Keynote Speech
Prof. Cheng-Lin Liu
Chinese Academy of Sciences, China

Director of NLPR; IEEE and IAPR Fellow

Cheng-Lin Liu is a Professor at the National Laboratory of Pattern Recognition (NLPR), Institute of Automation of Chinese Academy of Sciences, Beijing, China, and is now the director of the laboratory. He received the B.S. degree in electronic engineering from Wuhan University, Wuhan, China, the M.E. degree in electronic engineering from Beijing Polytechnic University, Beijing, China, the Ph.D. degree in pattern recognition and intelligent control from the Chinese Academy of Sciences, Beijing, China, in 1989, 1992 and 1995, respectively. He was a postdoctoral fellow at Korea Advanced Institute of Science and Technology (KAIST) and later at Tokyo University of Agriculture and Technology from March 1996 to March 1999. From 1999 to 2004, he was a research staff member and later a senior researcher at the Central Research Laboratory, Hitachi, Ltd., Tokyo, Japan. His research interests include pattern recognition, image processing, neural networks, machine learning, and especially the applications to character recognition and document analysis. He has published over 200 technical papers at prestigious international journals and conferences. He won the IAPR/ICDAR Young Investigator Award of 2005. He is an associate editor-in-chief of Pattern Recognition Journal, an associate editor of Image and Vision and Computing, International Journal on Document Analysis and Recognition, and Cognitive Computation. He is a Fellow of the IAPR and the IEEE.

Speech Title:  Deep Prototype Learning for Robust Pattern Recognition

Abstract: Existing pattern classification studies mostly concern the generalized classification accuracy, but ignore the rejection and robustness in open world. In recent years, deep learning methods achieved huge successes in pattern recognition, but the popular deep neural networks show inferior generalization when training with small sample and poor robustness to noise and outlier. In the talk, I first explain the robustness of pattern recognition, and introduce some methods for improving the robustness from the viewpoint of rejection. The rejection methods fall in two categories: ambiguity rejection and outlier rejection, which are based on different models and learning methods. I will give the formulations of two rejection modes and introduce some methods. Last, I will introduce a newly proposed deep learning method for robust pattern classification: deep convolutional prototype learning (CPL). The CPL uses a prototype classifier for classification, which is inherently robust to outlier. And combining with feature learning by convolutional neural network (CNN), the CPL yields high classification accuracy. Through regularization based on maximum likelihood (ML), the generalization performance on small sample and robustness can be further improved. The CPL model also shows potential in domain adaptation, online learning, novel class discovery, and so on.


Plenary Speech
Prof. Linlin Shen
Shenzhen University, China
Director of Computer Vision Institute and China-UK Joint Research Lab for Visual Information Processing

Prof. Linlin Shen is currently a professor at Computer Science and Software Engineering, Shenzhen University, Shenzhen, China. He is also a Honorary professor at School of Computer Science, University of Nottingham, UK. He serve as the director of Computer Vision Institute and China-UK joint research lab for visual information processing. He received the B.Sc. degree from Shanghai Jiaotong University, Shanghai, China, and the Ph.D. degree from the University of Nottingham, Nottingham, U.K. He was a Research Fellow with the University of Nottingham, working on MRI brain image processing. His research interests include deep learning, facial recognition, analysis/synthesis and medical image processing. Prof. Shen is listed as the Most Cited Chinese Researcher by Elsevier. He received the Most Cited Paper Award from the journal of Image and Vision Computing. His cell classification algorithms were the winners of the International Contest on Pattern Recognition Techniques for Indirect Immunofluorescence Images held by ICIP 2013 and ICPR 2016.

Speech Title: Deep Learning for Medical Image Analysis

Abstract: In this talk, I will mainly introduce deep learning and its applications in medical image analysis. Our work using facial analysis for depression analysis will be introduced and followed by our recent work in applying deep neural network for pathology based autoimmune disease, gastric and breast cancer diagnosis. Patch based strategy will be elaborated to address the small sample problem. Finally, Lung nodule detection and ophthalmology will be introduced.


Invited Speech
Dr. Junmei Zhong
Inspur USA Inc, USA

Dr. Junmei Zhong has been the Chief Data Scientist at Inspur USA Inc, Seattle, WA, USA since March 2017. He has both academic and industrial experiences with research interests ranging from data science, applied mathematics, machine learning, data mining, statistical analysis, NLP, text mining, digital advertising, information retrieval, knowledge graph, computer vision, pattern recognition, image processing, signal processing, to medical physics for CT and MR imaging. He was the Senior Principal Data Scientist at Spectrum Platform Company and Twelvefold Media Inc for content-based display advertising from 2015-2017. He was the Principal Data Scientist at Pitchbook Data Inc about NLP and graph theory from 2014 to 2015. He was the research faculty in University of Rochester, NY, and Assistant Professor in Cincinnati Children's Hospital Medical Center for improving CT imaging and MR imaging. He received his Ph.D. from EEE, The University of Hong Kong in 2000, M.S. about computer science from Nankai University and B.S. about computer science from Dalian University of Technology, China. In addition to many successful industrial projects, he has totally generated more than 20 publications in the prestigious journals and top conference proceedings with 3 patented technologies.

Speech Title: Edge-Preserving Image Denoising Based on Orthogonal Wavelet Transform and Level Sets

The level set approach has the potential to accomplish simultaneous noise reduction and edge preservation when it is used for image denoising. However, this kind of techniques is not very efficient for denoising very noisy images for their non-reliable edge-stopping criterion in the partial differential equation (PDE). In addition, the numerical calculation of curvature and other partial derivatives in the PDE is very sensitive to noise. In this paper, a new algorithm is developed to tackle such problems. Our idea is to first decompose the noisy image with the orthogonal wavelet transform (OWT) and then we only filter the noisy wavelet coefficients at the three finest scales without touching the wavelet coefficients at higher levels for reducing noise while preserving edge-related coefficients. The level-set based curve evolution is finally performed on the less-noisy image reconstructed from the denoised wavelet coefficients. Thus, the PDE model can be optimized by removing the Gaussian smoothing component. Furthermore, the numerical calculation of all partial derivatives in the PDE is influenced by less noise and the selective denoising becomes more efficient. Experimental results show that the proposed algorithm outperforms the conventional level set methods and generates state-of-the-art denoising results in edge preservation and noise reduction.