Kalantarian Haik, Jedoui Khaled, Washington Peter, Wall Dennis P
Department of Pediatrics and Biomedical Data Science at Stanford University.
Department of Mathematics at Stanford University.
IEEE Trans Games. 2020 Jun;12(2):213-218. doi: 10.1109/tg.2018.2877325. Epub 2018 Oct 22.
In this paper, we describe challenges in the development of a mobile charades-style game for delivery of social training to children with Autism Spectrum Disorder (ASD). Providing real-time feedback and adapting game difficulty in response to the child's performance necessitates the integration of emotion classifiers into the system. Due to the limited performance of existing emotion recognition platforms for children with ASD, we propose a novel technique to automatically extract emotion-labeled frames from video acquired from game sessions, which we hypothesize can be used to train new emotion classifiers to overcome these limitations. Our technique, which uses probability scores from three different classifiers and meta information from game sessions, correctly identified 83% of frames compared to a baseline of 51.6% from the best emotion classification API evaluated in our work.
在本文中，我们描述了为自闭症谱系障碍（ASD）儿童开发一款用于社交训练的手机猜谜式游戏时所面临的挑战。要提供实时反馈并根据孩子的表现调整游戏难度，就需要将情感分类器集成到系统中。由于现有针对ASD儿童的情感识别平台性能有限，我们提出了一种新颖的技术，可从游戏环节获取的视频中自动提取带有情感标签的帧，我们推测这些帧可用于训练新的情感分类器以克服这些限制。我们的技术使用来自三个不同分类器的概率分数以及游戏环节的元信息，与我们工作中评估的最佳情感分类应用程序编程接口（API）的51.6%的基线相比，正确识别了83%的帧。
