Automated Surface Texture Classification of Inkjet and Photographic Media

Digital imaging and signal processing technologies offer new methods for inkjet and photographic media engineers and manufacturers, and those responsible for product quality control, to classify and characterize printing materials surface textures using new and more quantitative methods. This paper presents a collaborative project to systematically and semi-automatically characterize the surface texture of inkjet media. These methods have applications in product design and specification, and in manufacturing quality control. Surface texture is a critical feature in the manufacture, marketing and use of inkjet papers, especially those used for fine art printing. Raking light reveals texture through a stark rendering of highlights and shadows. Though raking light photomicrographs effectively document surface features of inkjet paper, the sheer number and diversity of textures prohibits efficient visual classification. This work provides evidence that automatic, computer-based classification of texture documented with raking light photomicrographs is feasible by demonstrating an encouraging degree of success sorting a set of 120 photomicrographs made from diverse samples of inkjet paper and canvas available in the market from 2000 through 2011. The samples used for this study were drawn from the Wilhelm Analog and Digital Color Print Materials Reference Collection. Using this dataset, four university teams applied different image processing strategies for automatic feature extraction and degree of similarity quantification. All four approaches were successful in detecting strong affinities among similarity groupings built into the dataset as well as identifying outliers. The creation and deployment of the algorithms was carried out by the teams without prior knowledge of the distributions of similarities and outliers. These results indicate that automatic classification of inkjet paper based on texture photomicrographs is feasible. To encourage the development of additional classification schemes, the 120 inkjet sample “training” dataset used in this work is available to other academic researchers at www.PaperTextureID.org