Automated defect detection methods allow the forest products industry to better utilize its resources by improving yield, reducing labor costs, and allowing minimum lumber grades to be utilized more intelligently. While many methods have been proposed on what sensors and processing methods should be used to detect and classify wood features, there exists a lack of understanding of what parameters are best used to differentiate wood features. The goal of this research is to demonstrate that by having an in depth knowledge of how wood features are represented by color, shape, and density parameters, more accurate classification methods can be developed. This goal was achieved through describing wood features using parameters derived from color and x-ray images and characterizing the variability and interrelationships of these parameters, determining the effect of resolution and species on these relationships, and determining the importance and contribution of each parameter for differentiating between wood features using a statistical prediction model relating feature types to the parameters. Knots, bark pockets, stain and mineral streak, and clearwood were selected as features from red oak, (Quercus rubra), hard maple, (Acer saccharum), and Eastern white pine (Pinus stobus). Color (RGB and HSI), shape (eccentricity and roundness), and density (gray-scale values) parameters were measured. Parameters were measured for each wood feature from images and parameter differences between feature types were tested using analysis of variance techniques (ANOVA) and Tukey's pairwise comparisons with a=0.05. Discriminant classifiers were then developed to demonstrate that an in-depth knowledge of how parameters relate between feature types could be used to develop the best possible classification methods. Classifiers developed using the knowledge of parameter relationships were found to provide higher classification accuracies for all features and species than those which used all parameters and where variable selection procedures had been used< It was determined that differences exist between all feature types and can be characterized and classified based on two color means, one color standard deviation, the mean density, and a shape parameter. A reduction in image resolution was determined not to affect the relationship of parameters. For different species, the intensity of features was to be related to the intensity of clearwood. The ability to explain classification errors using the knowledge gained about feature parameters was demonstrated. This knowledge could be used to reduce future classification errors. It was determined that combining parameters collected using multiple sensors increases classification accuracy of wood features. Shape and density were found not to provide good classification variables for features when used separately, but were found to contribute to classification of features when used with other parameters. The ability to differentiate between the feature types examined in this research was found be equal when using the RGB or HSI colorspace. / Ph. D.

No description available.

Diss. (sammanfattning). Umeå : Sveriges lantbruksuniv., 2003. / Härtill 5 uppsatser.

Diss. (sammanfattning) Uppsala : Sveriges lantbruksuniv. / Härtill 3 uppsatser.

Diss. Uppsala : Sveriges lantbruksuniv., 2000.

