报告题目1:Research and application of image segmentation algorithm
报 告 人:Jinming Duan PhD, University of Nottingham, UK
报告人简介:Jinming Duan received the BSc degree from the Nanjing University of information science and technology, PR China, in 2011, and the MSc degree from the Qingdao University, PR China, in 2014. He is currently a second-year PhD student in computer science in the University of Nottingham, UK. His research interest focuses on computer vision and image processing, including image restoration, multiphase image segmentation, implicit surface reconstruction, medical image analysis. He has already published more than 10 peer-review international journal papers, in conjunction with several papers in important conferences.
报告摘要: Segmentation aims to automatically divide an observed image into useful segments of features with sharp boundaries such as buildings, desks, people or trees or organs or cars or whatever are within a picture. In this report, we are concerned with modelling multiple objects in different intensities (so called multiphase segmentation). A major problem to consider is how to represent each region with a characteristic function. Since different characteristic function leads to different computational complexity. Designing a proper characteristic function is thus crucial. In addition, there exist many studies in segmentation of images in planar 2D images. Not all methods can be generalised to the 3D. This report will assess a class of 2D models and methods, and explore the limit of how much we could generalise them to 3D. Both testing and development work will be done in the course. We are mainly concerned with the more reliable variational models. In such high dimensions, fast algorithms development is also a key component. The use of clinical data is linked to some form of CT, MRT, etc. On-going collaboration with oncology experts will be useful on the application and assessment stages.
报告题目2: 拓盟医疗影像处理系统的研究与应用
报 告 人:邱兆文 博士,黑龙江拓盟科技有限公司CTO
报告人简介:邱兆文,博士,副教授。黑龙江拓盟科技有限公司CTO,大发体育平台-(中国)科技公司,三维数字化技术研究所所长,CCF理事,CCF YOCSEF哈尔滨副主席。美国卡内基梅隆大学访问学者。
内容摘要:拓盟医疗影像处理系统对三维断层扫描数据进行滤波、分割、三维重建处理后形成可直接3D打印的stl格式文件。在医学上主要用于病情诊断、手术方案规划、手术风险评估等。介绍拓盟医疗影像处理系统在医疗、木材内部缺陷检测、动物体内肿瘤精准测量、矿石内部成份分析等领域的研究与应用。
时 间:2016年4月7日 下午14:00-16:00
地 点:成栋楼1016室
欢迎广大师生参与交流!