Automated inspection system for metallic surfaces

An automated inspection system particularly adapted for detection and discrimination of surface irregularities of specularly reflecting and other materials, such as are employed in laminate chip carriers and printed circuit boards, includes an area scan image sensor allowing illumination sources to surround an area of a surface being inspected. The illumination source preferably provides either or both bright field and dark field illumination of the surface; developing generally complementary images of surface irregularities. A self-registering rules-driven process for developing inspection masks reduces alignment operations and improves performance. Image enhancement and morphological operations to detect surface irregularities are performed by digital signal processing, preferably using a dedicated vision processor. Masks screen potential defects to critical mounting and bonding surfaces accurately without requiring alignment of data or reference images to acquired images. Since potential defects are copied from acquired images and stored, verification of defects may be performed without further access to the inspected part and without removal of the part to another specialized apparatus, simplifying processing and increasing throughput and operator efficiency.