ABSTRACT
A microscope vision system to characterize a microscale surface via micro laser line projection is presented. The characterization is performed by means of surface descriptors, which include the root mean square, kurtosis, skewness, homogeneity, entropy, contrast, and correlation. These descriptors are computed from surface irregularities, which are retrieved by means of the micro laser line projection. The characterization is carried out by an optical microscope system on which a CCD camera and a 36 µm laser line are attached. Thus, the microscope vision system projects the micro laser line on the surface, and the CCD camera captures the line reflection, which provides the surface contour. The contour dimension is computed via Bezier networks by means of the micro laser line coordinates. Thus, the surface descriptors are computed by means of the surface contour to accomplish the characterization. The proposed characterization improves the accuracy of the optical microscope imaging systems, which characterize the microscale surface by means of the gray-level intensity. Thus, the capability of the characterization via micro laser line projection is established by means of the descriptors' accuracy. This contribution is corroborated by characterizing metal and paper surfaces.
