I want to write an application on (Android) phone for image recognition. The (Keras) model itself is written and trained on a desktop machine and works satisfactorily with standard images. However, I have no experience with app programing so I have no clue how to write an app itself which could utilize the model.

The purpose is to use the mobile camera for seeking the object; have a big button to shot an image; have the image classified and display the output label as text. No need for any sophisticated outlook. I can write programs in Python.

Is there any handy framework that could be used for this purpose?


1 Answer 1


I would advise you to use kivy for Python. It has an active community and there is also a book on this topic Practical Computer Vision Applications Using Deep Learning with CNNs With Detailed Examples in Python Using TensorFlow and Kivy. Kivy is very easy for newbies and you can develop multiplatform applications (Windows, iOs, Android).


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.