TY - GEN
T1 - A preliminary study on visual estimation of taste appreciation
AU - Zulfikar, Idil Esen
AU - Dibeklioglu, Hamdi
AU - Ekenel, Hazim Kemal
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/9/22
Y1 - 2016/9/22
N2 - From past to present, individuals' appreciation of taste has always been wondered. Moreover, there is an increasing research interest in measuring taste appreciation. Most of the previous work in this area are psychological studies that rely on manual coding of facial actions and/or emotional expressions. Consequently, these studies depend on human observations. We propose a preliminary study for an automatic visual analysis system that estimates taste liking of individuals. Our results show that the proposed system performs with 56.6% accuracy to classify appreciation in terms of liking, neutral, and disliking categories. In order to explore this result in detail, classification of liking level pairs such as disliking-vs-liking, neutral-vs-liking, and neutral-vs-disliking are also evaluated. Our system achieved 72.5% accuracy for distinguishing between dislike and liking, however, classification accuracy for dislike and neutral, and for liking and neutral have been found to be lower. Our results suggest that reliable and fast automatic systems can be developed to estimate taste appreciation, yet classes of liking and neutral state are not easily separable as indicated in previous studies.
AB - From past to present, individuals' appreciation of taste has always been wondered. Moreover, there is an increasing research interest in measuring taste appreciation. Most of the previous work in this area are psychological studies that rely on manual coding of facial actions and/or emotional expressions. Consequently, these studies depend on human observations. We propose a preliminary study for an automatic visual analysis system that estimates taste liking of individuals. Our results show that the proposed system performs with 56.6% accuracy to classify appreciation in terms of liking, neutral, and disliking categories. In order to explore this result in detail, classification of liking level pairs such as disliking-vs-liking, neutral-vs-liking, and neutral-vs-disliking are also evaluated. Our system achieved 72.5% accuracy for distinguishing between dislike and liking, however, classification accuracy for dislike and neutral, and for liking and neutral have been found to be lower. Our results suggest that reliable and fast automatic systems can be developed to estimate taste appreciation, yet classes of liking and neutral state are not easily separable as indicated in previous studies.
KW - Appreciation estimation
KW - Expression
KW - Facial response
KW - Peak frame
UR - http://www.scopus.com/inward/record.url?scp=84992153667&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84992153667&partnerID=8YFLogxK
U2 - 10.1109/ICMEW.2016.7574764
DO - 10.1109/ICMEW.2016.7574764
M3 - Conference contribution
AN - SCOPUS:84992153667
T3 - 2016 IEEE International Conference on Multimedia and Expo Workshop, ICMEW 2016
BT - 2016 IEEE International Conference on Multimedia and Expo Workshop, ICMEW 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2016 IEEE International Conference on Multimedia and Expo Workshop, ICMEW 2016
Y2 - 11 July 2016 through 15 July 2016
ER -