# Appearance-based Gesture recognition in the compressed domain

## TL;DR

This paper introduces a new gesture recognition method that directly uses compressed measurements for feature extraction, improving efficiency and memory use over traditional approaches, validated through simulations and hardware tests.

## Contribution

The paper presents a novel appearance-based gesture recognition algorithm operating in the compressed domain, enhancing efficiency and reducing memory compared to existing methods.

## Key findings

- Effective gesture recognition from compressed measurements
- Improved computational efficiency over previous methods
- Validated through simulation and hardware implementation

## Abstract

We propose a novel appearance-based gesture recognition algorithm using compressed domain signal processing techniques. Gesture features are extracted directly from the compressed measurements, which are the block averages and the coded linear combinations of the image sensor's pixel values. We also improve both the computational efficiency and the memory requirement of the previous DTW-based K-NN gesture classifiers. Both simulation testing and hardware implementation strongly support the proposed algorithm.