Creation of an iPhone app to incorporate Core ML 3 models to perform object and character recognition.
Recognition to be performed real time using the video stream from the iPhone camera and also optionally from an external camera source.
If object of interest is found in the video stream Capture a still image, crop the image. Display the results on screen and also send data in JSON format to our restful api cloud database.
Compare results and matches against data contained in our restful api cloud database and provide on screen alert and play sound if a match.
Clean, modern UI design is required.
Regular publishing of code to shared repository.
NOT required to build / train the ML models which will be provided.
Prior demonstrated experience with Apple Core ML is required.
Will be ongoing work if successful with initial project.
About the recuiterMember since Nov 11, 2022 V Singh
from Veracruz, Mexico