Amazon Technologies, Inc.

Laura Varnum Finney

Bhavesh Anil Doshi

Neil David Cooper

Prashant Hegde

Kevin Robert McGehee

John Ryan Sherritt

Louis LeRoi LeGrand, Iii

Yue Liu

Daniel Bibireata

Chang Yuan

Geoffrey Heller

Avnish Sikka

Matthew Joseph Cole

David Paul Ramos

Sonjeev Jahagirdar

Emilie Noelle McConville

Utkarsh Prateek

Ankur Datta

Michael Vanne

Saurabh Verma

An extendable augmented reality (AR) system for recognizing objects. The AR system may incorporate plugins to improve the AR system's ability to recognize objects, such as by adding external matchable data or using external recognition algorithms. The plugins may be installed/activated dynamically by a user to expand the system's AR capabilities. The AR system may also incorporate plugins to improve the AR system's post-recognition features such as supplying a user with supplemental content or follow-up functionality. The AR system may filter communications with the plugins to centralize identification processes, to shield plugins, and to ensure plugins are only activated at appropriate times.

Extendable architecture for augmented reality system

Disclosed are techniques for recognizing text from one or more frames of image data using contextual information. In some implementations, image data including a captured textual item is processed to identify an entity in the image data. A context can be selected using the entity, where the context corresponds to a dictionary. Text in the captured textual item can be identified using the dictionary. The identified text can be output to a display device.

Recognizing text from frames of image data using contextual information

The accuracy of a text recognition process can be improved using a set of semantic boosting rules, as may be contained in a sequence or other such arrangement. When text is output from a text recognition process, that text can have alternatives and confidence values for different characters or portions of the string. In order to improve the accuracy, this data can be processed using the organized rules, where rules are applied as long as any preconditions for that rule are satisfied, and each rule has the ability to modify the confidence values or modify one or more of the alternatives. When a result it produced with a minimum confidence level, or all applicable rules have been applied, the result can be provided as a refined text output of the recognition process.

Semantic boosting rules for improving text recognition

Growing community of inventors

Seattle, WA, United States of America

Laura Varnum Finney