e-ISSN: 2582-5208

International Research Journal of Modernization in Engineering Technology and Science

( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:06/Issue:04/April-2024 Impact Factor- 7.868 www.irjmets.com
QR CODE RECOGNITION BASED ON IMAGE PROCESSING
Swathi. J*1, Sangeetha. V*2, V. Sarala Devi*3
*1MCA Student, Department of Computer Applications Dr. M.G.R. Educational and Research Institute,
Chennai – 95, India.
*2,3Assistant Professor, Department of Computer Applications Dr. M.G.R. Educational and Research Institute,
Chennai – 95, India.
ABSTRACT
To solve the QR code recognition problem caused by ordinary camera collection, the recognition algorithm based
on image processing is put forward in this paper. The whole process including image binarization, image tilt
correction, image orientation, image geometric correction and image normalization allows images collected on
different illumination conditions. Experiments show that the improved method can enhance the recognition
speed of two-dimensional code and accuracy. QR i.e. “Quick Response” code is a 2D matrix code that is designed
by keeping two points under consideration, i.e. it must store large amount of data as compared to 1D barcodes
and it must be decoded at high-speed using any handheld device like phones. QR code provides high data storage
capacity, fast scanning, omnidirectional readability, and many other advantages including, error-correction (so
that damaged code can also be read successfully) and different type of versions. Different varieties of QR code
symbols like logo QR code, encrypted QR code, QR Code are also available so that user can choose among them
according to their need. Now these days, a QR code is applied in different application streams related to
marketing, security, academics etc. and gain popularity at a really high pace. Day by day more people are getting
aware of this technology and use it accordingly. The popularity of QR code grows rapidly with the growth of
smartphone users and thus the QR code is rapidly arriving at high levels of acceptance worldwide.
Keywords: QR code, recognition algorithm, image processing, image binarization, tilt correction, orientation,
geometric correction, normalization, data storage capacity, error correction.
I. INTRODUCTION
On the basis of computer technology and information technology, QR code technology composed by encoding,
printing, identification, data acquisition and processing is booming. Compared with bar code, two-dimensional
code has significant outstanding advantages in the data capacity, data types, data density and data recovery
capability. QR code recognition relies on image processing techniques to identify and decode QR codes embedded
within images. Through pixel analysis and pattern recognition, the software locates QR code patterns amidst
varying backgrounds. Once identified, specialized algorithms interpret the encoded information within the QR
code. This process enables seamless integration of QR code functionality into applications, facilitating tasks such
as digital payments, authentication, and information retrieval. [1]
According to the realization principle, structure and shape differences, two-dimensional code can be divided into
linear barcodes and matrix barcodes. And the main application is in logistics management, catering orders,
security applications, ticketing system, authentication, business transactions, etc[2]
Quick Response Code (QR Code) is one kind of two-dimensional matrix code developed by the Japanese Denso
company in September 1994. In addition to the advantages of two-dimensional bar code, it also has features such
as ultra-fast response, comprehensive reading, the portable offline application database, more efficiently
representation on numbers of letters, characters, images, etc. [3]
QR Code increased by 20% than the other two-dimensional bar code on efficiency of the characters
representation, its proprietary Chinese model is more suitable for our application. In practical applications,
barcode reading technology will encounter the following difficulties.[4]
Together with much of information that is nothing to do with the bar code, the bar code symbols are printed on
the packaging of commodities. The condition results in a complex barcode image background. Changes in
illumination, resulting in uneven image brightness, increase the difficulty of identification.[5]
Acquisition in different angles and distances, coupled with the geometric distortion and flat distortion caused by
image capture device, the image of the QR codes will be rotated, zoomed and stretched. To solve the problems
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[12080]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:06/Issue:04/April-2024 Impact Factor- 7.868 www.irjmets.com
above, two-dimensional code image should have a series of image processing before adopting national standards
for rapid response code decoding algorithm.[6]
