B. Ramamoorthy, B. Dhanasekar
Assessment of surface roughness of moving surfaces
Computer vision with digital image processing is one of the widely used research tools and finds many applications in various branches of engineering. In a manufacturing environment, it is used for many applications such as inspection, recognition and navigation. In this work, the objective is to evaluate the surface roughness of uniformly moving machined surface using machine vision technique. Basically, the problem in estimating the roughness of moving surfaces based on their images is blurring. It is important that blurred image has to be corrected for its distortion and restored before any further analysis. This image restoration needs to be resolved before proceeding to the evaluation of roughness of such surfaces. In this work, geometric distortion removal technique is used for image restoration. Then, the quantification of surface roughness using these improved quality images is carried out using various parameters such as spatial frequency, arithmetic mean value and standard deviation. Group method of data handling (GMDH) technique was used to compare the optical roughness parameters calculated using the digital surface images and the widely used mechanical stylus instrument values. An analysis based on the comparison to understand the validity of the present approach of estimation of surface finish based on the digitally processed images for implementation in practice, is presented in this paper.