- 专利标题: Systems and methods for trainable deep active contours for image segmentation
-
申请号: US17149432申请日: 2021-01-14
-
公开(公告)号: US11854208B2公开(公告)日: 2023-12-26
- 发明人: Demetri Terzopoulos , Ali Hatamizadeh
- 申请人: The Regents of the University of California
- 申请人地址: US CA Oakland
- 专利权人: The Regents of the University of California
- 当前专利权人: The Regents of the University of California
- 当前专利权人地址: US CA Oakland
- 代理机构: KPPB LLP
- 主分类号: G06T7/149
- IPC分类号: G06T7/149 ; G06T7/11 ; G06N3/04 ; G06N3/08
摘要:
Systems and methods for image segmentation using neural networks and active contour methods in accordance with embodiments of the invention are illustrated. One embodiment includes a method for generating image segmentations from an input image. The method includes steps for receiving an input image, identifying a set of one or more parameter maps from the input image, identifying an initialization map from the input image, and generating an image segmentation based on the set of parameter maps and the initialization map.
公开/授权文献
信息查询