This special issue on computer graphics consists of four papers addressing respectively the elds of image morphing, video processing, document visualization andGPU algorithms. Image morphing is a classic technique widely used for special e ects in entertainment industry. The rst paper by Tomohisa Manabe et al. proposes a method for generating a sequence of images with smooth change of illumination between two input images under di erent lighting conditions. It adopts isoluminance curves as a feature primitive. Transformed luminance distributions are generated from the warped isoluminance curves. In the second paper, Chunxia Xiao et al. present a fast gradient domain based framework for video compositing. Rather than the conventional approaches which performs Poisson image editing in the gradient-domain pixel by pixel, the new framework conducts video compositing by incorporating an octree data structure, requesting greatly reduced computational time and memory space. Discovering concepts from vast amount of text is an important but hard explorative task. The third paper by Qian You et al. proposes the iterative visual clustering (IVC), a noval visual text analytical model. IVC has a formal on-line learning model which learns users' preference iteratively. With the engagement of domain knowledge, it can achieve insightful concepts with interesting patterns. Graphics processing units (GPUs) have an SIMD architecture and have found wide applications in various elds. The last paper by Baoyuan Wang and Yizhou Yu investigates e cient GPU-based data cubing which is an expensive operation well suited for SIMD parallel e ective methods. The proposed algorithms can achieve more than one order of magnitude speedup when compared with their sequential counterparts on a single CPU. Finally, I would like to thank all the authors of the above four papers for their contribution to this special issue and appreciate the excellent work by all the reviewers.
Qunsheng Peng. Preface. International Journal of Software and Informatics, 2012,6(1):1Copy