一种改进的自适应模糊阈值图象分割方法

自适应模糊阈值图象分割方法的关键和困难在于隶属函数窗宽的自动调整和阈值搜索范围的确定.依靠图象灰度的统计特性初步确定阈值搜索范围，提出了一种改进方法，进而得到隶属函数的窗宽.实验表明这种方法避免了确定图象灰度直方图峰位置的困难，对较低亮度图象分割效果良好.     

机器人头部的视觉跟踪系统研究

对运动目标进行识别和跟踪是机器人视觉的一项关键技术。提出了一种可以快速跟踪运动目标的系统设计方案,采用了双计算机处理和Memolink通信方式的机器人控制结构,以图像处理为基础,在图像经过校正之后,通过区域分割和目标识别两个步骤来确定目标的位置,并控制机器人对目标进行跟踪。实验表明,该方法具有较高的速度和准确性。     

运用反例基于识别的手写数字串分割

采用基于识别的分割方法进行手写数字串分割.在识别的过程中,运用反例样本估计分类器参数,实验数据表明,这种运用反例样本训练的分类器与没有经过反例样本训练的分类器相比,将提高拒识率到19%左右,从而保证了较高的识别率,验证了只有经过反例训练的分类器的输出结果才是可信赖的.     

一种基于代价函数和模糊熵的图像分割方法

提出了一种基于代价函数和模糊熵的图像分割方法.该方法先用代价函数最小化法对退化的图像作预处理,之后,利用模糊熵作进一步的处理.实验结果表明:新方法和一般的阈值分割方法相比,不但分割图像的错分率较小,而且图像的视觉效果也有较大的改善.     

基于小波变换及布朗分形模型的纹理分割

在研究小波变换及布朗分形模型的基础上，定义了水平分维数，垂直分维数，对角分维数，并将它们作为纹理特征量来实现纹理的分割．实验结果表明，这些特征量能够很好地反映纹理特征，从而分割时不需有关图象中纹理类别的先验信息，较以往方法在准确度和计算复杂程度上都有很大提高．     

Two methods for semi-automated quantification of changes in ventricular volume and their use in schizophrenia

Two semi-automated methods for quantification of ventricular volume change from baseline and follow-up magnetic resonance imaging scans have been developed. Technique 1 employs direct segmentation of the ventricles from both the scans using thresholding and contour extraction. Technique 2 operates on difference images produced by voxel based intensity subtraction of the baseline from the registered follow-up images. Here, all voxels with intensities above a noise threshold and in a restricted area are monitored to compute volumetric changes. In phantom measurements the first technique was accurate to 0.0046%, the second to 0.167% of the phantom volume. Results from normal volunteers was that the average ventricular volume changed by 1.52% and 1.54% for images acquired within 9 months using techniques 1 and 2, respectively. With schizophrenic patients mean change of 10.78% and 9.43% were found employing the first and second procedures, respectively. All measurements agreed with a radiologist’s visual grading of the changes. Robust, objective, fast, easy-to-use, and fairly accurate procedures have been developed and validated to quantify volumetric changes.     

Low-level radiometric detection in LC using solvent segmentation and an effluent storage loop

Summary In this study a new approach is presented for on-line radiometric detection in reversed phase LC of medium to low polarity compounds labelled with¹⁴C. The test compounds,¹⁴C-carbaryl and¹⁴C-parathion, are extracted post-column into a non-water miscible liquid scintillation cocktail. The segmented two-phase system formed is introduced into the beta-detector without phase separation and collected in a capillary storage tube. After completion of the LC separation and detection process, the direction of the flow in the storage system is reversed and the segmented contents of the loop led at lower flow-rates through the beta-detector again. An enhanced signal, corresponding to the increase in counting time is obtained without measurable peak broadening. The lowest possible detection limit of the system is 9 counts per peak corresponding to subnanogram quantities of tested pesticides. Calibration curves are linear over at least 2 orders of magnitude and have the expected theoretical slopes. The reproducibility of the system is better than 4 % rel. S.D. An application to a recovery study of parathion shows the practical potential of this technique. Presented at the 15th International Symposium on Chromatography, Nürnberg, October 1984     

基于COLLATE融合多图谱的心脏电影MRI右心室分割

右心室分割对肺动脉高压等疾病的心功能分析具有重要的临床意义.然而，右心室心肌薄、易变且不规则，其传统的医学图像分割方法仍然未能取得突破性进展.本文提出基于COLLATE（Consensus Level，Labeler Accuracy and Truth Estimation）的多图谱分割方法，首先以归一化互信息为相似测度对目标图像和图谱集进行B样条配准以获取粗分割结果；然后利用COLLATE对粗分割结果进行融合；最后采用基于形状约束的区域生长算法修正出现错误的数据.10例临床心脏磁共振短轴电影图像被用于算法验证.本文还将使用基于COLLATE的多图谱分割方法得到的结果与深度学习算法及手动分割进行了比较.结果显示与深度学习算法比较，使用本文算法得到的射血分数（Ejection Fraction，EF）与手动分割更加一致和相关，表明该算法的分割结果有望辅助临床心脏功能诊断.     

A high accuracy flow segmentation method in crowded scenes based on streakline

Flow segmentation based on similar motion patterns in crowded scenes remains an open problem in computer vision due to inherent complexity and vast diversity found in such scenes. To solve this problem, the streakline framework based on Lagrangian fluid dynamics had been proposed recently. However, this framework computed optical flow field using conventional optical flow method (Lucas Kanade method) which has poor anti-interference performance, and serious deviation would be brought to the computation of optical flow field. Moreover, our experimental results show that using the formulation of streak flow similarity in this framework can result in incorrect flow segmentation. Therefore, we combine this framework with a high accurate variational model, and modify the corresponding formulation of streak flow similarity after analyzing the streakline framework in detail. Finally, an improved method is proposed to solve flow segmentation in crowded scenes. Experiments are done to compare these two methods and results verify the validity and accuracy of our method.