Skoči na glavni sadržaj

Stručni rad

https://doi.org/10.19279/TVZ.PD.2020-8-1-12

ENHANCING THE PERFORMANCE OF IMAGE PREPROCESSING FOR CLASSIFICATION AND OBJECT DETECTION

Ivan Cesar ; Tehničko veleučilište u Zagrebu, Zagreb, Hrvatska
Valentin Solina ; Aether-signum Vrbovec, Hrvatska
Renata Kramberger ; Tehničko veleučilište u Zagrebu, Zagreb, Hrvatska
Tin Kramberger ; Tehničko veleučilište u Zagrebu, Zagreb, Hrvatska


Puni tekst: engleski pdf 1.269 Kb

str. 8-14

preuzimanja: 344

citiraj


Sažetak

The image preprocessing optimization is a challenging task with numerous applications including classification and object detection on which this paper is oriented the most. Enhancing the performance in terms of processing time for image preprocessing is crucial to every researcher engaged into deep learning. A few common mistakes and practices are presented in this paper which can greatly impact training time, alongside practices and tools used for diagnosing potential pitfalls. In this paper, we evaluate several common Python libraries which are used for image preprocessing and analyze the impact of different augmentation ordering with respect to central processing unit (CPU) usage

Ključne riječi

computer vision; deep learning; training optimization

Hrčak ID:

242763

URI

https://hrcak.srce.hr/242763

Datum izdavanja:

17.6.2020.

Podaci na drugim jezicima: hrvatski

Posjeta: 1.481 *