II. LITERATURE SURVEY
According to Hicham Tribak and Youssef Zaz, developing QR code recognition systems based on computer vision
poses significant challenges, primarily stemming from two key factors: (1) The system's ability to accurately
detect QR codes within captured images, even in challenging conditions like varying lighting and perspective
distortions. (2) It must be tailored for efficient operation on embedded system platforms, taking into account
limitations in processing capabilities and resource allocation. Past approaches to QR code recognition often relied
on intricate feature descriptors such as Harris features and Hough transforms to extract QR code patterns and
estimate their positions. These techniques were further enhanced by employing pattern classifiers like Random
Forests and Support Vector Machines (SVM) to discern genuine QR code patterns from erroneous detections. [7]
According to Hicham Tribak, Salah Moughyt, Youssef Zaz, Gerald Schaefer QR codes have become useful and
efficient data storage tools which are exploited in many commercial applications including product tracking,
website redirection, etc. A QR code is a 2-dimensional barcode localised through three finder patterns (three
squares characterised by a series of alternative black and white modules at ratios 1:1:3:1:1) placed in its three
corners. QR codes are generally placed in different environments with complex backgrounds (overlapping text,
pictures, etc.), and are often captured under unfavourable conditions such as poor lighting. These factors can
significantly affect the recognition ability and thus may hinder correct QR code localisation and identification. In
order to appropriately address these issues, in this paper, we present a QR code recognition algorithm based on
histogram of oriented gradients (HOG) features combined with support vector machine (SVM) classifiers. Using
HOG, we extract gradient features of each extracted pattern. Subsequently, the obtained features are passed to
two linear SVM classifiers, one trained with finder patterns and one trained with alignment patterns, to remove
irrelevant patterns. QR codes are then conveniently localised according to a pattern closeness constraint. In the
last stage, the captured code is enhanced by applying a perspective correction followed by image binarisation
and morphological processing. Finally, the patterns are decoded using an accurate 2-d barcode decoder. Our
proposed approach is designed for an embedded systems using a Raspberry Pi equipped with a HD camera and
a small robot carrying the equipment.[8]
According to Benjamin C.M. Fung, Ke Wang and Martin Ester A major challenge in document clustering is the
extremely high dimensionality. For example, the vocabulary for a document set can easily be thousands of words.
On the other hand, each document often contains a small fraction of words in the vocabulary. These features
require special handlings. Another requirement is hierarchical clustering where clustered documents can be
browsed according to the increasing specificity of topics. In this paper, we propose to use the notion of frequent
itemsets, which comes from association rule mining, for document clustering. The intuition of our clustering
criterion is that each cluster is identified by some common words, called frequent item sets, for the documents
in the cluster. Frequent item sets are also used to produce a hierarchical topic tree for clusters. By focusing on
frequent items, the dimensionality of the document set is drastically reduced. We show that this method
outperforms best existing methods in terms of both clustering accuracy and scalability.[9]
According to N. M. Z. Hashim, N. A. Ibrahim, N. M. Saad, F. Sakaguchi, Z. Zakaria Barcode became essential
elements in sales and products services due to importance of keeping records of all items in on place. For this
purpose, there are many methods implemented to make the barcode reading process became easier to users.
This project is to develop a barcode recognition system by using image processing. The system will be able to
read barcode through an image and the system capable to capture the image by using a webcam. This project will
be using MATLAB software program to develop the system and it will integrate with webcam or digital camera.
System will analyse the image and then display on the Graphical User Interface (GUI) the barcode type, data and
size of the image. System is designed to recognize different types of barcodes and display the data once the
barcode image is captured. System also is to provide convenience way of observing data from the barcode with
lower costing compared by using the electronic barcode scanners. This system can be used anytime and
anywhere by the user who likes to observe the data represented by the barcode numbers without going any
places providing the barcode scanner services. As the result, the project has been developed smoothly and

