Content uploaded by Vijendra Babu D
Author content
All content in this area was uploaded by Vijendra Babu D on Mar 02, 2019
Content may be subject to copyright.
INTERNATIONAL CONFERENCE ON RECENT ADVANCEMENT IN MECHANICAL ENGINEERING &TECHNOLOGY
(ICRAMET’ 15)
Journal of Chemical and Pharmaceutical Sciences ISSN: 0974-2115
JCHPS Special Issue 9: April 2015 www.jchps.com Page 418
LINEAR BARCODE SCANNING SYSTEM BASED ON DYNAMIC TEMPLATE
MATCHING FOR OOF BLURRED IMAGES
D.Vijendra Babu, S.Shalini, P.T.Sarath, Enugula Niharika, Ismail Shurab
ECE Department, Aarupadai Veedu Institute of Technology, Vinayaka Missions University, Paiyanoor-603
104.Chennai.Tamil Nadu.
ABSTRACT
A Novel Linear Barcode scanning system based on a Dynamic template matching scheme. The proposed
system works entirely in the Spatial domain and is capable of reading Linear Barcodes from low-resolution Images
containing severe OOF blur. This paper treats Linear barcode scanning under the perspective of deformed Binary
waveform analysis and classification. A directed graphical model is designed to characterize the relationship
between the blurred barcode waveform and its corresponding symbol value at any specific blur level. A Dynamic
programming-based inference algorithm is designed to retrieve the optimal state sequence, enabling real-time
decoding on Mobile devices of limited processing power.
Key Words: Barcode, Dynamic Template Matching, Blurred Images
INTRODUCTION
Digital Image refers to processing of a 2 Dimensional picture by a Digital Computer. In a broader context,
it implies Digital processing of any two dimensional data. A Digital Image is an array of real or complex numbers
represented by a finite number of bits. An Image given in the form of a transparency, slide, photograph or an X-ray
is first digitized and stored as a matrix of binary digits in computer memory. This digitized image can then be
processed and/or displayed on a high-resolution television monitor. An Image Processor does the functions of
Image Acquisition, Storage, Pre-processing, Segmentation, Representation, Recognition and Interpretation and
finally displays or records the resulting image. Digital Image Processing has a broad spectrum of applications, such
as Remote Sensing, Medical Processing, RADAR, SONAR & Acoustic Image Processing, Robotics & Automated
inspection of Industrial parts.
This paper mainly addresses the analysis and classification of Binary waveforms under Out of Focus
(OOF) Blur in the form of Linear Barcode scanning, the methodology presented can be extended to other blurs
such as moving Blur and other related domains, such as Document Analysis and Recognition, where Image Blurs
are also challenging issues and Deblurring is normally resorted for Character Segmentation and Word Recognition
BARCODE
Barcode Technology has found its applications in many industries and has been playing an important part
in people’s daily lives. Multiple generations of barcode scanning systems ranging from earlier LASER Scanners to
more recent area Charge Coupled Device (CCD) scanners have been invented and developed. As the location/size
information of bars and spaces is of paramount importance for deciphering information embedded in barcodes,
modern barcode scanning systems generally request well-focused barcode signals, which help in the retrieval of
location/size-related features by confining the edge interaction between the code patterns. Depth-of-field (DOF),
the range of distance at which the scanned symbol is sufficiently in focus to be read without error, is an important
aspect of any specific barcode scanning system. Area CCD scanners have the advantage of reading both linear and
2D barcodes, but have less DOF than that of laser scanners, because the directional and coherent nature of laser
light permits expanded DOF. This DOF constraint has limited the availability of area CCD scanners on various
occasions. For example, linear barcode scanning based services are largely not available on mobile devices with
fixed-focus lenses because the barcode images captured by these devices contain excess edge interactions triggered
by out-of-focus (OOF) blur, which cannot be handled by current techniques.
