Abstract: In order to extract relative data for quality control of wire harness terminals, an microscope image segmentation for wire harness terminals in chromaticity brightness space was proposed. This method divided the harness terminal by threshold method using the color distribution characteristic of the harness terminal micrograph.After analyzing the color distribution character, the microscopic image was first converted to brightness chromaticity space, and to insure the color homogenization within the image, the chromaticity vector was filtered. Then for the color channel, an optimal thresholding was determined for the two cases: the histogram with two peaks and one valley and the histogram with two peaks and two or more valleys. Finally, the mathematical morphology was performed on the binary image to produce the inner contour. The experimental results show that the circumference deviation of the inner diameter of the terminal is less than 0.1%, which indicates that the method can segment the harness terminal image completely and accurately.