- Patent Title: Object recognition and tagging based on fusion deep learning models
-
Application No.: US17102675Application Date: 2020-11-24
-
Publication No.: US11416672B2Publication Date: 2022-08-16
- Inventor: Vlad Morariu , Rajiv Jain , Nishant Sankaran
- Applicant: Adobe Inc.
- Applicant Address: US CA San Jose
- Assignee: Adobe Inc.
- Current Assignee: Adobe Inc.
- Current Assignee Address: US CA San Jose
- Agency: Kilpatrick Townsend & Stockton LLP
- Main IPC: G06F40/117
- IPC: G06F40/117 ; G06N5/04 ; G06K9/62 ; G06V30/416

Abstract:
Certain embodiments involve transforming an electronic document into a tagged electronic document. For instance, an electronic document processing application generates a tagged electronic document from an input electronic document. The electronic document processing application accesses one or more feature maps that identify, via a set of object-recognition rules, identified objects in the electronic document. The electronic document processing application also obtains a heat map of the electronic document that represents attributes in a pixel-wise manner. The electronic document processing application computes a tag by applying a fusion deep learning model to the one or more feature maps and the heat map. The electronic document processing application generates the tagged electronic document by applying the tag to the electronic document.
Public/Granted literature
- US20210103695A1 OBJECT RECOGNITION AND TAGGING BASED ON FUSION DEEP LEARNING MODELS Public/Granted day:2021-04-08
Information query
IPC分类: