PRIMENA VEŠTAČKE INTELIGENCIJE ZA IDENTIFIKACIJU STANJA ELEKTRIČNOG BROJILA
Ključne reči:
Veštačka inteligencija, Mašinsko učenje, Duboko učenje, Neuronske mreže
Apstrakt
Skeniranje slika i pretvaranje skeniranih informacija u digitalni format je aktivna oblast istraživanja. Skeniranje je automatizovan, brz i efikasan proces u poređenju sa tradicionalnim unosom podataka. Prepoznavanje cifara sa slika je izazovan zadatak. Tradicionalni pristupi za rešavanje ovog problema obično razdvajaju korake lokalizacije, segmentacije i prepoznavanja. Ovaj rad predstavlja jedinstven pristup koji integriše ova tri koraka korišćenjem duboke konvolucione neuronske mreže koja radi direktno na pikselima slike.
Reference
[1] https://github.com/mdbloice/Augmentor, skripta za augmentaciju, poslednji pristup 14.12.2022.
[2] Muhammad Asif, Maaz Bin Ahmad, Shiza Mushtaq et al. “Long Multi-digit Number Recognition from Images Empowered by Deep Convolutional Neural Network”. The Computer Journal, Volume 65, Issue 10, October 2022, Pages 2815–2827. 13 September 2021.
[3] Tetko, I. V., Livingstone, D. J. and Luik, A. I. „Neural network studies. 1. Comparison of overfitting and overtraining,“ Journal of chemical information and computer sciences, 1995, 35.5: 826-833.
[4] Dietterich, T. „Overfitting and undercomputing in machine learning,“ ACM computing surveys (CSUR), 1995, 27.3: 326-327.
[5] Caruana, R., Lawrence, S., Giles, CL. „Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping.“ In: Advances in neural information processing systems. 2001. p. 402- 408.
[2] Muhammad Asif, Maaz Bin Ahmad, Shiza Mushtaq et al. “Long Multi-digit Number Recognition from Images Empowered by Deep Convolutional Neural Network”. The Computer Journal, Volume 65, Issue 10, October 2022, Pages 2815–2827. 13 September 2021.
[3] Tetko, I. V., Livingstone, D. J. and Luik, A. I. „Neural network studies. 1. Comparison of overfitting and overtraining,“ Journal of chemical information and computer sciences, 1995, 35.5: 826-833.
[4] Dietterich, T. „Overfitting and undercomputing in machine learning,“ ACM computing surveys (CSUR), 1995, 27.3: 326-327.
[5] Caruana, R., Lawrence, S., Giles, CL. „Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping.“ In: Advances in neural information processing systems. 2001. p. 402- 408.
Objavljeno
2023-07-07
Sekcija
Elektrotehničko i računarsko inženjerstvo
