Search

The energy function of active contour model is not convex, so the solution of a minimization problem is prone to fall into a local minimum. Dealing with the problem, this paper proposed a novel convex active contour model for interactive color image segmentation. It defined a new energy function including not only image edge and color information, but also a spatial information term which was adaptively fused with the color information. It defined the spatial information term by fuzzy connectedness and introduced to get more accurate segmentation results. In the energy numerical minimization process, it used split Bregman method to obtain a global solution. Experimental results demonstrate that the proposed method can accurately and quickly get desired segmentation results. [ABSTRACT FROM AUTHOR]

The wind pressures on four 546 m height super-tall buildings, one basic building model with a square cross-section, one with tapered elevation, one with comer cut and one with open comer area of the equipment floors at three different heights (local aerodynamic strategy, LAS), were synchronously measured in a boundary layer wind tunnel. The distribution characteristics of fluctuating pressure, cross wind aerodynamic force (CWAF) and coherence of CWAF between different building height spacing, power spectrum density (PSD) of cross wind aerodynamic base bending moment (CWABBM) and wind induced response (WIR) were analyzed in detail. The results show that the LAS can significantly reduce the PSD of CWABBM near the vortex shedding frequency, and for the comer cut building model LAS can also effectively reduce remainder energy of vortex shedding that is reduced by comer cut on the corresponding without comer cut building. The appropriate position for LAS is 0.6 ~ 0.8 times building height range where the distribution of fluctuating wind pressure is stronger. The results show that across wind induced peak base bending moment(BBM) of 100 year return period of four buildings are reduced by 25.7%, 21.0%, 24.9% and 15.5% when the comer of the three equipment floors of the buildings are opened. And the LAS can make a reduction of 10% ~ 23% in wind induced peak BBM over a wide range of structural period ratio that varies from 0.60 to 1.35. [ABSTRACT FROM AUTHOR]

To establish the tensor model for color morphological operators, the paper proposed counter-harmonic mean-based color morphological operators by translating three-dimensional vectors into two-order positive definite symmetric tensors from HSV color space to tensor space. It used reference tensor method and tensorial similarity measure to construct input-preserving morphological operators. Finally, it conducted morphological gradient-based edge detection experiments to prove the feasibility and effectiveness of the proposed model. Experimental results show compared with traditional vector-based method, the tensor-based operators can get better effect. [ABSTRACT FROM AUTHOR]

The concept of S-rough set is introduced to represent images as S-rough sets for fitting complex background and noisy environment by combining migration characteristics. This model can remove pixels with singular nature from original object dynamically. A more adaptable technique of image thresholding segmentation is proposed by establishing a rough entropy to compromise the values of object roughness and background roughness. In order to adjust the transfer of singular points and avoid choice of granule size, images are further described by variable precision S-rough sets in combination with the notion of inclusion degree to extract object from background. Experimental results show that the proposals have better performance of thresholding segmentation of noised images. [ABSTRACT FROM AUTHOR]

Coix seeds from 9 different origins were taken as the research object. An attempt was made to achieve geographical origin traceability of Coix seeds through the combination of excitation-emission matrix (EEM) fluorescence spectroscopy with improved random forest algorithm. The improvements to the random forest algorithm mainly include two aspects, firstly, principal component analysis (PCA) was adopted to reduce the dimension of EEM fluorescent data; secondly, a grid search method was used to identify the optimal number of principal components(PCs) to retain and the hyperparameters of the discriminant model during the PCA dimension reduction process. The results showed that an improved random forest model, incorporating standard deviation normalization and PCA dimension reduction modules, based on Coix seeds EEM fluorescence spectroscopy data, accurately predicted the geographical origin of Coix seed samples from 9 different areas. The optimal model was constructed by combining 100 decision trees with a maximum depth of 3 and a minimum sample size of 1 at the leaf node, using 16 principal components (PCs). This model achieved 100% prediction accuracy for both the validation and test sets, which consisted of a total of 108 samples, outperforming the PLS-DA model constructed by the partial least squares method (96% prediction accuracy). [ABSTRACT FROM AUTHOR]