US 8,619,340 B2Granted

Augmenting page orientation direction detection in a digital document processing environment

AssigneeXerox Corporation

InventorsZhigang Fan, Michael R. Campanelli

Life of this patent

Estimating the term…

Loading patent…

Abstract

What is disclosed is a novel system and method for augmenting present methods used for determining the orientation direction automatically being detected of digital pages of a plurality of scanned documents in a digital document processing environment. The present method takes advantage of the observation that pages scanned in data processing centers are often highly correlated. The present method contains five primary steps. 1) Page orientation (i.e., up/down) is detected using a traditional method. 2) Each page is classified as either directional or non-directional. 3) The pages classified as directional are clustered into groups. 4) The direction for each group is determined. 5) The directional group's direction is used to revise the orientation for pages contained in the group. Through the implementation of the teachings hereof, performance, in terms of both speed and accuracy, are very high relative to current methods and detection error rates can be reduced significantly.

Claims16

Dependent claims

A method for correcting the orientation direction detected for pages of scanned documents, the method comprising:

receiving a plurality of pages of at least one digital document;
for each page of said plurality of pages:
determining an initial orientation direction for this page using a first direction detection algorithm, said initial orientation direction being one of:
a forward and an inverted direction;
determining a confidence level associated with this page's initial orientation direction, based upon a pre-determined threshold;
in response to said confidence level being below said pre-determined threshold, re-determining said initial orientation direction for said page using a second detection algorithm, said first detection algorithm and said second detection algorithm being different;
determining a structural similarity between this page's forward and inverted versions
classifying, based upon said structural similarity, said page as being one of:
directional and non-directional;
clustering pages classified as being directional into groups of pages based upon a similarity in page structure;
for each group of pages:
estimating a group orientation direction based upon a total amount of pages having a same initial orientation direction;
and
for each page within each group:
determining, based upon this page's confidence level, whether this page's orientation direction requires correction;
and
in response to said page's orientation direction requiring correction, signaling a document processing system to change this page's initial orientation direction.

14 more elements

A system for correcting the orientation direction detected for pages of scanned documents, the system comprising:

a document scanning device;
a document processing system capable of changing a given page's detected orientation direction;
a memory and a storage medium;
and
a processor in communication with said document scanning device and said memory and storage medium, said processor executing machine readable instructions for performing the method of:
receiving a plurality of pages of at least one digital document;
for each page of said plurality of pages:
determining an initial orientation direction for this page using a first direction detection algorithm, said initial orientation direction being one of:
a forward and an inverted direction;
determining a confidence level associated with this page's initial orientation direction, based upon a pre-determined threshold;
in response to said confidence level being below said pre-determined threshold, re-determining said initial orientation direction for said page using a second detection algorithm, said first detection algorithm and said second detection algorithm being different;
determining a structural similarity between this page's forward and inverted versions
classifying, based upon said structural similarity, said page as being one of:
directional and non-directional;
clustering pages classified as being directional into groups of pages based upon a similarity in page structure;
for each group of pages:
estimating a group orientation direction based upon a total amount of pages having a same initial orientation direction;
and
for each page within each group:
determining, based upon this page's confidence level, whether this page's orientation direction requires correction;
and
in response to said page's orientation direction requiring correction, signaling a document processing system to change this page's initial orientation direction.

19 more elements

Dependencies are inferred from the claim text.