Barcode identification in blurred images

VIETNAM NATIONAL UNIVERSITY, HANOI
UNIVERSITY OF ENGINEERING AND TECHNOLOGY







NGUYEN DUY KHUONG







BARCODE IDENTIFICATION
IN BLURRED IMAGES



Major: Computer Science
Code : 60 48 01





MASTER THESIS

Hanoi – 2010
ĐẠI HỌC QUỐC GIA HÀ NỘI
TRƯỜNG ĐẠI HỌC CÔNG NGHỆ



NGUYYỄN DUY KHƯƠNG


NHẬN DẠNG MẪU CÓ CẤU TRÚC CHO ẢNH BỊ
BIẾN DẠNG LỚN







Chuyên ngành: Khoa học Máy tính
Mã số: 60 48 01

TÓM TẮT LUẬN VĂN THẠC SĨ















Hà Nội – 2010


3

Table of Contents
Chapter I: Introduction 6

Chapter II: Background 9

1.

Input data 9

2.

Pre-processing 10

2.1.

Image restoration 11

2.2.

Input standardization 15

3.

Feature extraction 17

4.

Techniques for pattern recognition 19

Chapter III: Our algorithm for structural pattern recognition 20

1.

Direct and indirect approaches 20

2.

Proposed solution 22

3.

Our algorithm 23

4.

Candidate evaluation 26

5.

Techniques to improve the speed and accuracy of our algorithm 28

Chapter IV: Applying our algorithm for barcode recognition 29

1.

The structure of bar code 29

2.

The signals of barcode 32

3.

Previous algorithms for recognizing barcode 35

4.

Applying our algorithm for recognizing barcode 36

Chapter V: Experiments and results 40

Chapter V: Conclusion 43

REFERENCES 44

4

Table of figures

Figure 1. Model of pattern recognition system 9

Figure 2. Example of grammar representation 10

Figure 3. Example of graph representation. 10

Figure 4. Model of image degradation 11

Figure 5. Oblique handwriting characters 16

Figure 6. Oblique bar code 16

Figure 7. The follow chart of the indirect pattern recognition 21

Figure 8. The follow chart of the direct pattern recognition 21

Figure 9. An example of the indirect pattern recognition 22

Figure 10. An example of the direct pattern recognition 22

Figure 11. The follow chart of structural pattern recognition in heavily distorted
images 23

Figure 12. An example of follow chart of motorbike plate pattern recognition 25

Figure 13. Model of candidate evaluation 26

Figure 14. Several kinds of linear barcodes 30

Figure 15. Barcode construction 32

Figure 16. A clear barcode image 33

Figure 17. Original signals of barcode 33

Figure 18. Blurred and noised signals of barcode 33

Figure 19. Blurred barcode image 34

Figure 20. Comparing Candidates 40

Figure 21. the blurred image with noise 41

Figure 22. The image is restored by blind deconvolution in Matlab 41

5

Figure 23. Barcodes are recognized correctly 41

Figure 24. Barcodes are recognized incorrectly 42


6

Chapter I: Introduction
Within images, pattern recognition problem becomes extremely hard. It is caused
mostly by the large number of dimensions of data and the limited visual information able
to extract from the images. Moreover, this problem becomes much more serious if the
images are heavily distorted, impossible to restore using common image restoring
techniques and restriction of the ability of heavy computation, especially for camera of
handled devices or robots.
Based on structural characteristics of patterns, in pattern recognition, we divide
patterns into two categories, namely non-structural and structural. Non-structural patterns
often have non-specific shape, while structural patterns contain several elements which
are related to each other based on the rules or syntaxes. Utilizing this structural
information to reduce the number of classes and the number of data dimensions can
increase precision and performance of the recognition of structural patterns (Horst B. and
Alberto S., 1990).
There are many factors affecting on the process of acquiring images such as
defocusing, lens aberration, internal reflections and scattering, moving pattern, and
transmission errors, etc. (Jèahne, Bernd, 2004). Among them, defocusing and
transmission errors (noise) are the factors which occurs the most frequently, especially
for camera of handled devices or robots. Hence, in some papers, it is assumed that other
factors are ignored (
Selim Esedoglu, 2006

