Multi-nature hierarchical approach for natural image segmentation with pattern refinement feedback

A hierarchical learning method for segmenting natural images is proposed in this paper. This approach combines the perceptual information of three natures – colour, texture, and homogeneity – in order to segment natural colour images. These low-level features are extracted using a multiple scale neu...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) 2013-01, Vol.99, p.325-338
Main Authors: Díaz-Pernas, F.J., Antón-Rodríguez, M., Martínez-Zarzuela, M., Perozo-Rondón, F.J., González-Ortega, D.
Format: Article
Language:English
Subjects:
Applied sciences
Artificial intelligence
ARTMAP models
Berkeley segmentation dataset
Computer science
control theory
systems
Connectionism. Neural networks
Exact sciences and technology
Hierarchical neural network
Natural image segmentation
Pattern recognition. Digital image processing. Computational geometry
Pattern refinement
Supervised categorisation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A hierarchical learning method for segmenting natural images is proposed in this paper. This approach combines the perceptual information of three natures – colour, texture, and homogeneity – in order to segment natural colour images. These low-level features are extracted using a multiple scale neural architecture we previously proven in [1,20]. Present approach incorporates the human knowledge to a hierarchical categorisation process, where the features of the three natures are independently categorised. The final segmentation is achieved through pattern refinement cycles. The approach is compared to other two significant natural scene segmentation methods, achieving better results in a global evaluation. These comparisons are performed using the Berkeley Segmentation Dataset.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2012.07.024