Abstract | ||
---|---|---|
Lighting is a key factor in creating impressive artistic portraits. In this paper, we propose to analyze portrait lighting by learning templates of lighting styles. Inspired by the experience of artists, we first define several novel features that describe the local contrasts in various face regions. The most informative features are then selected with a stepwise feature pursuit algorithm to derive the templates of various lighting styles. After that, the matching scores that measure the similarity between a testing portrait and those templates are calculated for lighting style classification. Furthermore, we train a regression model by the subjective scores and the feature responses of a template to predict the score of a portrait lighting quality. Based on the templates, a novel face illumination descriptor is defined to measure the difference between two portrait lightings. Experimental results show that the learned templates can well describe the lighting styles, whereas the proposed approach can assess the lighting quality of artistic portraits as human being does. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/TIP.2014.2369962 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
template learning,subjective scores,lighting style classification,image matching,face recognition,lighting,learning (artificial intelligence),regression analysis,informative feature selection,face illumination matching,regression model,face regions,contrast feature,artistic portrait lighting analysis,image classification,portrait lighting analysis,stepwise feature pursuit algorithm,local contrasts,portrait lighting quality,matching scores,feature selection,face illumination descriptor,quantitative assessment,face,harmonic analysis,histograms | Computer vision,Histogram,Pattern recognition,Portrait,Image-based lighting,Contrast (statistics),Artificial intelligence,Template,Pursuit algorithms,Mathematics | Journal |
Volume | Issue | ISSN |
24 | 2 | 1941-0042 |
Citations | PageRank | References |
3 | 0.38 | 27 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiaowu Chen | 1 | 605 | 45.05 |
Xin Jin | 2 | 162 | 17.20 |
Hongyu Wu | 3 | 20 | 2.73 |
Qinping Zhao | 4 | 363 | 43.20 |