).
Pattern recognition with distorted images can be conducted by two approaches, namely
direct and indirect recognition without the process of image restoration. In the first
approach, recognizing patterns is conducted directly in degraded images (Wang K. et al,
2007;
Ender T. and James C., 2009
). In this approach, it may be immensely difficult to
recognize patterns correctly from distorted images because with their bad quality,
features of patterns cannot be extracted from the images. Therefore, this approach is only
suitable with slightly distorted images (
Ender T. and James C., 2009
).
7

In the second approach, patterns are recognized indirectly after a step in which
degraded images are restored (
Selim Esedoglu, 2003
). Image restoration is considered as a
pre-process step, but it plays an important role in the success of the pattern recognition.
There are several different ways of restoring the images, namely inverse filter, Weiner
filtering, regularization methods (
Selim Esedoglu, 2003
), and statistical methods (Bertero,
Mario., 1998). Among these methods, regularization methods and statistical methods
achieve better results because these methods can be conducted well with the occurrence
of noisy in images, which leads to disastrous results in other methods. In addition, these
approaches can be highly successful if restored images differ slightly with the original
images and the image degradation is known exactly. However, in fact, image restoration
cannot always be performed well because the process of image degradation is often a
compound transform and unknown. Hence, it is absolutely difficult to enumerate them

wholly. As a result, the quality of restored images may be not good enough for pattern
recognition.
In overview, both of these approaches of recognizing structural patterns may have
many difficulties if only features extracted from images are used in pattern recognition.
Hence, some information from prior knowledge of patterns needs to be utilized in order
to improve pattern recognition accuracy.
In this thesis, we propose an effective algorithm in order to improve pattern
recognition accuracy by utilizing structural information of patterns. Candidates for
patterns are generated and evaluated via prior knowledge of characteristics of patterns’
structure and extraction information of image degradation. In addition, some techniques
such as divide-conquer and local search are offered in order to increase the accuracy and
performance of structural pattern recognition systems. Moreover, this approach can avoid
expensive but really uncertain computation such as image restoration and feature
extraction from heavily distorted images. For convincing the above theory, this algorithm
is applied to recognize a kind of linear bar code in heavily distorted image, which is a
kind of sensitive structural pattern.
The thesis is structured as follows: Firstly, we start by a more detailed review of
backgrounds related to structural pattern systems in the Chapter II. Subsequently, the
8

Chapter III focuses on our general algorithm for structural pattern recognition. After that,
an approach for bar code recognition based on our general algorithm is mentioned in the
Chapter IV and experiments and results of this approach are illustrated in the chapter V.
Finally, some conclusions are drawn in the chapter V.
9

Chapter II: Background
The principal function of a pattern recognition system is to locate the position and
identify the class of patterns. It contains several components: Input, preprocessor, feature
extractor and recognizer (Rafael et al, 1978).

Figure 1. Model of pattern recognition system
The input is signals which are transformed into a type suitable for machine
manipulation by a measurement device. Although a pattern recognition system can
operate directly on the input data from the device, it is common that there are some
additional components included such as pre-processor and feature extractor before
recognizer. For pattern recognition in images, the pre-process can be to enhance the
quality of images. Subsequently, feature extractor obtains the necessary information for
pattern recognition which is input for recognizer. In this chapter, therefore, we discuss
mainly three issues: Input data, pre-processing, feature extraction and techniques for
pattern recognition.
1. Input data
The input for pattern recognition is represented a form of signals which are stored in
the system such as images and audio, in which patterns are contained. Features extracted
from this input must be suitable with the recognizer of pattern recognition. Hence, pattern
recognition is generally categorized as statistical and structural (or syntactic) (Rafael et
al, 1978), which correspond to two kinds of feature, namely vector-based and structural
feature. Concisely, a vector-based feature pattern is represented in a numeric vector and
there is minor relation among its elements. Patterns including these features are called as
non-structural patterns.
On the other hand, structural pattern containing structural features in stronger relation
is a kind of pattern which contains several components which are related to each other
10

according to a given set of rules and syntaxes in relational descriptions and formal
grammars (Rafael et al, 1978). These rules and syntaxes are additional information about
patterns based on prior knowledge of the underlying structure of pattern classes. They are
structural constraints which are modeled in the graph model of pattern or grammars of a
restricted set of symbols which patterns have to follow such as character recognition and
bar code. Syntactic pattern recognition employs this information in innovative ways in

order to develop pattern recognition approaches.
Two following examples are two types of pattern constraints. In the first example,
there is a syntax-liked constraint for bar code like a syntax, in which there are a limited
number of pre-designed patterns to encode digits and there are guard bars for error
checking. In the second example, structural constraints are mainly represented by using
relational descriptions, e.g. graphs. These constraints can be absolutely helpful for pattern
recognition.

