230000000007 visual effect Effects 0.000 claims description 11.238000000513 principal component analysis Methods 0.000 claims description 11.230000000875 corresponding Effects 0.000 claims abstract description 33.Assignors: MICROSOFT CORPORATION Status Expired - Fee Related legal-status Critical Current Adjusted expiration legal-status Critical Links Assignors: HUA, XIAN-SHENG, LI, SHIPENG, ZHU, CAL-ZHI Publication of US20070101268A1 publication Critical patent/US20070101268A1/en Application granted granted Critical Publication of US7840898B2 publication Critical patent/US7840898B2/en Assigned to MICROSOFT TECHNOLOGY LICENSING, LLC reassignment MICROSOFT TECHNOLOGY LICENSING, LLC ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.) Filing date Publication date Application filed by Microsoft Corp filed Critical Microsoft Corp Priority to US11/264,357 priority Critical patent/US7840898B2/en Assigned to MICROSOFT CORPORATION reassignment MICROSOFT CORPORATION ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Original Assignee Microsoft Corp Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.) ( en Inventor Xian-Sheng Hua Shipeng Li Cai-Zhi Zhu Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.) Granted Application number US11/264,357 Other versions US7840898B2
USING EDGE INTENSITY IN PHOTOSKETCHER PDF
Additionally, the experiments indicate that higher quality edge information can be obtained by fusing range and intensity edge information.- Google Patents US20070101268A1 - Video bookletÄownload PDF Info Publication number US20070101268A1 US20070101268A1 US11/264,357 US26435705A US2007101268A1 US 20070101268 A1 US20070101268 A1 US 20070101268A1 US 26435705 A US26435705 A US 26435705A US 2007101268 A1 US2007101268 A1 US 2007101268A1 Authority US United States Prior art keywords thumbnail digital video shape segment Prior art date Legal status (The legal status is an assumption and is not a legal conclusion. Considering these result, it seems that segmentation tasks invovling range images captured by noisy scanners would benefit from the use of IEM information. The experimental results indicate that the use of IEMs can significantly improve edge-based segmentation of noisy range images. The other set is compared of images with varying levels of artificial, additive Gaussian noise. The first set comprises inherently noisy images. For our experiments, two sets of real range images are used. The performance of each algorithm, with and without the use of the IEM information, is evalute and reported in terms of correct segmentation rate. In the second form, the range edge map alone is used. In the first form, an IEM is fused with the range edge map prior to segmentation. Each of these algorithms is implemented in two different forms. The first is a watershed-based segmentation technique and the other is the scan-line grouping technique. Two edge-based segmentation algorithms are considered. In this paper, we investigate the impact of intensity edge maps (IEMs) on the segmentation of noisy range images.