art neural nw
TRANSCRIPT
![Page 1: Art Neural Nw](https://reader031.vdocument.in/reader031/viewer/2022021318/577d39731a28ab3a6b99c367/html5/thumbnails/1.jpg)
8/14/2019 Art Neural Nw
http://slidepdf.com/reader/full/art-neural-nw 1/6
Paint Coating Quality Inspection in Bridges Using Image Recognition
and Neural Networks
S.A.Dhivhya1 Aishwarya Murali2
II year Computer Science and Engineering
R.M.D Engineering College,Kavaraipettai. [email protected] [email protected]
Abstract
The most established technique of Visual Inspection of
painted body surfaces of bridges is a very timeconsuming and labor intensive process. Inaccurate or
subjective assessment techniques have been identified as
a critical obstacle to effective infrastructure or
constructed facilities management. This paper illustratesa more objective and reliable assessment method to
improve the conditions of the infrastructures or the
quality of constructed facilities. The proposed system will
automate the coating assessment process by using computers to analyze digital images of the areas to be
assessed based on the Back Propagation Network (BPN)
System in Neural Networks. The paint-Quality can be
inspected in four simple steps.
1. Introduction.
Engineers need accurate, consistent, and reliable
information regarding paint system performance for theeffective management and rehabilitation of bridge.Such
information includes quantitative paint system ratings and
accurate estimates of the useful life of the coating system.The extent of coating failure is most important in
determining when a coating is to be repaired. Currently,
the means available in the evaluation of coating
performance is limited. Visual rating of the coating
condition, which represents the most established
technique, is plagued by a number of significant
problems.
2.Earlier Paint Quality Assessment
Techniques
Conventionally ,a laser beam was made to fall on the
painted panel and on to a projection screen. Since the
light source is a coherent beam (has constant phase
relation), the amount of scatter observed in the reflected
image of the laser provides an indication of the quality of paint in bridges. In the past, inspection of scatter-pattern
was performed primarily by humans, because
conventional computer programming techniques that
could be used to automate the observation and scoring process suffered from a lack of flexibility, and were not
particularly robust.
By using a Back propagation type of neural network to
perform the quality-scoring operation, a system can be
constructed that captures the expertise of humaninspectors, and is relatively easy to maintain and update.
To improve the performance of the system, algorithmictechniques can be coupled with the above approach to
simplify the problem.
The main thrust of that research was the non-destructive
evaluation of bridge coatings using several techniques,
namely: Color Visible Imaging, Electrochemical
Impedance Spectroscopy (EIS), and Infrared Imaging.
The results were not reliable and inconsistent. The
research result presented a generic framework, but was
not developed to the implementation stage.
3.Base Concepts applied in our Coating
Quality Assessment Model
3.1. Artificial neural networksConventional computers concentrate on emulating human
thought processes, rather than actually how they are
achieved by the human brain. Neural computers, however,
take an alternative approach in that they directly model
the biological structure of the human brain and the way it
processes information (although at a much simpler level).
This necessitates a new kind of architecture, which, likethe human brain, consists of a large number of heavily
interconnected processing elements operating in parallel
manner. Such an architecture is now both technically and
commercially feasible to be deployed on a standard
computer (from the laptop and desktop to the mainframe)
and is certain to increase in general usage.
Neural networks are mathematical models, originally
inspired by biological processes in the human brain. They
are constructed from a number of simple processing
![Page 2: Art Neural Nw](https://reader031.vdocument.in/reader031/viewer/2022021318/577d39731a28ab3a6b99c367/html5/thumbnails/2.jpg)
8/14/2019 Art Neural Nw
http://slidepdf.com/reader/full/art-neural-nw 2/6
elements interconnected by weighted pathways to form
networks. Each element computes its output as a non-
linear function of its weighted input. When combined into
networks, these processing elements can implement
arbitrarily complex non-linear functions which can beused to solve classification, prediction or optimization
problems .An artificial neural network or simply a neuralnetwork is a system based on the operation of biological
neural networks, in other words, is an emulation of
biological neural system.
