SSL: A Novel Image Hashing Technique Using SIFT Keypoints with Saliency Detection and LBP Feature Extraction against Combinatorial Manipulations

Algorithm 2

Texture features extraction algorithm.

Input: Geometric information of keypoints

Output: Texture features around keypoints

 (1) for   to   do

 (2)  Determine the th local region according to the geometric information of the th keypoint

 (3)  The pixels in the are denoted as

 (4)  // Calculate the LBP value [26]

 (5)  for   to   do

 (6)   Initialize a 8-bit vector

 (7)   Determine the neighbourhood pixels of , which are denoted as

 (8)   for   to   do

 (9)    if gray value of < gray value of   then

 (10)     

 (11)    else

 (12)     

 (13)    end if

 (14)   end for

 (15)   Assign the vector to

 (16)  end for

 (17)  Convert vectors to decimal numbers

 (18)  Divide 0 to 255 into 32 intervals:

 (19)  Count the number of vectors in each interval as

 (20)  for   to   do

 (21)   if    then

 (22)     

 (23)   else

 (24)     

 (25)   end if

 (26)  end for

 (27)   

 (28) end for

 (29) return  Texture features