An Efficient Machine Learning-Based Model to Effectively Classify the Type of Noises in QR Code: A Hybrid Approach

被引:3
|
作者
Rasheed, Jawad [1 ]
Wardak, Ahmad B. [2 ]
Abu-Mahfouz, Adnan M. [3 ,4 ]
Umer, Tariq [5 ]
Yesiltepe, Mirsat [6 ]
Waziry, Sadaf [2 ]
机构
[1] Nisantasi Univ, Dept Software Engn, TR-34398 Istanbul, Turkey
[2] Istanbul Aydin Univ, Dept Comp Engn, TR-34295 Istanbul, Turkey
[3] Council Sci & Ind Res CSIR, ZA-0184 Pretoria, South Africa
[4] Univ Johannesburg, Dept Elect & Elect Engn Sci, ZA-2006 Johannesburg, South Africa
[5] COMSATS Univ Islamabad, Dept Comp Sci, Lahore Campus, Lahore 54000, Pakistan
[6] Yildiz Tech Univ, Dept Math Engn, TR-34220 Istanbul, Turkey
来源
SYMMETRY-BASEL | 2022年 / 14卷 / 10期
关键词
quick response; noisy images; noise classification; CNN; histogram analysis; SVM; CLASSIFICATION;
D O I
10.3390/sym14102098
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Granting smart device consumers with information, simply and quickly, is what drives quick response (QR) codes and mobile marketing to go hand in hand. It boosts marketing campaigns and objectives and allows one to approach, engage, influence, and transform a wider target audience by connecting from offline to online platforms. However, restricted printing technology and flexibility in surfaces introduce noise while printing QR code images. Moreover, noise is often unavoidable during the gathering and transmission of digital images. Therefore, this paper proposed an automatic and accurate noise detector to identify the type of noise present in QR code images. For this, the paper first generates a new dataset comprising 10,000 original QR code images of varying sizes and later introduces several noises, including salt and pepper, pepper, speckle, Poisson, salt, local var, and Gaussian to form a dataset of 80,000 images. We perform extensive experiments by reshaping the generated images to uniform size for exploiting Convolutional Neural Network (CNN), Support Vector Machine (SVM), and Logistic Regression (LG) to classify the original and noisy images. Later, the analysis is further widened by incorporating histogram density analysis to trace and target highly important features by transforming images of varying sizes to obtain 256 features, followed by SVM, LG, and Artificial Neural Network (ANN) to identify the noise type. Moreover, to understand the impact of symmetry of noises in QR code images, we trained the models with combinations of 3-, 5-, and 7-noise types and analyzed the classification performance. From comparative analyses, it is noted that the Gaussian and Localvar noises possess symmetrical characteristics, as all the classifiers did not perform well to segregate these two noises. The results prove that histogram analysis significantly improves classification accuracy with all exploited models, especially when combined with SVM, it achieved maximum accuracy for 4- and 6-class classification problems.
引用
收藏
页数:20
相关论文
共 50 条
  • [31] COVID-19 Perspective Diagnosis of Arrhythmia: A Machine Learning-Based Approach.
    Mallikarjuna, M.
    Reddy, A. Bharathi Malak
    2024 5TH INTERNATIONAL CONFERENCE ON INNOVATIVE TRENDS IN INFORMATION TECHNOLOGY, ICITIIT 2024, 2024,
  • [32] A Machine Learning-Based Model for Early Stage Detection of Diabetes
    Hasan, S. M. Mahedy
    Rabbi, Md Fazle
    Champa, Arifa Islam
    Zaman, Md Asif
    2020 23RD INTERNATIONAL CONFERENCE ON COMPUTER AND INFORMATION TECHNOLOGY (ICCIT 2020), 2020,
  • [33] Machine Learning-Based Model for the Prognosis of Postoperative Gastric Cancer
    Liu, Donghui
    Wang, Xuyao
    Li, Long
    Jiang, Qingxin
    Li, Xiaoxue
    Liu, Menglin
    Wang, Wenxin
    Shi, Enhong
    Zhang, Chenyao
    Wang, Yinghui
    Zhang, Yan
    Wang, Liru
    CANCER MANAGEMENT AND RESEARCH, 2022, 14 : 135 - 155
  • [34] A Machine Learning-Based Fall Risk Assessment Model for Inpatients
    Liu, Chia-Hui
    Hu, Ya-Han
    Lin, Yu-Hsiu
    CIN-COMPUTERS INFORMATICS NURSING, 2021, 39 (08) : 450 - 459
  • [35] Machine learning-based reproducible prediction of type 2 diabetes subtypes
    Tanabe, Hayato
    Sato, Masahiro
    Miyake, Akimitsu
    Shimajiri, Yoshinori
    Ojima, Takafumi
    Narita, Akira
    Saito, Haruka
    Tanaka, Kenichi
    Masuzaki, Hiroaki
    Kazama, Junichiro J.
    Katagiri, Hideki
    Tamiya, Gen
    Kawakami, Eiryo
    Shimabukuro, Michio
    DIABETOLOGIA, 2024, 67 (11) : 2446 - 2458
  • [36] A Model Recommends Best Machine Learning Algorithm To Classify Learners Based On Their Interactivity With Moodle
    Hassan, Suzan
    Hegazy, Abd El Fattah
    2015 SECOND INTERNATIONAL CONFERENCE ON COMPUTING TECHNOLOGY AND INFORMATION MANAGEMENT (ICCTIM), 2015, : 49 - 54
  • [37] Automated demarcation of requirements in textual specifications: a machine learning-based approach
    Abualhaija, Sallam
    Arora, Chetan
    Sabetzadeh, Mehrdad
    Briand, Lionel C.
    Traynor, Michael
    EMPIRICAL SOFTWARE ENGINEERING, 2020, 25 (06) : 5454 - 5497
  • [38] SecRiskAI: a Machine Learning-Based Approach for Cybersecurity Risk Prediction in Businesses
    Franco, Muriel F.
    Sula, Erion
    Huertas, Alberto
    Scheid, Eder J.
    Granville, Lisandro Z.
    Stiller, Burkhard
    2022 IEEE 24TH CONFERENCE ON BUSINESS INFORMATICS (CBI 2022), VOL 1, 2022, : 1 - 10
  • [39] THPep: A machine learning-based approach for predicting tumor homing peptides
    Shoombuatong, Watshara
    Schaduangrat, Nalini
    Pratiwi, Reny
    Nantasenamat, Chanin
    COMPUTATIONAL BIOLOGY AND CHEMISTRY, 2019, 80 : 441 - 451
  • [40] A machine learning-based approach for comprehensive fault diagnosis in transmission lines
    Franca, Isternandia Araujo
    Vieira, Cynthia Wanick
    Ramos, Daniel Correa
    Sathler, Lara Hoffmann
    Carrano, Eduardo G.
    COMPUTERS & ELECTRICAL ENGINEERING, 2022, 101