ASSIST: automatic system for surface inspection and sorting of tiles

“…Image processing (IP) techniques can be used for extracting information regarding the eroded areas in artworks, as indicated by previous works [6][7][8][9][10]. However, the investigation of such approaches is still in early stages.…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, methods for characterizing the stone structure and detecting regions of material loss were developed in the study of Moltedo et al [9] while Boukouvalas et al in Ref. [10] introduce computer vision techniques for the detection and classification of mineral veins encountered on ceramic tiles surfaces. Despite the fact that image analysis as a diagnostic tool, in artwork conservation is still in early stages, it has been recruited in many applications of Materials' Science and particularly for the determination of decay effects on aerospace materials.…”

Section: Introductionmentioning

confidence: 99%

Optical inspection for quantification of decay on stone surfaces

Kapsalas

Maravelaki-Kalaitzaki

Zervakis

et al. 2007

NDT & E International

View full text Add to dashboard Cite

This paper examines a novel approach of corrosion damage analysis based on image processing for quantitative and qualitative evaluation of degradation effects on stone surfaces. This methodology can be applied in situ in association with a variety of nondestructive monitoring schemes, and on images acquired from several imaging modalities, capturing from micro-to macro-scale characteristics. Our analysis methodology was evaluated on three non-destructive monitoring techniques of cleaned and not cleaned stone surfaces, namely on digital camera, reflectography and fiber optic microscope images. Further to validating the potential of the various imaging modalities, the paper also assesses the corrosion rate and the efficiency of the recruited cleaning methods. The derived results are in accordance with chemical analyses revealing the deterioration patterns of the studied surfaces. r

show abstract

“…Previously to the PCA transformation, the statistical parameters were normalized to achieve a new data set with mean and standard deviation equal to 0 and 1, respectively, with (11) where is the normalized feature, is the nonnormalized feature, and are respectively the mean and variance of is the number of features used to describe each pattern. After applying PCA, we selected a subset of features, where is the number of principal components that their individual contributions are equal or greater than 0.5% of the total variance of the data set.…”

Section: Feature Extractionmentioning

confidence: 99%

Automatic System for Quality-Based Classification of Marble Textures

Martínez‐Alajarín

Luis-Delgado

Tomas-Balibrea

2005

IEEE Trans. Syst., Man, Cybern. C

View full text Add to dashboard Cite

Abstract-In this paper, we present an automatic system and algorithms for the classification of marble slabs into different groups in real time in production line, according to slabs quality. The application of the system is aimed at the marble industry, in order to automate and improve the manual classification process of marble slabs carried out at present. The system consists of a mechatronic prototype, which houses all the required physical components for the acquisition of marble slabs images in suitable light conditions, and computational algorithms, which are used to analyze the color texture of the marble surfaces and classify them into their corresponding group. In order to evaluate the color representation influence on the image analysis, four color spaces have been tested: RGB, XYZ, YIQ, and K-L. After the texture analysis performed with the sum and difference histograms algorithm, a feature extraction process has been implemented with principal component analysis. Finally, a multilayer perceptron neural network trained with the backpropagation algorithm with adaptive learning rate is used to classify the marble slabs in three categories, according to their quality. The results (successful classification rate of 98.9%) show very high performance compared with the traditional (manual) system. Index Terms-Artificial neural networks, marble surfaces, pattern classification, principal component analysis, sum and difference histograms, texture analysis.

show abstract

ASSIST: automatic system for surface inspection and sorting of tiles

Cited by 41 publications

References 9 publications

Classification with color and texture: jointly or separately?

Classification with color and texture: jointly or separately?

Optical inspection for quantification of decay on stone surfaces

Automatic System for Quality-Based Classification of Marble Textures

Contact Info

Product

Resources

About