Vertical Images Research Articles

Clinical utility of multipolar ablation with a three-dimensional simulator system for patients with hepatocellular carcinoma

Purpose Recently, multipolar RFA has been utilized. Multipolar RFA offers the advantage of providing a large volume of ablation, providing more homogeneous necrosis with a higher rate of pathological complete necrosis. Although very encouraging results have been reported for multipolar RFA, the monopolar technique remains by far the most frequently used technique worldwide. We developed 3D sim-Navigator as a navigation and simulation system. For achieving insertion of electrodes around the tumor in a well-balanced manner, this system appeared very useful. To confirm the efficacy of multipolar ablation with new simulator system for patients with hepatocellular carcinoma by assessing for relapse-free survival and shape of the ablation volume under clinical conditions. Materials and Methods All participants provided written, informed consent, and study protocols were approved by the institutional ethics committee. Twenty-seven patients with 27 nodules were treated by no-touch ablation using the new simulator system. Another 21 patients with 21 nodules treated without the simulator system were enrolled as controls. Ablation was performed without inserting any applicator into the tumor by placing all electrodes around the tumor, if possible. Ablation was started after confirming a well-balanced positioning of electrodes around the tumor using the simulator system. In multipolar ablation, the positional relationships of multiple electrodes were easy to intuitively understand by repeated marking for insertions of the second and third RFA electrodes. The vertical cross-sectional image (C-plane) was utilized. Tumor progression and shape of ablation volume were assessed. Predictive factors of tumor progression were assessed by Cox proportional hazard model. Results No significant differences in clinical characteristics were seen between groups. Mean sphericity was 0.48 ± 0.07 with the 3D sim-Navigator and 0.37 ± 0.07 without the 3D sim-Navigator (P Conclusions Ideal ablation area was acquired by this simulation and navigation system in clinics. This system improved local tumor progression by appropriate insertion of multiple electrodes.

The effect of vertical centering and scout direction on automatic tube voltage selection in chest CT: a preliminary phantom study on two different CT equipments

PurposeTo determine the effect of patient’s vertical off-centering and scout direction on the function of automatic tube voltage selection (ATVS) and tube current modulation (TCM) in chest computed tomography (CT). MethodsChest phantom was scanned with Siemens and GE CT systems using three clinical chest CT protocols exploiting ATVS and a fixed 120 kVp chest protocol. The scans were performed at five vertical positions of the phantom (−6 to +6 cm from the scanner isocenter). The effects of scout direction (posterior-to-anterior, anterior-to-posterior, and lateral) and vertical off-centering on the function of ATVS and TCM were studied by examining changes in selected voltage, radiation dose (volume CT dose index, CTDIvol), and image noise and contrast. ResultsBoth scout direction and vertical off-centering affected ATVS. The effect differed between the vendors for the studied geometry, demonstrating differences in technical approaches. The greatest observed increase in CTDIvol due to off-centering was 91%. Anterior-to-posterior scout produced highest doses at the uppermost table position, whereas posterior-to-anterior scout produced highest doses at the lowermost table position. Dose varied least using lateral scouts. Vertical off-centering impacted image noise and contrast due to the combined effect of ATVS, TCM, structural noise, and bowtie filters. ConclusionsPatient vertical off-centering and scout direction affected substantially the CTDIvol and image quality in chest CT examinations. Vertical off-centering caused variation also in the selected tube voltage. The function of ATVS and TCM methods differ significantly between the CT vendors, resulting in differences in CTDIvol and image noise characteristics.

A novel automated classification technique for diagnosing liver disorders using wavelet and texture features on liver ultrasound images

A novel automated classification technique for diagnosing liver disorders is contributed in this paper by utilizing the merits of wavelet and texture features of ultrasound images. In this automated classification technique, initially the diseased part of the ultrasound image is isolated based on the application of improved active contour-based segmentation scheme. Improved active contour-based segmentation is mainly for preventing the issue of worse convergence, which is prevalent in the concave boundary regions of ultrasonic images. After segmentation, shift variant bi-orthogonal wavelet transform is applied for decomposing the region of focus into diagonal, vertical and horizontal component images. This shift variant bi-orthogonal wavelet transform is used in this approach for reducing the degree of prediction errors that are most possible in the classical discrete wavelet transform schemas. Finally, an improved random forest classifier (IRFC) is used for classifying the features that are extracted from the wavelet filtered images using gray level run length matrix (GLRLM). The performance of this scheme is evaluated based on sensitivity, specificity and accuracy metrics and shows the comparison of each classifier performance. The results of the proposed scheme infer an overall classification accuracy rate of 97.8% and confirm better results using GLRLM.

