Invention Grant
- Patent Title: Multi-object image parsing using neural network pipeline
-
Application No.: US16789088Application Date: 2020-02-12
-
Publication No.: US11238593B2Publication Date: 2022-02-01
- Inventor: Kerem Can Turgutlu , Jayant Kumar , Jianming Zhang , Zhe Lin
- Applicant: Adobe Inc.
- Applicant Address: US CA San Jose
- Assignee: Adobe Inc.
- Current Assignee: Adobe Inc.
- Current Assignee Address: US CA San Jose
- Agency: Finch & Maloney PLLC
- Main IPC: G06T7/00
- IPC: G06T7/00 ; G06T7/11 ; G06T3/40 ; G06T7/194 ; G06N3/04

Abstract:
Techniques are disclosed for parsing a source image, to identify segments of one or more objects within the source image. The parsing is carried out by an image parsing pipeline that includes three distinct stages comprising three respectively neural network models. The source image can include one or more objects. A first neural network model of the pipeline identifies a section of the source image that includes the object comprising a plurality of segments. A second neural network model of the pipeline generates, from the section of the source image, a mask image, where the mask image identifies one or more segments of the object. A third neural network model of the pipeline further refines the identification of the segments in the mask image, to generate a parsed image. The parsed image identifies the segments of the object, by assigning corresponding unique labels to pixels of different segments of the object.
Public/Granted literature
- US20210248748A1 MULTI-OBJECT IMAGE PARSING USING NEURAL NETWORK PIPELINE Public/Granted day:2021-08-12
Information query