TEXT RECOGNITION THROUGH IMAGES AND VIDEO

摘要

The display of text by a first device, that is extracted and used by a second communication device, based upon a determined context of the text, is provided. The image displayed for the first device is captured by an image capture element of a second communication device, which also has a recognition module and an extraction module. The image includes the text and a context element representing a context of the text.

主权项

1. A communication device, comprising:
an image capture element operable to capture an image displayed by a first device; a processor, in communication with the image capture element, and configured to:
recognize text in the image;recognize a context element in the image, the context element representing a context of the recognized text;perform optical character recognition of the recognized text;extract from the image the recognized text; anduse the recognized text in an application and in accordance with the context of the text.