An automatic visual system for marble tile classification

Abstract

The international market of ornamental stone has seen the use of materials quarrying from East Europe, Africa, Asia and South America, characterized by a low cost of labour. This event has embittered the competition in this ®eld. Hence, it becomes fundamental to produce machined products of high quality in a more e cient way. This work aims to design and ful®l a prototype to automatically classify the Royal Perlato tiles of Coreno. It is based on arti®cial vision. The implemented hardware visual system is cheap because it is made up of components readily available and is easily obtainable by small and medium ornamental stone businesses. The developed software algorithm is based on a multifactor analysis of variance and a quadratic discriminant analysis. The experimental results show that the developed hardware and software system permits all the tiles of Royal Perlato of Coreno to be classi®ed properly. Moreover, the developed system not only improves the e ciency of the selection but also reduces the controversies between the manufacturer and buyer, making tile classi®cation more selective and increasing the number of qualitative classes taken into consideration. Finally, it allows the duplication on the selection line without altering data dispersion.

An Investigation of Colour Properties of Orosei Limestones (Italy) by Using Computer Program

“…There have also been several image processing studies in the natural stone industry. Some of these have been about the colour identification of marble products [18] and most have discussed the classification of the final products or the texture recognition of pre-products of natural stones [19][20][21][22][23].…”

Sorting Speckled Granites (Nehbandan) and Measuring Their Surface Veining using Machine Vision

“…Topalova et al (2010) [26] proposed a method for grading surface tiles based on gray-scale histograms, reporting an excellent accuracy for a grading process that included four classes and five brightness variations. Similar texture features were also incorporated in the study by Carrino et al (2002) [13] used different Gabor filter banks to classify granites. Classification of marbles was also addressed using the scale-space [28] and wavelets [29].…”

“…[27] on the automated classification of the Rosa Perlato of Coreno. Other texture descriptors have also been successfully used in the past.…”

A computational methodology for the creation of photorealistic mosaic using breccia tiles

“…[5]. Levha yüzeylerinin dalgacık dönüşümü, çoklu faktör ve karesel diskriminant analizleri gibi metotlarla incelenmesi, bazı bölgesel mermerler için gerçekleştirilmiştir [6]- [8]. Bahsedilen sınıflandırma ile ilgili algoritma çalışmaları, levhaların piyasa fiyatlarını doğrudan belirleyen, renk, homojenlik ve doku gibi yüzey özellikleri kullanarak gruplandırmayı hedeflemektedirler.…”