Abacus Gestures

Designing an extensive set of mid-air gestures that are both easy to learn and perform quickly presents a significant challenge. Further complicating this challenge is achieving high-accuracy detection such using commonly available hardware, like 2D commodity camera. Previous work often proposed smaller, application-specific gesture sets, requiring specialized hardware struggling with adaptability across diverse environments. Addressing these limitations, paper introduces Abacus Gestures, comprehensive collection 100 gestures. Drawing on the metaphor Finger counting, formed from various combinations open closed fingers, each assigned different values. We developed algorithm off-the-shelf computer vision library capable detecting camera feed accuracy exceeding 98% for palms facing 95% body. assessed accuracy, ease learning, usability in user study involving 20 participants. The found participants could Gestures within five minutes after executing just 15 recall them four-month interval. Additionally, most motor memory performing Most were execute designated finger combinations, flexibility multiple further enhanced usability. Based findings, we created taxonomy categorizes into groups based development three difficulty levels according their execution. Finally, provided design guidelines potential use cases realm interaction.