subtracting two matrices in matlab, the negative values in result are substituted by zero

Question

I have two matrices in matlab,

> IRwindow =
> 
>   **183**  171  150  125  137
    138  167  184  173  152
    105  114  141  167  185  
    148  113  105  115  141  
    186  183  147  112  105
> 
> ILwindow =
> 
>   **201**  170  165  177  203
    181  174  167  169  189 
    154  150  156  168  181 
    187  175  158  131  144 
    173  186  183  167  141

I want to subtract these two matrices element-wise and get the result; for example for first element (183 - 201= -18 ) BUT the output for this element gives zero. the outcome result will be as below:

> IRwindow - ILwindow

 ans =

     **0**    1    0    0    0
     0    0   17    4    0
     0    0    0    0    4
     0    0    0    0    0    
     13    0    0    0    0

how could I keep the real results? without getting zero for negatives in my result-matrix

Answer 1

Run the following example code:

%# Create random matrices
X = randi(100, 5, 5);
Y = randi(100, 5, 5);

%# Convert to strictly non-negative format
X = uint8(X);
Y = uint8(Y);

%# Perform subtractions
A = X - Y;

%# Convert to double format
X = double(X);
Y = double(Y);

%# Perform subtraction
B = X - Y;

For a given sample run:

A =

    0   15   36    0    0
    0    0    0    0    3
    0    0    0   25    0
   13    0   15    0    0
    0   49    0    0   14

while:

B =

    -8    15    36    -4   -65
     0   -47   -45   -11     3
   -18   -17   -11    25   -52
    13   -53    15   -15    -1
   -35    49   -47    -8    14

You will notice that all the negative numbers in A have been replaced by 0, while the negative numbers in B are displayed correctly.

Stated simply: if you use a numerical format that is not able to store negative numbers, then Matlab truncates at 0. The solution is to convert to a format that is able to accomodate "real" numbers (or a close approximation thereof) such as double, or perhaps in your case one of the int formats may be more appropriate, such as int8, int16, int32 or int64.