Figure 2. Example of grammar representation

Figure 3. Example of graph representation.
2. Pre-processing
The main aim of this pre-processing step is to enhance the quality of and to
standardize the input. For pattern recognition in images, the enhancement contains many
different manipulations such as brightness and contrast enhancement (William, 2007),
supper-resolution (S. C. Park et al, 2003; S. Farsiu, 2004), and image restoration
11

(Katsaggelos, 2003), etc. However, in this section, only image restoration is focused on
because it is the most important technique to enhance the quality of distorted images.
Subsequently, in the second sub-section, several image standardization techniques are
discussed.
2.1. Image restoration
Until recent, image restoration is still a hard problem although this problem has been
tackled by numerous researchers. The aim of this process is to reconstruct or recover an
image which has been degraded by various factors such as defocusing, lens aberration,
moving pattern, vibration, etc. (Berne Jèahne, 2004). There have been several proposed
techniques to solve this problem: inverse filter (Wiener, 1949), Wiener filter (M.
Rothenberg, 1972), regularization methods and statistical methods (M. Bertero and P.
Boccacci, 1998). In these techniques, a linear space-invariant degradation process is

popularly modeled as a convolution of the original image with a degradation function:
( , ) ( , )* ( , ) ( , )
g x y f x y h x y n x y
= +

where:
•
( , )
f x y
is the original (desired) image,
•
( , )
g x y
is the degraded image,
•
( , )
h x y
is the degradation function and the most popular function known is the
point spread function,
•
( , )
n x y
is a noise function.

Figure 4. Model of image degradation
12

In this section, the techniques for image restoration will be discussed more details in
the following sections, especially models for blurred images with noise because it is
popular for the kind of devices used in this research, handled devices.

a. Estimating the degradation function
To recover the distorted image, estimating the degradation function is the first step
which needs to be done. An approach used popularly is derived from a mathematical
model as a blurred model. In the representation, the blurred image is modeled by the
following equation (Milan S., 1998):

0 0 0 0
0
1
( , ) [ ( ), ( )] [ ( ), ( )] ( , )
T
g x y f x x t y y t h x t y t dt n x y
T
= − − +
∫

Or also
( , ) ( , )* ( , ) ( , )
g x y f x y h x y n x y
= +

where
( , )
f x y
is the unblurred image and
T
is the exposure time.
b. Inverse filter
In this technique, it is assumed that the degradation model has a little noise. As the
discussion in the previous sub-section, we have:

( , ) ( , )* ( , ) ( , )
g x y f x y h x y n x y
= +

The Fourier transform gives (Milan S., 1998):
( , ) ( , ) ( , ) ( , )
G u v F u v H u v N u v
= +
i

Because the effect of noise is negligible, hence we have

^
( , )
( , )
( , )
G u v
F u v
H u v
=

where
^
( , )
F u v
is an estimation of
( , )
F u v
.

Hence, the error can be estimated by:
13

^
( , )
( , ) ( , )
( , )
N u v
F u v F u v
H u v
− =

This model has some problems. Firstly, if several values of H(u, v) are small, they can
cause overflow. Secondly, if there is some noise, it can dominate. Therefore, this model
is very sensitive with noise, in which case, the result cannot be really appreciated.
c. Wiener filtering
This technique can be known as minimum mean-square error (MMSE) filter. It is
assumed that images and noise can be in a way as random processes. An estimate
^
f
of
the uncorrupted image
f
can be found such that the mean square error is minimized
(Wiener, 1942; M. Rothenberg, 1972; M. Bertero and P. Boccacci, 1998):

