Vision
ML Kit offers two distinct services. One is for processing images and retrieving the results or any information on the image. The second service is using custom models such as TensorFlow to process the data for the results.
In ML Kit Vision, we have essential, ready-to-use models, which are listed as follows:
- Recognizing text
- Detecting faces
- Scanning barcodes
- Labeling images
- Recognizing landmarks
Let's explore what it is like to recognize text using ML-Kit.
Recognizing text
ML Kit offers powerful text recognition APIs. It can recognize any Latin-based language on an on-device basis, perhaps more when connected to a cloud. Text recognition can automate numerous data works. Using cloud-based APIs, we can extract text from different documents. Identifying the train schedule by PNR number on the ticket, we can write a model to set a reminder immediately or two hours before train departure, and in many more use cases.
Since recognizing text offers on-device and cloud-based features, it has a...
