Automatic System for Quality-Based Classification of Marble Textures

Juan Martinez-Alajarin(Polytech Univeristy of Cartagena, Spain), Jose D.Luis-Delgado (Univeristy of Murcia, Spain), Luis M.Tomas-Balibrea (Univeristy of Murcia, Spain)


Reviewer

Rajalaxmi Chandran (ID:1650849, UPI:rcha259@aucklanduni.ac.nz)


Reference

[1] V. Garceran-Hernandez, L.G. Garcia-Perez, P. Clemente-Perez, L.M Tomas-Balibrea and H.D. Puyosa-Pina, "Traditional and neural networks algorithms: Applications to the inspection of marble slabs", in IEEE Int.Conf. Systems, Man and Cyebernetics, Vancouver, BC, Canada, 1995, pp.3960-3965

[2]P. Clemente-Perez, V. Garceran-Hernandez, H. D. Puyosa-Pina, and L. M. Tomas-Balibrea, "Automatic system to quality control: Using artificial vision and neural nets for classification of marble slabs in production line", Proc. Int. Symp. Artificial Neural Networks, pp. 1995

[3]M. Deviren, M. K. Balci, U. M. Leloglu, and M. Severcan, "A feature extraction method for marble tile classification", Proc. 3rd Int. Conf. Computer Vision, Pattern Recognition, and Image Processing, pp. 2000 .

[4]J. Chang, G. Han, J. M. Valverde, N. C. Griswold, J. F. Duque-Carrillo, and E. Sanchez-Sinencio, "Cork quality classification system using a unified image processing and fuzzy-neural network methodology", IEEE Trans. Neural Netw., vol. 8, no. 4, pp. 1997

[5]P. R. Drake and M. S. Packianather, "A decision tree of neural networks for classifying images of wood veneer", Int. J. Adv. Manuf. Technol., vol. 14, pp. 1998.

[6]M. Unser, "Sum and difference histograms for texture classification", IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI-8, no. 1, pp. 1986 .


Keywords

Artificial Neural Networks, marble surfaces, pattern classification, principal component analysis, sum and difference histograms, texture analysis


Related Papers

Previous works [1],[2] describe analysis of the statistical properties of the marble slabs(variance, correlation between color channels),taking into account only color information without texture analysis. The paper [3] describes feature extraction method based on color segmentation for marble slabs classification. Other papers have developed automated visual inspection methods for other natural products like cork[4] and wood[5].

Summary

This paper presents a real time production line automatic system and algorithms for the classification of marble slabs into different groups, according to slabs quality. The categories (extra, commercial and low)are based on the texture(number of veins) of the marble. Fewer the veins, greater the quality of the slab.

The system consists of a mechatronic prototype(physical components for acquiring the marble slabs images in suitable lighting conditions) and computational algorithms(analysing the colour, texture of the surface and classifying them into their corresponding groups). Four colour spaces namely RGB, XYZ, YIQ and K-L are taken into consideration. Each colour space is a three dimensional gray level. Texture analysis is done based on the gray level dependence between adjacent pixel using the sum and difference histogram algorithm. Seven statistical features such as mean, variance, energy, correlation, entropy, contrast and homogeneity are then calculated from these histograms. In order to reduce the 21parameters(number of dimension*number of statistical feature=3*7) a feature extraction process is implemented using the principal component analysis. This gives a much smaller data(f) than the original without redundant information. The number of features is chosen such that their individual principal components contributes to over 0.5% of the total variance of the data set. Finally a neural network multilayer perceptron with backpropogation and adaptive learning rate is used to classify the marble slabs. The structure of the neural network consists of a three feedforward layers 1. The input layer with f neurons 2.the hidden layer 3.the output layer with 3 neurons (one for each category). The activation functions chosen are the hyperbolic tangent for the hidden layer and the linear function for the output layer. The parameters used where number of iterations=3000epochs, 1 cross validation, goal error=0.0001, maximum performance increase threshold=1.04, learning rate increasing ratio=1.05 and decreasing ratio=0.7.

The performance of the classifier was evaluated based on the percentage of correct classification, false positive and false negatives. The results showed that slabs of low quality were correctly classified than slabs of extra/commercial quality. Further RGB and XYZ had similar patter distribution and they both achieved poor results (only three quarters of the sample were correctly classified). In contrast, YIQ and KL achieved good results with high rates of correct classified patterns(above 98%). This is because YIQ and K-L provide texture and colour information in different channels, so the texture information needed to classify marble images according to their quality is extracted better than in the case of RGB and XYZ which do not provide such a clear separation between texture and colour. This automatic classification system increases the homogeneity of marbles supplied and reduces time, cost and discrepancies in the marble industry. This system can also be useful for other natural product like granites and wood.


Evaluation

On the whole this paper is well written and neatly structured. The authors have clearly defined their objectives and motivations. The experiment that they have conducted is intense and since their observations have been made based on a real time prototype, the outcomes seem to be reasonable and acceptable. The authors have done a good work in comparing different colour spaces and thereby providing the reader with interesting facts on the information contained by other spaces. The results (successful classification rate of 98.9%) show a very high performance compared with the traditional (manual) system. The neural network was able to converge faster and learn better because the PCA provided a good dataset without redundancy. Using the leave-one-out method as the database is small in order to train the neural network, seems to be a reliable method. However having a small dataset can lead to overfitting, and I am not very sure how far this method is suitable for other products like wood and granites. Also this paper does only cross validation and doesn’t do a separate secondary testing. I feel it would have been better if the system was tested on a set of unknown patterns to know how far it is successful rather than only stopping with cross validation.