Application Aspects of Fuzzy Color Modeling

Pakizar Shamoi, Atsushi Inoue, Hiroharu Kawanaka

2019

Closed access Metadata (CSL-JSON)
DOI 10.1109/smc.2019.8914471
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

Currently, processing data and presenting results in a human consistent manner is of great value. This paper provides some insights on application aspects of fuzzy color modeling in e-commerce apparel coordination and computational aesthetics. For that, we apply previously developed FHSI (Fuzzy HSI) color model. In FHSI, colors are modeled considering the imprecision, subjectivity, context-dependency, and non-uniformity of color distributions. Developed prototype of apparel online shop with underlying fuzzy color processing mechanisms allows overcoming the limitations of the traditional e-commerce search. Our method is effectively used to retrieve shopping items based on fuzzy dominant colors, make compositions based on harmonious color schemes we derived, predict the aesthetic preference for color combinations from an individual color preference and harmony.