Extraction of Buildings from Multiple-View Aerial Images Using a Feature-Level-Fusion Strategy

Aerial images are widely used for building detection. However, the performance of building detection methods based on aerial images alone is typically poorer than that of building detection methods using both LiDAR and image data. To overcome these limitations, we present a framework for detecting and regularizing the boundary of individual buildings using a feature-level-fusion strategy based on features from dense image matching (DIM) point clouds, orthophoto and original aerial images. The proposed framework is divided into three stages. In the first stage, the features from the original aerial image and DIM points are fused to detect buildings and obtain the so-called blob of an individual building. Then, a feature-level fusion strategy is applied to match the straight-line segments from original aerial images so that the matched straight-line segment can be used in the later stage. Finally, a new footprint generation algorithm is proposed to generate the building footprint by combining the matched straight-line segments and the boundary of the blob of the individual building. The performance of our framework is evaluated on a vertical aerial image dataset (Vaihingen) and two oblique aerial image datasets (Potsdam and Lunen). The experimental results reveal 89% to 96% per-area completeness with accuracy above almost 93%. Relative to six existing methods, our proposed method not only is more robust but also can obtain a similar performance to the methods based on LiDAR and images.

Relationship between the Vertical Asymmetry of the Posterior Pole of the Eye and the Visual Field Damage in Glaucomatous Eyes

This study investigated the relationship between the shape of the posterior pole of the eye and the vertical asymmetry of visual field (VF) damage in glaucomatous eyes. Cross-sectional study. A total of 83 eyes of 43 patients with open-angle glaucoma. The VF was measured using the Humphrey 24-2 or 30-2 Swedish Interactive Thresholding Algorithm (SITA) standard. The vertical asymmetry of VF damage was defined as the difference between the mean total deviation (mTD) values of the superior and inferior hemi-retinas. This difference was calculated for the hemifield, central, middle, and peripheral areas. A vertical cross-sectional image of the macula was obtained, and the magnitudes of superior and inferior retinal tilt (RT) were calculated as the difference between the lower margins of the retinal pigment epithelium (RPE) at the fovea and at a location 2 mm superior or inferior to the RPE. The RT asymmetry was defined as the difference between the inferior and superior RT. Data were analyzed using a multivariate linear mixed model. The relationship between mTD asymmetry (hemifield, central, middle, and peripheral) and both RT asymmetry and other factors (intraocular pressure, axial length, corneal radius, age, gender, mean deviation, refraction, and visual acuity) was assessed. The inferior RT was significantly larger than the superior RT (P < 0.001). Hemifield mTD asymmetry was related to RT asymmetry (P= 0.017). These relationships were significant in the middle (P= 0.029) and peripheral areas (P= 0.023), but not in the central area (P= 0.40). Other factors were not related to mTD asymmetry. Vertical asymmetry of the posterior pole was related to the vertical asymmetry of glaucomatous VF damage.

Semisupervised classification of hurricane damage from postevent aerial imagery using deep learning

Aerial images can greatly facilitate rescue efforts and recovery in the aftermath of hurricane disasters. Although supervised classification methods have been successfully applied to aerial imaging for building damage evaluation, their use remains challenging since supervised classifiers have to be trained using a large number of labeled samples, which are not available soon after disasters. However, rapid response is crucial for rescue tasks, which places greater demands on classification methods. To accelerate their deployment, a semisupervised classification method is proposed in this paper using a large number of unlabeled samples and only a few labeled samples that could be rapidly obtained. The proposed approach consists of three steps: segmentation, unsupervised pretraining using convolutional autoencoders (CAE), and supervised fine-tuning using convolutional neural networks (CNN). Leveraging the representation capability of CAE, the learned knowledge from CAE could be transferred to the counterparts of CNN. After pretraining, the CNN classifier is further refined with a few labeled samples to improve feature discrimination. To demonstrate this methodology, a recognition strategy of damaged buildings based on context information using only vertical postevent aerial two-dimensional images is presented in this paper. As a case study, a coastal area affected by the 2012 Sandy hurricane is investigated. Experimental results show that the proposed semisupervised method produces an overall accuracy of 88.3% and obtains an improvement of up to 9% against a CNN classifier trained from scratch.

