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

Some code of the implements of Geological Modeling Using 3D Pixel-Adaptive and Deformable Convolutional Neural Network

Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models

Performant, differentiable reinforcement learning

The project is associated with the recently-launched ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge (M2MeT) to provide participants with baseline systems for speech recognition and speaker diarization in conference scenario.

Look Closer: Bridging Egocentric and Third-Person Views with Transformers for Robotic Manipulation

DirectVoxGO reconstructs a scene representation from a set of calibrated images capturing the scene.

GPOEO is a micro-intrusive GPU online energy optimization framework for iterative applications

Domain Adaptation with Invariant RepresentationLearning: What Transformations to Learn?

Fuzzing tool (TFuzz): a fuzzing tool based on program transformation

A collection of pre-trained StyleGAN2 models trained on different datasets at different resolution.

Contextualized Perturbation for Textual Adversarial Attack, NAACL 2021

Visualizing lattice vibration information from phonon dispersion to atoms (For GPUMD)

MASS (Mueen's Algorithm for Similarity Search) - a python 2 and 3 compatible library used for searching time series sub-sequences under z-normalized Euclidean distance for similarity.

A very simple tool for situations where optimization with onnx-simplifier would exceed the Protocol Buffers upper file size limit of 2GB, or simply to separate onnx files to any size you want.

DrQ-v2: Improved Data-Augmented Reinforcement Learning

Unofficial PyTorch implementation of TokenLearner by Google AI

Code for the ICML 2021 paper "Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation", Haoxiang Wang, Han Zhao, Bo Li.

In this project we predict the forest cover type using the cartographic variables in the training/test datasets.

Wenzhou-Kean University AI-LAB

neural image generation