
Introduced to Google I / O Tuesday, ML Kit csists of a number of APIs that developers can integrate into their applicatis, with little prior knowledge of machine learning required to use them. The APIs are provided by Google and have been the subject of extensive training, which allowed developers to not create their own model and not to spend the resources necessary to train them properly.
The existing models proposed by Google in ML Kit allow text recogniti, face detecti, image labeling, marker recogniti and barcode reading, all based device imaging data. Future additis to the list include an API to add intelligent respses to messages, and a high-density face ctour feature for Face Detecti API that will be useful for adding imaging effects to a picture.
The ML Kit APIs are available in two versis with some compromises. The cloud-based versi requires an Internet cnecti, but offers great accuracy, while the versi the device is less accurate and depends the device's processing power, but can be used offline. For example, while the offline versi is able to identify a dog inside a photograph, it is unlikely to find any more precise details the …