On Thursday 7 September, Prof. Jie Yang, Inst. for Image Processing and Pattern Recognition at the Shanghai Jiao Tong University in China will be giving a lunch seminar at MTW with the title "Recent Research on Two Applications of Medical Image Analysis: (a) Diabetic Retinopathy in Fundus Images; (b) Spiking neural network models for obstacle avoidance in simulated prosthetic vision".
In the first part, we address the issue related to diabetic retinopathy. Diabetic retinopathy has a serious complication that may lead to retina damage. We propose a local connectedness constraint and contrast normalization-based framework for micro-aneurysm detection, and a gradual removal of vascular branch-based framework for hemorrhage detection, and a dual-scale morphological segmentation-based framework for exudate detection. An assisted-diagnosis system for diabetic retinopathy is realized.
In the 2nd part of the presentation, we address a research issue related to prosthetic vision. The implementation of artificial human vision has long been proposed to provide restored vision for blind individuals. In recent years, electronic visual prosthesis has been developing rapidly as an encouraging neuro-engineering field to restore functional vision for the profoundly blind. We present a NeuCube-based obstacle avoidance system that may result in high classification result. The proposed NeuCube system has a spiking neural network architecture, which provides a useful obstacle avoidance for the blind in prosthetic vision. Unlike existing image processing strategy in prosthetic vision that only supplies enhanced phosphenes for the blind to fulfill the object recognition themselves, the proposed NeuCube-based obstacle avoidance system is shown to outputs the existing classification results.
Prof. Jie Yang received BSc degree in Automatic Control and MSc degree in Pattern Recognition & Intelligent System both from Shanghai Jiao Tong University (China), and PhD degree at Department of Computer Science, University of Hamburg (Germany). He has been a full Professor and Director of Institute of Image Processing and Pattern recognition at Shanghai Jiao Tong University. He is the principal investigator of more than 30 national and ministry scientific research projects in image processing, pattern recognition, data mining, and artificial intelligence, including two national 973 research plan projects, three national 863 research plan projects, four National Nature Foundation projects, six international cooperative projects with France, Sweden, Korea, Japan, New Zealand. He has published 5 books，more than 500 articles in national and international academic journals and conferences. He has supervised 5 postdoctoral, 36 doctors and 66 masters, being awarded 6 research achievement prizes from The Ministry of Education in China and Shanghai municipality. One Ph.D. dissertation he supervised was evaluated as the “National Best Ph.D. Dissertation” in 2009. Two Ph.D. dissertations he supervised were evaluated as “Shanghai Best Ph.D. Dissertation” in 2009 and 2010 respectively. He has also owned 32 patents.
Registered participants will be served a light lunch after the seminar. Please, email: firstname.lastname@example.org your name, where you work/study and any special diet needs. We will need your registration at the latest at 12:00 on 6 September.
When? 11:30-12:30 (13:00 incl. lunch) Thursday 7 September, 2017
Where? MTW Conference Room, Röda stråket 10B, Sahlgrenska University Hospital