Selection of optimal textural features for maximum likelihood image classification
The classification or segmentation of images into land cover or object class is one of the fundamental remote sensing/image processing tasks. The classification techniques have reached a high level of maturity in the forms of statistical pattern recognition techniques applied to multispectral images. According to this approach each pixel has a spectral vector associated with it and pixels are segmented into the class they most closely resemble spectrally. While these techniques are reasonably successful they do not take advantage of the brightness patterns within a class or at object boundaries nor are they readily applicable to monochrome images or highly correlated multispectral images (e.g., true color images). To overcome these limitations several investigators have suggested the use of image derived features as additional factors for use in image classification. Robert (1989) has identified over forty textural features that have been suggested by various authors as useful for scene classification. Regrettably it is very compute intensive to generate all these features for every pixel in an image and to then use them in a classifier. Schott et al. (1988) developed a technique for selecting a small subset of spectral bands from a large set based on criteria intended to optimize maximum likelihood classification. Salvaggio et al. (1990) have implemented code to generate 46 image derived textural features and applied a two-step feature reduction and optimization process based largely on the band selection process of Schott et al. (1988). The current effort drew on this proof-of-concept work mentioned above and improved on several limitations noted in the earlier work. Specifically, the initial feature set reduction algorithm of Robert (1989) is shown to be deficient and an improved method implemented. 18 refs., 62 figs., 13 tabs.
- Research Organization:
- Rochester Inst. of Tech., NY (USA). Center for Imaging Science
- Sponsoring Organization:
- DOE/DP
- DOE Contract Number:
- FG01-88DP20153
- OSTI ID:
- 5098367
- Report Number(s):
- DOE/DP/20153-T7; RIT/DIRS--89/90-66-131; ON: DE90006901
- Country of Publication:
- United States
- Language:
- English
Similar Records
Cloud cover analysis with Arctic advanced very high resolution radiometer data. 2. Classification with spectral and textural measures
AFREET: HUMAN-INSPIRED SPATIO-SPECTRAL FEATURE CONSTRUCTION FOR IMAGE CLASSIFICATION WITH SUPPORT VECTOR MACHINES
Related Subjects
45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEFENSE
450000 -- Military Technology
Weaponry
& National Defense
98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL PROTECTION
99 GENERAL AND MISCELLANEOUS
990200 -- Mathematics & Computers
AERIAL SURVEYING
ALGORITHMS
ARMS CONTROL
COMPUTERIZED CONTROL SYSTEMS
CONTROL SYSTEMS
DATA PROCESSING
IDENTIFICATION SYSTEMS
IMAGE PROCESSING
MATHEMATICAL LOGIC
MATHEMATICAL MODELS
MILITARY STRATEGY
OPTIMIZATION
PROCESSING
REMOTE SENSING
STATISTICAL MODELS
TASK SCHEDULING
TECHNOLOGY ASSESSMENT
TEXTURE