Abstract: The color distribution of lead-free solder joint image, which is acquired by a 3-color (red, green, and blue) hemispherical LED arrays light resource and a 3-CCD color camera, can express the 3 dimensional shape of the solder joint. The region features, digital features and logical features are extracted from the solder joint image. Base on these features, an automatic optical inspection (AOI) algorithm for transistor lead-free solder joints is presented. The features obtained in the algorithm reflect the shape information of the lead-free solder joint properly, which can be applied to inspect the quality of the transistor lead-free solder joints in surface mounted technology (SMT). The experiment and analysis results show that the proposed method can effectively identify the lead-free solder joint defects of the transistor, such as surplus solder, lacking solder, no solder, pseudo solder, shift, bridging and component absent.