Grayscale Version of RGB Image

IMAGE_RGB_TO_GRAY, a MATLAB function which creates a grayscale version of an RGB image.

An RGB image is an (M,N,3) array.

A grayscale image is an (M,N) array.

A grayscale version of an RGB image can be made by averaging the RGB components of each pixel.

A more sophisticated approach uses the luminance function:

        GRAY = 0.2126 * R + 0.7152 * G + 0.0722 * B
which attempts to better model the contributions to brightness of the different colors.


function gray = rgb_to_gray ( rgb, equal )


The computer code and data files described and made available on this web page are distributed under the GNU LGPL license.


IMAGE_RGB_TO_GRAY is available in a MATLAB version.

Related Data and Programs:

  • IMAGE_BOUNDARY, a MATLAB library which reports the pixels which form the boundary between the black and white regions of a simple image.
  • IMAGE_CONTRAST, a MATLAB program which applies image processing techniques to increase the contrast in an image.

    IMAGE_DECIMATE, a MATLAB library which compresses an image by dropping the even rows and columns of data.

    IMAGE_DENOISE, a MATLAB program which applies image processing techniques to remove noise from an image.

    IMAGE_DOUBLE, a MATLAB library which doubles the height and width of an image by repeating each row and column.

    IMAGE_EDGE, a MATLAB program which demonstrates a simple technique for edge detection in an image.

    IMAGE_MATCH_GENETIC, a MATLAB program which tries to match a 256x256 JPEG image by blending 32 colored rectangles, using ideas from genetic algorithms, based on an example by Nick Berry.

    IMAGE_NOISE, MATLAB programs which add noise to an image.

    IMAGE_QUANTIZATION, a MATLAB library which demonstrates how the KMEANS algorithm can be used to reduce the number of colors or shades of gray in an image.


    IMAGE_THRESHOLD, a MATLAB library which creates a black and white version of a grayscale image by specifying a single threshold value; pixels below this value become black, and above this value they are white.


    MathWorks documentation for the Image Processing Toolbox is available at

    Source Code:

    Last revised on 04 February 2019.