13 March 2003 SAR image classification with a directional-oriented discrete Hermite transform
Author Affiliations +
Abstract
This paper presents a novel classification scheme for SAR images based on the perceptual classification of image patterns in the Discrete Hermite Transform (DHT) domain over a roughly hexagonal sampling lattice. The DHT analyzes a signal through a set of binomial filters which approximate the Gaussian derivatives with the advantage that they are computed efficiently. In order to obtain the DHT referred to a rotated coordinate system the set of coefficients of a given order are mapped through a unitary transformation that is locally specified. Such a transformation is based on the generalized binomial functions so that the rotation algorithm is efficient too. This representation allows a perceptual classification, which is achieved by thesholding the approximation errors that are obtained under the hypotheses that the underlying pattern is a constant (0-D), an oriented structure (1-D) or a non-oriented structure (2-D). The threshold is based on light adaptation and contrast masking properties of the human vision.
© (2003) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Boris Escalante-Ramirez, Penelope Lopez-Quiroz, Jose Luis Silvan-Cardenas, "SAR image classification with a directional-oriented discrete Hermite transform", Proc. SPIE 4885, Image and Signal Processing for Remote Sensing VIII, (13 March 2003); doi: 10.1117/12.463082; https://doi.org/10.1117/12.463082
PROCEEDINGS
12 PAGES


SHARE
Back to Top