350 rub
Journal Neurocomputers №1 for 2021 г.
Article in number:
Hierarchical pyramidal subsampling in deep convolutional networks for visual pattern recognition
DOI: 10.18127/j19998554-202101-03
UDC: 681.142
Authors:

A. E. Averyanikhin, A. I. Vlasov, E. V. Evdokimova Department IU4 of Designing and Technology of Electronic Equipment, Bauman Moscow State Technical University (Moscow, Russia)

Abstract:

The main problem of known deep convolutional neural networks (CNN) is that they require a fixed-size input image. This requirement is “artificial” and can reduce recognition accuracy for images or its parts of arbitrary size/scale. The paper proposes a strategy of combining “hierarchical pyramidal subselection” to eliminate the above restriction. The structure of the neural network using the proposed combining strategy allows the generation of prediction regardless of the size/scale of the original image, and also improves the accuracy of recognition.

Features of application of CNN for identification and recognition of defects of conducting pattern of printed circuit board blanks have been considered. Features of defects of conductive pattern of printed circuit board blanks have been briefly discussed. The invention proposes the use of artificial CNN, which have advantages in speed and accuracy in solving problems of object recognition on images relative to existing methods. The focus is on the architecture of CNN using hierarchical pyramidal subselection. Capabilities of application of CNN for recognition of defects of conducting pattern of printed circuit board blanks have been shown.

Proposed method of hierarchical pyramidal subselection in deep convolutional networks has been implemented in software complex, which allows processing digital data of photographs of conducting pattern of printed circuit boards, in particular during their flaw detection, and can be used for localization of existing defects of conducting pattern. The conclusion draws the possibilities of using methods and means of image processing in flaw detection of radio-electronic equipment and instruments

Pages: 17-35

Averyanikhin A.E., Vlasov A.I., Evdokimova E.V. Hierarchical pyramidal subsampling in deep convolutional networks for visual pattern recognition. Neurocomputers. 2021. Vol. 23. No. 1. P. 17–31. DOI: 10.18127/j19998554-202101-03. (in Russian)

