Automatic classification of granite tiles through colour and texture features

This paper is about the development of an expert system for automatic classification of granite tiles through computer vision. We discuss issues and possible solutions related to image acquisition, robustness against noise factors, extraction of visual features and classification, with particular focus on the last two. In the experiments we compare the performance of different visual features and classifiers over a set of 12 granite classes. The results show that classification based on colour and texture is highly effective and outperforms previous methods based on textural features alone. As for the classifiers, Support Vector Machines show to be superior to the others, provided that the governing parameters are tuned properly.

Highlights

We discuss the development of an expert system for automatic classification of granite tiles. We propose new approaches to granite classification based on combined colour and texture analysis. We evaluate the performance of different visual descriptors and classifiers. Combination of colour and texture features proves highly effective in discriminating granite appearance. Classification based on SVM support vector classification outperforms the other methods.The quality control process in stone industry is a challenging problem to deal with nowadays. Due to the similar visual appearance of different rocks with the same mineralogical content, economical losses can happen in industry if clients cannot recognize properly the rocks delivered as the ones initially purchased. In this paper, we go toward the automation of rock-quality assessment in different image resolutions by proposing the first data-driven technique applied to granite tiles classification. Our approach understands intrinsic patterns in small image patches through the use of Convolutional Neural Networks tailored for this problem. Experiments comparing the proposed approach to texture descriptors in a well-known dataset show the effectiveness of the proposed method and its suitability for applications in some uncontrolled conditions, such as classifying granite slab under different image resolutions.Unlike ceramic tiles, granite grey tiles have limited variation. Granite tiles, which were made from natural stones, tend to have irregular patterns with a limited choice of colors and motifs. In addition, granite tiles only have two kinds of finishing.In recent years, the manual recognition and classification of natural stones have become a multifaceted challenge due to the similar patterns and visual appearance. Therefore in the current study, a robust and more effective system has been developed for an automatic classification of natural stones i.e. black granite wall tiles using the Convolutional Neural Networks (CNNs). This approach is based on fine-tuning pre-trained networks such as AlexNet and VGGNet. The techniques of data augmentation such as reflection Gorgeous and tough, granite makes a great countertop material. Unfortunately, greatness has its price: Granite slab countertops start at about $100 per sq. ft. But you can have granite countertops for half that cost (or even less) by using granite tile instead of professionally installed granite slabs. Budget-conscious builders and homeowners have done this for decades—and now there are red granite floor tiles designed especially for countertops.