Methods and system of electronic image analysis
AssigneeDigital Medical Records, LLC
InventorDavid Lewis
Life of this patent
Estimating the term…
Abstract
A machine translation of a document is created via a compilation of services by mapping textual content from an image to create a plurality of mapped locations correspondent to at least one object from the image, populating each of the mapped locations with at least one character indicative of the object, each character sharing at least one similar attribute, adding to the image the populated mapped locations, and highlighting at least a portion of the textual content in accordance with the populated at least one character. A compilation of services is provided for identifying, extracting, and assessing electronic images by using a layered approach that reduces time and improves reviewing of medical records and other kinds of documentation.
Claims15
A method for transforming documentation in a computing device, the method comprising:
- receiving, by the computing device, a request from a user to transform a document;
- storing, by the computing device, an original copy of the document and documentation details associated with the document to a database;
- extracting, using a Web service, textual content from each page of the document;
- identifying information about the extracted textual content from each page of the document;
- creating an invisible and searchable layer of each page the document based on the extracted textual content;
- combining, for each page of the document, an image of the original copy of the document with the corresponding invisible and searchable layer of the document to create a searchable version of the document;
- storing the searchable version of the document and the identified information to the database for subsequent retrieval;
- and
- wherein, for each word of the extracted textual content and each page of the document, creating the invisible and searchable layer further comprises:
- determining original bounding box size and bounding box coordinates for each word of the extracted textual content based on the identified information;
- setting the page transparency of the page to maximum;
- reducing, gradually, the font size until the word fits within the original bounding box size;
- and
- writing the word to the page based on the bounding box coordinates of the page.
A system for transforming documentation in a computing device, the system comprising:
- a graphical user interface capable of receiving a request from a user to transform a document stored on a non-transitory computer readable storage medium;
- at least one network port for receiving a source document and at least one document attribute;
- a database for recording the extraction of textual content from at least one page of the source document;
- a rules engine for identifying information about the extracted textual content and creating a hidden and searchable layer on at least one page of the source document based on the extracted textual content;
- a data layer for receiving a searchable version of the source document and the identified information wherein an image of the source document with the corresponding hidden and searchable layer of the document are merged to create a searchable version of the documents and
- wherein the creating the hidden and searchable layer further comprises:
- determining original bounding box size and bounding box coordinates for each word of the extracted textual content based on the identified information;
- setting the page transparency of the page to maximum;
- reducing, gradually, the font size until the word fits within the original bounding box size;
- and
- writing the word to the page based on the bounding box coordinates of the page.
Dependencies are inferred from the claim text.