Thesis (MSc)--Stellenbosch University, 2015. / ENGLISH ABSTRACT: This study aimed to classify wood from trees that were exposed to forest fires with regards to their end use. Exposure to high temperatures over time is known to degrade wood in various ways. This degradation could limit the end use by altering mechanical, chemical and physical properties, leading to difficulty in processing or failing to meet required specifications for various grades. In this study wood from Pinus radiata trees that were exposed to forest fires of different levels of heat intensity was analysed with regards to its anatomical and physical changes. Trees were visually classified into three classes of burn severity. Moisture content measurements were taken from 135 standing trees, divided among the three classes. 30 trees, 10 from each of the three classes, were sampled and used for CT analysis. Samples were taken to include growth from before and after the fire. Two samples were taken from each tree, one from the charred and one from the uncharred side. The CT data was analysed and used to measure properties like growth ring width, cell wall thickness, lumen diameter and cell wall density. The data was used to compare properties from the charred and uncharred sides within a given year, as well as compare properties between years. The study showed that there were significant differences in the MC between the burnt and unburnt sides of trees from classes 2 and 3. The difference between the MC measurements on the burnt sides of three classes differed significantly from each other. Lightness measurements were taken on samples from classes 2 and 3. These samples showed no significant difference between the burnt and unburnt sides for either of the two classes. The samples from the less exposed class were lighter, but not significantly so. The macroscopic wood density was determined using core samples. A decrease in wood density was observed with an increase in fire exposure. The mean densities for all three classes however still fulfilled the requirements for structural timber set by the SABS. Growth ring width, cell wall thickness and lumen diameter analysis gave varied results, with some cases showing a decline in properties while others were seemingly unaffected. For many of the outcomes of this study, results found by previous studies could not be reproduced. / AFRIKAANSE OPSOMMING: Hierdie studie het gepoog om bome wat aan plantasiebrande blootgestel is volgens hul eindgebruik te klassifiseer. Dit is bekend dat blootstelling aan hoë tempreature hout in vele maniere afbreuk. Hierdie afbreuking kan die eindgebruik van die hout beperk deur die meganiese, fisiese en chemiese eienskappe sodanig te verander dat dit kan lei tot probleme met verwerking of ongeskiktheid vir sterktegrade. In hierdie studie is Pinus radiata bome wat aan plantasiebrande van verskillende grade blootgestel is ondersoek in terme van hul fisiese en anatomiese veranderinge. Bome is visueel in drie klasse van verskillende brandskade gegroepeer. Voglesings is op 135 staande bome, verdeel tussen die drie klasse, geneem. Monsters is van 30 bome, 10 uit elke klas, geneem vir CT analiese. Monsters is so geneem dat dit groei van voor en na die brand ingesluit het. Daar is twee monsters van elke boom geneem, een van die gebrande en een van die ongebrande kant. Die CT data is geanalieseer en gebruik om eienskappe soos jaarringwydte, selwanddikte, lumendiameter en selwand digtheid te meet. Die data is gebruik om eienskappe tussen die gebrande en ongebrande kante, sowel as tussen jare te vergelyk. Die studie het gewys dat daar noemenswaardige verskille is tussen die voginhoud van die gebrande en ongebrande kante van bome uit klasse 2 en 3. Die voginhoud van die gebrande kante van al drie klasse verkil ook noemenswaardig van mekaar. Ligtheidmetings is gedoen op monsters van klasse 2 en 3. Die monsters het nie ‘n noemenswaardige verskil tussen die gebrande en ongebrande kante getoon nie. Alhoewel die klas 2 monsters ligter vertoon het as die klas 3 monsters, was die verskil nie betekenisvol nie. Houtdigtheid is bepaal deur fisiese metings op die monsters wat vir die CT skandering gebruik is te doen. ‘n Daling in digtheid met ‘n toename in blootstelling aan die brand het duidelik na vore gekom. Die digtheid is egter nog hoog genoeg om aan die vereistes vir strukturele hout te voldoen, soos die die SABS bepaal. Jaarringwydte, selwanddikte en lumen diameter het wisselende resultate opgelewer, met sommige gevalle wat ‘n afname in eienskappe wys en ander wat ooglopend onveranderd was. Vir vele van hierdie uitkoms kon die resultate van vorige studies nie bevestig word nie.

The biggest obstacle to robust color image processing of wood is in developing a color model that represents all possible defect colors. When the color model is too general or too specific, defect recognition fails because too many or too few non-defect pixels match the model, respectively. Because a color image of wood contains far more clear and clear-grain colored pixels than grain-knot and knot colored pixels, it is beneficial to first statistically identify and remove the clear and clear-grain colors and to use the accumulated data to simultaneously enhance and normalize the remaining grainknot and knot colored pixels. This process is here called adaptive color correlation. The normal image processing strategy is to search and test for defect features directly. The strategy proposed and developed here is to instead classify all wood pixels containing non-defect colors first, and then identify defect features. Once non-defect features are removed from an image, the task of finding candidate defects becomes easier and faster. This improvement is realized in a sigmoid-shaped color correlation implemented as an adaptive look-up table. As wood has become more expensive relative to manufacturing costs, more efficient methods of maximizing the recovery of clear wood in every board are sought. Optimization, in the present context, is a broad term for selecting products that are made from wood boards so the value of products produced is maximized for a given production requirement. Wood contains random defects which prohibit the production of some products. The normal optimization strategy is to mathematically change the value of under/over-produced products directly. The strategy proposed and developed here is to instead separate optimization into two steps: 1) determine all possible product solutions for a board; and 2) select the single best solution that satisfies value and production goals. Maximum utilization of clear wood is achieved because the solution is "frozen" before mathematically changing the value of products. Recovering long-lengths of clear wood is achieved because various length-based valuation strategies may be implemented as postsolution processes. Separating the product selection process from the solution generation process is shown by this work (simulation) to maximize value recovery.

The theoretical part summarizes pieces of knowledge about the most common defects and wood pests including their impact on the properties of the material. The following practical part describes the destructive testing of wood - its course, calculation and evaluation of results. The final section is devoted to the structural and chemical wood protection. There are introduced basic principles and methods of protection and in the last chapter there are some examples of companies in our region that performs chemical protection.