The Tiling Suite

The algorithm used in MicroTiling to choose the best tiles to build the single level image is based on the Grey Level Co-occurrence Matrix Contrast calculation of each correspondent tile in the different z-stack levels. The tile with the highest contrast is selected and used to build the new deep focus image. The contrast calculation takes in account and can vary in accordance with the gray level image chosen (Red or Green or Blue channel in a RGB image) and the chosen offset (i.e. displacement vector).

A GLCM can be defined as “A two dimensional histogram of grey levels for pair of pixels, which are separated by a fixed spatial relationship”. GLCM of an image is computed using a displacement vector (offset) defined as the distance to the next adjacent neighbour (usually equal to one) and rotational angles (0°, 45°, 90°, 135°).

Many publications are available explaining GLCM and the possible statistical inferences that can be calculated on it. Two simple and clear publications are attached to this manual (1-GLCM.pdf and 2-GLCM). An excellent definition and example can be found in:

 

Co-Occurrence Matrix and Its Statistical Features as an Approach for Identification Of Phase Transitions Of Mesogens by C.Nageswara Rao et al.

International Journal of Innovative Research in Science, Engineering and Technology

Vol. 2, Issue 9, September 2013

(available on line at www.ijirset.com/upload/september/44_Co-Occurrence.pdf)

 

 

The above-mentioned algorithm used in MicroTiling is derived from the following equation calculated on the GLCM of each tile:

​

Contrast

​