Image processing as a tool for assessment and analysis of blue stain discolouration of coated wood

Wood used outdoors needs protection against physical and biological factors. Solvent-borne and the more recently developed water-borne coatings with low fungicide content need thorough testing for their blue stain resistance. Especially, water-borne systems have been brought into focus due to their environmental-friendly profile. Conventional tests like the European Standard EN 152 use a subjective rating scale for blue stain assessment. On the one hand, such a scale gives a value of depreciation of a surface degraded by blue stain fungi, on the other the estimation is a subjective rating of fungal disfigurement and makes comparison difficult. For this reason other techniques have been sought and tested for their usefulness in the assessment and quantification of surface and interior fungal discolouration of coated wood. Different image-processing algorithms, such as neural networks, and a subjective rating scale are compared. Furthermore, three-dimensional reconstruction of the fungal development in wood is explored as a tool for in-depth analysis of the growth in the wood substrate.

[1]  Ming-Te Tsai,et al.  Expert system of a crude oil distillation unit for process optimization using neural networks , 2004, Expert Syst. Appl..

[2]  Philip A. Araman,et al.  Automated hardwood lumber grading utilizing a multiple sensor machine vision technology , 2003 .

[3]  J. Zeyer,et al.  Quantification of fungal hyphae in leaves of deciduous trees by automated image analysis , 1995, Applied and environmental microbiology.

[4]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[5]  Henk J. Busscher,et al.  Application of an artificial neural network in the enumeration of yeasts and bacteria adhering to solid substrata , 1998 .

[6]  P. Cox,et al.  Image analysis of the morphology of filamentous micro-organisms. , 1998, Microbiology.

[7]  Formulating high solids coatings : The solution to VOC problem , 1996 .

[8]  V. Rijckaert,et al.  Quantitative assessment of the penetration of water-borne and solvent-borne wood coatings in Scots pine sapwood , 2001, Holz als Roh- und Werkstoff.

[9]  Frieke Vancoillie.  Design and application of artificial neural networks for digital image classification of tropical savanna vegetation , 2003 .

[10]  Luh-Maan Chang,et al.  Intelligent Model for Constructed Facilities Surface Assessment , 2000 .

[11]  M. Meijer.  Review on the durability of exterior wood coatings with reduced VOC-content , 2001 .

[12]  Heinz Liebscher.  Economic solutions for compliance to the new European VOC Directive , 2000 .

[13]  R. Spear,et al.  Fluorescent labels, confocal microscopy, and quantitative image analysis in study of fungal biology. , 1999, Methods in enzymology.

[14]  H. T. M. 0 Voort,et al.  Three‐dimensional visualization methods for confocal microscopy , 1989, Journal of microscopy.

[15]  R. Funada,et al.  THREE-DIMENSIONAL IMAGING AND ANALYSIS OF DIFFERENTIATING SECONDARY XYLEM BY CONFOCAL MICROSCOPY , 2003 .

[16]  S. Dickson,et al.  Visualisation of mycorrhizal fungal structures and quantification of their surface area and volume using laser scanning confocal microscopy , 1999, Mycorrhiza.

[17]  David G. Stork,et al.  Computer Manual in MATLAB to Accompany Pattern Classification, Second Edition , 2004 .

[18]  S. Harrison,et al.  Morphological characterisation of yeast colony growth on solid media using image processing , 1998 .

[19]  Avinash C. Kak,et al.  Principles of computerized tomographic imaging , 2001, Classics in applied mathematics.

[20]  J. Bjurman.  Fungal and microbial activity in external woodenpanels as determined by finish, exposure, and constructiontechniques , 1999 .

[21]  P. Pfeifer,et al.  Microbial growth patterns described by fractal geometry , 1990, Journal of bacteriology.

[22]  T. Furuno,et al.  The fractal estimation of wood color variation by the triangular prism surface area method , 2002, Wood Science and Technology.

[23]  K. Clarke.  Computation of the fractal dimension of topographic surfaces using the triangular prism surface area method , 1985 .

[24]  R. Spear,et al.  Quantitative fluorescence in situ hybridization of Aureobasidium pullulans on microscope slides and leaf surfaces , 1997, Applied and environmental microbiology.

[25]  Els Ducheyne,et al.  Multiple objective forest management using GIS and genetic optimisation techniques , 2003 .

[26]  J. Crawford,et al.  Quantification of the in situ distribution of soil bacteria by large‐scale imaging of thin sections of undisturbed soil , 2001 .

[27]  T. M. Lillesand,et al.  Remote Sensing and Image Interpretation , 1980 .

[28]  S. Bardage.  Colonization of painted wood by blue stain fungi , 1997 .

[29]  Lynne Boddy,et al.  Fractal analysis in studies of mycelium in soil , 1999 .

[30]  M. Osumi,et al.  Application of a FIB-STEM system for 3D observation of a resin-embedded yeast cell. , 2004, Journal of Electron Microscopy.

[31]  Po-Han Chen,et al.  INTELLIGENT STEEL BRIDGE COATING ASSESSMENT USING NEURO-FUZZY RECOGNITION APPROACH , 2002 .

[32]  T. Furuno,et al.  The Fractal Evaluation of Wood Texture by the Triangular Prism Surface Area Method , 2007 .

[33]  David G. Stork,et al.  Pattern Classification , 1973 .

[34]  J. Campbell.  Introduction to remote sensing , 1987 .

[35]  C. Björdal,et al.  Three-dimensional visualisation of bacterial decay in individual tracheids of Pinus sylvestris , 2005 .

[36]  C. Gaylarde,et al.  Fungal colonization and succession on newly painted buildings and the effect of biocide. , 2002, FEMS microbiology ecology.

[37]  Edmund T. Rolls,et al.  Introduction to Connectionist Modelling of Cognitive Processes , 1998 .