^
2
{( ( , ) (x,y)) }
MSE E g x y g= −

In the frequency domain, we have:

2
ˆ
{| ( , ) ( , ) | }
MSE E G u v G u v= −

In this technique, to recover the original image, we need to assume that the original
signal and noise are independent.
d. Regularization methods
To recover the degraded image, a common approach is to solve the regularized least
squares (RLS) minimization problem (M. Bertero and P. Boccacci, 1998):
2
min{|| || ( , )}
x
LSR Af b R x y
λ
= − +
where:
2
|| ||
Af b
−
is a least squares term that measures the noise
( )
R
i
is a convex regularizer used to stabilize the solution.
0

λ
>
is a regularization parameter providing the tradeoff between fidelity to
measurements and noise sensitivity.
14

In practice, there are some interests of
( )
R
i
as follows:
1. Tikhonov regularization (Gene H. G. et al, 1999, M. Bertero and P. Boccacci,
1998): by setting
2
( ) || ||
R Lf
=
i
, we obtain the standard Tikhonov regularization
problem:
2 2
min{|| || || || }
x
LSR Af b Lf
λ
= − +
2.
1
l
regularization: by setting

1
( ) || ||
R f
=
i
, we obtain the standard Tikhonov
regularization problem:
2
1
min{|| || || || }
x
LSR Af b f
λ
= − +
3. Wavelet-based regularization: by setting
1
( ) || ||
R Wf
=
i
, in which W is a wavelet
transform matrix, the wavelet-based regularization problem is recovered as
follows:
2
1
min{|| || || || }
x
LSR Af b Wf
λ
= − +

4. Total variation-based (TV-based) regularization (Chan T.F. et al, 1998): by
setting
,
1 1
( ) ( ) || || || ( ) ||
m n
i j
i j
R TV x f f
= =
= = ∇ = ∇
∑∑
i
, we can achieve the TV-based
regularization problem as follows:
2
min{|| || || ||}
x
LSR Af b f
λ
= − + ∇

Although Total variation-based regulation is focused on research in recent years, the
results of this technique still are not completely precise. In other word, the restored
images may be not accurate enough for pattern recognition because the image
degradation can be unknown exactly and there may be some additional factors affecting
on the process of degradation. The energy function LSR used in the TV-based technique
is very sensitive with the suitability of the original image with the blurred image.
Therefore, in next chapter, this energy function can be used as an evaluation function in
our pattern recognition system.

15

e. Statistical methods
In this technique, it is assumed that captured images are realizations of random
processes. There are two primary classes of statistical methods: Maximum likelihood
methods and Bayesian methods. In maximum likelihood methods (Timothy 1988; M.
Bertero and P. Boccacci, 1998), the object (desired image) is assumed to be deterministic.
It takes the role of parameters representing the probability distribution of the captured
image. Meanwhile, in Bayesian methods (M. Bertero and P. Boccacci, 1998), the object
is also assumed to be a realization of a random process with a given probability
distribution.
f. Evaluation of image restoration methods
Among these types of techniques, inverse filtering responds very badly to any noise
which tends to be high frequency since it is a form of high pass filter (Tinku A. and Ajoy
K. R., 2005). Besides, Wiener filtering performs better than the previous method since it
executes an optimal tradeoff between inverse filtering and noise smoothing. It can
remove the additive noise and invert the blurring simultaneously, though it is very
sensitive to additive noise. In addition, it is optimal in terms of the mean square error to
minimize the overall mean square error in the process of inverse filtering and noise
smoothing (Tinku A. and Ajoy K. R., 2005). In the fact, this method is not evaluated
highly because it needs an assumption about a linear estimation of original images.
Hence, regularization methods and statistical methods are considered as the most
effective methods. They have more precise results because they can response noisy
factors (M. Bertero and P. Boccacci, 1998).
2.2. Input standardization
Input standardization can be considered as a preparing step to normalize input data for
pattern recognition system. It is suited better for feature extractors and recognizers
because it makes the following processing steps become simpler and it also improves the
accuracy of pattern recognition. There are two standardization techniques as scale and
direction normalization of patterns.

