Morphology-based interslice interpolation on manual segmentations of joint bones and muscles in MRI

This paper presents a validation study on the application of a novel interslice interpolation technique for musculoskeletal structure segmentation of articulated joints and muscles on human magnetic resonance imaging data. The interpolation technique is based on morphological shape-based interpolation combined with intensity based voxel classification. Shape-based interpolation in the absence of the original intensity image has been investigated intensively. However, in some applications of medical image analysis, the intensity image of the slice to be interpolated is available. For example, when manual segmentation is conducted on selected slices, the segmentation on those unselected slices can be obtained by interpolation. We proposed a two- step interpolation method to utilize both the shape information in the manual segmentation and local intensity information in the image. The method was tested on segmentations of knee, hip and shoulder joint bones and hamstring muscles. The results were compared with two existing interpolation methods. Based on the calculated Dice similarity coefficient and normalized error rate, the proposed method outperformed the other two methods.

The potential for consumer segmentation in the Finnish housing market

This article examines whether cluster analysis can be used to identify groups of Finnish residents with similar housing preferences. Because homebuilders in Finland have been providing relatively homogeneous products to an increasingly diverse population, current housing may not represent the occupiers' preferences so a segmentation approach relying on socioeconomic characteristics and expressed preferences may not be sufficient. We use data collected via questionnaire in a principal component analysis followed by a hierarchical cluster analysis to determine whether different combinations of housing attributes are important to groups of residents. We can identify four clusters of housing residents based on important characteristics when looking for a house. The clusters describe Finnish people in different phases of the life cycle and with different preferences based on their recreational activities and financial expenditures. Mass customization of housing could be used to better appeal to these different clusters of consumers who share similar preferences, increasing consumer satisfaction and improving profitability.

Growth and carcass characteristics of cast-for-age Merino ewes fed sorghum-based feedlot diets

Grain feeding low bodyweight, cast-for-age (CFA) sheep from pastoral areas of eastern Australia at the end of the growing season can enable critical carcass weight grades to be achieved and thus yield better economic returns. The aim of this work was to compare growth and carcass characteristics for CFA Merino ewes consuming either simple diets based on whole sorghum grain or commercial feed pellets. The experiment also compared various sources of additional nitrogen (N) for inclusion in sorghum diets and evaluated several introductory regimes. Seventeen ewes were killed initially to provide baseline carcass data and the remaining 301 ewes were gradually introduced to the concentrate diets over 14 days before being fed concentrates and wheaten hay ad libitum for 33 or 68 days. Concentrate treatments were: (i) commercial feed pellets, (ii) sorghum mix (SM; whole sorghum grain, limestone, salt and molasses) + urea and ammonium sulfate (SMU), (iii) SMU + whole cottonseed at 286 g/kg of concentrate dry matter (DM), (iv) SM + cottonseed meal at 139 g/kg of concentrate DM, (v) SMU + virginiamycin (20 mg/kg of concentrate) for the first 21 days of feeding, and (vi) whole cottonseed gradually replaced by SMU over the first 14 days of feeding. The target carcass weight of 18 kg was achieved after only 33 days on feed for the pellets and the SM + cottonseed meal diet. All other whole grain sorghum diets required between 33 and 68 days on feed to achieve the target carcass weight. Concentrates based on whole sorghum grain generally produced significantly (P < 0.05) lower carcass weight and fat score than pellets and this may have been linked to the significantly (P < 0.05) higher faecal starch concentrations for ewes consuming sorghum-based diets (270 v. 72 g/kg DM on day 51 of feeding for sorghum-based diets and pellets, respectively). Source of N in whole grain sorghum rations and special introductory regimes had no significant (P > 0.05) effects on carcass weight or fat score of ewes with the exception of carcass weight for SMU + whole cottonseed being significantly lower than SM + cottonseed meal at day 33. Ewes finished on all diets produced acceptable carcasses although muscle pH was high in all ewe carcasses (average 5.8 and 5.7 at 33 and 68 days, respectively). There were no significant (P > 0.05) differences between diets in concentrate DM intake, rumen fluid pH, meat colour score, fat colour score, eye muscle area, meat pH or meat temperature.

