Invention Grant
- Patent Title: Measurement and application of image colorfulness using deep learning
-
Application No.: US17672427Application Date: 2022-02-15
-
Publication No.: US12125244B2Publication Date: 2024-10-22
- Inventor: Kilho Shin , Dongpei Su
- Applicant: KYOCERA Document Solutions, Inc.
- Applicant Address: JP Osaka
- Assignee: KYOCERA Document Solutions, Inc.
- Current Assignee: KYOCERA Document Solutions, Inc.
- Current Assignee Address: JP Osaka
- Agency: Rowan TELS LLC
- Main IPC: G06T7/90
- IPC: G06T7/90 ; G06N3/04

Abstract:
A method includes generating multiple attention map for an image from outputs of a corresponding different one of multiple convolutional hidden layers of a neural network. A different weighted attention map is then generated from each of the attention map. The weighted attention maps are input to a first fully-connected neural network layer to generate a colorfulness metric, which may be used to augment human-perceived colorfulness of the image.
Public/Granted literature
- US20230260161A1 MEASUREMENT AND APPLICATION OF IMAGE COLORFULNESS USING DEEP LEARNING Public/Granted day:2023-08-17
Information query