
2-parallel lines, and therefore, are also falsely detected
However, this algorithm has difficulties in processing
as plate-candidates. To reject such incorrect candidates,
bad quality images due to scratches, plug-in helixes. [n
we implement a module for evaluating whether a candi
these cases, the contour algorithm produces incomplete
date is a plate or not.
closed boundary lines that do not contain correctly the
plate-images. 3.2.2. P/lIte-ClIJI(lhlules Verijictltioll
Our second approach was applying Hough transform to From the two horizontal lines of a candidate, we can
the binary image to extract lines from object-images. calculate exactly how inclined it was from horizontal
Then we looked for two parallel lines, whose the con coordinate. Then we apply a rotate transformation to
tained region is considered plate-candidates. Each can- adjust it to straight angle. After processed, these straight
748
Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing October 20-22,2004 Hang Kong
binary plate-candidate images were passed to a number number of cut objects will be calculated. This evaluation
of heuristics and algorithms for evaluating. help identify the correct plate-candidates.
3.2.2.2. E!'GIl/ale by using horizontal crosscuts Table 2. Image sets were used in tests
In this stage, we use two horizontal cuts and count the Evaluating was taken on the two image sets above and
number of objects that are cut by these crosscuts. A can sh owed th e fill
o owmg
' resu Its:
didate will be considered as a plate if the number of cut Imae:e set A B A+B
objects in a range that was practical given (see examples Number of imall,es 415 390 80S
in Table I). This number must be in the approximate Corrects 412 383 795
range of the number of characters in a VLP, we have Errors 3 7 10
two appropriate constraints for two types of Vietnamese
Correct accuracy 99.27% 98.2% 98.76%
plates:
Error accuracy 0.73% 1.8% 1.24%
4:::; N:::; 8 with I-row plate-candidates
Avg speed to proc- 0.65s 0.655 0.655
7:::; N :::; 16 with 2-row plate-candidates ess one image
With N is the number of cut-objects. Table 3. Test results
The candidates that satisfied one of two above con In the evaluation, the algorithm were proved to be suc
straints are selected as the final result cessful on a number of difficult cases with bad quality
Plate-candidates Number Result plates (Fig 7), or multiple plates in the same image, or
of objects different types of vehicles such as motorbike plates, car
. ....-.-,.
.- 2 Non-plate plates or truck plates (Fig 8).
-:..-= :-;"�
.. ., 2 Non-plate
:�
,.
10 Plate
�M439%=
4 Plate
-5rf-
-1atJ--
Table 1. A sample of using horizontal cu ts to evaluate Fig 7. A successful case
plate-candidates with a bad quality plate
748
Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing October 20-22,2004 Hong Kong
5. REFERENCES
quality plates. If we used the more modem camer a, the 59, 1995.
results would be be tter and we could reduce many errors
[4] Yasuharu Yanamura, Ma sah ir o Goto, Daisuke Ni
of bad plates. For example, by using an infrared camera,
s hiyama , "Extraction and Tracking of the License
we can obtain high quality images of pl at es which are
Plate Using Hough Transform and Voted Block
not clearly seen due to mud or dust.
Ma tc hin g", IEEE IV2003 Intelligent Vehicles Sym
In summary, the combination of Hough transform and p osi um Conference, 2003.
contour algorithm produces the higher accuracy and
[5] A. Rahman, Ahmad Radmanesh, "A Real Time
faster speed for VLP detection. This made the approach
Vehicle's License Plate Recognition", P rocee di n gs
practical for real time systems. In practice, we use this
of the IEEE on Advanced Video and Signal Based
algorithm in our automatic VLPs recog ni ti on system.
Surveillance, AVSS'OJ, 2003.
4.2. Future work
[6] K. Kanayama, Y. Fujikawa, K.Fujimoto, and
We are working on a number of algorithms in the M.Horino, "Development of Vehicle-License Num
preprocessing module. The purpose is to detect regions ber Recognition System Using Real-Time Image
that are likely plate regions first and thus to reduce the Processing and Its Application to Tracal-time meas
computation cost of the VLP detection algorithm. In urement", In Proceedings of IEEE Vehicular Tech
addition, we intend to combine a number of texture· nology Conference, p 798-804, 1991.
based approachs, and machine learning methods to
750