Estimation of Semantic Impressions from Portraits

Mari MIYATA  Kiyoharu AIZAWA  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E104-D   No.6   pp.863-872
Publication Date: 2021/06/01
Publicized: 2021/03/18
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2020EDP7140
Type of Manuscript: PAPER
Category: Image Processing and Video Processing
Keyword: 
portrait,  semantic impression,  deformation,  learning to rank,  relative attribute,  

Full Text: PDF>>
Buy this Article




Summary: 
In this paper, we present a novel portrait impression estimation method using nine pairs of semantic impression words: bitter-majestic, clear-pure, elegant-mysterious, gorgeous-mature, modern-intellectual, natural-mild, sporty-agile, sweet-sunny, and vivid-dynamic. In the first part of the study, we analyzed the relationship between the facial features in deformed portraits and the nine semantic impression word pairs over a large dataset, which we collected by a crowdsourcing process. In the second part, we leveraged the knowledge from the results of the analysis to develop a ranking network trained on the collected data and designed to estimate the semantic impression associated with a portrait. Our network demonstrated superior performance in impression estimation compared with current state-of-the-art methods.