Restoration of blurred images for surface roughness evaluation using machine vision

An attempt is made to evaluate the surface roughness of uniformly moving machined surface (grinding, milling) using machine vision technique. In the case of moving surfaces the images are likely to blur due to the relative motion between the CCD camera and the object to be captured. Hence the degraded image has to be restored by removing distortion due to motion before subsequent analysis. In this work, image blur due to motion is considered, in particular, blur that occurs when the motion is uniform at constant speed and in a fixed direction. The blurred image is modeled as a convolution between the original image and a known point spread function. The Richardson–Lucy Restoration algorithm, a method of estimation based on Bayes theorem has been used to correct the image. The algorithm is tested in simulations and in practical experiments. A simulation gives complete control over the setup and enables to test the performance of the algorithm. The quantification of roughness for restored images are performed using the statistical parameters such as spatial frequency, arithmetic average of gray level and standard deviation after pre-processing. An Artificial Neural Network (ANN) was used with these three statistical parameters as input to predict the vision roughness. Finally, vision roughness values calculated using the deblurred images are compared with the stylus roughness value. An analysis based on the comparison to understand the validity of the present approach of estimation of surface roughness based on the digitally processed images for implementation in practice, is presented in this paper.