AI RESEARCH

Proper Body Landmark Subset Enables More Accurate and 5X Faster Recognition of Isolated Signs in LIBRAS

arXiv CS.CV

ArXi:2510.24887v3 Announce Type: replace This paper investigates the feasibility of using lightweight body landmark detection for the recognition of isolated signs in Brazilian Sign Language (LIBRAS). Although the skeleton-based approach by Alves enabled substantial improvements in recognition performance, the use of OpenPose for landmark extraction hindered time performance. In a preliminary investigation, we observed that simply replacing OpenPose with the lightweight MediaPipe, while improving processing speed, significantly reduced accuracy.