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[12081]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:06/Issue:04/April-2024 Impact Factor- 7.868 www.irjmets.com
perfectly. For the future system development, it is suggested that the system also should consist a slider so that
the user would able to control the brightness of the image which captured by webcam.[10]
According to Raed M. Bani-Hani Yarub A. Wahsheh Mohammad B. Al-Sarhan Quick Response (QR) codes are two
dimensional barcodes that can be used to efficiently store small amount of data. They are increasingly used in all
life fields, especially with the wide spread of smart phones which are used as QR code scanners. While QR codes
have many advantages that make them very popular, there are several security issues and risks that are
associated with them. Running malicious code, stealing users' sensitive information and violating their privacy
and identity theft are some typical security risks that a user might be subject to in the background while he/she
is just reading the QR code in the foreground. In this paper, a security system for QR codes that guarantees both
users and generators security concerns is implemented. The system is backward compatible with current
standard used for encoding QR codes. The system is implemented and tested using an Android-based
smartphone application. It was found that the system introduces a little overhead in terms of the delay required
for integrity verification and content validation.[11]
III. EXISTING SYSTEM
QR code (Best Available Rate Code) is a trademark for a form of barcode. Traditional one-dimensional bar codes
can only store about 20 digits, however QR codes may hold several dozen to several hundred times more
information. QR codes allow us to encode the same amount of data in one-tenth the space of regular barcodes
since they can store data both horizontally and vertically. Micro QR Code is also available in smaller printable
sizes.
DISADVANTAGES
• One dimensional QR and BAR Code, it can only store a maximum of approximately 20 digits
• Less capability and performance
• Less storage
Proposed System- Here for this project, we are using OpenCV module to predict the QR code. The QR code can
be predicted by using the Images and web cam access. The csv file dataset is also included in this project. We are
using module like pyzbar, cv2 and argparse.
ADVANTAGES
• Powerful, flexible, and easy to use
• Increased efficiency of doctor.
• Improved patient satisfaction.
• Reduce the use of papers.
• Simple and Quick.
• More accurate result.
ARCHITECTURE DIAGRAM

FIGURE .1. Architecture diagram

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[12082]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:06/Issue:04/April-2024 Impact Factor- 7.868 www.irjmets.com
1.Data Collection
Data collection involves the systematic gathering, measurement, and analysis of precise information for research
purposes, employing established and validated methodologies. Researchers leverage collected data to assess
their hypotheses. Regardless of the discipline, data collection typically constitutes the initial and pivotal stage in
research endeavours. The methods for gathering data vary depending on the research topic and the required
information. In this project, we have opted to utilize the CSV file format for our dataset.
2. Module Implementation
We constructed a QR code recognition system utilizing modules such as OpenCV, Pyzbar, and the argparse
package. The OpenCV falls under the deep learning model.
Open CV:
The OpenCV tutorial covers both fundamental and advanced aspects of this library. Tailored for both novices and
experts, OpenCV is an open-source toolset for computer vision tasks. Its primary function is to enable machines
to identify faces or objects within images. This tutorial explores OpenCV concepts through the lens of Python
programming. Computer vision aims to comprehend the contents of images by extracting relevant information.
This can include identifying objects, interpreting text descriptions, constructing three-dimensional models, and
more. For instance, computer vision technology can empower vehicles to recognize various elements on the road,
such as traffic lights, pedestrians, road signs, and respond accordingly.
Pyzbar:
The Pyzbar module possesses the ability to scan and decipher both one-dimensional barcodes and QR codes. Its
functionalities include:
• Simple integration with Python
• Compatible with PIL / Pillow images, OpenCV / NumPy ndarrays, and raw bytes
• Provides barcode location decoding capabilities
• PIL or Pillow, an Image Processing library, offers a wide array of image manipulation functions. We'll utilize
it for image opening purposes.
Argparse: The argparse module simplifies the creation of intuitive command-line interfaces. By specifying the
required arguments, the program delegates the parsing task to argparse, which extracts them from sys.argv.
Additionally, argparse automatically generates informative help and usage prompts. Furthermore, the module
detects and reports errors when users provide invalid arguments.
3. Prediction
By using these modules, we are gaining the inputs from the real time in web cam frame. The camera is on and
you can show the QR code to that. Giving the data as an input format.
4. Final output
After giving the input, the QR code is recognized and it will show the name of the QR code.
IV. CONCLUSION
In this project, we studied QR code technology, its benefits, application areas, and its impact on marketing and
technological world. Initially, QR code are developed and use for inventory tracking stuff but, now these days,
they found applications in many new areas like marketing, advertising, secure payment systems, education
industries, etc. Adoption of the QR codes grows rapidly during past years and number of users increases
exponentially, due to its features like high data storage capacity, fast scanning, error-correction, direct marking
and ease of use.
V. REFERENCES
[1] Joseph, Eugene, and Theodosios Pavlidis. "Bar code waveform recognition using peak locations." IEEE
Transactions on Pattern Analysis and Machine Intelligence 16, no. 6 (1994): 630-640.
[2] Kuroki, Mikio, Takayuki Yoneoka, Tetsua Satou, Yoichi Takagi, Tadaaki Kitamura, and Noriaki Kayamori.
"Bar-code recognition system using image processing." In 1997 IEEE 6th International Conference on
Emerging Technologies and Factory Automation Proceedings, EFTA'97, pp. 568-572. IEEE, 1997.

