Automatic Attribute Profiles
- 6 February 2017
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 26 (4) , 1859-1872
Abstract
Morphological attribute profiles are multilevel decompositions of images obtained with a sequence of transformations performed by connected operators. They have been extensively employed in performing multiscale and region-based analysis in a large number of applications. One main, still unresolved, issue is the selection of filter parameters able to provide representative and non-redundant threshold decomposition of the image. This paper presents a framework for the automatic selection of filter thresholds based on Granulometric Characteristic Functions (GCFs). GCFs describe the way that non-linear morphological filters simplify a scene according to a given measure. Since attribute filters rely on a hierarchical representation of an image (e.g., the Tree of Shapes) for their implementation, GCFs can be efficiently computed by taking advantage of the tree representation. Eventually, the study of the GCFs allows the identification of a meaningful set of thresholds. Therefore, a trial and error approach is not necessary for the threshold selection, automating the process and in turn decreasing the computational time. It is shown that the redundant information is reduced within the resulting profiles (a problem of high occurrence, as regards manual selection). The proposed approach is tested on two real remote sensing data sets, and the classification results are compared with strategies present in the literature.Keywords
Funding Information
- EU FP7 Theme Space project North State
- Program J. Verne 2014 (31936TD)
- INS2I JCJC 2015 under Project IDES
This publication has 45 references indexed in Scilit:
- Spectral and Spatial Classification of Hyperspectral Images Based on ICA and Reduced Morphological Attribute ProfilesIEEE Transactions on Geoscience and Remote Sensing, 2015
- Discriminant Tensor Spectral–Spatial Feature Extraction for Hyperspectral Image ClassificationIEEE Geoscience and Remote Sensing Letters, 2014
- Spectral–Spatial Classification of Hyperspectral Images Using Wavelets and Extended Morphological ProfilesIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014
- Automatic Spectral–Spatial Classification Framework Based on Attribute Profiles and Supervised Feature ExtractionIEEE Transactions on Geoscience and Remote Sensing, 2013
- Change Detection in VHR Images Based on Morphological Attribute ProfilesIEEE Geoscience and Remote Sensing Letters, 2012
- Automatic Generation of Standard Deviation Attribute Profiles for Spectral–Spatial Classification of Remote Sensing DataIEEE Geoscience and Remote Sensing Letters, 2012
- Classification of Remote Sensing Optical and LiDAR Data Using Extended Attribute ProfilesIEEE Journal of Selected Topics in Signal Processing, 2012
- Automatic threshold selection for morphological attribute profiles2012
- Differential Area Profiles: Decomposition Properties and Efficient ComputationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- Study on the capabilities of morphological attribute profiles in change detection on VHR images2010