To improve the surface properties of fiber-reinforced polymer composites, one method is to employ thermal spray to apply a coating on the composite. For this purpose, it uses a metal mesh serving as an anchor between the composite and the coating to increase adhesion. However, the composite manufacturing covers the metal mesh with resin, and getting an acceptable coating is only possible through an optimum exposure of the metal mesh by sand blasting prior to coating. Therefore, this study aims to develop a computer vision and image processing method to inspect the parts and provide the operator with feedback. Initially, this approach takes the images from a single-view microscope as the inputs, and then it classifies the images into two regions of resin and metal mesh using the Otsu’s adaptive thresholding. Next, it segments the resin areas into distinct connected clusters, and it makes a histogram based on the clusters’ size. Finally, the distribution of the histogram can determine the status of the surface preparation. The state-of-the-art has only examined the sand-blasted composites manually, requiring expertise and experience. This research presents a deterministic method to automate the inspection process efficiently with an inexpensive portable digital microscope. This method is practical, especially when there is a lack of standardized data for machine learning. The experimental results show that the method can get different histograms for various samples, and it can distinguish whether a sample is under-blasted, proper-blasted, or over-blasted successfully. This study also has applications to various fields of manufacturing for defect detection and closed-loop control.