Tieming Su

Dalian University of Technology, Lü-ta-shih, Liaoning, China

Are you Tieming Su?

Claim your profile

Publications (14)2.49 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: Automatic face recognition is a challenge task, especially working in practical uncontrolled environments. Over the past two decades, numerous innovative ideas and effective processing approaches had been proposed and developed, e.g. various normalization techniques, intrinsic feature extractions and representation schemes, machine learning methods and recognition mechanisms etc. Those approaches based on different principles had been shown possessing varying degrees of effectiveness in different aspects. It is expected that the techniques of information fusion with integrating the advantages of existing methods will boost the recognition performance. This paper deals with developing effective approaches for face recognition using information fusion techniques based on integrating multiple cues. The multiple stage integrating techniques dedicated to localization of landmark points and pose estimation were presented. The precise data of localization of landmarks and pose estimation provide the essential geometry basics for further processing. A face recognition classifier scheme with integration of multiple feature representation and multiple block region scores is also proposed. The experiment results show that the proposed approach can reduce equal error rate EER significantly, compared with using single feature and single block representations. The proposed approach had been shown possessing the best performance in participating MCFR2011 competition.
    Journal of Signal Processing Systems 03/2014; · 0.55 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Automatic detection and precise localization of human eye centers are the essential processes in photo related multimedia applications. Since eye center points are used as reference base points for further intelligent processing, precise eye center localization is very important. In face recognition the accuracy of localization of eye centers directly influences the identification accuracy. A multiple stage approach with multiple cues for detection and precise localization of eye centers is presented in this paper. Multiple scopes searching strategy is used for correctly extracting eye patch images from the background. Dedicated gradient based features and curvelet based features are constructed and used for comprehensively revealing the intensity distribution characteristics and the edge based texture around eye centers. A rebuilt score calculation mechanism is proposed and the rebuilt scores are used as a specific measurement index reflecting the matching accuracy. The final localizations of eye centers are determined with integrating the gradient based scores and curvelet based scores. The experiment results testing on public face datasets show that the localization accuracy of proposed approach outperforms the accuracy with other state of the art methods.
    Multimedia Tools and Applications 02/2014; · 1.01 Impact Factor
  • Tieming Su, Xinpeng Qiu, Chunyan Yang
    [Show abstract] [Hide abstract]
    ABSTRACT: Under the Ontology-based collaborative design framework constructed by OWL and SWRL, in order to further extend the expression and reasoning abilities of domain knowledge description and to achieve the reasoning based on fuzzy theory, this paper expresses fuzzy domain knowledge by fuzzy logic and realizes the reasoning to make the design process more intelligent. First, fuzzy variables are formed by describing related fuzzy domain concepts and rules in OWL and SWRL. Fuzzy sets which are described by membership functions are then used to define fuzzy variables. At last, the fuzzy knowledge-based collaborative product design is completed by using fuzzy reasoning. A case of die selection shows the feasibility and intelligence of this approach.
    Cooperative Design, Visualization, and Engineering - 7th International Conference, CDVE 2010, Calvia, Mallorca, Spain, September 19-22, 2010. Proceedings; 01/2010
  • Tieming Su, Xinpeng Qiu, Yunlong Yu
    [Show abstract] [Hide abstract]
    ABSTRACT: A collaborative design system architecture based on ontology is proposed. In the architecture, OWL is used to construct global shared ontology and local ontology; both of them are machine-interpretable. The former provides a semantic basis for the communication among designers so as to make the designers share the common understanding of knowledge. The latter which describes knowledge of designer’s own is the basis of design by reasoning. SWRL rule base comprising rules defined based on local ontology is constructed to enhance the reasoning capability of local knowledge base. The designers can complete collaborative design at a higher level based on the local knowledge base and the global shared ontology, which enhances the intelligence of design. Finally, a collaborative design case is presented and analyzed.
    Cooperative Design, Visualization, and Engineering, 6th International Conference, CDVE 2009, Luxembourg, Luxembourg, September 20-23, 2009. Proceedings; 01/2009
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Intelligent mobile phones equipped with a camera are very popular in our daily lives now. Face verification running on mobile phone provides not only a tool for the protection of the owner's authority but also an approach for verification from a distance. The combination of biometrics and telecommunication technologies possesses broad application potentials in information exchanges. However, there are also some critical issues needing solving. Usually the processing power and memory size of a mobile phone system are limited, and the acquisition images are suffered from the illumination changes.
    International Journal of Distributed Sensor Networks 01/2009; · 0.92 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: A collaborative design system architecture based on Grid is proposed. The architecture can take full advantage of grid features such as computing capability, massive data storage and device sharing etc., which is more suitable for the development of a complex collaborative design environment compared with the widely used Distributed Component Object and existing Grid based collaborative design architectures. Under this architecture, the construction method of Grid services is researched. Parallel and distributed Grid computing technology is used to increase the efficiency of complex product design. A collaborative modeling method based on XML is put forward to support real-time modeling by using design semantics instead of 3D solid model data transport. Finally, a collaborative design prototype system based on Globus Toolkit 4.0 is presented and analyzed.