Estimating morphometric attributes of baleen whales with photogrammetry from small UASs: A case study with blue and gray whales

AbstractSmall unmanned aircraft systems (sUASs) are fostering novel approaches to marine mammal research, including baleen whale photogrammetry, by providing new observational perspectives. We collected vertical images of 89 gray and 6 blue whales using low cost sUASs to examine the accuracy of image based morphometry. Moreover, measurements from 192 images of a 1 m calibration object were used to examine four different scaling correction models. Results indicate that a linear mixed model including an error term for flight and date contained 0.17 m less error and 0.25 m less bias than no correction. We used the propagation uncertainty law to examine error contributions from scaling and image measurement (digitization) to determine that digitization accounted for 97% of total variance. Additionally, we present a new whale body size metric termed Body Area Index (BAI). BAI is scale invariant and is independent of body length (R2 = 0.11), enabling comparisons of body size within and among populations, and over time. With this study we present a three program analysis suite that measures baleen whales and compensates for lens distortion and corrects scaling error to produce 11 morphometric attributes from sUAS imagery. The program is freely available and is expected to improve processing efficiency and analytical continuity.

무인항공기로 촬영한 수직 영상과 고경사 영상을 이용한 소규모 계단식 지형에 대한 정사영상 및 3차원 모델 제작 및 비교

무인항공기로 촬영한 수직 영상과 고경사 영상을 이용한 소규모 계단식 지형에 대한 정사영상 및 3차원 모델 제작 및 비교

Quantification of the Posterior Cornea Using Swept Source Optical Coherence Tomography

PurposeWe define optical coherence tomography (OCT) measurement parameters of the corneal endothelium/Descemet's membrane (DM) complex and peripheral transition zone (TZ) and describe these measurements in an ethnically Chinese population.MethodsOCT images of the anterior segment and iridocorneal angle were obtained from 129 healthy Chinese subjects (129 eyes), aged 40 to 81 years. The scleral spur (SS) and Schwalbe's line (SL) were identified in each image. Endothelium/DM diameter, referred to as endothelial arc length (EAL), is the SL-to-SL distance. The SS-to-SL distance encompasses the TZ and trabecular meshwork (TM). Since the TZ cannot be visualized by OCT, a ratio of TZ-to-TZ+TM width was calculated from scanning electron microscopy (SEM) images obtained from 5 cadaveric corneas. The SS-to-SL distance was multiplied by this ratio to approximate in vivo TZ width.ResultsFrom SEM measurements, the relationship TZ = 0.20*(TZ+TM) was determined. From OCT measurements, mean EAL was 12.15 ± 0.58 mm and mean TZ width was 156 ± 20 μm. For eyes with horizontal and vertical images, vertical EAL was significantly greater than horizontal EAL (P = 0.03).ConclusionsCorneal endothelium/DM diameter and TZ width can be obtained from OCT images. Although only combined TZ+TM is visualized on OCT, TZ width can be reasonably approximated.Translational RelevanceEmerging procedures, like endothelial cell injection and DM transplantation (DMT), require accurate measurements of endothelium/DM size for preoperative planning. Size of the TZ, which may contain progenitor cells, also could contribute to endothelial regeneration in these procedures.

Dissolved organic carbon in snow cover of the Chinese Altai Mountains, Central Asia: Concentrations, sources and light-absorption properties

