Invention Grant
- Patent Title: Selecting instances of detected objects in images utilizing object detection models
-
Application No.: US17387195Application Date: 2021-07-28
-
Publication No.: US11797847B2Publication Date: 2023-10-24
- Inventor: Scott Cohen , Zhe Lin , Mingyang Ling
- Applicant: Adobe Inc.
- Applicant Address: US CA San Jose
- Assignee: Adobe Inc.
- Current Assignee: Adobe Inc.
- Current Assignee Address: US CA San Jose
- Agency: Keller Preece PLLC
- Main IPC: G06N3/00
- IPC: G06N3/00 ; G06N3/08 ; G06T7/11 ; G06T7/90 ; G06F16/33 ; G10L15/22 ; G06F18/214 ; G06N3/045 ; G06V10/25 ; G06V10/764 ; G06V10/82

Abstract:
The systems, methods, a non-transitory computer readable mediums relate to an object selection system that accurately detects and automatically selects user-requested objects (e.g., query objects) in a digital image. For example, the object selection system builds and utilizes an object selection pipeline to determine which object detection neural network to utilize to detect a query object based on analyzing the object class of the query object. In addition, the object selection system can add, update, or replace portions of the object selection pipeline to improve overall accuracy and efficiency of automatic object selection within an image.
Public/Granted literature
- US20210358130A1 SELECTING INSTANCES OF DETECTED OBJECTS IN IMAGES UTILIZING OBJECT DETECTION MODELS Public/Granted day:2021-11-18
Information query
IPC分类:
G | 物理 |
G06 | 计算;推算或计数 |
G06N | 基于特定计算模型的计算机系统 |
G06N3/00 | 基于生物学模型的计算机系统 |