6533b7d0fe1ef96bd125a9b6

RESEARCH PRODUCT

Digitization and characterization of local reflectance of complex surfaces for visual inspection

subject

description

Mastering the visual perception of the surfaces of manufactured products is a central issue for industry. However, in industry, the quality of surfaces is often assessed by human inspectors. Only a few specific cases use an instrumental or photometric approach. Among the photometric approaches, one of them is experiencing significant growth: Reflectance Transformation Imaging (RTI). The RTI makes it possible to obtain a reduced and simplified estimate of the Bidirectional Reflectance Distribution Function (BRDF) and an estimate of the geometry of the surface. However, this technique has limitations in terms of data acquisition and processing. The objective is therefore to correct some of these limits in order to improve the RTI and, consequently, the visual quality control of surface conditions in industry.One of these limitations is the large amount of data, complex to analyze, obtained with an RTI acquisition. We propose a methodology to characterize the appearance of surfaces from RTI measurements. The characterization of surface states is based on the use of appearance, statistical and geometric descriptors. From the descriptors extracted from the RTI acquisitions, we propose a method to estimate the multi-scale and multi-level visual salience in each pixel and thus make it possible to discriminate surface anomalies. A methodology, to segment RTI data using salience, is then applied to an application case. The method makes it possible to determine the most relevant descriptors for segmentation. Distance calculation is extended to RTI acquisitions in order to compare surface states. These methods are based on the Mahalanobis distance using the descriptors.Another limitation of RTI is measurement bias. Some descriptors are invariant to these measurement biases except that of the exposure time for which no descriptor is insensitive. We then propose to use High Dynamic Range (HDR) coupled with RTI (HD-RTI). The coupling is done in such a way as to take into account the specificities of each of the techniques in order to optimize the RTI acquisition time while allowing the full measurement of the Dynamics of the scene in each angular position of the light source. With HD-RTI stereo-photometric data, we can virtually reconstruct the scene by simulating an arbitrary exposure time, but also better characterize and therefore discriminate surface anomalies.