Unfortunately, images taken by cell phone cameras are often of low quality. Many cell phone cameras on
the market are equipped with low-grade lenses, generally lacking focusing capability, which often produce blurred
images. Few cell phones have a flash and, therefore, motion blur and noise can be expected with low ambient light.
All of these factors, possibly combined with low image resolution, make barcode reading difficult in certain
situations. Indeed, all existing image-based barcode readers have limited performance when it comes to images
taken in difficult light conditions, or when the camera is not close enough to the barcode. In order to improve
accuracy, barcode reading apps usually prompt the user to precisely position the camera to ensure that the barcode
covers as much of the frame as possible. This operation can be somewhat bothersome, as it requires a certain
amount of interaction with the user, who needs to frame the barcode correctly using the viewfinder.
EXISTING SYSTEM
Existing system requires that the Barcode has been localized with fairly good precision. This operation is
facilitated by the fact that a Barcode is bordered to the side by a white area whose size is prescribed by the
standard. We propose a simple and fast algorithm for localization that assumes that the bars are approximately
INTERNATIONAL CONFERENCE ON RECENT ADVANCEMENT IN MECHANICAL ENGINEERING &TECHNOLOGY
(ICRAMET’ 15)
Journal of Chemical and Pharmaceutical Sciences ISSN: 0974-2115
JCHPS Special Issue 9: April 2015 www.jchps.com Page 419
vertical. The localization algorithm has no pretense of optimality but works reasonably well in existing method.
The disadvantages of the Existing methods are (i)OOF blur cannot be handled by current techniques,(ii)not feasible
for real-time barcode scanning in real-world situations,(iii)Template matching scheme only matches the scan lines
which are not affected by maximum noise & (iv) Its capability of real-time processing, which is made quite
impossible because sometimes resolution low images may need to find.
PROPOSED SYSTEM
The proposed approach is different in the aspects that it neither exploits Blur invariant features because
none of the currently popular features are robust to severe OOF blur, nor tries to reconstruct OOF free barcode
signal from the blurred images because Image Reconstruction is usually a mathematically ill-defined problem,
computationally difficult to be dealt with. One notable feature of the proposed system is that its Template Matching
scheme takes Image Blur and interactions of character templates into consideration by modelling the waveform of
Barcode characters and their interactions at any specific Blur level. This gives the proposed system the capability to
deal with severe OOF level. The maximum OOF blur level that can be handled by the current implementation of
the proposed system is up to seven times of the X-dimension of a Barcode. Another feature of the proposed system
is its capability of Real Time processing, which is needed in practical situations. This feature is made possible by
designing a directed graphical model, which not only establishes the relationship between the blurred barcode
waveform and its corresponding symbol value
Figure.1.Block diagram of proposed system
DYNAMIC TEMPLATE MATCHING
Dynamic Template Matching (DTM) which can efficiently find the optimal state variable sequence and,
therefore, the barcode value. Merits of the Proposed Systems are as .(i)It gives the capability to deal with OOF
level.(ii)Its capability of real-time processing, which is made possible by directed graphical model.(iii)Similar to
OOF blur any blur can able to handle by proposed techniques.(iv)Directed graphical model will help to generate
closer scan line of original barcodes.
MODULE DESCRIPTION
The work presented in this paper consists of the following major modules such as
Barcode localization
Linear barcode scan line segmentation and observation sequence modelling
Standard reference waveform segments generation
A directed graphical model
Dynamic template matching
RESULTS
Figure 2 & 3 shows the Clear & Blurred Input Images .Figure 4 & 5 shows the Gray scale conversion of
Clear & Blurred Input Images respectively .Figure 6 & 7 shows the Gradient Images .Figure 8 & 9 shows the
Gaussian Motion Filtered Noise. Figure 10 & 11 is the Binarized Barcode. Figure 12 & 13 is Deformed
Scanline.Figure 14 & 15 is Observation sequence. Figure 16 & 17 is Standard Deviation Waveform.
