a11y / Sign Language Detection A&B Public

Target: Arduino Nano 33 BLE Sense (Cortex-M4F 64MHz) Clone this project

Welcome to Edge Impulse, the largest community of edge AI developers!
This is a public Edge Impulse project, use the navigation bar to see all data and models in this project; or clone to retrain or deploy to any edge device.

Sign Language Detection A&B

Images

A11y SignLanguage Accessibility ASL

About this project

The goal of the project is to implement a recognition system for some elements of American Sign Language fingerspelling. To achieve the goal, a neural network model was developed and then loaded into a microcontroller.

Data (6,084 items)

View all

A1995

ID: 765807610

Label: 0

A1937

ID: 765807662

Label: 0

A2973

ID: 765806740

Label: 0

A1390

ID: 765808148

Label: 0

B1430

ID: 765805704

Label: 1

B2618

ID: 765804653

Label: 1

A1915

ID: 765807679

Label: 0

B600

ID: 765804047

Label: 1

Model accuracy (Unoptimized (float32))

Validation set

98.3%

Test set

96.5%

On-device performance (Arduino Nano 33 BLE Sense (Cortex-M4F 64MHz), Quantized (int8))

Latency

104 ms.

Peak RAM usage

13.3K

Flash usage

36.8K

Run this model

Scan QR code or launch in browser

Launch in browser

Dataset summary

Data collected

6,084 items

Labels

0, 1

Project info

Project ID	318850
Project version	4
License	Apache 2.0
No. of views	64,645
No. of clones	9