colorize

Estimate color image of hyperspectral data

collapse all in page

Syntax

coloredImage = colorize(hcube)
coloredImage = colorize(hcube,band)
[coloredImage,indices] = colorize(___)
___ = colorize(___,Name,Value)

Description

example

coloredImage = colorize(hcube) estimates a false-color image of hyperspectral data based on the three most informative bands of the hypercube object hcube.

coloredImage = colorize(hcube,band) returns a false-color image using the specified spectral bands band.

example

[coloredImage,indices] = colorize(___) returns the indices of the bands used in the color image.

___ = colorize(___,Name,Value) specifies options using one or more name-value pair arguments in addition to any combination of arguments from previous syntaxes. Use this syntax to specify the options to estimate false-colored and color-infrared (CIR) images of the input data.

Note

This function requires the Image Processing Toolbox™ Hyperspectral Imaging Library. You can install the Image Processing Toolbox Hyperspectral Imaging Library from Add-On Explorer. For more information about installing add-ons, see Get and Manage Add-Ons.

Examples

collapse all

Open Live Script

Read a hyperspectral data into the workspace.

hcube = hypercube('paviaU.dat');

Estimate a false-color image of the hyperspectral data.

coloredImg = colorize(hcube);

Display the false-color image. 

imshow(coloredImg)

Open Live Script

Read a hyperspectral data into the workspace.

hcube = hypercube('paviaU.dat');

Estimate an RGB image of the hyperspectral data. Increase the image contrast by applying contrast stretching.

coloredImg = colorize(hcube,"Method","rgb","ContrastStretching",true);

Display the contrast-stretched RGB image. 

imshow(coloredImg)

Input Arguments

collapse all

Input hyperspectral data, specified as a hypercube object. The DataCube property of the hypercube object stores the hyperspectral data cube as an M-by-N-by-C numeric array, where C is the number of bands.

Spectral band numbers, specified as a 3-element vector of positive integers. All elements of the vector must be less than or equal to the total number of bands C in the input data.

Data Types: double

Name-Value Pair Arguments

Specify optional comma-separated pairs of Name,Value arguments. Name is the argument name and Value is the corresponding value. Name must appear inside quotes. You can specify several name and value pair arguments in any order as Name1,Value1,...,NameN,ValueN.

Example: colorize(hcube,'Method','rgb')

Method used to visualize the bands, specified as the comma-separated pair consisting of 'Method' and one of these options.

  • 'falsecolored' — Create a false-color image consisting of the three most informative bands selected using selectBands function.

  • 'rgb' — Create an RGB image by dividing the spectral range into red (R), green (G), and blue (B) bands. The red band ranges from 610 nm to 700 nm, the green band ranges from 500 nm to 570 nm, and the blue band ranges from 450 nm to 500 nm. The displayed R, G, and B channels consist of the most representative bands within the corresponding spectral range based on the correlation coefficient metric.

  • 'cir' — Create a color-infrared (CIR) image by dividing the spectral range into near infrared (NIR), R, and G bands. The NIR band ranges from 750 nm to 1400 nm, the red band ranges from 610 nm to 700 nm, and the green band ranges from 500 nm to 570 nm. The displayed channels consist of the most representative bands within the corresponding spectral range based on the correlation coefficient metric.

To create RGB or CIR images, the Wavelength property of the hypercube object hcube must have wavelengths in each of the corresponding ranges.

Data Types: char | string

Perform contrast stretching of the image, specified as the comma-separated pair consisting of 'ContrastStretching' and the logical 0 (false) or 1 (true). When true, the colorize function applies contrast-limited adaptive histogram equalization, using the adapthisteq function.

Data Types: logical

Output Arguments

collapse all

Color image, returned as an M-by-N-by-3 numeric array. Each of the three color planes contains one band of the hyperspectral image.

Data Types: single | double

Indices of the selected bands, returned as a 3-element column vector of positive integers.

Data Types: double

References

[1] Su, Hongjun, Qian Du, and Peijun Du. “Hyperspectral Image Visualization Using Band Selection.” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 7, no. 6 (June 2014): 2647–58. https://doi.org/10.1109/JSTARS.2013.2272654.

See Also

|

Introduced in R2020a

Image Processing Toolbox Documentation

Support