Simulations of lighting for an optimal defect detection by artificial vision

Summary form only given. Lighting which is an important side of quality control by artificial vision is often neglected. Scientists often have to spend time and make several experiments before finding a good solution. We realized simulations of viewing on smooth and rough metallic surfaces in order to optimize the choice of the lighting. These simulations take into account the shape of the surface, the shape and position of defects, the parameters and the position of the camera and the size and position of the light source. These simulations allow one to find the best solution concerning quality control of surfaces without having to make all the experiments.