木材构造特征在地板用材纠纷仲裁上的应用

通过对标为"柚木"实木地板的木材构造特征与对照标本进行比较分析,判定待检材料不是马鞭草科柚木属的柚木,而是木兰科(MAGNOLIACEAE)白兰属(含笑属)的一种(Michelia sp)和木莲属的一种(Manglietia sp),它们同属于一类商品材,为由此而引起的地板用材纠纷提供了仲裁依据.     

Predicting beef tenderness using color and multispectral image texture features

The objective of this study was to investigate the usefulness of raw meat surface characteristics (texture) in predicting cooked beef tenderness. Color and multispectral texture features, including 4 different wavelengths and 217 image texture features, were extracted from 2 laboratory-based multispectral camera imaging systems. Steaks were segregated into tough and tender classification groups based on Warner-Bratzler shear force. The texture features were submitted to STEPWISE multiple regression and support vector machine (SVM) analyses to establish prediction models for beef tenderness. A subsample (80%) of tender or tough classified steaks were used to train models which were then validated on the remaining (20%) test steaks. For color images, the SVM model correctly identified tender steaks with 100% accurately while the STEPWISE equation identified 94.9% of the tender steaks correctly. For multispectral images, the SVM model predicted 91% and STEPWISE predicted 87% average accuracy of beef tender.     

Predicting beef tenderness using color and multispectral image texture features

The objective of this study was to investigate the usefulness of raw meat surface characteristics (texture) in predicting cooked beef tenderness. Color and multispectral texture features, including 4 different wavelengths and 217 image texture features, were extracted from 2 laboratory-based multispectral camera imaging systems. Steaks were segregated into tough and tender classification groups based on Warner–Bratzler shear force. The texture features were submitted to STEPWISE multiple regression and support vector machine (SVM) analyses to establish prediction models for beef tenderness. A subsample (80%) of tender or tough classified steaks were used to train models which were then validated on the remaining (20%) test steaks. For color images, the SVM model correctly identified tender steaks with 100% accurately while the STEPWISE equation identified 94.9% of the tender steaks correctly. For multispectral images, the SVM model predicted 91% and STEPWISE predicted 87% average accuracy of beef tender.     

Content-based lace fabric image retrieval system using texture and shape features

A content-based lace fabric image retrieval system using texture and shape features is presented in this article. The retrieval system consists of two steps: registration and identification. During the registration procedure, a feature vector corresponding to each lace fabric sample image is extracted and then stored in a feature database. During the identification procedure, a feature vector of a lace fabric query image is extracted and then the similarities between the query image and all the sample images are calculated. Finally, the retrieval results can be sorted based on their similarities to the query image. Experimental results demonstrate the effectiveness of retrieval performance of the proposed algorithm and possible practical application of the retrieval system in lace fabric industry to improve management efficiency.     

Dynamic MOE of 55 species using small wood beams

Nondestructive impact-induced resonance vibrations and spectral analysis were used to determine the dynamic modulus of elasticity (MOE) of specimens from 45 hardwood and 10 softwood species. Relationships were obtained between air-dry specimens measuring 20×20×300 mm and small wood beams measuring 20×2×150 mm (nominal) cut from them. Dynamic longitudinal elastic modulus (E_L) and wave velocity (V_L) in the fiber direction were determined from the larger specimens. These were compared with the dynamic flexural elastic modulus (E_CB-cantilever mode) and the dynamic longitudinal elastic modulus (E_LB) with the corresponding wave velocity (V_BL) measured from the small beams. E_CB and E_LB were highly related to E_L. V_LB was similarly related to V_L. The methods developed for small wood beams allow rapid evaluation of MOE from the outer wood of standing trees or they can be used for studies involving detailed localized evaluation of elastic wood properties.     