Quantitative methods to measure pigmentation variation in farmed Giant Tiger Prawns, Penaeus monodon, and the effects of different harvest methods on cooked colour

Cooked prawn colour is known to be a driver of market price and a visual indicator of product quality for the consumer. Although there is a general understanding that colour variation exists in farmed prawns, there has been no attempt to quantify this variation or identify where this variation is most prevalent. The objectives of this study were threefold: firstly to compare three different quantitative methods to measure prawn colour or pigmentation, two different colorimeters and colour quantification from digital images. Secondly, to quantify the amount of pigmentation variation that exists in farmed prawns within ponds, across ponds and across farms. Lastly, to assess the effects of ice storage or freeze-thawing of raw product prior to cooking. Each method was able to detect quantitative differences in prawn colour, although conversion of image based quantification of prawn colour from RGB to Lab was unreliable. Considerable colour variation was observed between prawns from different ponds and different farms, and this variation potentially affects product value. Different post-harvest methods prior to cooking were also shown to have a profound detrimental effect on prawn colour. Both long periods of ice storage and freeze thawing of raw product were detrimental to prawn colour. However, ice storage immediately after cooking was shown to be beneficial to prawn colour. Results demonstrated that darker prawn colour was preserved by holding harvested prawns alive in chilled seawater, limiting the time between harvesting and cooking, and avoiding long periods of ice storage or freeze thawing of uncooked product.

A feedback-based algorithm forMotion analysis with application to object tracking

We present a motion detection algorithm which detects direction of motion at sufficient number of points and thus segregates the edge image into clusters of coherently moving points. Unlike most algorithms for motion analysis, we do not estimate magnitude of velocity vectors or obtain dense motion maps. The motivation is that motion direction information at a number of points seems to be sufficient to evoke perception of motion and hence should be useful in many image processing tasks requiring motion analysis. The algorithm essentially updates the motion at previous time using the current image frame as input in a dynamic fashion. One of the novel features of the algorithm is the use of some feedback mechanism for evidence segregation. This kind of motion analysis can identify regions in the image that are moving together coherently, and such information could be sufficient for many applications that utilize motion such as segmentation, compression, and tracking. We present an algorithm for tracking objects using our motion information to demonstrate the potential of this motion detection algorithm.

Learning Feature Trajectories Using Gabor Filter Bank for Human Activity Segmentation and Recognition

We describe a novel method for human activity segmentation and interpretation in surveillance applications based on Gabor filter-bank features. A complex human activity is modeled as a sequence of elementary human actions like walking, running, jogging, boxing, hand-waving etc. Since human silhouette can be modeled by a set of rectangles, the elementary human actions can be modeled as a sequence of a set of rectangles with different orientations and scales. The activity segmentation is based on Gabor filter-bank features and normalized spectral clustering. The feature trajectories of an action category are learnt from training example videos using dynamic time warping. The combined segmentation and the recognition processes are very efficient as both the algorithms share the same framework and Gabor features computed for the former can be used for the later. We have also proposed a simple shadow detection technique to extract good silhouette which is necessary for good accuracy of an action recognition technique.

Automatic Road Extraction using High Resolution Satellite Image Based on Texture Progressive Analysis and Normalized Cut Method

In this paper the approach for automatic road extraction for an urban region using structural, spectral and geometric characteristics of roads has been presented. Roads have been extracted based on two levels: Pre-processing and road extraction methods. Initially, the image is pre-processed to improve the tolerance by reducing the clutter (that mostly represents the buildings, parking lots, vegetation regions and other open spaces). The road segments are then extracted using Texture Progressive Analysis (TPA) and Normalized cut algorithm. The TPA technique uses binary segmentation based on three levels of texture statistical evaluation to extract road segments where as, Normalizedcut method for road extraction is a graph based method that generates optimal partition of road segments. The performance evaluation (quality measures) for road extraction using TPA and normalized cut method is compared. Thus the experimental result show that normalized cut method is efficient in extracting road segments in urban region from high resolution satellite image.

