中国科学院机构知识库网格系统: 检索

浏览/检索结果: 共7条，第1-7条

帮助

条数/页：排序方式：
	Transformer-Based Neural Texture Synthesis and Style Transfer 会议论文 OAI收割 Virtual Event Thailand, 2022-2 作者: Jiahao, Lu \| 收藏 \| 浏览/下载：28/0 \| 提交时间：2022/06/28 low-level vision, style transfer
	Transformers in computational visual media: A survey 期刊论文 OAI收割 Computational Visual Media, 2021, 卷号: 8, 期号: 1, 页码: 33-62 作者: Xu,Yifan; Wei,Huapeng; Lin,Minxuan; Deng,Yingying; Sheng,Kekai \| 收藏 \| 浏览/下载：62/0 \| 提交时间：2021/12/28 visual transformer computational visual media (CVM) high-level vision low-level vision image generation multi-modal learning
	Practical Method of Low-Light-Level Binocular Ranging Based on Triangulation and Error Correction 会议论文 OAI收割 Kalbis Institute, Jakarta, Indonesia, December 5-7, 2017 作者: Qi Shi; Lei Ma; Yiping Yang \| 收藏 \| 浏览/下载：35/0 \| 提交时间：2018/01/29 Low-light-level Image Binocular Stereo Vision Triangulation Trilateration Error Correction
	Weighted Schatten p-Norm Minimization for Image Denoising and Background Subtraction 期刊论文 OAI收割 IEEE TRANSACTIONS ON IMAGE PROCESSING, 2016, 卷号: 25, 期号: 10, 页码: 4842-4857 作者: Xie, Yuan; Gu, Shuhang; Liu, Yan; Zuo, Wangmeng; Zhang, Wensheng \| 收藏 \| 浏览/下载：29/0 \| 提交时间：2016/10/26 Low Rank Weighted Schatten P-norm Low-level Vision
	Image Sketching Using Low-, Mid-level Vision Cues 期刊论文 OAI收割 Journal of Computational Information Systems, 2008, 期号: 1, 页码: 1 作者: Kun Zeng; Liang Lin; Huai-Yu Wu; Chunhong Pan; Qing Yang 收藏 \| 浏览/下载：10/0 \| 提交时间：2016/10/20 Image Sketching Using Low-, Mid-level Vision Cues
	A new algorithm of image segmentation for overlapping grain image (EI CONFERENCE) 会议论文 OAI收割 ICO20: Optical Information Processing, August 21, 2005 - August 26, 2005, Changchun, China 作者: Zhang X.; Zhang X.; Zhang X. 收藏 \| 浏览/下载：17/0 \| 提交时间：2013/03/25 Image segmentation is primary issue in image processing at the same time it is principal problem in low level vision in computer vision field. It is the key technology to process image analysis image comprehend and image depict successfully. Aim at measurement of granularity size of nonmetal grain a new algorithm of image segmentation and parameters calculation for overlapping grain image is studied. The hypostasis of this algorithm is present some new attributes of graph sequence from discrete attribute of graph consequently achieve that pick up the geometrical characteristics from input graph and new graph sequence which in favor of image segmentation is recombined. The conception that image edge denoted with "twin-point" is put forward base on geometrical characters of point image edge is transformed into serial edge and on recombined serial image edge based on direction vector definition of line and some additional restricted conditions the segmentation twin-points are searched with thus image segmentation is accomplished. Serial image edge is transformed into twin-point pattern to realize calculation of area and granularity size of nonmetal grain. The inkling and uncertainty on selection of structure element which base on mathematical morphology are avoided in this algorithm and image segmentation and parameters calculation are realized without changing grain's self statistical characters.
	Adaptive Image Segmentation based on Fast Thresholding and Image Merging (EI CONFERENCE) 会议论文 OAI收割 16th International Conference on Artificial Reality and Telexistence - Workshops, ICAT 2006, November 29, 2006 - December 1, 2006, Hangzhou, China 作者: Zhang Y.; Wang Y.; Wang Y.; Wang Y.; Wang Y. 收藏 \| 浏览/下载：15/0 \| 提交时间：2013/03/25 Image segmentation is the first essential and important step of low level vision. This paper proposes a novel algorithm for adaptive image segmentation it can be applied in many conditions based on thresholding technique and segments merging according to their characteristics combine with spatial position. Our earlier work of getting the entire information of the histogram could help choose the multiple thresholds. However including complex target segmented. We describe the algorithm in detail and perform simulation experiments. The computation based on pixels can fully parallel processing to save time. 2006 IEEE. not all the peaks of the histogram correspond to obvious structural unit in the image. Spatial information must be involved. This paper also suggests subjoining segments matching for video image tracking. They will give great help to image segmentation. The proposed algorithm can meet the real-time requirement and lead to higher segmentation accuracy some types of texture can also be segmented well