Function interactive_maxflow2d

examples/demo_maxflow.py:26–44

maxflow for 2D interactive image segmentation. Only binary segmentation is supported. input parameters: I : a numpy array of shape [H, W], or [H, W, C] where C should be 3. type of I should be np.float32 P : a probability map of shape [H, W, L], where L=

(I, P, S, param)

    return lab 

def interactive_maxflow2d(I, P, S, param):
    """
    maxflow for 2D interactive image segmentation. Only binary segmentation is supported.
    input parameters:
        I    : a numpy array of shape [H, W], or [H, W, C] where C should be 3.
               type of I should be np.float32
        P    : a probability map of shape [H, W, L], where L==2 is the number of classes
               type of P should be np.float32
        S    : a numpy array showing user interactions, shape should be [H, W, L], where L == 2
               type of S should be np.uint8
        param: a tuple giving parameters of CRF (lambda, sigma), where
                lambda :   weight of smooth term, e.g. 20.0
                sigma  :   std intensity value, e.g., 10
                
    output parameters:
        lab  : a numpy array of shape [H, W], where pixel values represent class indices. 
    """
    lab = maxflow.interactive_maxflow2d(I, P, S, param)
    return lab 

def maxflow3d(I, P, param):
    """