Method for assessing aesthetic quality of natural image based on multi-task deep learning
US10685434B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 30, 2016 |
| Grant date | Jun 16, 2020 |
| Priority date | — |
| Expiry date | Sep 10, 2036 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04N17/00
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
The present application discloses a method for assessing aesthetic quality of a natural image based on multi-task deep learning. Said method includes: step 1: automatically learning aesthetic and semantic characteristics of the natural image based on multi-task deep learning; step 2: performing aesthetic categorization and semantic recognition to the results of automatic learning based on multi-task deep learning, thereby realizing assessment of aesthetic quality of the natural image. The present application uses semantic information to assist learning of expressions of aesthetic characteristics so as to assess aesthetic quality more effectively, besides, the present application designs various multi-task deep learning network structures so as to effectively use the aesthetic and semantic information for obtaining highly accurate image aesthetic categorization. The present application can be applied to many fields relating to image aesthetic quality assessment, including image retrieval, photography and album management, etc.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.