FUTURE ENHANCEMENT
This paper mainly addresses the analysis and classification of binary waveforms under OOF blur in the
form of linear barcode scanning, the methodology presented can be extended to other Blurs such as moving Blur
and other related domains, such as Document Analysis & Recognition, where Image blurs are also challenging
issues and Deblurring is normally resorted for Character Segmentation and Word Recognition
INTERNATIONAL CONFERENCE ON RECENT ADVANCEMENT IN MECHANICAL ENGINEERING &TECHNOLOGY
(ICRAMET’ 15)
Journal of Chemical and Pharmaceutical Sciences ISSN: 0974-2115
JCHPS Special Issue 9: April 2015 www.jchps.com Page 420
Figure 1
Figure 2
Figure3
Figure4
Figure5
Figure6
Figure7
Figure8
Figure9
Figure10
INTERNATIONAL CONFERENCE ON RECENT ADVANCEMENT IN MECHANICAL ENGINEERING &TECHNOLOGY
(ICRAMET’ 15)
Journal of Chemical and Pharmaceutical Sciences ISSN: 0974-2115
JCHPS Special Issue 9: April 2015 www.jchps.com Page 421
Figure11
Figure12
Figure13
Figure14
Figure15
Figure16
REFERENCES
A.Zamberletti, I. Gallo, M. Carullo, and E. Binaghi, Neural image restoration for decoding 1-D barcodes using
common camera phones, In Proc. 5th Int. Conf. Comput. Vision Theory and Appl., 2010, 5–11.
D. Kundur and D. Hatzinakos, Blind image deconvolution, IEEE Signal Process. Mag., 13(3), 43–63, 1996.
Information Technology—Automatic Identification and Data Capture Techniques—Bar Code Symbology
Specification—EAN/UPC, ISO Standard IEC 15420, 2000.
J. Liang, D. Doermann, and H. Li, Camera-based analysis of text and documents: A survey, Int. J. Document Anal.
Recognit., 7(2-3), 2005, 84–104.
J. Massieu, Autofocus barcode scanner and the like employing micro-fluidic lens, U.S. Patent 7 296 749, Nov. 20,
2007.
K. Wang, Y. Zou, and H. Wang, 1D bar code reading on camera phones, Int. J. Image Graph., vol. 7, no. 3, pp.
529–550, 2007.
N. Dridi, Y. Delignon, W. Sawaya, and F. Septier, Blind detection of severely blurred 1D barcode, in Proc.
GLOBECOM, Dec. 2010, pp. 1–5.
O. Gallo and R. Manduchi, Reading 1D barcodes with mobile phones using deformable templates, IEEE Trans.
Pattern Anal. Mach. Intell, vol. 33, no. 9, pp. 1834–1843, Sep. 2011.
R. Choksi and Y. van Gennip, Deblurring of one dimensional bar codes via total variation energy minimization,
SIAM J. Imag.Sci., vol. 3, no. 4, pp. 735–764, 2010.
R. Fischer, B. Tadic-Galeb, and P. Yoder, Optical System Design, 2nd ed. New York, NY, USA: McGraw-Hill,
Jan. 2008.
R. Shams and P. Sadeghi, Bar code recognition in highly distorted and low resolution images, in Proc. IEEE
ICASSP, vol. 1. Apr. 2007, pp. I-737–I-740.
S. Esedoglu, Blind deconvolution of bar code signals, Inverse Problems, vol. 20, no. 1, pp. 121–135, Feb. 2004.
T. Miwa and T. Matsushima, Bar code reading apparatus with multifocal length optical system, U.S. Patent 5 473
149, Dec. 5, 1995.
T. Wittman, Lost in the supermarket: Decoding blurry barcodes, SIAM News, 37(7), 2004, 5–6.
W. Turin and R. A. Boie, Bar code recovery via the EM algorithm, IEEE Trans. Signal Process, vol. 46, no. 2, pp.
354–363, Feb. 1998.