E-mail: caixunzh AT sdu DOT edu DOT cn

  • Research interests: Image/Video Recognition; Optimization Algorithm; Digital Signal Processing.
  • Cai Xun is an Associate Professor in the Department of Computer Science and Technology at Shandong University. She graduated with a BA in Industrial Automation from the Department of Controller and Engineer of Shandong University, MS in Application of Computation from Shandong University, and Ph.D. in Computer Science from Shandong University.
  • Cai Xun's research aims to improve the design and efficiency of complex systems such as video surveillance systems and automation controller system by using some machine learning methods such as machine learning methods, especially neural network, SVM and other new techniques of optimization algorithms. She is also interested in digital signal processing to improve the object recognition and tracing. She is very interested in how to reduce the various illumination effects of image recognition and how to speed the convergence and reduce the complexity of neural network. Her research in UTA as a visitor lightens her that the deeply learning the theory of optimization algorithms and digital processing is needed for solving practically relevant problems . Her recent work examines how to improve the convergence of neural network.


  • [1] Training multilayer perceptron by using optimal input normalization,Cai, Xun,Tyagi, Kanishka , Manry, Michael T. . 2011 IEEE International Conference on Fuzzy Systems: 2771-2778.
  • [2]An optimal construction and training of second order RBF network for approximation and illumination invariant image segmentation; Cai, Xun , Tyagi, Kanishka (2); Manry, Michael T. (2), 2011 International Joint Conference on Neural Networks, IJCNN 2011: :3120-3126
  • [3] Background color constancy algorithm based on neural network. Long, Jiang1;Xun, Cai. 2nd International Workshop on Computer Science and Engineering, WCSE 2009. 10.28-10.30, 2009, :272-275.
  • [4] A new neural network algorithm based on conjugate gradient and output weight optimization; Li, Yongming (1); Cai, Xun (1); Li, Ming (1); Proceedings - 2011 7th International Conference on Natural Computation, ICNC 2011: 38-42.
  • [5] Fuzzy C-means clustering based construction and training for second order RBF network;Tyagi, Kanishka ; Cai, Xun ; Manry, Michael T. , FUZZ 2011 - 2011 IEEE International Conference on Fuzzy Systems – Proceedings: 248-255
  • [6]A new region Gaussian background model for video surveillance. Cai,Xun; Hao, Xingwei; Jiang,Long; Meng, Xiang-xu. The Fourth International Conference on Neural Computation, 10.18-20, 2008.vol 6, n1: 123-127
  • [7] 一种基于Phong反射模型颜色不变性的阈值分割算法. 蔡珣, 孟祥旭. 中国计算机学报, vol.32, n2,2009:282-287
  • [8] An New Image Segmentation for Virtual Background Reconstruction. Cai Xun, Meng Xiang-xu, Cai Fei, Jiang Long. 电子学报(英文版), vol.17, n.2, 2008: 223-226
  • [9] Video-based Virtual-Reality Game System. Cai Xun,Meng Xiang xu, Yu Kuan, Cai Fei. Journal of Computational Information Systems, v2, n2, June, 2006: 745-749
  • [10]一个新的基于区域的高速公路多车辆跟踪方案. 蔡珣,孟祥旭,刘强. 光电工程, v33, n6, 2006: 20-23
  • [11] 光照色调颜色恒常性算法研究. 蔡珣,孟祥旭,向辉.中国图像图形学报, v9, no.8, 2004: PP.922-926
  • [12]基于视频识别的虚拟踩气球系统. 蔡珣, 孟祥旭.小型微型计算机系统, v25, n6, 2004: PP.1089-1091

  • 教学

    • Fall 2012: The Fundamental Theory of Digital Signal Processing
    • Spring 2010: The Introduction of Computer Culture
    • Fall 2009: The Fundamental Theory of Digital Signal Processing