Property-Specific Aesthetic Assessment With Unsupervised Aesthetic Property Discovery
We propose the property-specific aesthetic assessment (PSAA) algorithm with unsupervised aesthetic property discovery. The proposed PSAA algorithm uses an aesthetic feature extractor, an aesthetic property classifier, and multiple property-specific assessment networks. The aesthetic feature extracto...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8805397/ |
| _version_ | 1818736631083958272 |
|---|---|
| author | Jun-Tae Lee Chul Lee Chang-Su Kim |
| author_facet | Jun-Tae Lee Chul Lee Chang-Su Kim |
| author_sort | Jun-Tae Lee |
| collection | DOAJ |
| description | We propose the property-specific aesthetic assessment (PSAA) algorithm with unsupervised aesthetic property discovery. The proposed PSAA algorithm uses an aesthetic feature extractor, an aesthetic property classifier, and multiple property-specific assessment networks. The aesthetic feature extractor analyzes aesthetics of images to generate features. Using such aesthetic features, we discover diverse aesthetic properties in an unsupervised manner and develop the aesthetic property classifier to predict the aesthetic property of each image. For each discovered aesthetic property, we train a property-specific assessment network. Thus, we can assess the aesthetic quality of an image using the property-specific network that corresponds to its property. Experimental results on a large dataset show that the proposed PSAA algorithm achieves state-of-the-art aesthetic assessment performance. Furthermore, we demonstrate that PSAA is useful for improving aesthetic qualities of images in two applications: contrast enhancement and image cropping. |
| first_indexed | 2024-12-18T00:40:13Z |
| format | Article |
| id | doaj.art-863bd110b5cf4f41b976516c410d1851 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-18T00:40:13Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-863bd110b5cf4f41b976516c410d18512022-12-21T21:26:54ZengIEEEIEEE Access2169-35362019-01-01711434911436210.1109/ACCESS.2019.29362898805397Property-Specific Aesthetic Assessment With Unsupervised Aesthetic Property DiscoveryJun-Tae Lee0Chul Lee1https://orcid.org/0000-0001-9329-7365Chang-Su Kim2https://orcid.org/0000-0002-4276-1831School of Electrical Engineering, Korea University, Seoul, South KoreaDepartment of Multimedia Engineering, Dongguk University, Seoul, South KoreaSchool of Electrical Engineering, Korea University, Seoul, South KoreaWe propose the property-specific aesthetic assessment (PSAA) algorithm with unsupervised aesthetic property discovery. The proposed PSAA algorithm uses an aesthetic feature extractor, an aesthetic property classifier, and multiple property-specific assessment networks. The aesthetic feature extractor analyzes aesthetics of images to generate features. Using such aesthetic features, we discover diverse aesthetic properties in an unsupervised manner and develop the aesthetic property classifier to predict the aesthetic property of each image. For each discovered aesthetic property, we train a property-specific assessment network. Thus, we can assess the aesthetic quality of an image using the property-specific network that corresponds to its property. Experimental results on a large dataset show that the proposed PSAA algorithm achieves state-of-the-art aesthetic assessment performance. Furthermore, we demonstrate that PSAA is useful for improving aesthetic qualities of images in two applications: contrast enhancement and image cropping.https://ieeexplore.ieee.org/document/8805397/Image aestheticsaesthetic assessmentimage compositionconvolutional neural networkunsupervised property discoveryunsupervised attribute clustering |
| spellingShingle | Jun-Tae Lee Chul Lee Chang-Su Kim Property-Specific Aesthetic Assessment With Unsupervised Aesthetic Property Discovery IEEE Access Image aesthetics aesthetic assessment image composition convolutional neural network unsupervised property discovery unsupervised attribute clustering |
| title | Property-Specific Aesthetic Assessment With Unsupervised Aesthetic Property Discovery |
| title_full | Property-Specific Aesthetic Assessment With Unsupervised Aesthetic Property Discovery |
| title_fullStr | Property-Specific Aesthetic Assessment With Unsupervised Aesthetic Property Discovery |
| title_full_unstemmed | Property-Specific Aesthetic Assessment With Unsupervised Aesthetic Property Discovery |
| title_short | Property-Specific Aesthetic Assessment With Unsupervised Aesthetic Property Discovery |
| title_sort | property specific aesthetic assessment with unsupervised aesthetic property discovery |
| topic | Image aesthetics aesthetic assessment image composition convolutional neural network unsupervised property discovery unsupervised attribute clustering |
| url | https://ieeexplore.ieee.org/document/8805397/ |
| work_keys_str_mv | AT juntaelee propertyspecificaestheticassessmentwithunsupervisedaestheticpropertydiscovery AT chullee propertyspecificaestheticassessmentwithunsupervisedaestheticpropertydiscovery AT changsukim propertyspecificaestheticassessmentwithunsupervisedaestheticpropertydiscovery |