16

The scale normalization is simply a process to translate pattern signals into the same
scale ratio. This step may be not important for scale-invariant feature extraction and
recognition, but for scale-variant ones such as shape matching, it is particularly
significant.
Meanwhile, the orientation normalization changes the angle or directions of pattern in
order to enhance the quality of feature extraction and improve pattern recognition
accuracy because the presence of patterns in different directions may make feature
extraction and recognition methods become more complex. Although there are rotation-
invariant methods such as Wavelet or Fourier transform to extract feature vectors of
patterns, slight direction change can cause great difficulties some other methods. For
example, localization of characters or bar codes becomes a serious master if these
patterns are shelved.

Figure 5. Oblique handwriting characters

Figure 6. Oblique bar code
17

3. Feature extraction
Feature extraction is an important step in pattern recognition in mages to locate
significant feature regions and to reduce the number of data dimensions via extracted
important information. These features should depend on the characteristics of patterns or
objects and they need to be suitable with pattern recognition. The determination of these
regions can be based on global or local operators in images. Global operators is operators
performed in the whole image in order to enhance the quality and contrast of image,
while local operators are often local operators to find out the characteristic details of
patterns such as edges, corners and shapes.
Based on the abstract of information, features can be divided into two kinds: low-level

and high-level features (M. S. Nixon and A. S. Aguado, 2008). Low-level features are
features which are extracted automatically from an image without any shape information
such as edges and corners. In other word, these features do not have spatial relationships
with each other. Meanwhile, high-level features contain higher abstract information such
shape and object description. They are frequently represented in mathematical models
such as graph model and template matching.
To detect features of patterns, edge and corner detection are the two most significant
operators. They are insensitive to overall illumination change while sensitive to the
contrast level of image. The contrast represented by difference in intensity in local
regions can detect the boundaries of features within an image (M. S. Nixon and A. S.
Aguado, 2008). Hence, the difference of this detection can be found out by the following
basic operators:

( , )
| ( , ) ( 1, ) |
f x y
f x y f x y
dx
= − +

( , )
| ( , ) ( , 1)|
f x y
f x y f x y
dy
= − +

where
( , )
f x y

is the image.
18

Based on this idea, first order edge detection operators such as Prewitt (Prewitt and
Mendelsohn, 1966), Sobel (Sobel, 1970), and Canny (Canny, 1986) are employed with
second order edge detection operators such Laplacian (Vliet and Young, 1989) and Marr–
Hildreth (Marr and Hildreth, 1980).
Besides edges, corners are frequently exploited in pattern recognition. The detection
approaches of corner can be based on two factors, namely boundary and gray.
Eigenvalues of the covariance matrix, template and gradient-based techniques and
gradient-direction are boundary-based approaches which are employed by Tsai et al
(1999), Singh and Shneier (1990), and Zheng et al. (1999) repectively.
Meanwhile, for grey-based approaches, Gao et al (2007) used log-Gabor wavelet
transform, while Arnow and Bovik (2007) utilized foveated visual search and automated
fixation selection to search the corner of patterns and Ando (2000) detected corners and
edges via gradient covariance.
Based on the low-level features, high-level features are extracted from computer
images. Shape or template matching extracts significant component features such as the
eyes, the ears and the nose in the face (M. S. Nixon and A. S. Aguado, 2008). The main
idea of this technique is to try the best match and the maximum count between detected
components and templates in databases. The basic requirements of this approach is that
techniques need to be size or orientation-invariant, hence, Hough transform (Hough,
1962) and Generalized Hough transform (Ballard, 1981) are employed popularly.
More complexly, flexible shape extraction is used to describe components of patterns
with sufficient accuracy and spatial information(M. S. Nixon and A. S. Aguado, 2008).
Among techniques on this approach, active shape modeling (Lanitis et al., 1997; Cootes
et al., 1994; Hill et al., 1994) can be considered a major new approach.
Finally, mathematical models are employed in order to describe objects such as
Fourier descriptors (Cosgriff, 1960), regional shape descriptors (Rosin and Zunic, 2005)
and graph model (D. Conte et al, 2004). The most major advantage of these methods is

the scale and orientation-invariant ability and representing the relational and relevant
information between components of patterns in recognition system.
19

