Automated method and system for naming documents from a scanned source based on manually marked text

A method for automatically identifying and associating text with scanned documents, the method comprising:

• scanning a first document into image data, the first document comprising one or more selected portions of text that are manually marked for recognition;
• recognizing the one or more selected portions of text in the image data of the first scanned document;
• identifying a location of the recognized one or more selected portions of text in the image data of the first scanned document;
• storing the location of the recognized one or more selected portions of text, and, thereafter:
• scanning at least a second document into image data;
• and
• storing the image data for the at least second scanned document,
• wherein the location of the recognized one or more selected portions of text in the first scanned document is used to identify a corresponding location in the at least second scanned document, such that text in the corresponding location of the at least second scanned document is recognized, and wherein the method further comprises associating the image data of the at least second scanned document with the recognized text identified in the corresponding location of the at least second scanned document, and assigning a name to image data for the at least second scanned document using the text identified in the corresponding location of the at least second scanned document before storing the at least second scanned document.

A system for automatically identifying and associating text in a scanned document, the system comprising:

• a scanner for scanning a first physical document having one or more selected portions of text that are manually marked into image data, the scanner configured to form a first scanned document of image data corresponding to the first physical document and configured to scan at least a second physical document to form at least a second scanned document of image data corresponding to the at least second physical document;
• a module for recognizing the one or more selected portions of manually marked text in the image data of the first scanned document;
• a module for identifying a location of the recognized one or more selected portions of manually marked text in the image data of the first scanned document;
• a module for storing the location of the recognized one or more selected portions of manually marked text of the first scanned document,
• wherein the module for identifying the location of the recognized one or more selected portions of manually marked text in the first scanned document is configured to identify a corresponding location in the at least second scanned document and configured to recognize text in the corresponding location of the at least second scanned document, and wherein the system further comprises:
• a module for generating text in response to recognizing the text in the corresponding location of the at least second scanned document,
• a module for assigning the image data of the at least second scanned document a name using the generated text before storing the second scanned document, and
• a module for storing the image data for the at least second scanned document with the assigned name.