The recognition of human feeling is a major contribution to many applications of computer vision. Despite its significance, this study is the first move towards an automated Autistic Children’s Emotion Detection Device to guarantee their wellbeing during the breakdown crisis. Present responses to the crisis meltdown are based on a reactive approach. Indeed, Meltdown symptoms are determined by abnormal facial expressions related to compound emotions. To provide for this correspondence, we experimentally evaluate, in this paper, hand-crafted Geometric Spatio-Temporal and Deep features of realistic autistic children facial expressions. Towards this end, we compared the Compound Emotion Recognition (CER) performance for different combinations of these features, and we determined the features that best distinguish a Compound Emotion (CE) of autistic children during a meltdown crisis from the normal state. We used “Meltdown crisis”1 dataset to conduct our experiments on realistic Meltdown / Normal scenarios of autistic children. In this evaluation, we show that the gathered features can lead to very encouraging performances through the use of Random Forest classifier (91.27%) with hand-crafted features. Moreover, classifiers trained on deep features from InceptionResnetV2 show higher performance (97.5%) with supervised learning techniques.