You could try difference matting.
I quote from A bayesian approach to digital matting
Under some circumstances, it might be possible to photograph
a foreground object against a known but non-constant
background. One simple approach for handling such a scene
is to take a difference between the photograph and the known
background and determine α to be 0 or 1 based on an arbitrary
threshold. This approach, known as difference matting (see,
e.g., [9]) is error prone and leads to “jagged” mattes. Smoothing
such mattes by blurring can help with the jaggedness but
does not generally compensate for gross errors.
Its a very simple algorithm, making it easy to implement and fast to run. You would not even need a trimap. It has the obvious accuracy problems mentioned in that paper, but given your picture is on a constant white background I doubt they would be an issue. Of course, if you wanted it to work on more complex backgrounds, you might have to come up with something else.
Also see Video background replacement without a blue screen