Towards Recognizing Emotion with Affective Dimensions Through Body Gestures

Abstract

Due to the ever-increasing importance of computers in many areas of today's society such as e-learning, telehome-health care, and entertainment, their ability to interact well with humans is essential. Currently, researchers are using facial expression and voice recognition modalities to create systems that interact with humans. But still two problems exist: gesture is not yet a concern as a channel of affective communication in interactive technology, and existing systems only model discrete categories but not affective dimensions, e.g., intensity. Our focus has been on creating affective gesture recognition system that recognize child's emotion with intensity through body gestures in context of game. This information is then used by a game control module that users a rule-based adaptation model to change game level according to the child's intensity of emotions. Results show that affective gesture recognition model recognized child's emotion over 79% of the cases and the proposed intensity estimate model has a strong relationship with observer perception except in the low intensity level

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 33 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.