A Neural Network will have 3 basic parts which are
1)Input Layer 2)Hidden layer and 3)Output layer.
Although computing these days is truly advanced, thereare certain tasks that a program made for a common
microprocessor is unable to perform; even so a software
implementation of a neural network can be made. An
Artificial Neural Network is an adaptive system thatlearns to perform a function (an input/output map) from
data. Adaptive means that the system parameters are
changed during operation, normally called the training
phase.
Fig 1: Neural Network for Back Propagation Algorithm
After the training phase the Artificial Neural Network
parameters are fixed and the system is deployed to solve
the problem at hand (the testing phase). The Artificial
Neural Network is built with a systematic step-by-step
procedure to optimize a performance criterion or to follow
some implicit internal constraint, which is commonly
referred to as the learning rule. An Artificial NeuralSystem (ANS) that is found to be useful in addressing
problems requiring recognition of complex patterns and
performing nontrivial mapping functions is the Back
Propagation Network.
3.2. Back propagation (BPN)
A BPN network is designed to operate as a multi-layer,
feed forward network, using supervised mode of learning.The basic back propagation model is a three-layeredforward architecture. The first layer is the Input Layer, the
second layer the Hidden Layer, and the third layer the
Output Layer. Each layer contains a group of nodes that
are linked together with nodes from other layers by
connections among the nodes. Layers are connected only
to the adjacent layers. The network is a feed-forward
network, which means a Unit’s output can only originate
from a lower level, and a unit's output can only be passedto a higher level.
The Input Layer receives the features of the data that are
entered into the neural network. If n feature values are to be entered into the Input Layer, then there must be n
nodes; where n is the number of features supplied to the
net. The values are passed to the Hidden Layer through
connections from the Input Layer. The nodes in the firstlayer distribute the individual inputs to all of the nodes in
the Hidden Layer. The main function of the hidden layer
is to process the input data during the network training to
connect to the output, i.e. to do the regression process.
The connections between the layers are weighted to
emphasize or de-emphasize the relative value of the input.
Each node sums the n weighted inputs to the Hidden
Layer. The value of the summation can be different for each node, due to differently weighted connections between the first and second layers. The values that are
summed in the hidden nodes are then passed to the nodes
in the Output Layer via another set of weighted
connections.
Fig 2: BPN System for Paint Coating Quality Assessment
FRAMEGRABBER-DATA
ACQUISITION
SELF ORGANIZING
ALGORITHMUSER
INTERFACE-
RESULT
BACK PROPAGATION
NETWORK-
PROCESSING
STAGE
![Page 3: Art Neural Nw](https://reader031.vdocument.in/reader031/viewer/2022021318/577d39731a28ab3a6b99c367/html5/thumbnails/3.jpg)
8/14/2019 Art Neural Nw
http://slidepdf.com/reader/full/art-neural-nw 3/6
![Page 4: Art Neural Nw](https://reader031.vdocument.in/reader031/viewer/2022021318/577d39731a28ab3a6b99c367/html5/thumbnails/4.jpg)
8/14/2019 Art Neural Nw
http://slidepdf.com/reader/full/art-neural-nw 4/6
Step 4: ASSESSMENT RESULTS
The Assessment Results stage, where quantitative
measures of defects are obtained from the output of the previous stage. From mapped output of the neural
network, the whole image is represented as 0's or 1's. The
1 values represent the defect; hence, defects can be
identified and quantitatively measured. The system can be
trained to identify different types of defects according to
the specific application.
Once, the network was constructed (and trained), 10
sample images were taken from the snapshot using 2
different sampling techniques. In the first test, the samples
were selected randomly from the image (in the sense that
their position on the beam image was random); in the
second test, 10 sequential samples were taken, so as to
ensure that the entire beam was examined. In both cases,the input sample was propagated through the trained
BPN, and the score produced as output by the network was averaged across the 10 trials. The average score, as
well as the range of scores produced, were then provided
to the user for comparison and interpretation.
6. Examining Rust on a Steel Bridge-
An Example
The following example illustrates how a simple 3 pixel x
3 pixel mage could be used to illustrate the methodology.
