Evaluating the Feasibility of Standard Facial Expression Recognition in Individuals with Moderate to Severe Intellectual Disabilities
CoRR(2024)
摘要
Recent research has underscored the increasing preference of users for
human-like interactions with machines. Consequently, facial expression
recognition has gained significance as a means of imparting social robots with
the capacity to discern the emotional states of users. In this investigation,
we assess the suitability of deep learning approaches, known for their
remarkable performance in this domain, for recognizing facial expressions in
individuals with intellectual disabilities, which has not been yet studied in
the literature, to the best of our knowledge. To address this objective, we
train a set of twelve distinct convolutional neural networks in different
approaches, including an ensemble of datasets without individuals with
intellectual disabilities and a dataset featuring such individuals. Our
examination of the outcomes achieved by the various models under distinct
training conditions, coupled with a comprehensive analysis of critical facial
regions during expression recognition facilitated by explainable artificial
intelligence techniques, revealed significant distinctions in facial
expressions between individuals with and without intellectual disabilities, as
well as among individuals with intellectual disabilities. Remarkably, our
findings demonstrate the feasibility of facial expression recognition within
this population through tailored user-specific training methodologies, which
enable the models to effectively address the unique expressions of each user.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要