Invention Grant
- Patent Title: Computer vision systems and methods for unsupervised learning for progressively aligning noisy contours
-
Application No.: US17104698Application Date: 2020-11-25
-
Publication No.: US11610322B2Publication Date: 2023-03-21
- Inventor: Venkata Subbarao Veeravasarapu , Abhishek Goel , Deepak Mittal , Maneesh Kumar Singh
- Applicant: Insurance Services Office, Inc.
- Applicant Address: US NJ Jersey City
- Assignee: Insurance Services Office, Inc.
- Current Assignee: Insurance Services Office, Inc.
- Current Assignee Address: US NJ Jersey City
- Agency: McCarter & English, LLP
- Main IPC: G06T7/33
- IPC: G06T7/33 ; G06N3/08 ; G06T3/00 ; G06N3/088
Abstract:
Computer vision systems and methods for noisy contour alignment are provided. The system generates a loss function and trains a convolutional neural network with the loss function and a plurality of images of a dataset to learn to align contours with progressively increasing complex forward and backward transforms over increasing scales. The system can align an attribute of an image of the dataset by the trained neural network.
Public/Granted literature
- US20210158549A1 Computer Vision Systems and Methods for Unsupervised Learning for Progressively Aligning Noisy Contours Public/Granted day:2021-05-27
Information query