4. Techniques for pattern recognition
Pattern recognition is known as a fundamental topic in learning machine, of which
major task is to identify the class of patterns. Based on the characteristics of used
techniques, pattern recognition can be divided into two main approaches (): statistical
pattern recognition and structural recognition. Statistical pattern recognition is primarily
based on statistical learning techniques, in which statistical distributions of pattern feature
vectors is the most basic in order to determine the class of patterns. There are many
unsupervised and supervised learning machines known in this approach such as:
clustering techniques (P. Berkhin, 2006), Bayes classifiers (Barber, D., 2011), support
vector machine (Shigeo Abe, 2005) and artificial neural networks(K. Gurney, 1995). The
accuracy of statistical pattern recognition largely depends on the quality of pattern
database and the suitability between learning machines and feature extraction approaches.
Meanwhile, structural pattern recognition utilizes structural features of the patterns to
identify the class of patterns (R. C. Gonzalez, 1978). In this approach, interrelationships
between the primitive components of patterns are emphasized to compare the pattern.
Hence, besides feature extraction techniques employed, the representation of
interrelationships between componential features of patterns plays an important role in
the success of this approach. These interrelationships are frequently represented in formal
grammar or graph model. In addition, establishing these constraints need to be based on
the prior structural of patterns. The main advantages of this approach are no requirement
about pattern databases and the ability of classifying the large number of pattern classes.
20

Chapter III: Our algorithm for structural pattern
recognition
Until recent, pattern recognition in heavily distorted images is considered as a hard

problem because there are several differences faced simultaneously, especially image
restoration and pattern recognition in images. Image restoration does not only cost
computationally but not always have correct answers. In particular, image restoration
requires a complex computation such as statistic inference (Aristidis C. L., Nikolas P. G.,
2004) or solving partial differential equation (PDE) (Chan T.F., Chiu-Kwong W., 1998;
Selim Esedoglu, 2004). Moreover, the finding of this performance is only approximate
and not completely accurate if the degrading process of image is unknown or complex
but it often happens. In addition, pattern recognition in distorted images is quite hard
because the numerous dimensions of data and impossible to extract these features from
images, especially in heavily distorted images. As a result, pattern recognition accuracy
in distorted images is regularly lower than other environments, for example online
handwriting character recognition often has the higher accuracy than offline handwritten
character recognition (Réjean P. and Sargur N. S., 2000).
The main aim of this chapter is to represent our algorithm to recognize structural
patterns in heavily distorted images more effectively. More particular, within heavily
distorted image, structural pattern recognition may have more advantages than non-
structural images because besides features extracted from data; our algorithm has utilized
prior structural knowledge of the patterns in order to improve recognition accuracy.
1. Direct and indirect approaches
In pattern recognition, there are two different approaches which depend on
characteristics of patterns, in which a pattern can be recognized directly or indirectly, see
Figure 7 and Figure 8. In the indirect pattern recognition, patterns are identified after an
image restoration process (
Selim Esedoglu, 2003
). Meanwhile, in the direct pattern
recognition, patterns are recognized directly from the image (Ohbuchi E. et al, 2004).
21


Figure 7. The follow chart of the indirect

pattern recognition

Figure 8. The follow chart of the direct
pattern recognition
In both of these two approaches, there are still disadvantages why applying them. In
the first approach, it is only suitable with insensitive patterns which have high differences
between these patterns’ classes. In this case, if the quality of restored image is not
limited, patterns can be recognized correctly. However, structural patterns often contain
symbols which are very remarkably similar to each other, especially in heavily distorted
images when the sharp of objects is restricted considerably. Hence, this approach is
inappropriate unless image is restored successfully. Nevertheless, in fact, it is hard to
restore heavily distorted images restoration because image degradation is a compound
transform, impossibly restorable and unknown. As a result, there are still errors in
restored images compared with the images of distorted images.
In the second approach, structural patterns are recognized directly from distorted
images (see Figure 8). There are two techniques known as statistical (Ohbuchi E. et al,
2004) and based-structural can be employed. For the first technique, statistical pattern
recognition will face a couple of significant problems. Firstly, the number of dimensions
may be very large since feature extraction techniques cannot be involved due to image
degradation. Another problem, more significantly, is the high maintain cost of preparing
training data for recognition since each kind of devices or objects also requires an
individual training set (Ohbuchi E. et al, 2004). Likewise, structural pattern recognition
may be implemented difficultly for heavily distorted images.

