Naslov
Automatic Visual Reading of Meters Using Deep Learning

Autori
Koščević, Karlo ; Subašić, Marko

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the Croatian Computer Vision Workshop 2018 / Petković, Tomislav - Zagreb : Fakultet elektrotehnike i računarstva Sveučilišta u Zagrebu, 2018, 1-6

Skup
7th Croatian Computer Vision Workshop (CCVW 2018)

Mjesto i datum
Zagreb, Hrvatska, 24.10.2018

Vrsta sudjelovanja
Poster

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Image analysis, Object detection, OCR, Deep neural networks

Sažetak
In this paper, we present a novel approach to the problem of reading residential meters using deep learning algorithms. As a starting point we use Faster R-CNN method and, to acquire more precise readings, we modify its functionality. As there were no databases for this kind of task, one had to be collected and properly annotated. This paper also provides a brief introduction to methods for image augmentation and a technique to augment annotated image dataset. For each part of the presented method as well as the whole method as one unit experiments were conducted to show the overall successfulness.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo

POVEZANOST RADA