Salīdzināt metodes
Apskatiet izvēlētās metodes blakus; rindas, kas atšķiras, ir izceltas.
| Attēla estētiskās kvalitātes novērtēšana× | Vizualās sarežģītības mērījums× | |
|---|---|---|
| Nozare | Vizuālā māksla | Vizuālā māksla |
| Saime | Process / pipeline | Process / pipeline |
| Izcelsmes gads≠ | 2006 | 2011 |
| Autors≠ | Ritendra Datta | Adrian Forsythe |
| Tips | Analytical pipeline | Analytical pipeline |
| Pirmavots≠ | Datta, R., Joshi, D., Li, J., & Wang, J. Z. (2006). Studying Aesthetics in Photographic Images Using a Computational Approach. Computer Vision—ECCV 2006, 3953, 288–301. DOI ↗ | Forsythe, A., Nadal, M., Shackelford, N., & Cela-Conde, C. J. (2011). Predicting Beauty: Fractal Dimension and Visual Complexity in Art. Biology Letters, 7(2), 203–205. DOI ↗ |
| Citi nosaukumi | Computational Aesthetics Evaluation, Photo Quality Scoring | Aesthetic Complexity Assessment, Visual Information Density Metric |
| Saistītās | 5 | 5 |
| Kopsavilkums≠ | Image Aesthetics Assessment is a computational pipeline for predicting and quantifying the aesthetic quality of photographs and digital images. Drawing from computer vision and human perception research, this method extracts low-level visual features and applies machine learning or rule-based scoring to estimate how viewers will perceive image quality and beauty. | Visual Complexity Measure is a computational pipeline for quantifying the informational density and structural intricacy of visual compositions. Drawing from cognitive psychology and computational aesthetics research, this method provides objective metrics for how much visual processing demand a design, image, or artwork places on viewers. |
| ScholarGateDatu kopa ↗ |
|
|