Deciding of HMM parameters based on number of critical points for gesture recognition from motion capture data

TL;DR

This paper proposes a method to determine the optimal number of states in Hidden Markov Models for gesture recognition by analyzing the critical points in motion capture data, aiming to improve recognition accuracy.

Contribution

It introduces a novel predictor for HMM state count based on critical points in motion data, enhancing parameter selection for gesture recognition.

Findings

Predictor effectively estimates the number of HMM states.

Improves recognition performance by better parameter tuning.

Validated on sample motion capture data.

Abstract

This paper presents a method of choosing number of states of a HMM based on number of critical points of the motion capture data. The choice of Hidden Markov Models(HMM) parameters is crucial for recognizer's performance as it is the first step of the training and cannot be corrected automatically within HMM. In this article we define predictor of number of states based on number of critical points of the sequence and test its effectiveness against sample data.