基于互相关的印花织物疵点检测

为实现印花织物中疵点的自动检测,以互相关理论为基础,结合图像处理技术,以MatLab7.0构建了一套印花织物疵点自动检测系统。在疵点检测过程中,提出以加和表理论为基础实现互相关系数的快速计算。通过对软件模拟的印花花纹疵点的识别,说明这个系统能够实现印花过程中常见的花纹偏移、颜色色差等疵点的自动检测。实际印花织物疵点的检测实验表明,所提出的算法具有有效性、鲁棒性等优点。通过比较不同子窗口大小的检测结果,选定25像素×25像素作为最终检测系统中子窗口的大小。

基于视频跟踪和FSA的车辆行为模式分析

提出一种基于视频跟踪和有限状态自动机的运动车辆行为表达与分析方法。采用减背景法得到前景运动车辆,基于快速归一化互相关理论,通过预测实现车辆跟踪,得到准确的车辆运动轨迹。利用有限状态自动机,将车辆的行为表达为连续的微观行为状态,从而在运动跟踪的基础上,结合时域与空域信息分析车辆行为模式。对交叉路口的运动车辆进行跟踪实验,结果表明,该方法能够准确得到车辆的状态信息。

Bulgaria,Boosting Energy Cooperation with China——Interview with Deputy Minister Yaneva,Ministry of Economy and Energy,the Republic of Bulgaria

Deputy Minister Yaneva of Economy and Energy,the Republic of Bul- garia,a nice lady with outstanding talents,headed a delegation of Bulgaria to visit China in late June,for the participation at the 13th Bulgarian-Chi- nese Intergovernmental Commission for Economic,Trade,Scientific and Technical Cooperation.As an important instrument,the Joint Commission played a significant role in promoting the overall development of the bilat- eral economic relations. China's Foreign Trade interviewed Deputy Minister Yaneva and she gave very constructive suggestions on promoting the bilateral economic and trade cooperation between the two countries,especially in the area of energy cooperation.The following is a written interview with Deputy Min- ister Yaneva.

基于多子窗口快速归一化互相关的肿瘤识别

对肿瘤进行快速准确地精细分割和生长监控是当前医学图像实时处理需要解决的一个问题,本文通过使用基于加和表的快速归一化互相关(FNCC)方法提高肿瘤识别速度,通过大子窗口技术提高肿瘤识别的正确度,通过多子窗口技术实现肿瘤的精细分割。对人体脑部核磁共振(MR)图像的肿瘤进行识别实验表明,本文方法可以很好地实现肿瘤的快速准确精细分割和生长监控。