“…We divide them into four classes depending on the way they check the neighborhood in the first scan in order to assign a provisional label and to determine label equivalences: pixel-based [3,7,9,10,22,23,24], run-based [8,11,14], block-based [5,6,12,13,19,21] and stripe-based [25]. According to the number of times of scanning an image for labeling, there are multi-scan [7,22], two-scan [5,6,8,9,10,12,13,19,21,23,24,25], one-and-a-half-scan [11,19] and one-scan [3,14] algorithms.…”