Features and classification methods to locate deciduous trees in images

    Authors

    N. Haering;N. D. Lobo

    Comments

    Authors: contact us about adding a copy of your work at STARS@ucf.edu

    Abbreviated Journal Title

    Comput. Vis. Image Underst.

    Keywords

    FRACTAL GEOMETRY; TEXTURE; SEGMENTATION; FILTERS; Computer Science, Artificial Intelligence; Engineering, Electrical &; Electronic

    Abstract

    We compare features and classification methods to locate deciduous trees in images. From this comparison we conclude that a back-propagation neural network achieves better classification results than the other classifiers we tested. Our analysis of the relevance of 51 features from seven feature extraction methods based on the graylevel co-occurrence matrix, Gabor filters, fractal dimension, steerable filters, the Fourier transform, entropy, and color shows that each feature contributes important information. We show how we obtain a 13-feature subset that significantly reduces the feature extraction time while retaining most of the complete feature set's power and robustness. The best subsets of features were found to be combinations of features of each of the extraction methods. Methods for classification and feature relevance determination that are based on the covariance or correlation matrix of the features (such as eigenanalyses or linear or quadratic classifiers) generally cannot be used, since even small sets of features are usually highly linearly redundant, rendering their covariance or correlation matrices too singular to be invertible. We argue that representing deciduous trees and many other objects by rich image descriptions can significantly aid their classification. We make no assumptions about the shape, location, viewpoint, viewing distance, lighting conditions, and camera parameters, and we only expect scanning methods and compression schemes to retain a "reasonable" image quality, (C) 1999 Academic Press.

    Journal Title

    Computer Vision and Image Understanding

    Volume

    75

    Issue/Number

    1-2

    Publication Date

    1-1-1999

    Document Type

    Article

    Language

    English

    First Page

    133

    Last Page

    149

    WOS Identifier

    WOS:000082266200010

    ISSN

    1077-3142

    Share

    COinS