The 2nd International Conference on Image and Signal Processing (CISP’09) was held during October 17–19, 2009 in Tianjin, China. Tianjin is a financial and commercial center in Northern China. At this dynamic city with a long and splendid history, CISP’09 turned out to be a big success. The conference attracted a total of 2,030 submissions from over 30 countries and regions. After rigorous reviews, 1,092 high-quality papers were accepted and included in the CISP’09 proceedings. Then, the program committee of the conference identified about 30 best papers for this special issue, all of which are related to multimedia research. The authors of the selected papers were asked to submit substantially expanded versions of their conference papers to the special issue. After a standard review of the expanded papers, 17 of them were accepted and included in this special issue. These papers cover a wide range of topics related to multimedia tools and applications. They should represent the state of the art research in the multimedia area, as evidenced by their brief description below.

  • S.P. Sun, Y.J. Chou, and Y.H. Chiu propose a multimedia 3D clinical planning system that simulates internal fixation surgeries for calcaneal collapse, by using full-scale computer-assisted engineering techniques in the design and development of preoperative planning modules.

  • S. He, C. Xing, and P. Zhao suggest a frame interpolation algorithm for applications of low-bit-rate video coding.

  • R. Liu, X. Zhou, N. Wang, and M. Zhang propose an eye tracking algorithm and an automatic focusing technique for acquiring clear eye images by an eye-gaze tracking system.

  • J. Hou, J. Qian, W. Zhang, Z. Zhao, and P. Pan present a novel adaptively updating target extraction algorithm for fire detection in large space structures.

  • X. Su, L. Ji, and X. Li propose an algorithm of low complexity and fast speed for H.264/AVC intra prediction.

  • F. Zhang, and Q. Zhu propose a new calibration method of single viewpoint constraint for catadioptric omni-directional vision.

  • Y. Xiang, L. Feng, S. Xie, and Z. Zhou propose an efficient spatio-temporal boundary matching algorithm for video error concealment.

  • X. Jiang, T. Sun, and S. Wang propose a novel visual feature representation for automatic video content classification, which is shown to be effective in differentiating among various video contents.

  • H. Song, and M. Shen propose a novel algorithm for real-time target tracking, by incorporating target corner detection into the optical flow algorithm.

  • Y. Zou, G. Shi, H. Shi, and H. Zhao present a state-of-the-art traffic incident detection system for automatic traffic incident detection at urban road intersections.

  • M. Shi, R. Fu, Y. Guo, B. Xu, and S. Bai propose an approach for developing an automated fabric defect detection system using local contrast deviation.

  • Y. Shan, and J. Liu employ several new cross-channel compensation techniques to develop a novel dynamic Gaussian selection algorithm for tackling the speaker recognition problem.

  • J. Zhang, Q. Chen, Q. Sun, H. Sun, and D. Xia propose an improved Harris-Laplace feature detector with a high repeatability for local feature detection in object recognition and object tracking.

  • X. Lu, S. Matsuda, M. Unoki, and S. Nakamura propose a novel noise reduction algorithm for automatic speech recognition.

  • L. Mao, Y. Fan, H. Wang, and G. Lv propose a novel algorithm for image watermark identification using fractal and neural networks.

  • H. Zhang, X. Tian, and Y. Chen study a visual attention model in order to accurately analyze the spatio-temporal saliency based on intensity, texture, and motion features.

  • B. Luo, Y. Wang, and Y. Liu investigate head pose tracking for a flight cockpit system using sensor fusion.