We propose a new automatic image segmentation method. Color edges in an ima
ge are first obtained automatically by combining an improved isotropic edge
detector and a fast entropic thresholding technique. After the obtained co
lor edges have provided the major geometric structures in an image, the cen
troids between these adjacent edge regions are taken as the initial seeds f
or seeded region growing (SRG). These seeds are then replaced by the centro
ids of the generated homogeneous image regions by incorporating the require
d additional pixels step by step. Moreover, the results of color-edge extra
ction and SRG are integrated to provide homogeneous image regions with accu
rate and closed boundaries. We also discuss the application of our image se
gmentation method to automatic face detection. Furthermore, semantic human
objects are generated by a seeded region aggregation procedure which takes
the detected faces as object seeds.