| Title | An Edge Preserving Filter-based Selective Unsharp Masking for Noisy Images |
| Author | *Go Tanaka, Noriaki Suetake, Eiji Uchino (Yamaguchi University, Japan) |
| Page | pp. 469 - 472 |
| Keyword | Unsharp masking, image sharpening, noise removal |
| Abstract | In this paper, a new image sharpening method is proposed. The proposed method is a kind of selective unsharp masking, and it has an advantage on enhancement of the noisy images. And, the optimum values of parameters of the proposed method can be determined by the amplitude of an additive noise. The effectiveness of the proposed method is illustrated through the comparison with the conventional unsharp masking and cubic unsharp masking. |
| Title | An Efficient Color Transferring Interface with 3-Dimensional Transformation |
| Author | *Tsuneo Kagawa, Hiroaki Nishino, Kouichi Utsumiya (Oita University, Japan) |
| Page | pp. 473 - 476 |
| Keyword | Color transferring, GUI, Color space, Free form deformation |
| Abstract | We propose a user interface for color transferring with 3D computer graphics techniques. Proposing user interface can plot points describing color information of images in an arbitrary color space, such as RGB, HSI, and CIELAB (L*a*b*). These colors form three-dimensional distributions in the color spaces. Users can facilitate some operations, such as transformation, rotation and scaling, to these shapes representing color distribution in 3D space without altering visual appearance of original images. This type of interactive color transferring makes control very intuitive. |
| Title | A Study on Improvement Extraction Stability of Active Net Using All-Image BL-DCDAM Introduced BL-DCDAM |
| Author | *Fukuya Namba, Yasuaki Sumi (Tottori University of Environmental Studies, Japan), Takuya Ueta (GALAXY Inc., Japan), Noboru Yabuki (Tsuyama National College of Technology, Japan), Takao Tsukutani (Matsue National College of Technology, Japan) |
| Page | pp. 477 - 480 |
| Keyword | Computer Vision, Active Net, BL-DCDAM, Self-Organizing Map |
| Abstract | In this paper, we have described the new All-Image DCDAM that introduces BL-DCDAM into conventional All-Image DCDAM that we have proposed before. BL-DCDAM adopts the algorithm independent on the order of presenting the input vectors. To our research, BL-DCDAM is effective because we used all pixels of the input image as the input vectors. New All-Image BL-DCDAM has obtained a correct result even in the case that conventional one has failed from the experiment. |
| Title | FPGA Verification of the Video Retrieval System using MPEG-7 Visual Descriptors |
| Author | *Jang-Hui Kim, Hye-Youn Lim, Dae-Seong Kang (Department of Electronics Engineering, Dong-A University, Republic of Korea) |
| Page | pp. 481 - 484 |
| Keyword | retrieval, video segmentation, visual descriptors, FPGA verification |
| Abstract | Multimedia is rapidly spreading due to the increasing number of application fields and Internet technologies. The development of a retrieval system is urgently needed to retrieve the demanded information by users. Image information is widely used for the content-based retrieval of moving pictures. It is mainly used to segment a video by scene. The process that divides video into shots is called "video segmentation". For the video segmentation, detecting cuts which are turn point of scene is called "cut detection". In this paper, for the video segmentation, we use two MPEG-7 visual descriptors; HMMD (Hue- Max-Min-Diff) color model and the EHD (Edge Histogram Descriptor). The goal of this paper is to implement the retrieval system as hardware. It is designed by Verilog HDL. We perform the FPGA verification, and implement the retrieval system for the moving picture. |