Browse Prior Art Database

Automatic translation and association of text in document to regions on graphics images

IP.com Disclosure Number: IPCOM000180497D
Original Publication Date: 2009-Mar-10
Included in the Prior Art Database: 2009-Mar-10
Document File: 2 page(s) / 27K

Publishing Venue

IBM

Abstract

This invention describes a system that has the ability to identify and associate words being read in a document (for example, software usage instructions) to the portion of the graphic image (in the doc) where the words are describing. Further more; if the language of the document does not match the language of the text on the graphic image, a translation of the image text appears as a pop up over the image. This system helps the reader quickly identify where on the image the words in the document are describing and performs auto text translation for the user if necessary.

This text was extracted from a PDF file.
At least one non-text object (such as an image or picture) has been suppressed.
This is the abbreviated version, containing approximately 54% of the total text.

Page 1 of 2

Automatic translation and association of text in document to regions on graphics images

This invention describes a system that has the ability to identify and associate words being read in a document (for example, software usage instructions) to the portion of the graphic image (in the doc) which the words describe. Further more; if the language of the document does not match the language of the text on the graphic image, a translation of the image text appears as a pop up over the image. This system helps the reader quickly identify where on the image the words in the document are describing and performs auto text translation for the user if necessary

There are many documents, books or technical manuals that describe or teach the reader how to do certain things. Quite often images/graphics are included in the document to help with comprehension. There is text in the document that describes these images. For example, a paragraph in the document is used to describe a screen capture of a software user interface and instructs the user on how to interact with the user interface. It may be time consuming to read the description text, find the region on the image/graphics that the text is referring to (going back for forth between text and image). This can be more painful if the language of the doc and the language shown on the images/graphics are not the same.

Using this system, as the user hovers the cursor over the words in the paragraph, the related region/portion o...