- Patent Title: Shape-based segmentation using hierarchical image representations for automatic training data generation and search space specification for machine learning algorithms
-
Application No.: US15802313Application Date: 2017-11-02
-
Publication No.: US10372984B2Publication Date: 2019-08-06
- Inventor: Georgios Ouzounis , Kostas Stamatiou , Nikki Aldeborgh
- Applicant: DigitalGlobe, Inc.
- Applicant Address: US CO Longmont
- Assignee: DigitalGlobe, Inc.
- Current Assignee: DigitalGlobe, Inc.
- Current Assignee Address: US CO Longmont
- Agency: Galvin Patent Law, LLC
- Agent Brian R. Galvin
- Main IPC: G06K9/62
- IPC: G06K9/62 ; G06K9/00 ; G06T7/00 ; G06T7/90 ; G06F16/583 ; G06T7/12 ; G06T7/11 ; G06K9/40
Abstract:
A system and various methods for processing an image to produce a hierarchical image representation model, segment the image model using shape criteria to produce positive and negative training data sets as well as a search-space data set comprising shapes matched to a search query provided as input, and using the training data sets to train a machine learning model to improve recognition of shapes that are similar to an input query without being exact matches, to improve object recognition.
Public/Granted literature
Information query
