[Retracted] A Pavement Crack Detection Method Based on Multiscale Attention and HFS

Algorithm 1.

	Input: crack binarized image
	Output: the crack binarized image that is the same as or within a certain similarity threshold range
(1)	The feature database is initialised.
(2)	//Store the hesitant fuzzy set of images and
(3)	for // is the number of crack images in
(4)	//Hesitating fuzzy attribute index
(5)
(6)
(7)	//Calculate the generalized hesitation fuzzy distance
(8)	//Similarity of hesitating fuzzy sets
(9)	//Convert the calculation of the similarity between the crack images to the calculation of the similarity between the set of hesitation modes
(10)	Add to table
(11)	if then// is the similarity threshold set by the user
(12)	return image //Return the crack image that meets the conditions
(13)	end if
(14)	end for