Embedment tests parallel-to-grain and ductility aspects using various wood species

Embedment tests parallel-to-grain using dowels with different steel grades and five wood species were carried out. The specimen sampling with regard to density was random and the specimens were tested at different moisture contents. Furthermore, own tests were extended by results from literature. Observed ductility aspects using different wood species are discussed. Comparisons with the existing design equation in Eurocode 5 were made. It was found that the equation penalises species with higher densities. An adjustment of density and embedment strength to 12 % moisture content reduced the scatter considerably. Moreover, based on the test results, the sophisticated distinction of softwood in many strength classes based on minor differences in density is considered to be overly precise as far as embedment strength is concerned. An influence of the dowel steel grade was measured although the dowels remained elastic as required by standard embedment test protocols.     

Multivariate prediction of wood surface features using an imaging spectrograph

This paper presents a muitispectral system for evelution of linear algorithms for prediction of wood surface features important for automatic inspection of lumber. The selection of training samples, the imaging spectrograph scaning method, raw data representation, evaluation of linear algorithms and testing of performance is discussed. A possible on line implementation for high speed wood scanning with a smart sensor is outpointed. An example, showing the evolution of linear algorithms for prediction of compression wood in softwood species (Picea abies, Pinus sylvestris), is reported, showing verified 92–94% correct classification. It is shown that compression wood classification could be reduced to an uncomplicated linear model using just a few spectral components where the most important one is around the limit for visible light going to the Ultraviolet spectra. This almost univariate behaviour for the model is not the common behaviour for other wood surface features (Brunner et al., 1996; Hagman, 1995; Hagman, 1996).     

Identification of important image features for pork and turkey ham classification using colour and wavelet texture features and genetic selection

A method to discriminate between various grades of pork and turkey ham was developed using colour and wavelet texture features. Image analysis methods originally developed for predicting the palatability of beef were applied to rapidly identify the ham grade. With high quality digital images of 50–94 slices per ham it was possible to identify the greyscale that best expressed the differences between the various ham grades. The best 10 discriminating image features were then found with a genetic algorithm. Using the best 10 image features, simple linear discriminant analysis models produced 100% correct classifications for both pork and turkey on both calibration and validation sets.     

融合局部纹理特征的颗粒图像SLIC超像素分割方法

将SLIC超像素分割的方法引入颗粒图像检测的分割过程中,将颗粒图像分割成感兴趣的超像素块,可降低后续图像处理过程的复杂度。由于SLIC超像素分割在聚类过程中计算相似度时没有考虑图像的纹理特征,一定程度上会影响颗粒目标外轮廓分割的细节。利用CRLBP局部纹理算子纹理特征,改进SLIC分割中聚类相似度的计算,并按照符合颗粒形状的圆形邻域搜索相似点,保证了分割速度。通过对棉种颗粒图像的分割试验,与传统分水岭算法和SLIC超像素算法进行比较,结果表明改进的SLIC超像素分割方法能更有效地分割出颗粒目标。     

Mechanical behaviour of Québec wood species heat-treated using ThermoWood process

Finnish wood heat treatment technology, ThermoWood, was recently introduced to Québec, Canada by Ohlin Thermo Tech. Subsequently, a large number of initial trials were conducted on five commercially important Québec wood species, spruce (Picea spp.), pine (Pinus spp.), fir (Abies spp.), aspen (Populus spp.), and birch (Betula spp.). These species were thermally-modified in different batches at temperatures of 200 °C or higher. The static bending and hardness of the thermally-modified wood were examined. Decreases of 0% to 49% were observed in modulus of rupture of heat-treated spruce, pine, fir, and aspen depending on species and treatment schedules used; modulus of rupture of birch increased slightly after the heat treatment. The decrease in modulus of elasticity of heat-treated spruce and pine ranged from 4% to 28%; but the modulus of elasticity of heat-treated fir, aspen, and birch increased except one trial for fir. Hardness of the heat-treated wood increased or decreased depending on the species, test directions (radial, tangential, and longitudinal), and treatment schedules.     