Nature of the colour-forming species in peroxy titanium sulphate

ALTHOUGH titanium is determined colorimetrically in aqueous sulphuric acid medium in presence of excess of hydrogen peroxide, the nature of the colour-forming species is not known definitely. Schwarz1 suggested that the colour was due to the peroxo-disulphato titanate anion [O 2Ti(SO4)2]2-. On the other hand, Jahr2 and later Gastinger3 considered that the colour of the compound was due to the peroxy titanyl cation [TiO2 aq.] 2+, and suggested the following equilibrium in solution: Schaeppi and Treadwell4 attributed the colour bo O2TiSO4 or [O2Ti(SO4)2]2-, whereas Babko and Volkova5 represented the coloured complex ion as [Ti(H 2O2)]4+. Mori, Shibata, Kyuno and Ito 6 regarded the coloured species as [TiO2 aq.]2+ or [Ti(OH)2 (H2O)(H2O2)] 2+, assuming the co-ordination number of titanium to be four. Thus, a variety of constitutions has been proposed to explain the colour-forming species of the titanium complex, based on the investigations carried out in dilute sulphuric acid medium, but the complex has not been isolated so far.

Fishes of the Darkness : Water colour-regulated competitive interactions in humic lakes

Humic lakes are abundant in the temperate and cold regions of the Boreal Zone. High levels of water colour and strong thermal stratification of humic lakes limit the potential fish habitats and give a special role to the intraspecific and interspecific interactions. Water colour has different effects on species depending on species-specific life-history traits and trophic interactions. Fish species whose success in predation is based on visual cues are more susceptible to suffer in competition. The main aim of the thesis was to demonstrate the effects of water colour on European perch (Perca fluviatilis) in humic lakes. The contribution of water colour to diet, feeding, growth and competitive interactions of fish was studied both in laboratory and in small humic lakes with varying levels of water colour. The main findings of the thesis were that water colour has different effects on species, depending on species-specific life-history traits and trophic interactions. Water colour affected visually-oriented perch feeding and growth negatively, and the prolonged benthic feeding phase of perch resulting from the increased water colour could increase intraspecific competition in perch populations and may result in a partial bottleneck in growth for perch. Moreover, water colour may act as a proximate factor behind the population dependency of sexual growth dimorphism in perch.

An eight-connected metal organic framework based on Cu(5) clusters: Synthesis, structure, magnetic and catalytic properties

A reaction of copper acetate, 5-nitroisophthalic acid in a water-methanol mixture under solvothermal condition results in a new metal-organic framework compound, [Cu(5)(mu(3)-OH)(2)(H(2)O)(6){(NO(2))-C(6)H(3)-(COO)(2)}(4)]center dot 5H(2)O, (1). The compound contains Cu5 pentameric cluster units connected by 5-nitro isophthalate (NIPA) moieties forming a CdCl(2)-like layer, which are further connected by another NIPA moiety forming the three-dimensional structure. The water molecules in (1) can be reversibly adsorbed. The removal of water accompanies a change in the colour as well as a structural re-organization. Magnetic studies suggest strong antiferromagnetie correlations between the Cu5 cluster units. The compound (1) exhibits heterogeneous Lewis acid catalysis for the cyanosilylation of imines with more than 95 % selectivity. Compound (1) has been characterized by IR, UV-vis, TGA, powder XRD studies.

