Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Classifier ensemble creation via false labelling

Autor: Antal, Bálint

Publikováno v: Knowledge-based Systems 89: pp. 278-287. (2015)

In this paper, a novel approach to classifier ensemble creation is presented. While other ensemble creation techniques are based on careful selection of existing classifiers or preprocessing of the data, the presented approach automatically creates a

Externí odkaz: http://arxiv.org/abs/1603.01716

An ensemble-based system for automatic screening of diabetic retinopathy

Autor: Antal, Balint, Hajdu, Andras

Publikováno v: Knowledge-Based Systems, Elsevier, Volume 60, April 2014, Pages 20-27

In this paper, an ensemble-based method for the screening of diabetic retinopathy (DR) is proposed. This approach is based on features extracted from the output of several retinal image processing algorithms, such as image-level (quality assessment,

Externí odkaz: http://arxiv.org/abs/1410.8576

An Unsupervised Ensemble-based Markov Random Field Approach to Microscope Cell Image Segmentation

Autor: Antal, Balint, Remenyik, Bence, Hajdu, Andras

Publikováno v: Proceeingds of the 10th International Conference on Signal Processing and Multimedia Applications (SIGMAP 2013), Reykjavik, Iceland, 2013, pp. 94-99

In this paper, we propose an approach to the unsupervised segmentation of images using Markov Random Field. The proposed approach is based on the idea of Bit Plane Slicing. We use the planes as initial labellings for an ensemble of segmentations. Wit

Externí odkaz: http://arxiv.org/abs/1410.7265

Improving microaneurysm detection in color fundus images by using context-aware approaches

Autor: Antal, Bálint, Hajdu, András

Publikováno v: In Computerized Medical Imaging and Graphics July-September 2013 37(5-6):403-408