Machine Vision System for Automated Visual Inspection of Tile’s Surface Quality

Visual inspection of material’s surface quality is an important quality determining step in industries dealing with surfaces as the prime feature of their product, for instance, plywood, metal, tiles, glass ware and many more. Primarily surfaces are inspected for smoothness and roughness quality. However, defects may arise in form of cracks, spots, holes, presence of excess material, flatness and shape of edges etc. A human inspection system can effectively challenge this task to a good accuracy. But with human system, there is an issue of fatigueness that arises over a long period of time. And in that case, the quality of inspection is biased towards either side. To avoid this biased inspection, a novel vision system based on image processing is proposed here. In the presented paper work, a case of tile industry has been tested out. The tiles surfaces are very sensitive to any of the defects as mentioned above. And a small defect on surface of a tile may lead to huge loss to the manufacturer. An automated visual inspection system inspects the tile’s surface for any crack, hole, spot, presence of any foreign material or excess material. The objective of the proposed paper work is to develop an automatic machine vision system that could visually inspect the tile’s surface to determine the quality as per the set standards. The work involves the extraction of defects from the surface using image processing techniques that are based on statistical properties of the defects observed on surfaces.