Battini Sonmez, Elena2024-07-182024-07-1820172147-1762https://hdl.handle.net/11411/8305This study focuses on the issue of automatic facial expression recognition on little databases of 2D faces. Convolutional Neural Networks (CNN) is a new classification technique, which reaches the state of the art on big databases; however, the use of CNN with a scarce number of samples is still an open challenge. Following the classical machine learning approach, we considered different combination of feature extraction and classifiers, and we compared their performances with special designed CNN. Our results show that CNN outperforms the other classifiers in the close system experiment; however, in the more challenging open system experimental setup the Sparse Representation based Classifier is more successful.eninfo:eu-repo/semantics/closedAccessLittle DatabasesFacial Expression RecognitionSparse Representation Based ClassifierConvolutional Neural NetworkFace RecognitionArticle2-s2.0-85040001986273Q31930N/AWOS:000418815100002