Ziggy is a prototype AI-powered conversational partner designed for engaging, intelligent and relaxed discussions. Supports both text and voice.

Github

E-Bot is a virtual English speaking friend that helps deaf and hearing learners practice English through casual text conversation - supporting them with corrections, translated responses and spoken responses.

Github

T-Bot is an AI powered tool to support Thai language learners. The user can practice Thai through text conversation. The bot responds with both text and speech. Responses are translated into the user's first language.

Github

Learn English by chatting with Phoebe. Includes grammar correction and first language translation.

Github

Chat with captain Jack Sparrow. A simple desktop chat app that can be used to experiment with the OpenAI API.

Github

Khuluma is a ChatGPT powered personal voicebot that's built using only html, css and javascript. It's like Jarvis from Iron Man.

Github

A desktop flask app that uses computer vision to detect and localize masses on full field digital mammograms.

GitHub

Acc Score: 0.65
Access: Desktop
App type: Flask

A desktop interactive flask app that uses computer vision to automatically detect and count wheat heads on wheat field images.

GitHub

map@0.5: 0.93
Access: Desktop
App type: Flask

A light and simple Ai powered desktop app that auto detects opacities on chest x-rays. Built for high volume TB and Pneumonia diagnosis support.

GitHub

Acc: 0.91
Access: Desktop
App type: Flask

Promote safe and open dialogue by using Ai to automatically analyze comments and reviews for toxicity.

Kaggle Notebook

AUC Score: 0.88
Access: Web and API
App type: Flask

Use computer vision to automatically count wheat heads on wheat images.

Kaggle Notebook

MAE: 5.03
Count Error: 20.5 %
Batch Processing: No
Access: Web and API
App type: Flask

Use computer vision to detect and localize Covid-19 on chest x-ray images.

GitHub

Acc Score: 0.84
Batch Processing: No
Access: Web and API
App type: Flask

Automatically analyze a picture of a skin lesion and classify it into one of 7 types, including melanoma.

Kaggle Notebook

F1 Score: 81%
Batch Processing: Yes
Model Size: 27MB
App type: Tensorflow.js

Automatically detect metastatic cancer and invasive ductal carcinoma on histopathology image patches.

Kaggle Notebook

IDC F1 Score: 88%
Metastatic F1 Score: 94%
Batch Processing: Yes
Model Size: 26MB
App type: Tensorflow.js

Automatically detect diabetic retinopathy on fundus (eye) images.

Kaggle Notebook

F1 Score: 96%
Batch Processing: Yes
Model Size: 27MB
App type: Tensorflow.js

Detect Bacterial and Viral Pneumonia in children aged 1 to 5.

Kaggle Notebook

F1 Score: 75%
Batch Processing: Yes
Model Size: 33MB
App type: Tensorflow.js

Automatically detect and isolate intracranial hemorrhages (bleeding) on brain CT images.

Kaggle Notebook

F1 Score: None
Batch Processing: No
Model Size: 50MB
App type: Tensorflow.js

Automatically detect TB on chest x-rays.

Kaggle Notebook

F1 Score: 81%
Batch Processing: Yes
Model Size: 7MB
App type: Tensorflow.js

Use computer vision to detect and localize Covid-19 on chest x-ray images.

GitHub

Acc Score: 0.84
Batch Processing: No
Access: Web and API
App type: Flask

A desktop flask app that uses computer vision to detect and localize masses on full field digital mammograms.

GitHub

Acc Score: 0.65
Access: Desktop
App type: Flask

Automatically diagnose malaria in segmented red blood cell images.

Kaggle Notebook

F1 Score: 97%
Batch Processing: Yes
Model Size: 36MB
App type: Tensorflow.js

Automatically count cells on a cell mask microscopy image.

Kaggle Notebook

Max Counting Error: 3
Batch Processing: No
Model Size: 91MB
App type: Tensorflow.js

Use computer vision to detect weed seedlings.

Kaggle Notebook

F1 Score: 78%
Batch Processing: No
Model Size: 20MB
App type: Tensorflow.js

Assess bee hive health by analyzing a bee image.

Kaggle Notebook

F1 Score: 94%
Batch Processing: No
Model Size: 27MB
App type: Tensorflow.js

Automatically detect 3 types of rice leaf diseases.

Kaggle Notebook

F1 Score: 100%
Batch Processing: No
Model Size: 18MB
App type: Tensorflow.js

Automatically analyze the health of apple tree leaves - detect three disease classes.

Kaggle Notebook

F1 Score: 91%
Batch Processing: No
Model Size: 18MB
App type: Tensorflow.js

Use computer vision to automatically count wheat heads on wheat images.

Kaggle Notebook

MAE: 5.03
Count Error: 20.5 %
Batch Processing: No
Access: Web and API
App type: Flask

A desktop interactive flask app that uses computer vision to automatically detect and count wheat heads on wheat field images.

GitHub

map@0.5: 0.93
Access: Desktop
App type: Flask

Let an Ai artist convert your selfie into a painting.

Kaggle Notebook

F1 Score: None
Batch Processing: No
Model Size: 8MB
App type: Tensorflow.js

Practice on 3,662 fundus images. The image labels are: No DR, Mild, Moderate, Severe and Proliferative DR.

Data Source

Practice on 800 chest x-ray images. The image labels are: Normal and Tuberculosis.

Data Source

Sound2Vibe is a prototype electronic open source music and gaming aid for the deaf. It converts sound into vibrations that are transmitted through the body via bone conduction.

Github

A web based video dictionary to help students practice South African Sign Language (SASL). Includes signs for more than 1,500 words.

Github

A project that shows how to get a machine learning python script to send data to an Arduino micro-controller.

Github

This project shows a simple way to use computer vision to monitor a person who is at risk of having an epileptic seizure. When a seizure is detected, an alarm is triggered.

Github