References
  1. Gridnev V.N., Gridneva G.N. Proektirovanie kommutatsionnykh struktur elektronnykh sredstv. M.: Izd-vo MGTU im. N.E. Baumana. 2014. (in Russian)
  2. Buyanov A.I., Vlasov A.I., Zagoskin A.V. Primenenie nejrosetevykh metodov pri defektoskopii pechatnykh plat. Nejrokomp'yutery: razrabotka, primenenie. 2002. № 3. S. 42–70. (in Russian)
  3. Vlasov A.I., Gridnev V.N., Konstantinov P., Yudin A.V. Nejrosetevye metody defektoskopii pechatnykh plat. Elektronnye komponenty. 2004. № 8. S. 148–155. (in Russian)
  4. Panfilova S.P., Vlasov A.I., Gridnev V.N., Chervinskij A.S. Beskontaktnyj teplovoj kontrol' izdelij elektronnoj tekhniki. Proizvodstvo elektroniki. 2007. № 3. S. 25–30. (in Russian)
  5. Panfilova S.P., Vlasov A.I., Gridnev V.N., Chervinskij A.S. Beskontaktnyj teplovoj kontrol' elektronno-vychislitel'nykh sredstv. Tekhnologiya i konstruirovanie v elektronnoj apparature. 2007. № 6. S. 42–49. (in Russian)
  6. Gridnev V.N., Sergeeva M.D., Chebova A.I. Linejnye modeli raspoznavaniya teplovizionnykh izobrazhenij neispravnostej elektronnykh yacheek. Kontrol'. Diagnostika. 2014. № 8. S. 57–66. (in Russian)
  7. Buyanov A.A., Vlasov A.I., Gridnev V.N. The neuronet hardware and software integrated system for defectoscopy of printed circuits based on microsections. Sb. tezisov dokladov 3-j mezhdunar. konf. «Komp'yuternye metody i obratnye zadachi v nerazrushayushchem kontrole i diagnostike». 2002. S. 71.
  8. Makushina N.V., Sergeeva M.D. Analiz defektov metallizirovannykh otverstij pechatnykh plat. Proektirovanie i tekhnologiya elektronnykh sredstv. 2018. № 1. S. 3–12. (in Russian)
  9. Viryasova A.Yu., Vlasov A.I., Gladkikh A.A. Nejrosetevye metody defektoskopii integral'nykh struktur. Nejrokomp'yutery: razrabotka, primenenie. 2019. № 2. S. 54–67. (in Russian)
  10. Uossermen F. Nejrokomp'yuternaya tekhnika: Teoriya i praktika. M.: Mir. 1992. (in Russian)
  11. Balukhto A.N., Bulaev V.I., Buryj E.V. i dr. Nejrokomp'yutery v sistemakh obrabotki izobrazhenij. Ser. Biblioteka zhurnala «Nejrokomp'yutery: razrabotka, primenenie». T. 7. M.: Radiotekhnika. 2003. (in Russian)
  12. Balukhto A.N., Galushkin A.I., Koval'chuk D.V., Nazarov L.E., Tomashevich N.S. Nejrokomp'yutery v prikladnykh zadachakh obrabotki izobrazhenij. Ser. Biblioteka zhurnala «Nejrokomp'yutery: razrabotka, primenenie». T. 8. M.: Radiotekhnika. 2003. (in Russian)
  13. Dembitskij N.L., Nazarov A.V. Primenenie metodov iskusstvennogo intellekta v proektirovanii i proizvodstve radiotekhnicheskikh ustrojstv. Ser. Nauchnaya biblioteka. M.: Izd-vo MAI. 2009. (in Russian)
  14. Grigor'ev V.P., Kamyshnaya E.N., Nesterov Yu.I., Nikitin S.A. Primenenie metodov iskusstvennogo intellekta v SAPR tekhnologi­cheskikh protsessov proizvodstva elektronnoj apparatury. M.: Izd-vo MGTU im. N.E. Baumana. 1998. (in Russian)
  15. Glushko A.A., Busov V.D., Perederin K.D. Metody algoritmicheskogo proektirovaniya iskusstvennogo intellekta. Tekhnologii inzhenernykh i informatsionnykh sistem. 2019. № 2. S. 72–88. (in Russian)
  16. Shakhnov V.A., Vlasov A.I., Polyakov Yu.A., Kuznetsov A.S. Nejrokomp'yutery: arkhitektura i skhemotekhnika. Ser. Prilozhenie k zhurnalu «Informatsionnye tekhnologii». № 9. M.: Mashinostroenie. 2000. (in Russian)
  17. Vlasov A.I., Papulin S.Yu. Analiz dannykh s ispol'zovaniem gistogrammnoj modeli kombinatsii priznakov. Nejrokomp'yutery: razrabotka, primenenie. 2019. T. 21. № 5. S. 18–27. (in Russian)
  18. Rys'myatova A.A. Ispol'zovanie svertochnykh nejronnykh setej dlya zadachi klassifikatsii tekstov. M.: MGU im. M.V. Lomonosova. 2016. (in Russian)
  19. Prokhorov V.G. Ispol'zovanie svertochnykh setej dlya raspoznavaniya rukopisnykh simvolov. Problemi programuvaniya. 2008. № 2–3. S. 669–674. (in Russian)
  20. Rowley H.A., Baluja S., Kanade T. Neural network-based face detection. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1998. V. 20. № 1. P. 23–38.
  21. Juell P., Marsh R. A hierarchical neural network for human face detection. Pattern Recognition 1996. V. 29. № 5. P. 781–787.
  22. Lin S.-H., Kung S.-Y., Lin L.-J. Face recognition/detection by probabilistic decision-based neural network. IEEE Transactions on Neural Networks. 1997. V. 8. № 1. P. 114–132.
  23. Lawrence S., Giles C.L., Tsoi A.C., Back A.D. Face recognition: A convolutional neural network approach. IEEE Transactions on Neural Networks. Special Issue on Neural Networks and Pattern Recognition. P. 1–24.
  24. CS231n convolutional neural networks for visual recognition: Image classification [Elektronnyj resurs] / URL: http://cs231n.github.io/ classification/.
  25. Svidetel'stvo o registratsii programmy dlya EVM RU 2019618937. Ekspertnaya sistema po obnaruzheniyu defektov provodyashchego risunka pechatnykh plat / E.V. Evdokimova, A.E. Aver'yanikhin, A.I. Vlasov. Opubl. 08.07.2019. (in Russian)
  26. Demin A.A. Metody avtomatizirovannoj otsenki kalligrafii. Programmnye produkty i sistemy. 2011. № 1. S. 20–23. (in Russian)
  27. Demin A.A., Vlasov A.I., Shakhnov V.A. Metody i sredstva vizual'nykh uprazhnenij dlya adaptivnoj korrektsii tonkoj motoriki kistej ruk v usloviyakh nevesomosti. Vestnik Moskovskogo gosudarstvennogo tekhnicheskogo universiteta im. N.E. Baumana. Ser. Priborostroenie. 2015. № 3 (102). S. 23–38. (in Russian)
Date of receipt: 19.11.2020
Approved after review: 03.12.2020
Accepted for publication: 15.12.2020