Abstract: An improved CHNN method which is called Weighted CHNN (WCHNN) is constructed.This method puts n weights on the n connections of each sub-network of CHNN.They can be determined by training the WCHNN network using local search and optimization methods with the designated sample input and output images.Thus WCHNN gains the abilities of tuning the sensitivity of edge detection according to different sample images and correcting the too-wide edges detected by CHNN, while retaining the advantages of CHNN.Experimental results show that the trained WCHNN network can get lower error rate while processing the images which noise rate is similar to sample input images than CHNN, and it can also detect those methods missed by CHNN.