A new automatic algorithm for line generalization based on key point detection is presented in this paper.An adaptive threshold corner detector is used to detect all corner points

from which key points are selected.To keep the shape characteristic of lines

all key points must be reserved.For the segmented lines at these key points

each sub-line is generalized with the Li-Openshaw algorithm.Compared with conventional algorithms

the results of our experiments show that the shape of lines is better preserved and the positions are more accurate.