Approach to Automated Visual Inspection of Objects Based on Artificial Intelligence

被引:16
|
作者
Kuric, Ivan [1 ]
Klarak, Jaromir [2 ]
Bulej, Vladimir [1 ]
Saga, Milan [3 ]
Kandera, Matej [1 ]
Hajducik, Adrian [4 ]
Tucki, Karol [5 ]
机构
[1] Univ Zilina, Dept Automat & Prod Syst, Fac Mech Engn, Univ 8215-1, Zilina 01026, Slovakia
[2] Slovak Acad Sci, Inst Informat, Dubravska Cesta 9, Bratislava 84507, Slovakia
[3] Univ Zilina, Fac Mech Engn, Dept Appl Mech, Univ 8215-1, Zilina 01026, Slovakia
[4] Univ Zilina, Dept Design & Mech Elements, Fac Mech Engn, Univ 8215-1, Zilina 01026, Slovakia
[5] Warsaw Univ Life Sci, Inst Engn Mech, Fac Prod Engn, Nowoursynowska St 164, PL-02787 Warsaw, Poland
来源
APPLIED SCIENCES-BASEL | 2022年 / 12卷 / 02期
关键词
visual inspection; object detector; optical recognition; camera systems; deep learning; machine vision; defect detection; DEFECT DETECTION;
D O I
10.3390/app12020864
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
The article discusses the possibility of object detector usage in field of automated visual inspection for objects with specific parameters, specifically various types of defects occurring on the surface of a car tire. Due to the insufficient amount of input data, as well as the need to speed up the development process, the Transfer Learning principle was applied in a designed system. In this approach, the already pre-trained convolutional neural network AlexNet was used, subsequently modified in its last three layers, and again trained on a smaller sample of our own data. The detector used in the designed camera inspection system with the above architecture allowed us to achieve the accuracy and versatility needed to detect elements (defects) whose shape, dimensions and location change with each occurrence. The design of a test facility with the application of a 12-megapixel monochrome camera over the rotational table is briefly described, whose task is to ensure optimal conditions during the scanning process. The evaluation of the proposed control system with the quantification of the recognition capabilities in the individual defects is described at the end of the study. The implementation and verification of such an approach together with the proposed methodology of the visual inspection process of car tires to obtain better classification results for six different defect classes can be considered as the main novel feature of the presented research. Subsequent testing of the designed system on a selected batch of sample images (containing all six types of possible defect) proved the functionality of the entire system while the highest values of successful defect detection certainty were achieved from 85.15% to 99.34%.
引用
收藏
页数:19
相关论文
共 50 条
  • [1] Artificial Dataset Generation for Automated Aircraft Visual Inspection Artificial Dataset Generation for Automated Aircraft Visual Inspection
    Gaul, Nathan J.
    Leishman, Robert C.
    PROCEEDINGS OF THE 2021 IEEE NATIONAL AEROSPACE AND ELECTRONICS CONFERENCE (NAECON), 2021, : 302 - 306
  • [2] Artificial intelligence and visual inspection in cervical cancer screening
    Nakisige, Carolyn
    de Fouw, Marlieke
    Kabukye, Johnblack
    Sultanov, Marat
    Nazrui, Naheed
    Rahman, Aminur
    de Zeeuw, Janine
    Koot, Jaap
    Rao, Arathi P.
    Prasad, Keerthana
    Shyamala, Guruvare
    Siddharta, Premalatha
    Stekelenburg, Jelle
    Beltman, Jogchum Jan
    INTERNATIONAL JOURNAL OF GYNECOLOGICAL CANCER, 2023, 33 (10) : 1515 - 1521
  • [3] Adaptive explainable artificial intelligence for visual defect inspection
    Rozanec, Joze M.
    Sircelj, Beno
    Fortuna, Blaz
    Mladenic, Dunja
    5TH INTERNATIONAL CONFERENCE ON INDUSTRY 4.0 AND SMART MANUFACTURING, ISM 2023, 2024, 232 : 3034 - 3043
  • [5] Artificial intelligence-based automatic visual inspection system for built heritage
    Mansuri, Lukman E.
    Patel, D. A.
    SMART AND SUSTAINABLE BUILT ENVIRONMENT, 2022, 11 (03) : 622 - 646
  • [6] Automated Visual Information Processing Using Artificial Intelligence
    Gavrilov, D. A.
    Lovtsov, D. A.
    SCIENTIFIC AND TECHNICAL INFORMATION PROCESSING, 2021, 48 (06) : 436 - 445
  • [7] Automated Visual Information Processing Using Artificial Intelligence
    D. A. Gavrilov
    D. A. Lovtsov
    Scientific and Technical Information Processing, 2021, 48 : 436 - 445
  • [8] A Support Vector Machine Based Online Learning Approach for Automated Visual Inspection
    Sun, Jun
    Sun, Qiao
    2009 CANADIAN CONFERENCE ON COMPUTER AND ROBOT VISION, 2009, : 192 - 199
  • [9] Artificial intelligence-based visual inspection system for structural health monitoring of cultural heritage
    Mayank Mishra
    Tanmoy Barman
    G. V. Ramana
    Journal of Civil Structural Health Monitoring, 2024, 14 : 103 - 120
  • [10] Artificial intelligence-based visual inspection system for structural health monitoring of cultural heritage
    Mishra, Mayank
    Barman, Tanmoy
    Ramana, G., V
    JOURNAL OF CIVIL STRUCTURAL HEALTH MONITORING, 2024, 14 (01) : 103 - 120