0

GLCM considers the relation between two pixels at a time, called the reference and the neighbour pixel. Based on the selection of the neighbour pixel generally 4 different Gray Level Co-occurrence Matrices (GLCM) can be calculated for an image.

Selection of the neighbour pixel is as follows.

reference pixel  |  neighbour pixel

(x,y)              (x+1, y)   the pixel to its right
(x,y)              (x+1, y+1) the pixel to its right and above
(x,y)              (x, y+1)   the pixel above
(x,y)              (x-1, y+1) the pixel to its left and above

A good, in-detail explanation about GLCM is available here (Original link).

My question is, is it required to consider all 3 intensity values of an image pixel when calculating Gray Level Co-occurrence Matrices (GLCM) of a "gray scale image"?

As an example consider an image with 2 pixels

------------------------------------------------------------------------------------
|               [pixel1]                 |                [pixel2]                 |
|            /      |     \              |             /      |     \              |
| [intensity1] [intensity2] [intensity3] | [intensity4] [intensity5] [intensity6]  |
------------------------------------------------------------------------------------

When calculating the GLCM of a gray scale image is it required to take into account all 3 intensity values of a pixel?

E.g- When the reference pixel is (x,y) and its neighbour pixel is (x+1, y) the pixel to its right

Is it required to take into account the occurrences of intensity levels individually as follows?

 [intensity1] & [intensity2]
 [intensity2] & [intensity3]
 [intensity3] & [intensity4]
 [intensity4] & [intensity5]
 [intensity5] & [intensity6]

Or can I just take into account one intensity value from each pixel, assuming all 3 intensity values of a pixel is same as follows?

[intensity1] & [intensity4]

Which is the correct method? Is it applicable for all 4 neighbours?

biziclop
  • 14,466
  • 3
  • 49
  • 65
user3347358
  • 13
  • 1
  • 6
  • 1
    By definition the Red=Green=Blue intensity in a greyscale image, so just do any one. – Mark Setchell Aug 30 '14 at 19:06
  • @MarkSetchell Thanks for the reply, wont the results vary under each method? which is the most recommended method? – user3347358 Aug 30 '14 at 19:12
  • It is my understanding that the point of using a greyscale image is to reduce the complexity by only needing to calculate for a single channel. I may be wrong - we shall see if anyone else knows better. – Mark Setchell Aug 30 '14 at 19:33
  • For a colour image, convert it to grayscale, then calculate the co-occurrence matrix. That's if your image is colour. If your image is purely grayscale, then using any channel is sufficient as all components in each channel are the same. – rayryeng Sep 06 '14 at 18:14

0 Answers0