FULLY CONVOLUTIONAL NEURAL NETWORKS FOR IMAGE SEGMENTATION

Andrei Leica (), Mihai Bogdan Voicescu (), Răzvan-Ștefan Brînzea () and Costin-Anton Boiangiu ()
Additional contact information
Andrei Leica: Politehnica University of Bucharest, Bucharest, Romania
Mihai Bogdan Voicescu: Politehnica University of Bucharest, Bucharest, Romania
Răzvan-Ștefan Brînzea: Politehnica University of Bucharest, Bucharest, Romania
Costin-Anton Boiangiu: Politehnica University of Bucharest, Bucharest, Romania

Journal of Information Systems & Operations Management, 2018, vol. 12, issue 2, 400-410

Abstract: Image segmentation is a Computer Vison process in which an input image is split into different and fully-disjoint parts, which are considered to possess a certain characteristic of interest (they have almost the same color, a resembling texture, they represent the same object inside a scene, etc.). In most scenarios, the key for a successfully image analysis, in which there is required a high-level interpretation of its content, may be found in a correct segmentation, but, unfortunately, in most of the real-life cases, this is a very difficult task. Our method is based on deep learning neural network architectures, which hold state of the art accuracy for pixel-wise segmentation on various challenges. We will design and train different architectures and use all of them together as a voting-based image segmentation system.

Date: 2018
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.rebe.rau.ro/RePEc/rau/jisomg/Wi18/JISOM-WI18-A16.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:rau:jisomg:v:12:y:2018:i:2:p:400-410

Access Statistics for this article

More articles in Journal of Information Systems & Operations Management from Romanian-American University Contact information at EDIRC.
Bibliographic data for series maintained by Alex Tabusca ().