讲座题目：Local N-ary Pattern and Its Extension for Texture Classification
主讲人：何祥健（University of Technology, Sydney）
Texture image classification is important in computer vision research. In order to effectively capture texture patterns, a distinctive feature such as local binary pattern (LBP) is needed. LBP is robust against monotonic and gray- scale variations and it is fast to compute. Its robustness and speed advantage has made it popular in various texture analysis applications. However, LBP is sensitive to noise, particularly smooth weak illumination gradients in near- uniform regions. In order to mitigate the effect of noise and increase distinctiveness, a local ternary pattern (LTP) is proposed. Compared to the binary coding LBP, LTP adopts ternary coding. As a result, LTP can better tolerate noise and is significantly more distinctive. These advantages of LTP effectively improve its classification accuracy. However, the potential of ternary coding is not fully explored in LTP because the ternary pattern is spitted into a pair of binary patterns. In our work, in order to fully explore the distinctiveness in the local pattern, the feature extraction process is formulated as an integer decomposition problem, which is a generalized version of the Bachet de Meziriac Weight Problem (BMWP). Following this generalization, a local n-ary pattern (LNP) is proposed, for which the LBP is a special case parametrized under n = 2. The LTP is not a special case of the LNP. Both LBP and LTP are used as benchmark methods to evaluate the LNP’s performances due to their well-recognized success. In addition, rotation invariant and uniform LNP is also proposed and compared to rotation invariant and uniform LBP. The proposed LNP achieves significantly improved texture classification accuracy when compared to LBP and also demonstrates considerable improvement over LTP.
Professor Xiangjian He, as a Chief Investigator has received various research grants including four national Research Grants awarded by Australian Research Council (ARC).
He is the Director of Computer Vision and Recognition Laboratory at the Global Big Data Technologies Centre (GBDTC) at the University of Technology, Sydney (UTS).
He is an IEEE Senior Member and an IEEE Signal Processing Society Student Committee member. He has been awarded ‘Internationally Registered Technology Specialist’ by International Technology Institute (ITI). He has been carrying out research mainly in the areas of image processing, network security, pattern recognition and computer vision in the previous years. He is a leading researcher for image processing based on hexagonal structure. He has played various chair roles in many international conferences such as ACM MM, MMM, IEEE CIT, IEEE AVSS, TrustCom and ICARCV.
In recent years, he has many high to top quality publications in IEEE Transactions journals such as IEEE Transactions on Computers, IEEE Transactions on Parallel and Distributed Systems, IEEE Transactions on Circuits and Systems for Video Technology, IEEE Transactions on Reliability, IEEE Transactions on Consumer Electronics, and in Elsevier’s journals such as Signal Processing, Neuro-computing, Future Generation Computer Systems, Computer Networks, Computer and System Sciences, Network and Computer Applications. He has also had papers published in premier international conferences and workshops such as CVPR, ECCV, ACM MM and WACV. His papers have been cited thousands of times.
He has recently been a guest editor for various international journals such as Journal of Computer Networks and Computer Applications (Elsevier) and Signal Processing (Elsevier). He has also been in the editorial boards of various international journals.
He has been a supervisor of postdoctoral research fellows and PhD students.
Since 1985, he has been an academic, a visiting professor, an adjunct professor, a postdoctoral researcher or a senior researcher in various universities/institutions including Xiamen University, China, University of New England, Australia, University of Georgia, USA, Electronic and Telecommunication Research Institute (ETRI) of Korea, University of Aizu, Japan, Hong Kong Polytechnic University, and Macau University.