Inspection of a Machined Mold Metal Surface Adopting Scanned Contrast Image

Abstract

This study presents a proper methodology for the effective assessment and classification of mold surfaces on medium-and large measured shape items, such as those utilized for automobiles, TVs, and refrigerators. Although there are numerous kinds of exact surface investigation and estimation strategies, most are hard to apply at industrial sites or by completing robots because of speed, setup limitations, and robustness. An accurate and objective method of machined surface inspection has thus been needed. Specular surfaces pose difficulties for machine vision. In some applications, this may be further complicated by the presence of marks from a machining process. This study proposes a system that directly illuminates specular machined surfaces with a programmable array of high-power LEDs that allow the incident light's angle to be varied over a series of images and two main image processing techniques. First, both the reflected light distribution and the intensity of the captured near-field contrast image generated right adjacent to the reflected specular are used to determine the machined surface state. Besides, the presence of tool marks as the line light source scans clockwise or counterclockwise. The most significant advantage of near-field contrast image, as compared with other vision techniques, is the capturing of compassionate contrast image data. It makes it possible to distinguish the machined surface state by using the shape of the reflected light and the intensity of the image according to the tool mark, and the tool mark can also be detected. Second, the photometric stereo technique is adopted to detect surface scratches through the normal map that recovers the surface, which shows the entire surface at one time and can detect scratches. The proposed techniques show localized machined patterns and classify them with high accuracy through the statistical process. After the inspection process, the user has to measure the surface roughness and decide the surface-level. Respectively, Grey Level Co-occurrence Matrix(GLCM) and diffraction grating effect techniques were proposed to meet that process. Those techniques also are non-contact methods. One single image which is captured using specular highlight can be used The GLCM technique. When the metal surface is getting finishing, groove shapes are also changing. Based on those characteristics, the diffraction grating effect technique can be used for the metal surfaces.