At present, automatic machines have gradually replaced human labor for improving both the stability and effectiveness of manufacturing operations. Five-axis CNC machine tools are commonly used for traditional surface milling machining. However, it is still necessary to manually reposition the work-piece for the CNC machine tools that enviably lowers position accuracy. As such, it is essential to develop an integrated fusion system that can scan any objects and conduct repair operations automatically. The primary purpose of this research is to integrate the stereo vision system into an existing industrial manipulator. With the proposed method and system, the position error can be reduced by avoiding moving the work-pieces during operations. Also, reconstructing the scan results from multiple views avoids the common blocking problem in vision. Finally, the distance of the manipulator path is optimized by the Hill Climbing algorithm, allowing to create a trajectory of the manipulator end-effector to reprocess the work-piece. In the future, this system can be implemented for automated optical inspection (AOI), such as pipeline maintenance, turbine engine maintenance, and automatic classification of defects.