Gravic, Inc.

Owen C Davison

Bruce D Holenstein

Victor F Berutti

Paul J Holenstein

Tristan E Hoffmann

Steven P Joslin

Dylan R Holenstein

A method and apparatus are provided for processing a document and validating data integrity and reliability of document processing results. The document includes one or more data collection areas which are located in and are part of the document and which are configured to receive input by a person who enters information in the one or more data collection areas, and a unique identifier which is located in and is part of the document. In operation, a document is received at the document distributor which distributes an electronic representation of the document to each of two or more document processing systems, each of which has an associated database. Processing of the document is initiated in each of the two or more document processing systems by reading the unique identifier of the document, interpreting any inputted information in the one or more data collection areas, and updating the associated database for each of the two or more document processing systems with document processing results including the read unique identifier of the document, and any interpreted inputted information. A hash value is computed in each of the two or more document processing systems, for each of the document processing results. A validation engine matches the computed hash values. The validation engine validates data integrity and reliability of the document processing results when the computed hash values match. The processing of the document in the database of each of the two or more document processing systems is then finalized when the data integrity and reliability of the document processing results has been validated. In one embodiment, the document is an election ballot.

Method and system for processing a document and validating data integrity and reliability of document processing results

A system, method and article of manufacture are provided for detecting message impressions from a document. The document includes one or more data collection areas adapted to receive input, and one or more message areas. Each message area includes a message. Memory representations of messages are stored in a memory. The document is received at a document processing engine which is adapted to access the memory to obtain the representations of messages. Message impressions are detected from the document by analyzing the document in the document processing engine. Message impressions are detected if it is determined that there is relevant input in the one or more data collection areas, and the document includes a representation of one or more of the messages.

System, method, and article of manufacture for analyzing a document and detecting message impressions from the document

A method and article of manufacture are provided for detecting message impressions from a document. The document includes one or more data collection areas adapted to receive input, and one or more message areas. Each message area includes a message. Memory representations of messages are stored in a memory. The document is received at a document processing engine which is adapted to access the memory to obtain the representations of messages. Message impressions are detected from the document by analyzing the document in the document processing engine. Message impressions are detected if it is determined that there is relevant input in the one or more data collection areas, and the document includes a representation of one or more of the messages.

System, method, and article of manufacture for analyzing and selectively further processing a document

Image data of a response form is processed. The response form has a plurality of response bubbles, including at least one filled and at least one unfilled response bubble. One or more baseline response bubble attributes for unfilled response bubbles are provided in a memory. Image data of a response form is processed to determine one or more response bubbles that are unfilled. One or more actual response bubble attributes of the one or more unfilled response bubbles is then calculated. A difference metric value is then calculated by comparing the one or more baseline response bubble attributes to the one or more actual response bubble attributes. The one or more baseline response bubble attributes are reset to a new set of one or more baseline response bubble attributes if the difference metric value exceeds a predetermined threshold. The one or more baseline response bubble attributes are maintained at their present value if the difference metric value does not exceed the predetermined threshold. The image data of the response form is then processed using either the reset or maintained one or more baseline response bubble attributes to determine the filled and unfilled response bubbles of the response form.

Dynamic response bubble attribute compensation

A method is provided for using at least one response bubble on a response form to indicate one or more responses. The response form has a key definition area that includes one or more response bubbles corresponding to one or more intended responses, and a response area that includes one or more response bubbles for indicating intended responses. A response form is completed by defining an unambiguous symbology of one or more marks by completing the key definition area, and filling in the response area using the defined unambiguous symbology. The response form is then electronically imaged. The unambiguous symbology is then automatically interpreted from the key definition area of the response form. The indicated intended responses of the one or more response bubbles of the completed response form are automatically interpreted using the interpreted unambiguous symbology, and the electronically imaged completed response form.

Dynamic response form symbology processing

Image data of a zone in a response form that has a plurality of response bubbles in the zone is processed. The image data of the zone has at least one response bubble that is well-formed and at least one response bubble that is not well-formed. Well-formed response bubbles are located in the zone from image data of the zone. The locations of the well-formed response bubbles in the zone are compared to a form template that defines the zone and contains data regarding locations of all expected response bubbles in the zone. It is determined from the comparison whether sufficient information exists to determine that the well-formed response bubbles constitute a specific part of the form template zone. If so, then the well-formed response bubbles are processed from the image data of the zone.

Inferential self-registration of imperfect OMR forms

Response bubbles on a scannable form are provided that allow a user to mark the bubbles in a manner that signifies that the user wishes to have a response disregarded.

Optical mark reading that uses a disregard state as part of an unambiguous symbology of marks to fill into response bubbles

One or more response bubbles are used on a scannable form to be read by a scanning system. An unambiguous symbology of marks is defined to fill into each response bubble, thereby allowing at least one of a plurality of different non-empty intended responses having different output values to be entered into each response bubble. One or more response bubbles are provided on the scannable form to be filled in according to the defined symbology of unambiguous marks. A filled in form is scanned with the scanning system and an image of the scanned form is processed by identifying pixels associated with each response bubble, interpreting the pixels associated with each response bubble to define a raw score according to the defined unambiguous symbology of marks used to mark each response bubble, translating the raw score for each response bubble into one of the plurality of different intended non-empty responses, and outputting the value of the non-empty response for each response bubble. Different output values have different meanings.

Growing community of inventors

Honey Brook, PA, United States of America

Owen C Davison