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[12083]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:06/Issue:04/April-2024 Impact Factor- 7.868 www.irjmets.com
[3] LIU, Ning-zhong, and Jing-yu YANG. "Recognition of two-dimensional bar code based on Fourier
Transform." Journal of Image and Graphics 8, no. 8 (2003): 877-882.
[4] Ohbuchi, Eisaku, Hiroshi Hanaizumi, and Lim Ah Hock. "Barcode readers using the camera device in mobile
phones." In 2004 International conference on cyberworlds, pp. 260-265. IEEE, 2004.
[5] GU, Xiao-lin, Ming HUANG, and Hai-yin QI. "2-Dimensional Bar Code Recognition Based on Genetic
Algorithms [J]." Journal of Dalian Railway Institute 4 (2005).
[6] Youssef, Sherin M., and Rana M. Salem. "Automated barcode recognition for smart identification and
inspection automation." Expert Systems with Applications 33, no. 4 (2007): 968-977.
[7] Falas, Tasos, and Hossein Kashani. "Two-dimensional bar-code decoding with camera-equipped mobile
phones." In Fifth Annual IEEE International Conference on Pervasive Computing and Communications
Workshops (PerComW'07), pp. 597-600. IEEE, 2007.
[8] Liu, Yue, Ju Yang, and Mingjun Liu. "Recognition of QR Code with mobile phones." In 2008 Chinese control
and decision conference, pp. 203-206. IEEE, 2008.
[9] Gu, Yunhua, and Weixiang Zhang. "QR code recognition based on image processing." In international
conference on information science and technology, pp. 733-736. IEEE, 2011.
[10] Zhang, Yunfei, Bo Lu, and Limin Su. "A barcode recognition based on multiform algorithms." In 2012 4th
International Conference on Intelligent Human-Machine Systems and Cybernetics, vol. 2, pp. 17-20. IEEE,
2012
[11] Narayan, Gayathri Rema, and Mr Vinoth James. "Barcode recognition from video by combining image
processing and xilinx." Procedia engineering 38 (2012): 2140-2146.
[12] Hashim, N. M. Z., N. A. Ibrahim, N. M. Saad, F. Sakaguchi, and Z. Zakaria. "Barcode recognition system."
International Journal of Emerging Trends & Technology in Computer Science (IJETTCS) 2, no. 4 (2013):
278-283.

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[12084]