In this paper we present an Automatic Optical Inspection system to diagnose Printed Circuit Board... more In this paper we present an Automatic Optical Inspection system to diagnose Printed Circuit Boards mounted in Surface Mounting Technology. The diagnosis task is handled as a classification problem with a neural network approach. The Printed Circuit Board tested images are preprocessed by means of several methods to reduce the amount of data to feed to the neural networks. We compare the results obtained in the diagnosis for all methods. The Automatic Optical Inspection system seems to be a good solution in an industrial application because of the low cost, very fast diagnosis and easiness to set-up and handle.
An investigation of the imaging of spheres can aid in understanding details of the surface profil... more An investigation of the imaging of spheres can aid in understanding details of the surface profiling method of confocal microscopy. The use of semicircular masks to eliminate artifacts in confocal profiling is investigated experimentally. A theoretical treatment of image formation for a spherical object in reflection confocal microscopy is presented. For large spheres a simple approximate theory is described and is shown to be equivalent to application of the Kirchhoff theory for surface scattering.
An investigation of the imaging of spheres can aid in understanding details of the surface profil... more An investigation of the imaging of spheres can aid in understanding details of the surface profiling method of confocal microscopy. The use of semicircular masks to eliminate artifacts in confocal profiling is investigated experimentally. A theoretical treatment of image formation for a spherical object in reflection confocal microscopy is presented. For large spheres a simple approximate theory is described and is shown to be equivalent to application of the Kirchhoff theory for surface scattering.
In this paper we present an Automatic Optical Inspection system to diagnose Printed Circuit Board... more In this paper we present an Automatic Optical Inspection system to diagnose Printed Circuit Boards mounted in Surface Mounting Technology. The diagnosis task is handled as a classification problem with a neural network approach. The Printed Circuit Board tested images are preprocessed by means of several methods to reduce the amount of data to feed to the neural networks. We compare the results obtained in the diagnosis for all methods. The Automatic Optical Inspection system seems to be a good solution in an industrial application because of the low cost, very fast diagnosis and easiness to set-up and handle.
An investigation of the imaging of spheres can aid in understanding details of the surface profil... more An investigation of the imaging of spheres can aid in understanding details of the surface profiling method of confocal microscopy. The use of semicircular masks to eliminate artifacts in confocal profiling is investigated experimentally. A theoretical treatment of image formation for a spherical object in reflection confocal microscopy is presented. For large spheres a simple approximate theory is described and is shown to be equivalent to application of the Kirchhoff theory for surface scattering.
An investigation of the imaging of spheres can aid in understanding details of the surface profil... more An investigation of the imaging of spheres can aid in understanding details of the surface profiling method of confocal microscopy. The use of semicircular masks to eliminate artifacts in confocal profiling is investigated experimentally. A theoretical treatment of image formation for a spherical object in reflection confocal microscopy is presented. For large spheres a simple approximate theory is described and is shown to be equivalent to application of the Kirchhoff theory for surface scattering.
Uploads