This research proposes the solder inspection using the digital image processing technique and machine learning base with our machine vision prototype. There are five classes of classifying solder, including acceptable, short circuit, insufficient, blow hole and too much of solder. Automatic Optical Inspection (AOI) is used for the light source in the designed prototype and industrial camera which are installed on the mini-CNC. For the algorithm, this research applies the scanning line of binary image for detecting short circuit defection and the Random Forrest model for classifying other defects. According to the experiments, the system can classify the defect types for two classes (acceptable and unacceptable types) and five classes as 89% and 71% of accuracy, respectively.