Dissolved organic carbon (DOC) in snow plays an important role in river ecosystems that are fed by snowmelt water. However, limited knowledge is available on the DOC content in snow of the Chinese Altai Mountains in Central Asia. In this study, DOC in the snow cover of the Kayiertesi river basin, southern slope of Altai Mountains, was investigated during November 2016 to April 2017. The results showed that average concentrations of DOC in the surface snow cover (1.01 ± 0.52 mg L−1) were only a little higher than those in glaciers of the Tibetan Plateau, European Alps, and Alaska, but much higher than in Greenland Ice Sheet. Depth variations of DOC concentrations from snowpack profiles indicated higher values in the surface layer. During the observation period, scavenging efficiency for DOC in snow cover is estimated to be 0.15 ± 0.10, suggesting that DOC in snow can be affected more by the meltwater during ablation season than during accumulation season. The average mass absorption cross section at 365 nm and the absorption Ångström exponent of DOC were 0.45 ± 0.35 m2 g−1 and 2.59 ± 1.03, respectively, with higher values in March and April 2017. Fraction of radiative forcing caused by DOC relative to black carbon accounted for about 10.5%, implying DOC is a non-ignorable light-absorber of solar radiation in snow of the Altai regions. Backward trajectories analysis and aerosol vertical distribution images from satellites showed that DOC in the snow of the Altai Mountains was mainly influenced by air masses from Central Asia, Western Siberia, the Middle East, and some even from Europe. Biomass burning and organic carbon mixed with mineral dust contributed significantly to the DOC concentration. This study highlights the effects of DOC in the snow cover for radiative forcing and the need to study carbon cycling for evaluation of quality of the downstreams ecosystems.

Grain Size information Extracting from Sand Conglomerate Reservoir based on FMI Data:A case study of sha4 formation in Dongying Sag

The evaluation of rock phase and reservoir property is the key problem to be solved in the exploration of deep sand conglomerate. The study of rock phase information is only in the qualitative stage according to the FMI logging data with the results are mainly image-lithologic models. It is urgent to extract gravel information based on image analysis. FMI image can be transformed into a vertical core gravel image after the operation of grayscale, blind area filling, image filtering, image segmentation and gravel extraction. The maximum gravel size is selected as the rock phase marker, and the statistical relationship of the conventional logging curves with resistivity, GR and density is established. It can provide a useful supplement for petrographic classification.

Reliability of wear measurements of CAD-CAM restorative materials after artificial aging in a mastication simulator.

The purpose of this in vitro study was to assess the 2-body wear behavior of computer-aided design and computer-aided manufacturing (CAD-CAM) restorative materials and additionally to validate an automatic approach to wear quantification as provided by newly developed software. Two composite resins (Experimental Composite, Shofu Block HC), 1 polymethyl methacrylate- (PMMA)-based material (Telio CAD), and 1 dual-network material (VITA Enamic) were tested (n = 12). The materials were stored in distilled water at 37 °C for 14 days, then aged in a mastication simulator (cycles: 400 000, 50 N, 1.2 Hz, 5/55 °C) for 2-body wear testing with human molars as antagonists. Software was developed as a freely available function in R for automatic wear quantification and was applied to 2 (vertical and horizontal) images obtained by an optical laser scanner (SDM). Wear measurements were validated with a reference confocal laser scanning microscope (LSM) system. The Kruskal-Wallis with Tukey-Kramer post hoc test (α = 0.05), coefficient of variation, Bland-Altman method, and intraclass correlation were applied. Shofu Block HC showed the greatest wear, and no differences were found among other materials. The automatic wear measurements agreed well with the reference LSM system. The reliability of the SDM scans was 98.5%. The wear resistance caused by two-body wear differed among the restorative materials tested, with the mean wear resistance of the 2 composite resin materials differing significantly. Wear quantification with R software based on SDM scans showed satisfactory agreement with the reference LSM system.

DEVELOPMENT OF UAV PHOTOGRAMMETRY METHOD BY USING SMALL NUMBER OF VERTICAL IMAGES

Abstract. This new and efficient photogrammetric method for unmanned aerial vehicles (UAVs) requires only a few images taken in the vertical direction at different altitudes. The method includes an original relative orientation procedure which can be applied to images captured along the vertical direction. The final orientation determines the absolute orientation for every parameter and is used for calculating the 3D coordinates of every measurement point. The measurement accuracy was checked at the UAV test site of the Japan Society for Photogrammetry and Remote Sensing. Five vertical images were taken at 70 to 90 m altitude. The 3D coordinates of the measurement points were calculated. The plane and height accuracies were ±0.093 m and ±0.166 m, respectively. These values are of higher accuracy than the results of the traditional photogrammetric method. The proposed method can measure 3D positions efficiently and would be a useful tool for construction and disaster sites and for other field surveying purposes.

