Sign Language Detection

TL;DR

This paper explores two approaches for sign language detection: feature extraction with ORB and SVM, and CNN-based classification, aiming to improve image classification and facilitate deployment on Android devices.

Contribution

It introduces a dual-model approach combining traditional feature extraction with deep learning for sign language detection.

Findings

CNN model achieves high accuracy in sign language classification

ORB + SVM provides a lightweight alternative for feature-based detection

Trained CNN can be converted to TFLite for Android deployment

Abstract

With the advancements in Computer vision techniques the need to classify images based on its features have become a huge task and necessity. In this project we proposed 2 models i.e. feature extraction and classification using ORB and SVM and the second is using CNN architecture. The end result of the project is to understand the concept behind feature extraction and image classification. The trained CNN model will also be used to convert it to tflite format for Android Development.