Naslov
Influence of quality of pixel level annotations on text detection performance in natural images

Autori
Dorkić, Ivan ; Brisinello, Matteo ; Grbić, Ratko ; Herceg, Marijan

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

Izvornik
2023 46th MIPRO ICT and Electronics Convention (MIPRO) / - , 2023, 1052-1056

ISBN
978-953-233-104-2

Skup
2023 46th MIPRO ICT and Electronics Convention (MIPRO)

Mjesto i datum
Opatija, Hrvatska, 22.05.2023. - 26.05.2022

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
object detection ; text detection ; instance segmentation ; Synthtext ; TextFuseNet

Sažetak
Text detection in natural images is a task that arises in many computer vision applications. State-of-the-art text detection methods are mainly based on deep neural networks designed for instance segmentation task. However, most of the available datasets for text detection do not have fine annotations at the pixel level which are required during supervised learning of such networks. Usually, a whole or reduced text bounding box is used as a segmentation mask. In this paper, a method that generates a synthetic dataset with precise annotations at the pixel level is proposed. The method is based on the available Synthtext script for generating synthetic datasets with text instances. By creating synthetic datasets with precise and coarse annotations at the pixel level we explore the efficiency of the state-of-the-art text detector TextFuseNet.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA