pca

From DavinciWiki
Jump to: navigation, search

Description

Principal Component Analysis

Compute the principal components of an N band real data image

NOTE: for the old 3 band pca version see pca_byte(). This version replaced the old byte version on 2-9-2011

Arguments and Return Values

Arguments: A numeric array and ignore value

Return Value: The rotated data

Usage

Syntax: pca(image [, ignore=FLOAT][, struct=BOOL])

'image' - A N-band image or data array

'ignore' - the ignore value for the black space of an image

'struct' - return the eigen vectors/values and covariance matrix

Examples

dv> a
600x600x3 array of byte, bip format [1,080,000 bytes]

dv> b=pca(a)
  data: 600x600x3 array of double, bip format [8,640,000 bytes]

Images

Original 3-band Image:

unfiltered.png

Three principal components:

comp1.png comp2.png comp3.png

Original 6-band Image:

NYC-Band Comparison.PNG

Six principal components:

NYC-PCA-C1.PNG NYC-PCA-C2.PNG NYC-PCA-C3.PNG NYC-PCA-C4.PNG NYC-PCA-C5.PNG NYC-PCA-C6.PNG


DavinciWiki Mini-Nav Bar

Contents


Contact Developers

  • davinci-dev [AT] mars.asu.edu

All other topics

  • See navigation on the left

Major Sub-Functions

Related Functions

Recent Library Changes

Created On: 02-15-2006
Modified On: 07-16-2012

Personal tools