Real-time-sign-language-recognition

The proposed work aims at converting american sign language gestures into English that can be understood by everyone.

Dataset

The dataset is made manually by running the Data_collection jupyter notebook that collects images from your webcam for all the signs mentioned above in the American Sign Language. Data has been collected for 24 alphabets only (not collected for 9=J and 25=Z because of gesture motions). For each alphabet 15 images with there annotations has been collected from which 10 images with there annotations has been used for training the ssd_mobnet model and 5 images with there annotations has been used for testing our ssd_mobnet model (I have only uploaded the test images with there annotations similarly train images were also used to train the ssd_mobnet).

The image annotations is done with the help of LabelImage file which you can use by simply git cloning the following- Link

Real time sign language recognition

Related tags

Overview

Real-time-sign-language-recognition

Dataset

Testing

Resources used

Owner

Mohit Kaushik

A computational optimization project towards the goal of gerrymandering the results of a hypothetical election in the UK.

High level network definitions with pre-trained weights in TensorFlow

Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models

Create Data & AI apps in 20 lines of code with Shimoku

It is modified Tensorflow 2.x version of Mask R-CNN

OneShot Learning-based hotword detection.

[CVPR2021] De-rendering the World's Revolutionary Artefacts

Clustering is a popular approach to detect patterns in unlabeled data

Source code for the BMVC-2021 paper "SimReg: Regression as a Simple Yet Effective Tool for Self-supervised Knowledge Distillation".

PyTorch implementation of "ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context" (INTERSPEECH 2020)

Official code for "On the Frequency Bias of Generative Models", NeurIPS 2021

[NeurIPS 2021] SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning

Wordle Env: A Daily Word Environment for Reinforcement Learning

RefineMask (CVPR 2021)

[PAMI 2020] Show, Match and Segment: Joint Weakly Supervised Learning of Semantic Matching and Object Co-segmentation

Code accompanying "Dynamic Neural Relational Inference" from CVPR 2020

EMNLP 2021 Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections

Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning

This project provides the proof of the uniqueness of the equilibrium and the global asymptotic stability.

Robust and Accurate Object Detection via Self-Knowledge Distillation