一种新颖的低层视觉特征到高层语义的映射方法*

通过在低层视觉特征上提取图像的局部颜色和纹理特征,再利用模糊神经网络建立低层视觉特征和高层语义特征之间的映射,实现了图像属性信息的有效传递和可靠检索.最后,为了提高检索效率,把相关反馈引进到图像检索系统中.实验证明,该方法取得了较好的检索查全率和准确率.     

一种新的基于梯度方向直方图的图像配准方法*

构建了一种新的局部梯度方向直方图,同时定义了特征点的主方向,从而提出了一种具有旋转不变性的图像配准算法.首先采用高斯加权求模技术对特征点邻域内的像素的梯度作直方图统计,确定出具有旋转不变性和抗噪性的特征点主方向;然后用主方向作角度直方图统计,确定待配准图像之间的旋转角度.根据得到的特征点信息及旋转角度定义了特征点对互信息匹配准则,这样使得新配准算法对于图像间旋转角度的范围没有限制,获得了良好的配准效果.     

粗糙集理论及其在图像处理中的应用*

首先描述了粗糙集理论的基本概念,包括粗糙集知识表示方法和粗糙集约简理论;叙述了粗糙集理论及其与其他非线性理论相结合在图像处理中的应用情况;最后指出了粗糙集理论应用于图像处理的基本思路,并指出将粗糙集理论与其他非线性理论相结合应用于图像处理,将会产生更加有效的结果.     

PPV Nanotube Sensor Arrays for Explosives Identification by Excitation Wavelength Regulation

The development of sensitive materials for standard and improvised explosives is greatly significant to homeland security. In this paper, the phosphotungstate (NaPT) doped polyphenylene vinylene (PPV) nanotube arrays (NTAs), with excellent optical response, chemical stability, and larger specific surface area, are successfully fabricated by means of the “precursor film” infiltration method. The efficient charge carriers' separation of PPV NTAs can be achieved by doping NaPT to realize the photoelectric detection of explosive vapors. In addition, the identification of six explosives, including ammonium nitrate (AN), dinitrotoluence (DNT), picric acid (PA), p-nitrotoluene (PNT), triacetone triperoxide (TATP), and trinitrotoluene (TNT), can also be realized through the fingerprint atlas. Moreover, the adsorption energy and excited oscillator intensity has also been employed to explain the interaction between NaPT doped PPV nanotube arrays and various explosive molecules. Obviously, the NaPT doped PPV developed has the potential to be used as an explosive sensor.     

Microstructural modeling approach applied to rock material

The importance of the microstructural parameters in rock mechanical behavior has been investigated by several authors. Moreover, the Weibull statistical model has been used to characterize the heterogeneity of several materials on the basis of the concept that the microscopic defects within the material determine their mechanical strength. The modeling of different rocks is a topic that is fundamental for the prediction of rock fragmentation. In this article, the analysis of rock microstructure is performed using the microstructural modeling approach, which consists of the simplification, quantification, and modeling of the main properties of rock microstructure. The grain size, grain shape, and microcracks are modeled by means of statistical density functions, namely, Cauchy, chi-squared, exponential, extreme value, gamma, Laplace, normal, uniform, and Weibull. It is found that the Weibull distribution is the most appropriate statistical model of the grain size and grain shape, when compared with the other eight statistical models. Regarding microcracks, the results show that the gamma distribution is the most appropriate model. The Weibull and gamma distributions are then used to analyze the heterogeneity of the microstructure. This is done by comparison of the statistical models of each microstructural property evaluated in several thin sections of the same rock. It is found that with respect to grain size and grain shape, the rock is homogeneous, while the size distribution of the microcracks shows a clear trend toward less homogeneity. The microstructural modeling approach is important for modeling, characterizing, and analyzing the microstructure of rock material. Among other applications, it can be used to explain differences in the mechanical behavior obtained in testing several specimens.     

基于网络文本的山地景观游客行为与形象感知研究——以重庆市长嘉汇弹子石老街为例

剖析网络评价文本能为景观规划设计提供科学的依据支撑,弥补因快速城镇化建设发展而导致的公众参与不足,对于景观设计而言是非常重要的。以重庆市弹子石老街为例,基于网络文本内容分析法,利用rostcm6、excel及python等分析和数据抓取软件,采集大众点评的相关评论数据,以山地景观设计视角结合相关数据分析软件进行定性定量分析并制作可视化分析图,最终从多维度分析游客评论得出结果及改进建议,总结针对重庆弹子石老街及山地景观设计的6条设计策略:(1)交通可达的组织方式;(2)垂直上下的衔接转换;(3)对景远眺的外向空间;(4)本土文化的特色彰显;(5)城市事件的策划安排;(6)游览夜景的慢行系统,期望对今后的类似山地景观空间规划设计提供一定参考和借鉴价值。     

高铬铸铁中铌碳化物的辨认

介绍了用背散射象法、彩色金相法和扫描电镜分析区别铬碳化物和铌碳化物。     

梭式窑火焰数字图像的边缘检测初探

本文介绍了几种典型的边缘检测算法,对它们各自的特点进行了比较。对梭式窑内的一幅原始图像,可用边缘检测算法提取火焰图像的边缘。     

基于Bayes特征判别的选煤建模与识别

研究了煤块的Harr小波变换和幅度投影分析,在对原始图像进行特征判别分析的基础上,建立了煤块和煤矸石的统计模型,提出了用Bayes判别函数分选煤块和煤矸石的算法,实现了用计算机视觉系统对样本进行了识别检验.并运用神经网络BP算法进行训练识别,检验其正确性,最后通过实验验证了算法有效性.     

Augment low-field intra-operative MRI with preoperative MRI using a hybrid non-rigid registration method

Background

Preoperatively acquired diffusion tensor image (DTI) and blood oxygen level dependent (BOLD) have been proved to be effective in providing more anatomical and functional information; however, the brain deformation induced by brain shift and tumor resection severely impairs the correspondence between the image space and the patient space in image-guided neurosurgery.

Method

To address the brain deformation, we developed a hybrid non-rigid registration method to register high-field preoperative MRI with low-field intra-operative MRI in order to recover the deformation induced by brain shift and tumor resection. The registered DTI and BOLD are fused with low-field intra-operative MRI for image-guided neurosurgery.

Results

The proposed hybrid registration method was evaluated by comparing the landmarks predicted by the hybrid registration method with the landmarks identified in the low-field intra-operative MRI for 10 patients. The prediction error of the hybrid method is 1.92 ± 0.54 mm, and the compensation accuracy is 74.3 ± 5.0%. Compared to the landmarks far from the resection region, those near the resection region demonstrated a higher compensation accuracy (P-value = .003) although these landmarks had larger initial displacements.

Conclusions

The proposed hybrid registration method is able to bring preoperatively acquired BOLD and DTI into the operating room and compensate for the deformation to augment low-field intra-operative MRI with rich anatomical and functional information.