System and method for automatic natural language translation of embedded text regions in images during information transfer
View Patent ↗Image or graphic elements such as pictures, icons and clip art, are intercepted during transfer from a computer source to a computer destination, such as during a cut-and-paste operation. Embedded text within the intercepted element is optically recognized, and encoded text is extracted. It is determined if the language of the text matches a desired language of the destination. If not, a translation of the optically-recognized text data is performed, and the translated text data is rendered into image data. The image data is then substituted into the intercepted element to overlay or replace the original embedded text, thereby “translating” the image or graphic element to a desired destination language. The modified image or graphic element is then delivered to the destination, such as a document, program, file or data structure.
1. A method comprising:
in a user interface portion of a computer display of a computing platform:
receiving from a user a preselection and predesignation of one or more destination points within a destination computer file; and
subsequently to said preselection and predesignation, receiving a selection from said user of one or more image elements within one or more source computer files;
receiving a copy of said selection image elements upon operation of a user cut-and-paste command via said user interface portion into an operating system clipboard buffer portion of said computing platform;
selectively isolating image elements by:
receiving a user-supplied isolation rule defining one or more typed of image elements to be isolated;
examining said image element in said clipboard buffer to determine a type of image element; and
responsive to said image element type meeting said isolation rule, transferring said image element from said clipboard buffer to an isolation store, thereby disabling pasting of the image element from the clipboard;
intercepting and preventing pasting of said image element remaining in said clipboard buffer responsive to said isolator determining said type of image element does not meet said isolation rule;
recognizing one or more embedded text instances within said intercepted source image element;
determining a natural language in which each recognized text instance is expressed;
comparing said expressed natural language of said recognized text for a match to a user-specified destination natural language; performing natural language;
responsive to said expressed natural language not matching said user-specified destination natural language, performing natural language translation of said embedded text instances into said user specified destination natural language;
rendering translated text data for each translated text instance into text image data;
replacing each embedded text instance in said intercepted image element with a corresponding translated embedded text image data; and
completing the pasting of said image element having said replaced text from said clipboard buffer to said one or more destination points within said destination computer file.
2. The method as set forth in claim 1 wherein said step of recognizing one or more text instances comprises performing at least one operation selected from the group of performing Optical Character Recognition on an embedded text region and extracting a text string from encoded text.
3. The method as set forth in claim 1 wherein said step of determining if each embedded text instance is expressed in a natural language which matches a user-specified destination natural language comprises searching for each recognized character in a system alphabet corresponding to said destination natural language.
4. The method as set forth in claim 1 wherein said step of determining if each text instance is expressed in a natural language which matches a user-specified destination natural language comprises searching for each recognized word in a system dictionary corresponding to said destination natural language.
5. The method as set forth in claim 1 wherein said step of performing natural language translation of one or more text instances which do not match said user specified destination natural language comprises:
determining a source natural language in which each source text instance was originally expressed;
selecting an appropriate translation resource corresponding to said source natural language and said destination natural language; and
invoking said selected translation resource to perform translation of the recognized text for said source embedded text instance.
6. The method as set forth in claim 5 wherein said step of determining a source natural language in which each source text instance was originally expressed comprises searching for each recognized character in one or more system alphabets, each system alphabet corresponding to a source natural language.
7. The method as set forth in claim 5 wherein said step of determining a source natural language in which each source text instance was originally expressed comprises searching for each recognized word in one or more system dictionaries, each system dictionary corresponding to a source natural language.