Currently one of the most time-consuming, costly and important phases of metal products production is the inspection process, in which automated optical inspection and image processing techniques are used to identify production defects. It is difficult to detect defects occurred on metallic surface, especially on smooth metallic surface. The major problems in inspection process involve complex reflections and noise. Based on 2-D Translation Invariant RI-Spline Wavelet Transform, a novel automated defects detection system is developed for smooth chrome-plated ABS resin surface. From encouraging experimental results, it is confirmed that it is possible for automated inspection system to accurately detect defects on smooth metallic surface. © 2008 IEEE.