Some models like NIMA evaluate photos aesthetically, but I believe these evaluations are more based on the basics of photography, like photos being focused and so on. I need to analyze more sophisticated photos.
Pre-Trained Models for Image Classification
- VGG-16
- ResNet50
- Inceptionv3
- EfficientNet
The best way is to use MATLAB, e.g., https://au.mathworks.com/help/images/referencelist.html?type=function&category=getting-started-with-image-processing-toolbox&s_tid=CRUX_topnav
https://au.mathworks.com/campaigns/offers/image-processing-tips-and-techniques.html
I'm not sure I understand your question perfectly. Anyway, here's my 2 cents. You can take a look at the research at the intersection of aesthetic assessment, visual perception and sentiment analysis in art based on visual features, made for example by Elgammal and others and Cetinic and others. From a dataset perspective, you can take a look at the WikiArt Emotions dataset and the papers that used it.
Gennaro Vessio Thank you, so far, these are the best sources I've seen.
- Badges
- Science topic