Abstract: A method and system are provided for non-contact evaluation of a machined surface of a cast-metal part, including a vision-based porosity inspection station. A digital image of the machined surface is acquired, oriented and scaled to an XY coordinate system, filtered, and inverted. A second image is generated with known design surface features eliminated. Each pixel of the inverted digital image is XOR-compared with a corresponding pixel of the second image. Identified common surface features common to both images is analyzed statistically for conformance to a threshold. A defect is identified as any identified surface feature common to both images which exceeds the threshold. The system moves the part for further processing if a statistical analysis of defects indicates an acceptable component, and alternatively, removes the part from further processing if the analysis indicates a flawed component.