Google Mobile Vision API - bounswe/bounswe2017group3 GitHub Wiki

Mobile Vision API by Google provides a framework for detecting specific objects in photos and videos using on-device visual technology. It includes facial, barcode and text detectors which could be applied either seperately or together, in detecting visual objects in images that could be interpreted as one of the three. It also uses an event driven API for videos.

#Face API It automatically finds and locates human faces in visual media. A face is reported at a position specified with a size and orientation. It further looks for facial landmarks such as the eyes and mouth, and provides information.

#Barcode API Automatically detects any barcode or barcodes in real-time. It reads a variety of barcode formats from 1-D EAN and UPC to 2-D QR Codes and Data Matrices. It further parses data read automatically to supported formats.

#Text API It recognizes texts in latin based languages, analyzes and represents structural objects like paragraphs,sentences and words. It can be used to automate data entry and in keeping track of real objects.

#References https://developers.google.com/vision