Invention Grant
- Patent Title: Method and system for establishing light source information prediction model
-
Application No.: US16813741Application Date: 2020-03-10
-
Publication No.: US11494585B2Publication Date: 2022-11-08
- Inventor: Yi-Jin Huang , Chien-Hung Li , Yin-Hsong Hsu
- Applicant: Acer Incorporated
- Applicant Address: TW New Taipei
- Assignee: Acer Incorporated
- Current Assignee: Acer Incorporated
- Current Assignee Address: TW New Taipei
- Agency: JCIPRNET
- Priority: TW109101420 20200115
- Main IPC: G06K9/62
- IPC: G06K9/62 ; G06V10/56 ; G06V10/141

Abstract:
A method and a system for establishing a light source information prediction model are provided. A plurality of training images are captured for a target object. A white object is attached on the target object. True light source information of the training images is obtained according to a color of the white object in each of the training images. A neural network model is trained according to the training images and the true light source information, and a plurality of pieces of predicted light source information is generated according to the neural network model during the training. A learning rate for training the neural network model is adaptively adjusted based on the predicted light source information.
Public/Granted literature
- US20210216816A1 METHOD AND SYSTEM FOR ESTABLISHING LIGHT SOURCE INFORMATION PREDICTION MODEL Public/Granted day:2021-07-15
Information query