Fracturing Mechanism of Compressed Hollow-Cylinder Sandstone Evaluated by X-ray Micro-CT Scanning

Triaxial compression experiments under confining pressures of 16 and 35 MPa were first carried out for hollow-cylinder sandstone specimens using a rock mechanics testing system. Four hollow-cylinder sandstone specimens were compressed to various deformation positions before or after the peak strength. Then, the compressed hollow-cylinder sandstone specimens were analysed using a three-dimensional X-ray micro computed tomography (CT) scanning system. Based on the horizontal and vertical cross-sectional CT images, the internal damage behaviour of hollow-cylinder sandstone specimens was evaluated. It can be seen that the crack system of hollow-cylinder sandstone specimens with higher compressed deformation after the peak strength are more complicated than those with lower compressed deformation close to the peak strength. In the present study, the hollow-cylinder sandstone specimens with lower compressed deformation are only dominated by some internal wall fractures resulting mainly from shear cracks, whereas the hollow-cylinder sandstone specimens with higher compressed deformation are mainly dominated by two shear fractures, as well as some tensile cracks. For the same axial stress level, hollow-cylinder sandstone under a higher confining pressure has a more complicated crack system than that under a lower confining pressure. The experimental results demonstrated that the three-dimensional cracks in the hollow specimen under triaxial compression are first initiated from the internal wall due to shear slippage, and then propagate towards the top or bottom boundary of the specimen in shear fracture mode. To better explain the internal crack evolution mechanism of hollow-cylinder sandstone during the entire loading, a conceptual model of hollow-cylinder sandstone material under the action of confining pressure is proposed. At the same time, the effect of the borehole size on the internal damage behaviour of the compressed specimen after the peak strength is also discussed. The investigated conclusions are significant for predicting the instability occurring around deep well bores in petroleum engineering and for ensuring the safety of deep excavation damage zones in tunnel engineering.

Mid-air imaging technique for architecture in public space

Mid-air imaging is promising for glasses-free mixed reality systems in which the viewer does not need to wear any special equipment. However, it is difficult to install an optical system in a public space because conventional designs expose the optical components and disrupt the field of view. In this paper, we propose an optical system that can form mid-air images in front of building walls. This is achieved by installing optical components overhead. It displays a vertical mid-air image that is easily visible in front of the viewer. Our contributions are formulating its field of view, measuring the luminance of mid-air images formed with our system by using a luminance meter, psychophysical experiments to measure the resolution of the mid-air images formed with our system, and selection of suitable materials for our system. As a result, we found that highly reflective materials, such as touch display, transparent acrylic board, and white porcelain tile, are not suitable for our system to form visible mid-air images. We prototyped two applications for proof of concept and observed user reactions to evaluate our system.

The Image of the Invisible Cross in the Russian Lyrical Poetry of the 20th Century: From The Twelve by Blok to the Roman Diary by Vyacheslav Ivanov

Referring to works of four poets, the author analyses a special image of the “invisible cross” that appears when horizontal and vertical poetic images come into contact. In Boris Pasternak’s poem Winter Night, it is formed by the image of windstorm and candles in the first stanza, in Blok’s The Twelve by crossing the lines from the “black sky” to the “white snow” with the “wind line”. In Georgy Ivanov’s poem, the image of the “invisible cross” appears from the troika’s movement and the image of the falling “black music by Blok”. The image of “windstorm” in Pasternak’s poem and that of “Blok’s music” in Ivanov’s poem allude to The Twelve . All the three works refer to the same historical reality: the collapse of former Russia and the uncertainty of human destiny in the tragic period of history. In Vyacheslav Ivanov’s poem written in Rome on 23 May 1944, the image of the “invisible cross” is also present. However, it appears when comparing the first and second stanzas of the poem. The first stanza represents the European image of the world, which is characterised as “vertical” which is accentuated by the images of “Gothic churches” and “cyclopic hammer”. The second stanza represents the “horizontal” image of the world, characteristic for Russia, accentuated by the images of “ways”, and “rails”. Every stanza contains details adding to the sensation of instability of both historical entities. The third verse is like looking from space at the earth and at the historical path of humanity, which has led it to the current war. The image found by Ivanov could emerge as a result of his life in Rome and his memory of Russia. At the same time, the perseverance with which the “invisible cross” appears in works of different authors at different times makes the image typical of the entire twentieth century.