STEP 1: Data Acquisition:
A digital image of a steel bridge coating area is obtained
and transferred to the computer.
STEP 2:Preprocessing
Image analysis software is used to enhance the image and
to represent the image in numerical format. Consider the
figure to be an image of a part of a rusted steel bridge beam with a coating on. The darker areas represent defect
object (rust) and the lighter areas represent background.
1 2 3
1 245 21 90
2 260 18 45
3 54 56 57
Table 1: Image Gray Levels
Pattern recognition is done and the numerical values are
classified into two clusters: rust or no rust. K-Means
algorithm is used for classification because it best fits thisspecific application in which the number of clusters to
classify must be predetermined.Given the data setobtained from the image numerical presentation ,the K-
means Algorithm is applied.
V= {245,21,90,260,18,45,54,56,57}
Any two values are selected randomly as centre.Let us assume that the initial centers selected are R1=245
and R2=56
Next, we assign each sample to the class with the closest
center, i.e. to class 1 if it is closer to R1=245 and to class
2 if it is closer to R2=56
.The following table shows the difference between each
pixel value and the initial two centers and hence to which
class it is assigned. The difference is calculated based onthe gray level, not based on the location of the pixel.
Pixel
Value
Difference
from R1
Difference
from R2
Class 1 Class 2
245 0 189 X
21 224 35 X
90 155 34 X
260 15 204 X18 227 38 X
45 200 11 X
54 191 2 X
56 189 0 X
57 188 1 X
Table 2: First Iteration of K-Means Algorithm
C1={245,260}
C2={21,90,18,45,54,56,57}
Fig:4: Graph Representing Initial Clustering
Initial Clusters with centers R1=245 and R2=56
X
Y
245
45260
9021
575654
18
2 31
1
2
3
![Page 5: Art Neural Nw](https://reader031.vdocument.in/reader031/viewer/2022021318/577d39731a28ab3a6b99c367/html5/thumbnails/5.jpg)
8/14/2019 Art Neural Nw
http://slidepdf.com/reader/full/art-neural-nw 5/6
![Page 6: Art Neural Nw](https://reader031.vdocument.in/reader031/viewer/2022021318/577d39731a28ab3a6b99c367/html5/thumbnails/6.jpg)
8/14/2019 Art Neural Nw
http://slidepdf.com/reader/full/art-neural-nw 6/6
learning algorithm. The learning algorithm changes the
functionality of the network to suit the problem by
modifying the values of the connection weights between
processing elements.
The time needed to develop a neural application is often
less than that in a conventional approach, since theinteraction between the analyst and the expert isminimized-there are no algorithms or rules to define.
The scope and accuracy of the finished application isimproved since the neural computer can be exposed to
many more examples than can be assimilated by a singlehuman. This system will make the assessment process
more objective, quantitative, and reliable.
8.Conclusion
The basic concept of this paper is to automate the
assessment process by taking digital images of the rustareas and analyzing the images to identify and measure
coating defects. Neural Networks do not require explicit
programming by an expert and are robust to noisy,
imprecise or incomplete data.
Furthermore, knowledge is encapsulated in a compact,
efficient way that can easily be adapted to changes in business environment. It saves time and reduces human
burden. Hence, the application of Neural Network andBPN technique is very crucial and of extremely
significant value. . The system will make the assessment
process more objective, quantitative, and reliable. This
vital technology can never be overlooked
9.References
[1] Neural Networks and their Applications in Industry
Dhruba J Sarma and Susmita C Sarma-DESlDOC
Bulletin of Information Technology, January & March2000
[2]Using Images Pattern and Neural Networks for
Coating Quality Assessment-L.M. Chang and Y.A. Abdel Razig
[3] Freeman, James A. & David, M. Neural networks:
Algorithms, applications, and programming techniques.
Skapura Addison-Wesley Longman, Inc.
[4] De La Blanca, N. (1992). Pattern recognition and
Image Analysis. World Scientific.
[5] Wikipedia Online Encyclopedia
http://en.wikipedia.org/wiki/Neural_network
http://en.wikipedia.org/wiki/Back-propagation