Detecting covid-19 using Xray images

Collecting data

Positive Covid-19 X-rays

This repository currently contains 68 covid-positive xrays as well as of MERS, SARS, and ARDS.

python build_dataset.py -m <dataset folder path> -o <output path>

Negative Covid-19 X-rays

Kaggle chest xray dataset.

We select 68 random images from the above dataset to keep balance.

Training the model

I use VGGNet which is pre-trained on the imagenet dataset.

python trainModel.py -d <dataset path>

Detection

python detectCovid.py -i <input image path> -m <trained model path>

This will give an output with image labeled as covid-positive or covid-negetive.

Output

For exmaple, for the image [covid1.jpeg], which is covid-positive.

python detectCovid.py -i test-data/covid1.jpeg -m model.h5

For the image [normal1.jpeg], which is covid-negetive, I got the following output:

python3 detectCovid.py -i test-data/normal1.jpeg -m model.h5