Abstract: This paper proposes a novel method to realize accurate seam tracking of butt micro-gap (less than 0.1mm) joint during laser welding based on the magneto-optical color images. Images of weld seam zone are captured by a magneto-optical sensor, and grayscale distribution of the weld seam magneto-optical images in the RGB(Red, Green, Blue)and HSV(Hue, Saturation, Value) color space are analyzed. The grayscale map of component of the RGB figure is extracted, and weld seam edge is determined based on the threshold derived from the grayscale distribution curve of each component. Also, the outline of weld seam transitional zone is obtained by integrating weld seam edges of the three components. The histogram of each HSV component is analyzed to determine the threshold and then the synthetic seam transition zone segmentation is obtained. Experimental results show that the proposed method can effectively detect micro-gap weld seam which is generally hard to distinguish by human eyes.