11TexturalClassificationPowerpnts

11TexturalClassificationPowerpnts - Textural Classification...

Info iconThis preview shows pages 1–5. Sign up to view the full content.

View Full Document Right Arrow Icon
Textural Classification • Machine reads a string of numbers • Point classifier: considers each raster independent of surrounding rasters • Humans see shape, texture, pattern, context • Textural classifier takes image texture or context into account • Trains machine to see texture
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Suburb is High Frequency • Grass (Fields) • Trees (Forest) • Rooftop • Pavement • Swiming Pool • But also a pattern- repetition of tones
Background image of page 2
Convert Textural Classes into Information Classes • Commercial (high frequency) • Residential (high frequency) • Forest (low frequency) • Fields (low frequency) • Bare Soil (low frequency) • Water (low frequency) • Normal supervised works for low frequency • Need textural classification for high frequeny
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Incorporating Texture into Classification • Need each pixel to incorporate information about surrounding pixels – Run 3x3 mean filter on data – Each pixel is an average of surrounding pixels • Take training fields based on image texture
Background image of page 4
Image of page 5
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 12/21/2010 for the course GIS 4037c taught by Professor Roberts during the Spring '10 term at FAU.

Page1 / 24

11TexturalClassificationPowerpnts - Textural Classification...

This preview shows document pages 1 - 5. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online