What is the problem?

Although most people think that a mosquito bite is harmless, in many countries across the world, getting stung can be downright fatal. Once we started researching why malaria is so dangerous, we learned that the most important reason is that medical professionals are too far away from rural citizens which means that they do not seek help. Thus, a mobile app which is convenient makes it easier for people to get a early diagnosis before seeing a doctor.

What is the solution?

Our project Identifiir identifies Malaria in human blood cells. The user first uploads an image and then Identifiir will look at that image and help identify whether/whether or not that person has malaria.

How we built it

We used tensorflow and python VGG16 model for classifying the cell images having infection or not

Challenges we ran into

  1. Since all our team members are new to tensorflow we invested a lot time in explaining each other code which led to less time for training our ml model.

Accomplishments that we're proud of

Finally we're able to train our model while keeping things clean and mostly accurate.

What we learned

We learned how to use tensorflow keras, VGG!6 and how to effectively work on a project in a team and much more.

What's next for Identifiir

Since our model requires more images to easily classify between infected cell images and healthier one. We're planning to make scale it and make it more accurate and easy to use. And also making it for classifying skin images.

Share this project: