Texture Representation and Classification: The Feature Frequency Matrix Approach

Shen, Helen C.; Srivastava, Durgesh

doi:10.1016/s1076-5670(08)70159-9

Cited by 2 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These measures include the mean, the standard deviation with respect to windows of various sizes, gradients in diVerent directions, and correlations between textural parameters at diVerent locations (Haralick et al 1973, Tamura et al 1978, Tomita and Tsuji 1990, Potopav et al 1991, Shen and Srivastava 1996. Radar image simulations were performed at C-band frequency at an incidence angle of 30°in order to understand the eVect of spatial resolution and spatial extent of the object on the image information content (Narayanan et al 1997 ), and the salient results are brie y described to develop the framework for subsequent sections of the paper.…”

Section: Proposed Information Content Model Based On Scene Classi Cationmentioning

confidence: 99%

Effect of spatial resolution on information content characterization in remote sensing imagery based on classification accuracy

Narayanan¹,

Desetty²,

Reichenbach³

2002

International Journal of Remote Sensing

View full text Add to dashboard Cite

Abstract. The information content of remote sensing imagery depends upon various factors such as spatial and radiometric resolutions, spatial scale of the features to be imaged, radiometric contrast between diVerent target types, and also the nal application for which the imagery has been acquired. Various textural measures are used to characterize the image information content, based upon which diVerent image processing algorithms are employed to enhance this quantity. Previous work in this area has resulted in three diVerent approaches for quantifying image information content, primarily based on interpretability, mutual information, and entropy. These approaches, although well re ned, are diYcult to apply to all types of remote sensing imagery. Our approach to quantifying image information content is based upon classi cation accuracy. We propose an exponential model for information content based upon target-background contrast, and target size relative to pixel size. The model is seen to be applicable for relating information content to spatial resolution for real Landsat Thematic Mapper (TM) as well as Shuttle Imaging Radar-C (SIR-C) images. An interesting conclusion that emerges from this model is that although the TM image has higher information content than the SIR-C image at smaller pixel sizes, the opposite is true at larger pixel sizes. The transition occurs at a pixel size of about 720 m. This tells us that for applications that require high resolution (or smaller pixel sizes), the TM sensor is more useful for terrain classi cation, while for applications involving lower resolutions (or larger pixel sizes), the SIR-C sensor has an advantage. Thus, the model is useful in comparing diVerent sensor types for diVerent applications.

show abstract

Section: Proposed Information Content Model Based On Scene Classi Cationmentioning

confidence: 99%

Effect of spatial resolution on information content characterization in remote sensing imagery based on classification accuracy

Narayanan¹,

Desetty²,

Reichenbach³

2002

International Journal of Remote Sensing

View full text Add to dashboard Cite

show abstract

“…These measures include the mean, the standard deviation with respect to windows of various sizes, gradients in different directions, correlations between textural parameters at different locations, etc. [2]- [7]. In most cases, the choice of the textural parameters used for analysis depends upon the end objective as well as the knowledge of the statistical characteristics of specific features within the image.…”

Section: Textural Characteristics Of R E M O T E Sensing Imagerymentioning

confidence: 99%

Characterization of information content in remote sensing imagery

Desetty

Narayanan

Reichenbach

1998

IGARSS '98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings.

View full text Add to dashboard Cite

Remote sensing imagery acquired at various spatial and radiometric resolutions is used to estimate certain geophysical parameters, gauge the extent of geophysical phenomena, or detect the presence of specific targets. The information content in an image is related to several variables including resolution (both spatial and radiometric), the spatial scale of features to be recognized, the mean radiometric intensity and intensity distribution of various target types, as well as the image statistical characteristics. Textura.1 measures appropriate for specific applications are analyzed in terms of resolution tradeoffs in order to yield the required information content.

show abstract

Texture Representation and Classification: The Feature Frequency Matrix Approach

Cited by 2 publications

References 15 publications

Effect of spatial resolution on information content characterization in remote sensing imagery based on classification accuracy

Effect of spatial resolution on information content characterization in remote sensing imagery based on classification accuracy

Characterization of information content in remote sensing imagery

Contact Info

Product

Resources

About