Verification of the Virtual Bandwidth SAR Scheme for Centimetric Resolution Subsurface Imaging From Space

This paper presents the first experimental demonstration of the virtual bandwidth synthetic aperture radar (VB-SAR) imaging scheme. VB-SAR is a newly developed subsurface imaging technique which, in stark contrast to traditional close proximity ground penetrating radar schemes, promises imaging from remote standoff platforms such as aircraft and satellites. It specifically exploits the differential interferometric SAR (DInSAR) phase history of a radar wave within a drying soil volume to generate high-resolution vertical maps of the scattering through the soil volume. For this study, a stack of C-band vertically polarized DInSAR images of a sandy soil containing a buried target was collected in the laboratory while the soil moisture was varied—first during controlled water addition, and then during subsequent drying. The wetting image set established the moisture-phase relationship for the soil, which was then applied to the drying DInSAR image set using the VB-SAR scheme. This allowed retrieval of high-resolution VB-SAR imagery with a vertical discrimination of 0.04 m from a stack of 1-m vertical resolution DInSAR images. This paper unequivocally shows that the basic principles of the VB-SAR technique are valid and opens the door to further investigation of this promising technique.

UAV로 촬영한 수직 영상과 고경사 영상을 이용한 정사영상 및 3차원 모델링 비교

UAV로 촬영한 수직 영상과 고경사 영상을 이용한 정사영상 및 3차원 모델링 비교

Characterization of macropore structure of Malan loess in NW China based on 3D pipe models constructed by using computed tomography technology

Malan loess is a grayish yellow or brownish yellow, clastic, highly porous and brittle late Quaternary sediment formed by the accumulation of windblown dust. The present-day pore structure of Malan loess is crucial for understanding the loessification process in history, loess strengths and mechanical behavior. This study employed a modern computed tomography (CT) device to scan Malan loess samples, which were obtained from the east part of the Loess Plateau of China. A sophisticated and efficient workflow for processing the CT images and constructing 3D pore models was established by selecting and programming relevant mathematical algorithms in MATLAB, such as the maximum entropy method, medial axis method, and node recognition algorithm. Individual pipes within the Malan loess were identified and constructed by partitioning and recombining links in the 3D pore model. The macropore structure of Malan loess was then depicted using quantitative parameters. The parameters derived from 2D images of CT scanning included equivalent radius, length and aspect ratio of pores, porosity, and pore distribution entropy, whereas those derived from the constructed 3D structure models included porosity, coordination number, node density, pipe radius, length, length density, dip angle, and dip direction. The analysis of these parameters revealed that Malan loess is a strongly anisotropic geomaterial with a dense and complex network of pores and pipes. The pores discovered on horizontal images, perpendicular to the vertical direction, were round and relatively uniform in shape and size and evenly distributed, whereas the pores discovered on vertical images varied in shape and size and were distributed in clusters. The pores showed good connectivity in vertical direction and formed vertically aligned pipes but displayed weak connectivity in horizontal directions. The pipes in vertical direction were thick, long, and straight compared with those in horizontal directions. These results were in good agreement with both numerical simulation and laboratory permeability tests, which indicate that Malan loess is more permeable in the vertical direction than in the horizontal directions.

Wood species recognition through multidimensional texture analysis

Wood recognition is a crucial task for wood sciences and industries, since it leads to the identification of the anatomical features and physical properties of wood. Traditionally, the recognition process relies almost exclusively on human experts, who are based on various characteristics of wood, such as color, structure and texture. However, there are numerous types of wood species in the nature that are difficult to be identified even by experienced scientists. Towards this end, in this paper we propose a novel approach for automated wood species recognition through multidimensional texture analysis. By taking advantage of the fact that static wood images contain periodic spatially-evolving characteristics, we introduce a new spatial descriptor considering each wood image as a collection of multidimensional signals. More specifically, the proposed methodology enables the representation of wood images as concatenated histograms of higher order linear dynamical systems produced by vertical and horizontal image patches. The final classification of images, i.e., histogram representations, into wood species, is performed using a Support Vector Machines (SVM) classifier. For the evaluation of the proposed method, a dataset, namely “WOOD-AUTH”, consisting of more than 4200 wood images (from cross, radial and tangential sections of normal wood structure) of twelve common wood species existing in Greek territory, was created. Experimental results presented in this paper show the great potential of the proposed methodology, which, despite a small number of misclassification cases with regards to both anatomically similar and different species, outperforms a number of state of the art approaches, yielding a classification rate of 91.47% in wood cross sections.