Ck. Leung et Fk. Lam, MAXIMUM A-POSTERIORI SPATIAL PROBABILITY SEGMENTATION, IEE proceedings. Vision, image and signal processing, 144(3), 1997, pp. 161-167
An image segmentation algorithm that performs pixel-by-pixel segmentat
ion on an image with consideration of spatial information is described
. The spatial information is the joint grey level values of the pixel
to be segmented and its neighbouring pixels. The conditional probabili
ty that a pixel belongs to a particular class under the condition that
the spatial information has been observed is defined to be the a post
eriori spatial probability. A maximum a posteriori spatial probability
(MASP) segmentation algorithm is proposed to segment an image such th
at each pixel is segmented into a particular class when the a posterio
ri spatial probability is maximum. The proposed segmentation algorithm
is implemented in an iterative form. During the iteration, a series o
f intermediate segmented images are produced among which the one that
possesses the maximum amount of information in its spatial structure i
s chosen as the optimum segmented image. Results from segmenting synth
etic and practical images demonstrate that the MASP algorithm is capab
le of achieving better results when compared with other global thresho
lding methods.