    Cooperative Design, Visualization, and Engineering, 5th International Conference, CDVE 2008, Calvià, Mallorca, Spain, September 21-25, 2008, Proceedings; 01/2008
  • Tieming Su, Xiaoliang Tai
    Proceedings of the 2008 International Conference on Modeling, Simulation & Visualization Methods, MSV 2008, Las Vegas, Nevada, USA, July 14-17, 2008; 01/2008
  • Tieming Su, Xiaoliang Tai, Zhixiang Xu
    [Show abstract] [Hide abstract]
    ABSTRACT: Aiming at improving the design and assembly efficiency of complex products in collaborative design, this paper proposes a parallel assembly model which is based on parallel computing. It divides assembly task into subtasks according to main branch in the virtual-link structure, and finally the subtasks run in parallel. This model supports large scale design, improves the speed and at the same time improves the computing resource utilization of collaborative design in Grid environment. A collaborative design prototype system based on Grid, which takes hybrid CSG/B-Rep model as geometric kernel, is developed to realize parallel assembly. Experimental results obtained from Lenovo DeepComp 1800 System are displayed and analyzed.
    Cooperative Design, Visualization, and Engineering, 5th International Conference, CDVE 2008, Calvià, Mallorca, Spain, September 21-25, 2008, Proceedings; 01/2008
  • [Show abstract] [Hide abstract]
    ABSTRACT: Nonlinear dimension reduction method Isomap has demonstrated promising performance in finding low dimensional manifolds from data points in the high dimensional input space. The Isomap method estimates geodesic distance between data points instead of taking the Euclidean distance and then uses multidimensional scaling (MDS) to induce a low dimensional embedding from the geodesic distance graph. However, since the original prototype Isomap does not discriminate data acquired from different classes, when concerned with multi-class data, several isolated sub-graphs will result in undesirable embedding. In this paper, a hierarchical Isomap algorithm is proposed for the multi-class data, which first computes within-class and between-class geodesic distances separately and the final embedding is obtained from the augmented geodesic distance matrix using MDS. The experimental results reveal a promising performance of the proposed algorithm.
    Automatic Identification Advanced Technologies, 2007 IEEE Workshop on; 07/2007
  • Advances in Biometrics, International Conference, ICB 2006, Hong Kong, China, January 5-7, 2006, Proceedings; 01/2006
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a novel feature optimization method to build a cascade Adaboost face detector for real-time applications, such as teleconferencing, user interfaces, and security access control. AdaBoost algorithm selects a set of weak classifiers and combines them into a final strong classifier. However, conventional AdaBoost is a sequential forward search procedure using the greedy selection strategy, the weights of weak classifiers may not be optimized. To address this issue, we proposed a novel Genetic Algorithm post optimization procedure for a given boosted classifier, which yields better generalization performance.
    12/2005: pages 121-128;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a novel approach for eye detection using a hierarchy cascade classifier based on Adaboost statistical learning method combined with SVM (Support Vector Machines) post classifier. On the first stage a face detector is used to locate the face in the whole image. After finding the face, an eye detector is used to detect the possible eye candidates within the face areas. Finally, the precise eye positions are decided by the eye-pair SVM classifiers which using geometrical and relative position information of eye-pair and the face. Experimental results show that this method can effectively cope with various image conditions and achieve better location performance on diverse test sets than some newly proposed methods.
    Advances in Neural Networks - ISNN 2005, Second International Symposium on Neural Networks, Chongqing, China, May 30 - June 1, 2005, Proceedings, Part II; 01/2005
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a novel feature optimization method to build a cascade Adaboost face detector for real-time applications on cellular phone, such as teleconferencing, user interfaces, and security access control. AdaBoost algorithm selects a set of features and combines them into a final strong classifier. However, conventional AdaBoost is a sequential forward search procedure using the greedy selection strategy, redundancy cannot be avoided. On the other hand, design of embedded systems must find a good trade-off between performances and code size due to the limited amount of resource available in a mobile phone. To address this issue, we proposed a novel Genetic Algorithm post optimization procedure for a given boosted classifier, which leads to shorter final classifiers and a speedup of classification. This GA-optimization algorithm is very suitable for building application of embed and resource-limit device. Experimental results show that our cellular phone embedded face detection system based on this technique can accurately and fast locate face with less computational and memory cost. It runs at 275ms per image of size 384×286 pixels with high detection rates on a SANYO cellular phone with ARM926EJ-S processor that lacks floating-point hardware.
    Advances in Natural Computation, First International Conference, ICNC 2005, Changsha, China, August 27-29, 2005, Proceedings, Part III; 01/2005
  • [Show abstract] [Hide abstract]
    ABSTRACT: Mutual information (MI)-based image registration is effective in registering medical images, but it is computationally expensive. This paper accelerates MI-based image registration by dividing computation of mutual information into spatial transformation and histogram-based calculation, and performing 3D spatial transformation and trilinear interpolation on graphic processing unit (GPU). The 3D floating image is downloaded to GPU as flat 3D texture, and then fetched and interpolated for each new voxel location in fragment shader. The transformed results are rendered to textures by using frame buffer object (FBO) extension, and then read to the main memory used for the remaining computation on CPU. Experimental results show that GPU-accelerated method can achieve speedup about an order of magnitude with better registration result compared with the software implementation on a single-core CPU.
    Transactions of Tianjin University 15(5):375-380.