Image segmentation is one of the most important steps in computerized
systems for analyzing geographic map images. We present a segmentation
technique, based on fuzzy rules derived from the K-means clusters, th
at is aimed at achieving human-like performance, In this technique, th
e K-means clustering algorithm is first used to obtain mixed-class clu
sters of training examples, whose centers and variances are then used
to determine membership functions, Based on the derived membership fun
ctions, fuzzy rules are learned from the K-means cluster centers. In t
he map image segmentation, we make use of three features, difference i
ntensity, standard deviation, and a measure of the local contrast, to
classify each pixel to the foreground which consists of character and
line patterns, and to the background. A centroid defuzzification algor
ithm is adopted in the classification step. Experimental results on a
database of 22 gray-scale map images show that the technique achieves
good and reliable results, and is compared favorably with an adaptive
thresholding method By using K-means clustering, we can build a segmen
tation system of fewer rules that achieves a segmentation quality simi
lar to that of using the uniformly distributed triangular membership f
unctions with the fuzzy rules learned from all the training examples.