TY - GEN
T1 - Automatic color palette design using color image and sentiment analysis
AU - Peng, Ya Fang
AU - Chou, Tzren Ru
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/4
Y1 - 2019/4
N2 - Designers are often forced to speculate on color combinations and other requirements from customers' abstract and sometimes contradictory descriptions. Thus, too much time is spent on collaboration and modification. Therefore, in this paper a method of combining color imagery with sentiment analysis is proposed to automatically convert colloquial descriptions into color palettes. The algorithm comprises four steps. First, it defines affect words as the basis for text classification. In this study affect words are CIS image words. Second, it collects relevant text corpora from Google and Wikipedia. Third, via model training, it applies word2vec (a word-embedding model) to calculate the lexical affinity of affect words and colors. Furthermore, a prototype system is built to demonstrate its efficacy for automatic color palette design.
AB - Designers are often forced to speculate on color combinations and other requirements from customers' abstract and sometimes contradictory descriptions. Thus, too much time is spent on collaboration and modification. Therefore, in this paper a method of combining color imagery with sentiment analysis is proposed to automatically convert colloquial descriptions into color palettes. The algorithm comprises four steps. First, it defines affect words as the basis for text classification. In this study affect words are CIS image words. Second, it collects relevant text corpora from Google and Wikipedia. Third, via model training, it applies word2vec (a word-embedding model) to calculate the lexical affinity of affect words and colors. Furthermore, a prototype system is built to demonstrate its efficacy for automatic color palette design.
KW - automatic color palette design
KW - color image
KW - sentiment analysis
KW - word embedding
UR - http://www.scopus.com/inward/record.url?scp=85067488514&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85067488514&partnerID=8YFLogxK
U2 - 10.1109/ICCCBDA.2019.8725717
DO - 10.1109/ICCCBDA.2019.8725717
M3 - Conference contribution
AN - SCOPUS:85067488514
T3 - 2019 IEEE 4th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2019
SP - 389
EP - 392
BT - 2019 IEEE 4th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 4th IEEE International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2019
Y2 - 12 April 2019 through 15 April 2019
ER -