Ba(3)(P(1-x)Mn(x)O(4))(2): Blue/green inorganic materials based on tetrahedral Mn(V)

We describe a blue/green inorganic material, Ba(3)(P(1-x)-Mn(x)O(4))(2) (I) based on tetrahedral MnO(4)(3-):3d(2) chromophore. The solid solutions (I) which are sky-blue and turquoise-blue for x <= 0.25 and dark green for x >= 0-50, are readily synthesized in air from commonly available starting materials, stabilizing the MnO(4)(3-) chromophore in an isostructural phosphate host. We suggest that the covalency/ionicity of P-O/Mn-O bonds in the solid solutions tunes the crystal field strength around Mn(V) such that a blue colour results for materials with small values of x. The material could serve as a nontoxic blue/green inorganic pigment.

A stochastic dynamical system for image segmentation

Image segmentation is formulated as a stochastic process whose invariant distribution is concentrated at points of the desired region. By choosing multiple seed points, different regions can be segmented. The algorithm is based on the theory of time-homogeneous Markov chains and has been largely motivated by the technique of simulated annealing. The method proposed here has been found to perform well on real-world clean as well as noisy images while being computationally far less expensive than stochastic optimisation techniques

Bilateral smoothing of gradient vector field and application to image segmentation

Medical image segmentation finds application in computer-aided diagnosis, computer-guided surgery, measuring tissue volumes, locating tumors, and pathologies. One approach to segmentation is to use active contours or snakes. Active contours start from an initialization (often manually specified) and are guided by image-dependent forces to the object boundary. Snakes may also be guided by gradient vector fields associated with an image. The first main result in this direction is that of Xu and Prince, who proposed the notion of gradient vector flow (GVF), which is computed iteratively. We propose a new formalism to compute the vector flow based on the notion of bilateral filtering of the gradient field associated with the edge map - we refer to it as the bilateral vector flow (BVF). The range kernel definition that we employ is different from the one employed in the standard Gaussian bilateral filter. The advantage of the BVF formalism is that smooth gradient vector flow fields with enhanced edge information can be computed noniteratively. The quality of image segmentation turned out to be on par with that obtained using the GVF and in some cases better than the GVF.

OTCYMIST: Otsu-Canny minimal spanning tree for born-digital images

Text segmentation and localization algorithms are proposed for the born-digital image dataset. Binarization and edge detection are separately carried out on the three colour planes of the image. Connected components (CC's) obtained from the binarized image are thresholded based on their area and aspect ratio. CC's which contain sufficient edge pixels are retained. A novel approach is presented, where the text components are represented as nodes of a graph. Nodes correspond to the centroids of the individual CC's. Long edges are broken from the minimum spanning tree of the graph. Pair wise height ratio is also used to remove likely non-text components. A new minimum spanning tree is created from the remaining nodes. Horizontal grouping is performed on the CC's to generate bounding boxes of text strings. Overlapping bounding boxes are removed using an overlap area threshold. Non-overlapping and minimally overlapping bounding boxes are used for text segmentation. Vertical splitting is applied to generate bounding boxes at the word level. The proposed method is applied on all the images of the test dataset and values of precision, recall and H-mean are obtained using different approaches.

MAPS: midline analysis and propagation of segmentation

Scenic word images undergo degradations due to motion blur, uneven illumination, shadows and defocussing, which lead to difficulty in segmentation. As a result, the recognition results reported on the scenic word image datasets of ICDAR have been low. We introduce a novel technique, where we choose the middle row of the image as a sub-image and segment it first. Then, the labels from this segmented sub-image are used to propagate labels to other pixels in the image. This approach, which is unique and distinct from the existing methods, results in improved segmentation. Bayesian classification and Max-flow methods have been independently used for label propagation. This midline based approach limits the impact of degradations that happens to the image. The segmented text image is recognized using the trial version of Omnipage OCR. We have tested our method on ICDAR 2003 and ICDAR 2011 datasets. Our word recognition results of 64.5% and 71.6% are better than those of methods in the literature and also methods that competed in the Robust reading competition. Our method makes an implicit assumption that degradation is not present in the middle row.