Invention Grant
- Patent Title: Feature density object classification, systems and methods
-
Application No.: US16128178Application Date: 2018-09-11
-
Publication No.: US10671879B2Publication Date: 2020-06-02
- Inventor: Mustafa Jaber , Jeremi M. Sudol , Bing Song
- Applicant: Nant Holdings IP, LLC
- Applicant Address: US CA Culver City
- Assignee: Nant Holdings IP, LLC
- Current Assignee: Nant Holdings IP, LLC
- Current Assignee Address: US CA Culver City
- Agency: Mauriel Kapouytian Woods LLP
- Agent Elaine Lee; Andrew Noble
- Main IPC: G06K9/52
- IPC: G06K9/52 ; G06T7/50 ; G06T7/11 ; G06K9/32 ; G06K9/46 ; G06K9/62

Abstract:
A system capable of determining which recognition algorithms should be applied to regions of interest within digital representations is presented. A preprocessing module utilizes one or more feature identification algorithms to determine regions of interest based on feature density. The preprocessing modules leverages the feature density signature for each region to determine which of a plurality of diverse recognition modules should operate on the region of interest. A specific embodiment that focuses on structured documents is also presented. Further, the disclosed approach can be enhanced by addition of an object classifier that classifies types of objects found in the regions of interest.
Public/Granted literature
- US20190012562A1 FEATURE DENSITY OBJECT CLASSIFICATION, SYSTEMS AND METHODS Public/Granted day:2019-01-10
Information query