Pattern Classification of Fabric Defects Using a Probabilistic Neural Network and Its Hardware Implementation using the Field Programmable Gate Array System

• Autorzy: Hasnat A. , Ghosh A. , Khatun A. , Halder S.

Identyfikatory

DOI

10.5604/12303666.1227881

Warianty tytułu

PL

Klasyfikacja rodzaju defektów tkanin za pomocą probabilistycznej sztucznej sieci neuronowej oraz za pomocą systemu FPGA

• Języki publikacji: EN

Abstrakty

EN

This study proposes a fabric defect classification system using a Probabilistic Neural Network (PNN) and its hardware implementation using a Field Programmable Gate Arrays (FPGA) based system. The PNN classifier achieves an accuracy of 98 ± 2% for the test data set, whereas the FPGA based hardware system of the PNN classifier realises about 94±2% testing accuracy. The FPGA system operates as fast as 50.777 MHz, corresponding to a clock period of 19.694 ns.

PL

W pracy zaprezentowano system klasyfikacji wad tkanin przy użyciu probabilistycznej sieci neuronowej (PNN) i przy zastosowaniu systemu Field Programmable Gate Array (FPGA). PNN pozwala na osiągnięcie dokładności 98 ± 2% dla zbioru danych testowych, podczas gdy system FPGA pozwala na osiągnięcie dokładności około 94 ± 2%. System FPGA pracuje przy częstotliwości 50,777 MHz, co odpowiada 19,694 ns.

Słowa kluczowe

EN

classification; fabric defect; field programmable gate array (FPGA); radial basis function; probabilistic neural network

PL

klasyfikacja wad tkanin; probabilistyczna sieć neuronowa

• Wydawca: Sieć Badawcza Łukasiewicz - Łódzki Instytut Technologiczny
• Czasopismo: Fibres & Textiles in Eastern Europe
• Rocznik: 2017
• Tom: Vol. 25, no. 1 (121)
• Strony: 42--48
• Opis fizyczny: Bibliogr. 16 poz., rys., tab.

Twórcy

autor

Hasnat A.

• Government College of Engineering and Textile Technology, Berhampore, West Benga, India

autor

Ghosh A.

• Government College of Engineering and Textile Technology, Berhampore, West Benga, India

autor

Khatun A.

• Jadavpur University, Kolkata, West Bengal, India

autor

Halder S.

• Government Govt. College of Engineering & Leather Technology, Kolkata, West Bengal, India

Bibliografia

• 1. John M and Sebastian S. Application Specific Integrated Circuits. Addison-Wesley, 1997.
• 2. Jenkins JH. Designing with FPGAs and CPLDs. Prentice-Hall, 1994.
• 3. Weste NH and Eshraghian K. Principles of CMOS VLSI Design: A Systems Perspective. Pearson Education Asia, 2000.
• 4. Bhasker J. A VHDL Primer. 3rd ed, Prentice Hall PTR, 1998.
• 5. Hai-feng C. Design and Implementation of Real-time Fabric Defect Detection System. Advances in information Sciences and Service Sciences 2012; 4(21): 23-30.
• 6. Diana M, Radu M, Nicholas HZ, Phillip S, Pradeep KK, Sungmee P, Sundaresan J, Stefan J, Christl L, Werner W, Tunde K, Didier C, Janusz G, Gerhard T, Mark J, Tom M and Zahi N. Electronic Textiles: A Platform for Pervasive Computing. The IEEE, 2003; 91(12): 1995- 2018.
• 7. Specht DF. Probabilistic neural networks. Neural Networks1990; 3(1): 109-118.
• 8. El-EmaryIMM and RamakrishnanS.On the Application of Various Probabilistic Neural Networks in Solving Different Pattern Classification Problems. World Applied Sciences Journal 2008; 4(6): 772-780.
• 9. Eason G, Randall Wilson and D. Center Point Selection for Probabilistic Neural Networks. In: International Conference on Artificial Neural Networks and Genetic Algorithms, 1997. pp. 514-517.
• 10. Wilson DR and Tony RM. Heterogeneous Radial Basis Functions. International Conference on Neural Networks,1996; paper no.2, pp.1263-1267.
• 11. Wilson DR. and Tony RM. Improved Heterogeneous Distance Function. Journal of Artificial Intelligence Research 1997; 6(1):1-34.
• 12. Stanfill C. and Waltz D. Towards Memory Based Reasoning. Communication of the ACM 1986; 29(12): 1213-1228.
• 13. Ramakrishnan S. and Selvan S. Classification of Brain Tissues Using Multiwavelet Transformation and Probabilistic Neural Network. International Journal of Simulation: Systems, Science and Technology 2006; 7(9): 9-25.
• 14. Ramakrishnan S and Selvan S. Image Texture Classification Using Wavelet Based Curve Fitting and Probabilistic Neural Network. International Journal of Imaging Systems and Technology 2007; 17(4): 266-275.
• 15. Tian B, Mahmood R A, Thomas H, Vonder H and Donald R. Temporal Updating Scheme for Probabilistic Neural Network with Application to Satellite Cloud Classification. IEEE Transactions on Neural Networks 2000; 11(4): 903-920.
• 16. Tsai S, Lin CH and Lin JJ. Applying an Artificial Neural Network to Pattern Recognition in Fabric Defects. Text Res J 1995; 65(3): 123-130.

Uwagi

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę (zadania 2017).