Performance evaluation of texture measures for ground cover identification in satellite images by means of a neural network classifier
IEEE Transactions on Geoscience and Remote SensingPublished 1 May 1995
Marijke F. Augusteijn, Laura E. Clemens, Kelly Shaw
Citations130
SJR quartileQ1
SJR score2.40
SNIP2.37
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The performance of several feature extraction methods for classifying ground covers in satellite images is compared and some Fourier features and some Gabor filters were found to be good choices, in particular when a single frequency band was used for classification.
Abstract
The performance of several feature extraction methods for classifying ground covers in satellite images is compared. Ground covers are viewed as texture of the image. Texture measures considered are: cooccurrence matrices, gray-level differences, texture-tone analysis, features derived from the Fourier spectrum, and Gabor filters. Some Fourier features and some Gabor filters were found to be good choices, in particular when a single frequency band was used for classification. A Thematic Mapper (TM) satellite image showing a variety of vegetations in central Colorado was used for the comparison. A related goal was to investigate the feasibility of extracting the main ground covers from an image. These ground covers may then form an index into a database. This would allow the retrieval of a set of images which are similar in contents. The results obtained in the indexing experiments are encouraging.>
Keywords
Computer ScienceEarth and Planetary SciencesEngineering
IEEE Transactions on Systems Man and CyberneticsTextural Features for Image Classification
22,499 Citations1973Robert M. Haralick, K. Shanmugam +1 more
These results indicate that the easily computable textural features based on gray-tone spatial dependancies probably have a general applicability for a wide variety of image-classification applications.
Pattern RecognitionUnsupervised texture segmentation using Gabor filters
2,142 Citations1991Anil K. Jain, F. Farrokhnia
Neural ComputationWhat Size Net Gives Valid Generalization?
1,555 Citations1989Eric B. Baum, David Haussler
It is shown that if m O(W/ ∊ log N/∊) random examples can be loaded on a feedforward network of linear threshold functions with N nodes and W weights, so that at least a fraction 1 ∊/2 of the examples are correctly classified, then one has confidence approaching certainty that the network will correctly classify a fraction 2 ∊ of future test examples drawn from the same distribution.
IEEE Transactions on Systems Man and CyberneticsA Comparative Study of Texture Measures for Terrain Classification
1,525 Citations1976Joan S. Weszka, Charles R. Dyer +1 more
Three standard approaches to automatic texture classification make use of features based on the Fourier power spectrum, on second-order gray level statistics, and on first-order statistics of gray level differences, respectively; it was found that the Fouriers generally performed more poorly, while the other feature sets all performned comparably.
IEEE Transactions on Pattern Analysis and Machine IntelligenceA Theoretical Comparison of Texture Algorithms
880 Citations1980Richard W. Conners, Charles A. Harlow
Pattern RecognitionPerformance evaluation for four classes of textural features
389 Citations1992Philippe P. Ohanian, Richard C. Dubes
Comparisons of textural features for pattern recognition show that co-occurrence features perform best followed by the fractal features, however, there is no universally best subset of features.
Artificial neural network classification using a minimal training set - Comparison to conventional supervised classification
274 Citations1990George F. Hepner, T. L. Logan +2 more
This reseach compares the use of an ANN back propagation classification procedure with a conventional supervised maximum likelihood classification procedure using a minimal training set and finds the neural network is able to provide a land-cover classification superior to the classification derived from the conventional classification procedure.
IEEE Transactions on Geoscience and Remote SensingA neural network approach to cloud classification
268 Citations1990J. Lee, R. C. Weger +2 more
It is shown that, using high-spatial-resolution data, very high cloud classification accuracies can be obtained with a neural network approach, and a texture-based neural network classifier using only single-channel visible Landsat MSS imagery achieves an overall cloud identification accuracy.
Pattern RecognitionTexture feature performance for image segmentation
205 Citations1990J. M. H. du Buf, Mohammad Reza Kardan +1 more
Results obtained show that direct feature statistics such as the Bhattacharyya distance are not appropriate evaluation criteria if texture features are used for image segmentation, and that the Haralick, Laws and Unser methods gave best overall results.
Photogrammetric Engineering & Remote SensingClassification of land cover using optimized neural nets on SPOT data
70 Citations1993Peter Dreyer
The results of experiments with the use of neural nets for land-cover classification in a SPOT satellite image are presented, and a backpropagation net with two hidden layers is used to classify the segments.
Texture segmentation by clustering of Gabor feature vectors
33 Citations2002S. Y. Lu, J. E. Hernández +1 more
By clustering Gabor features, the authors were able to segment an image into regions of uniform texture without prior knowledge of the types of texture, or the frequency and orientation characteristics of these textures.
Transactions of the ASAEFat Estimation in Beef Ultrasound Images Using Texture and Adaptive Logic Networks
24 Citations1994John McCauley, B. R. Thane +1 more
International Journal of Remote SensingInitial analysis of Landsat TM data for elk habitat mapping
21 Citations1990Thomas Huber, KIRT E. CASLER
Telematics and InformaticsFeature detection in satellite images using neural network technology
12 Citations1992Marijke F. Augusteijn, Arturo S. Dimalanta
A study of the feasibility of automated classification of satellite images characterized by the textures they contain, using the method of second-order gray level statistics and the Cascade-Correlation architecture as a classifier.
IEEE International Conference on Neural NetworksIdentification of unknown categories with probabilistic neural networks
10 Citations2002T.P. Washburne, Donald F. Specht +1 more
The method described solves the problem of identifying correctly a pattern as an unknown as opposed to misclassifying it as a known category by establishing a threshold on the probability density function as determined by a risk strategy.
CaltechAUTHORS (California Institute of Technology)Remote Sensing Image Analysis via a Texture Classification Neural Network
8 Citations1992Hayit Greenspan, R.M. Goodman
A texture classification network is applied to remote sensing image analysis to extract the characteristics of the area depicted in the input image, thus achieving a segmented map of the region.
Elsevier eBooksToward a Structural Textural Analyzer Based on Statistical Methods**This research supported in part by AFOSR Contract F49620-79-C-0042 and NSF Grant ENG 79-5154.
6 Citations1981Richard W. Conners, Charles A. Harlow
To mathematically verify that the features used with the SGLDM can be used to characterize the unit pattern and placement rules of a periodic texture, a mathematical tiling theory model is proposed and allows one to develop the mathematical machinery necessary to prove the result.