Image processing for classification and segmentation of rock samples

1. A method for processing an image, said image representing a rock sample, wherein the method comprises:

a) receiving said image;

for each current threshold value in a plurality of threshold values:

b) determining a threshold image, the threshold image having pixels associated with a first color value or a second color value, the determination of the threshold image being based on the received image and the current threshold;

c) for each current connected set of pixels associated with the first color value in the threshold image, determining a connected size of said current connected set of pixels;

d) determining at least one number of connected sets of pixels associated with the first color value for which the connected size is identical;

e) creating a plurality of histograms based on the determined at least one number of connected sets of pixels associated with a color value for which the connected size is identical;

f) creating a texture model from the plurality of histograms; and

g) classifying the rock sample based on the texture model.

2. The method according to claim 1 , wherein in the determination of step d), each set in said sets of pixels have a connected size higher than a predetermined size; and wherein, the method further comprises:

h) determining a target threshold value based on the determined numbers of connected sets of pixels having a connected size higher than the predetermined size.

3. The method according to claim 2 , wherein the determination of the target threshold value is based on a derivative of the determined numbers of connected sets of pixels having a connected size higher than the predetermined size.

4. The method according to claim 1 , wherein, the received image comprising pixels associated with a set of pixel values, the method further comprises:

h) for each current color value in the set of pixel values, determining a number of pixels in the pixels of the received image associated with said current color value; wherein for each current threshold value in a plurality of threshold values:

c′) for each current connected set of pixels associated with the second color value in the threshold image, determining a connected size of said current connected set of pixels;

d′) determining at least one number of connected sets of pixels associated with the second color value for which the connected size is identical.

5. A non-transitory computer readable storage medium, having stored thereon a computer program comprising program instructions, the computer program being loadable into a data-processing device and adapted to cause the data-processing device to carry out the steps of claim 1 when the computer program is run by the data-processing device.

6. A device for processing an image, said image representing a rock sample, wherein the device comprises:

an input interface for receiving said image;

a circuit for, for each current threshold value in a plurality of threshold values, said circuit

determining a threshold image, the threshold image having pixels associated with a first color value or a second color value, the determination of the threshold image being based on the received image and the current threshold; for each current connected set of pixels associated with the first color value in the threshold image, determining a connected size of said current connected set of pixels; and

determining at least one number of connected sets of pixels associated with the first color value for which the connected size is identical;

creating a plurality of histograms based on the determined at least one number of connected sets of pixels associated with a color value for which the connected size is identical;

creating a texture model from the plurality of histograms; and

classifying the rock sample based on the texture model.