de Wijk Rene A, Ushiama Shota, Ummels Meeke, Zimmerman Patrick, Kaneko Daisuke, Vingerhoeds Monique H
Wageningen Food & Biobased Research Institute, Wageningen University & Research, 6700 AA Wageningen, The Netherlands.
Kikkoman Europe R&D Laboratory B.V., 6709 PA Wageningen, The Netherlands.
Foods. 2021 Jun 10;10(6):1345. doi: 10.3390/foods10061345.
Food experiences are not only driven by the food's intrinsic properties, such as its taste, texture, and aroma, but also by extrinsic properties such as visual brand information and the consumers' previous experiences with the foods. Recent developments in automated facial expression analysis and heart rate detection based on skin color changes (remote photoplethysmography or RPPG) allow for the monitoring of food experiences based on video images of the face. RPPG offers the possibility of large-scale non-laboratory and web-based testing of food products. In this study, results from the video-based analysis were compared to the more conventional tests (scores of valence and arousal using Emojis and photoplethysmography heart rate (PPG)). Forty participants with varying degrees of familiarity with soy sauce were presented with samples of rice and three commercial soy sauces with and without brand information. The results showed that (1) liking and arousal were affected primarily by the specific tastes, but not by branding and familiarity. In contrast, facial expressions were affected by branding and familiarity, and to a lesser degree by specific tastes. (2) RPPG heart rate and PPG both showed effects of branding and familiarity. However, RPPG heart rate needs further development because it underestimated the heart rate compared to PPG and was less sensitive to changes over time and with activity (viewing of brand information and tasting). In conclusion, this study suggests that recording of facial expressions and heart rates may no longer be limited to laboratories but can be done remotely using video images, which offers opportunities for large-scale testing in consumer science.
食物体验不仅受食物的内在特性驱动，如味道、质地和香气，还受外在特性影响，如视觉品牌信息以及消费者先前对这些食物的体验。基于肤色变化的自动面部表情分析和心率检测（远程光电容积脉搏波描记法或RPPG）的最新进展，使得基于面部视频图像来监测食物体验成为可能。RPPG为食品的大规模非实验室和基于网络的测试提供了可能性。在本研究中，将基于视频的分析结果与更传统的测试（使用表情符号的效价和唤醒评分以及光电容积脉搏波描记法心率（PPG））进行了比较。向40名对酱油熟悉程度不同的参与者提供了米饭样本以及三种有或没有品牌信息的市售酱油。结果表明：（1）喜好和唤醒主要受特定口味影响，而非品牌和熟悉程度。相比之下，面部表情受品牌和熟悉程度影响，受特定口味影响较小。（2）RPPG心率和PPG均显示出品牌和熟悉程度的影响。然而，RPPG心率需要进一步改进，因为与PPG相比，它低估了心率，并且对随时间和活动（查看品牌信息和品尝）的变化不太敏感。总之，本研究表明，面部表情和心率的记录可能不再局限于实验室，而是可以使用视频图像进行远程记录，这为消费科学中的大规模测试提供了机会。