竹木地板的结构与特点

系统介绍各种不同结构的竹木地板,并根据地板的不同结构,讨论其用材、构造合理性、加工工艺、单元几何状态、装饰效果、安装与保养、尺寸稳定性和环境影响等方面的特点。     

Classification of tough and tender beef by image texture analysis

Texture features of fresh-beef images were extracted and used to classify steaks into tough and tender groups in terms of cooked-beef tenderness. Crossbred steers varying in quality were processed in a commercial plant and two short loin steaks were sampled from each carcass. One sample was used for imaging and the other was broiled for sensory evaluation of tenderness by a trained panel. The samples were segregated into tough and tender groups according to the sensory scores. A wavelet-based decomposition method was used to extract texture features of fresh-beef images. The texture feature data for 90 sample images were used to train and test sample calssifiers in a rotational leave-one-out scheme. A correct classification rate of 83.3% was obtained in cross validations. While texture features alone may not be sufficient to segregate beef products into many levels of tenderness, they can be significant members in a set of indicators that will lead to adequate tenderness prediction.     

Image texture features as indicators of beef tenderness

Image processing techniques were developed to predict cooked-beef tenderness from fresh-beef image characteristics. Cattle from different finishing treatments were processed in a commercial plant. Two short loin steaks were sampled from each carcass; one used for sensory evaluation and the other for imaging. The samples varied significantly in both US quality grades and sensory tenderness scores. Color, marbling and texture features were extracted from the beef images. Statistical and neural network analyses were performed to relate the image features to sensory tenderness scores. Image texture features were found to be useful indicators of beef tenderness. Partial least squares and neural network models were able to predict beef tenderness from color, marbling and image texture features to R(2)-values up to 0.70.     

Effect of moisture sorption state on transverse dimensional changes in wood

The purpose of the study was to understand the transverse dimensional changes and corresponding anisotropicity in wood during different states of moisture sorption. Oven dried samples of Erythrina variegata, Lannea coromandelica, Gmelina arborea and Albizia chinensis were adsorbed and subsequently desorbed at constant temperature (35°C). Tangential and radial dimensional changes (swelling) were analysed with respect to relative humidity and moisture content during both the states of sorption. Dimensions in tangential direction were found to change at a relatively greater rate than in radial direction at high humidities. It was observed that transverse dimensions were more during desorption compared to adsorption at a given equilibrium moisture content. This confirms presence a second order effect of moisture sorption on dimensional movement. This effect was found to be more prominent in tangential direction compared to radial direction resulting in higher coefficient of anisotropy ( _T / _R ratio) during desorption. The magnitude of this phenomenon was found to vary from species to species.

---

Einfluß der Feuchteaufnahme auf die transversale Dimensionsänderung in Holz

Zusammenfassung Ziel der Arbeit war es, die transversale Dimensionsänderung und die entsprechenden anisotropen Verhältnisse in Holz während unterschiedlicher Grade der Feuchteaufnahme zu untersuchen. Ofengetrocknete Proben von Erythrina variegata, Lannea coromandelica, Gmelina arborea und Albizia chinensis wurden bei konstanter Temperatur (35°C) einer Sorption und anschließender Desorption unterworfen. Tangentiale und radiale Dimensionsänderungen wurden analysiert im Hinblick auf die relative Feuchte und den Wassergehalt in beiden Zuständen. Bei hohen Feuchten änderten sich die tangentialen Dimensionen schneller als in radialer Richtung. Bei einer gegebenen Gleichgewichtsfeuchte war die transversale Dimensionsänderung stärker während der Desorption als während der Sorption. Dies bestätigt einen Effekt zweiter Ordnung für den Einfluss der Feuchteaufnahme auf die Dimensionsänderung. Dieser Effekt war in tangentialer Richtung vorherrschender im Vergleich zur radialen Richtung, woraus sich ein höherer Grad an Anisotropie ( _T / _R -Verhältnis) während der Desorption ergibt. Die Größe dieses Effekts variiert je nach Holzart.