A Semi-automatic Method Based on Statistic for Mandarin Semantic Structures Extraction in Specific Domains

This paper proposed a new method of semi-automatic extraction for semantic structures from unlabelled corpora in specific domains. The approach is statistical in nature. The extracted structures can be used for shallow parsing and semantic labeling. By iteratively extracting new words and clustering words, we get an inital semantic lexicon that groups words of the same semantic meaning together as a class. After that, a bootstrapping algorithm is adopted to extract semantic structures. Then the semantic structures are used to extract new key words and augment the semantic lexicon. The resultant semantic structures are interpreted by persons and are amenable to handediting for refinement. In this experiment, the semi-automatically extracted structures SSA provide recall rate of 84.5%.     

数字监控系统中基于阴影消除的目标自动提取

智能视频监控系统需要从静止摄像头拍摄的实际视频序列中抽取并跟踪运动物体，剔除物体的阴影区域。为此，本文提出一种基于图像边界差值信息的消除阴影的前景检测算法，利用阴影区域图像的边界信息与背景相比基本保持不变的特征，抽取输入图像与背景边沿特征的差值。这样图像前景区域特别是边界附近差值比较大，而背景和阴影区域差值比较小。接着本文采用基于固定网格的围线模型，从图像的外框开始，由外向内收敛，最后收敛围线就是前景物体的边界。实验结果表明，与其他前景检测算法相比，本文算法效率高，前景检测准确率高，可以非常好地消除图像噪声、室内阴影和室外弱阴影。     

一种改良式质粒DNA提取方法的建立与应用

目的建立一种稳定、可靠的质粒DNA提取改良方法,探讨其在分子生物学实验研究中的应用价值。方法将含有目的质粒的菌株扩增后,运用改良后的碱裂解法进行质粒DNA小量提取,微量核酸仪测定提取质粒DNA的产量及纯度;采用琼脂糖凝胶电泳、内切酶酶切及质粒转染真核细胞鉴定提取质粒DNA的质量及转染效率。结果改良式质粒提取方法获得质粒DNA产量为3.2 mg/L菌液,A260/280=1.91;内切酶酶切完全;质粒DNA以超螺旋结构为主;真核细胞转染效率为20%左右。结论改良式质粒DNA抽提方法操作简单、实用,获得质粒DNA产量多、质量高,能达到分子生物学常规实验的要求。     

基于混沌遗传算法的基元提取

提出了一种直接在灰度图像上进行基元提取的方法．与传统基元提取方法相比，该方法不需对灰度图像进行边缘检测二值化处理，而是利用图像边缘的梯度信息对混沌遗传算法导向，直接在灰度图像上提取基元．同时，该方法也避免了Hough变换高的时空开销问题．仿真表明该方法方便、有效并具有较高稳定性．     

基于内在因素提取的内河航运量神经网络预测方法

内河航运量预测是内河航道网规划的依据,利用主成分分析法提取影响内河航运量的内在因素,利用内在影响因素与内河航运量之间的联系,结合BP神经网络建立模型对内河航运量进行预测.算例表明,该模型可以提高预测精度.     

航空影像的直线特征检测算法

提出了从高分辨率航空影像中提取直线的算法．该算法首先检测出图像的边缘特征，以Freeman码表达连续的边缘，通过构造直线段上下一个像素可能位于的区域，将检测一段边缘线是否为直线段的复杂问题简化为一个简单的边缘条件判断问题．     

Hepatic CT image query based on threshold-based classification scheme with gabor features

Hepatic computed tomography(CT) images with Gabor function were analyzed.Then a threshold-based classification scheme was proposed using Gabor features and proceeded with the retrieval of the hepatic CT images.In our experiments, a batch of hepatic CT images containing several types of CT findings was used and compared with the Zhao's image classification scheme, support vector machines(SVM) scheme and threshold-based scheme.     

A HOS-based blind signal extraction method for chaotic MIMO systems

A novel method to extract multiple input and multiple output （MIMO） chaotic signals was proposed using the blind neural algorithm after transmitting in nonideal channel. The MIMO scheme with different chaotic signal generators was presented. In order to separate the chaotic source signals only by using the sensor signals at receivers, a blind neural extraction algorithm based on higher-order statistic （HOS） technique was used to recover the primary chaotic signals. Simulation results show that the proposed approach has good performance in separating the primary chaotic signals even under nonideal channel.     

声纹特征提取的关键技术研究

声纹在很多领域具有重要作用。为了对某声音信号的声纹特征进行提取,本文对声音信号进行时域分析,并建立相应的特征提取函数。结合多组滤波器对声音信号进行处理,获得了生纹特征频谱响应曲线。计算结果表明,提取得到的各声纹频率响应函数分界明显,中间值较少,声纹特征提取效果较好。同时,本文建立的特征提取模型具有计算速度快,计算精度高等优点,能够以最小的时间成本获得较好的声纹提取效果。     

基于混合高斯模型的道路背景提取方法研究

针对单高斯模型对道路背景提取的不足,提出一种基于混合高斯模型的道路背景提取方法。利用多个高斯分布组成混合高斯模型来表示道路背景图像中的各个像素点,并且针对该算法利用MATLAB进行仿真实验,实验结果验证了基于混合高斯模型的道路背景提取方法的实用性和有效性。