22


Figure 9. An example of the indirect pattern
recognition

Figure 10. An example of the direct pattern
recognition
2. Proposed solution
To solve these problems about the performance and accuracy, we have designed an
effective algorithm in order to recognize these structural patterns in heavily distorted
images by taking the advantages of prior-known knowledge. The knowledge is
constraints of the structural information or rules of patterns, which does not depend on
given data.
Quite different with those common approaches, our approach generates candidates for
elements of these patterns based on certain constraints which are come from rules of
structures or prior knowledge about patterns. From this information, appropriate
candidates are generated in the restricted space of patterns for reason that many
unsuitable candidates are eliminated. In addition, we select the most suitable elements to
construct a pattern. The element selection is done by employing a well-known evaluating
function in image restoration research and prior knowledge of patterns. Therefore, this
approach achieves higher recognition accuracy and higher performance.
More particular, we have designed an effective algorithm which avoids the expensive
computation of image restoration and difficulties of feature extraction from images by
23

taking advantage of prior-known knowledge of patterns. It can be accepted because the
kind of objects can be known before pattern recognition is conducted.
3. Our algorithm
Besides using the information of patterns extracted from the images, we use prior
structural knowledge of patterns such as rules of pattern’s structure in order to improve
the pattern recognition accuracy. Our algorithm described in Algorithm 1 can be
separated into four main steps:
1. Extracting parameters about degradation of the image;
2. Locating patterns in distorted image;
3. Generating candidates for patterns;

4. Finding out the most suitable candidates for pattern

Figure 11. The follow chart of structural pattern recognition in heavily distorted images
In the first step, parameters can be auto-extracted (Chan, T.F. and Chiu-Kwong Wong,
2002, Aristidis C. L. and Nikolas P. G., 2004) on one time or manipulated for multi-
images because each device has private parameters itself. The parameter auto-extraction
is conducted in the process of image restoration, so it may have a costly computation.
24

Fortunately, this process is conducted once time for each device because they are unique
in a specific environment.
Subsequently, locating patterns in distorted image is controlled by image segmentation
techniques (L. Lucchese Yz and S. K. Mitra Y). It is assumed that patterns is separated
clearly with other contents of images, so pattern location in heavily images can be carried
out effortlessly. Consequently, the position and size of pattern can be determined
approximately.
Within prior knowledge of patterns, candidates for patterns can be generated within
some structural information which can be extracted from images. Candidate generation is
based on extracted information from heavily distorted images. It is assumed that although
images are distorted heavily and some information may be lost, some information is still
extracted from the images such as approximate positions and size of patterns.
in
put :
A distorted image contains structural patterns
output: Information about structural patterns
Extracting parameters of degradation of image; //step 1
Locating patterns in distorted image; // step 2
Generating candidates for patterns; // step 3
foreach pattern from located patterns do // step 4
Extracting information of pattern in image

foreach candidate c from generated candidates do
Generate signals for candidate c based on extracted information;
Evaluating candidate c corresponding to the pattern in the image;
end
end
Choose the most suitable candidates with the highest evaluation value for the patterns;
Algorithm 1. Pseudo-code for Structural pattern recognition in distorted images
Therefore, the most challenging task in this approach is to choose the best candidates
for patterns. This issue will be discussed more fully in Section 4.
25

For more obvious, we consider an especial example of motorbike plate pattern
recognition, see Figure 12. From a distorted image captured from out-of-focus devices,
we can determine parameters of the degradation of this distorted image for the used
device in that specific environment. It is not difficult to locate the motorbike plate and the
positions of characters and digits in the distorted image and to estimate approximately the
size of these symbols. Based on the structural characteristics of motorbike, candidates for
these characters and digits are generated. Subsequently, signals of candidates are
generated. Finally, they are evaluated to find out the best suitable candidate for the
patterns in the distorted image.

Figure 12. An example of follow chart of motorbike plate pattern recognition
To find out the best candidate, we need to evaluate the suitability of candidate with the
pattern in the image. The method of this evaluation will be discussed in the next section.