Eastman-kodak Company

Kodak Alaris Inc.

Apple Inc.

Louis J Beato

Joseph Anthony Manico

Dale Frederick McIntyre

Andrew Charles Gallagher

Roger S Gaborski

Andrew C Blose

Lori L Barski

Yongchun Lee

Anthony Scalise

Hin-Leong Tan

Joseph M Basile

John J Alescio

Andrew M Assad

William J Lloyd

Stanley A Mielcarek

Dawn L Dutton

A system and method for detecting the quality of a captured digital image depicting a hardcopy document are disclosed. The captured digital image is analyzed to determine a corresponding blurriness, noise, hotspot, and uneven illumination metric representing a quality level of the image data. The blurriness, noise, hotspot, and uneven illumination metrics are then combined to formulate a pass/caution/fail indicator for the user to respond to the captured digital image quality.

System and method for measuring mobile document image quality

A method for automatically classifying scanned hardcopy media based on its physical size. The hardcopy media is classified as a photograph if the determined physical size matches a common physical sizes for photographs to within a predetermined tolerance, and is classified as a document if the determined physical size matches one of the common physical sizes for documents to within a predetermined tolerance. Otherwise, a media classification is determined using contextual processing.

Classification of scanned hardcopy media

A method for detecting a document boundary in a captured digital image depicting a hardcopy document on a background. Each color channel of the captured digital image is analyzed to determine a corresponding busyness metric representing a complexity level of the image data. The color channel having a lowest busyness level is selected and analyzed to detect a document boundary of the depicted hardcopy document. The detected document boundary can be used to perform a perspective correction process to determine a corrected digital image where the depicted document has a substantially rectangular boundary.

Method for detecting a document boundary

A method of producing a digital stereoscopic image using a processor is disclosed. The method includes providing a plurality of digital image files which include digital images and the time of capture of each image and using time of capture to identify candidate pairs of images. The method further includes using the processor to analyze the image content of the candidate pairs of images to identify at least one image pair that can be used to produce a stereoscopic image; and using an identified image pair to produce the digital stereoscopic image.

Producing stereoscopic image

The present invention relates to a system and method for data storage and retrieval, and more particularly, for indicating that ancillary data is stored in a header of a JPEG file and accessible to a user. The system comprises a JPEG file having an EXIF header and associated image data, and at least one other file of digital data, and a computer. The computer is programmed to scan the JPEG image file for a special indicator in the application marker section of the EXIF header. If the marker is present, the value of marker indicates what type of ancillary digital data is present in the header. For instance, if the marker contains the string EKC-JPEG, then the ancillary data is known to be another JPEG file. Other types of data can be indicated as appropriate. The presence of the ancillary data is then used for the appropriate type of presentation to the user. A reveal icon is then used in presenting the data to indicate whether the ancillary data is another JPEG file, video, audio, sound, document, etc. The user would be presented with the data as appropriate.

Storing and presenting ancillary information obtained from scanned prints

A method of determining the image capture date of scanned hardcopy medium, includes scanning hardcopy medium that includes at least one index print(s) to produce scanned digital images; detecting one or more index prints from among the scanned digital images; identifying thumbnail images contained within the one or more index prints; determining an image capture date for each index print and associating the image capture date with the thumbnail image(s) contained within that index print; matching a scanned digital image to a thumbnail image from the one or more index prints; associating the date from the thumbnail image to the scanned digital image that matches the thumbnail image; and storing the date in association with the scanned digital image that matches the thumbnail image.

Finding orientation and date of hardcopy medium

The present disclosure relates to automatically generating a dynamic set of metadata from digitized hardcopy media. The technique includes scanning the image side and non-image side of a plurality of hardcopy media. A dynamic digital metadata record of each of the plurality of hardcopy media is created and used for manipulating each of the plurality of hardcopy media.

Method for automatically generating a dynamic digital metadata record from digitized hardcopy media

A system and method for determining the image and ancillary image sides of scanned hardcopy media. Hardcopy prints typically provide ancillary data to supply additional information for an area of interest and can enhance the analysis of key data in the print. Postcards, for example, provide a unique form of ancillary data. On the back of a postcard image, ancillary data information such as stamps, user notes, dates, addresses, and other types of annotation can be found. This data typically provides additional information to a reader of the postcard. Dual sided scanners provide both the image and ancillary (i.e., non-image) scans simultaneously. In addition, ancillary data can be in a variety of formats, such as audio, video and the like. When a hardcopy print is scanned the scanner provides two image files that represent the image and ancillary image sides of the print. However, given two image files that represent a hardcopy print scan, the front and back need to be automatically identified as to which is of primary interest to a user.

Automatic determining image and non-image sides of scanned hardcopy media

An image processing method for detection and removal of halftone dots includes converting a gray scale image into a binary thresholded image with halftone dots; identifying halftone regions within the binary thresholded image; and removing halftone dots from the identified halftone regions. The identifying halftone regions step is effected by classifying the binary thresholded image to produce a halftone classification map; reclassifying the halftone classification map to produce a halftone reclassification map of lines with plural halftone pixels in each line; merging the halftone pixels in each line in the halftone reclassification map to produce a halftone line map; and merging the lines of the halftone line map to produce a halftone region map.

Method and apparatus for digital halftone dots detection and removal in

In processing a text image prior to optical character recognition processing, non-text graphical material is removed from the image by first discarding all lines in accordance with the length of the line and/or the percentage of black pixels in the entire pixel row (or column) in which the line is located. The line length and black pixel percentage are parameters which are traded off against one another on a sliding scale. Then, the remaining objects in the image are processed in a two-step process in which: (a) objects whose size is above a maximum threshold or below a minimum threshold are discarded and (b) individual sub-objects comprised within any of the discarded objects whose individual area and height are within threshold percentages of the median area and height of all objects in the image are restored to the image.

Bi-tonal image non-text matter removal with run length and connected

Character images which are to be sent to a neural network trained to recognize a predetermined set of symbols are first processed by an optical character recognition pre-processor which normalizes the character images. The output of the neural network is processed by an optical character recognition post-processor. The post-processor corrects erroneous symbol identifications made by the neural network. The post-processor identifies special symbols and symbol cases not identifiable by the neural network following character normalization. For characters identified by the neural network with low scores, the post-processor attempts to find and separate adjacent characters which are kerned and characters which are touching. The touching characters are separated in one of nine successively initiated processes depending upon the geometric parameters of the image. When all else fails, the post-processor selects either the second or third highest scoring symbol identified by the neural network based upon the likelihood of the second or third highest scoring symbol being confused with the highest scoring symbol.

Optical character recognition neural network system for machine-printed

In character normalization for optical character recognition preprocessing employing horizontal and vertical scaling factors A and B, the value of each pixel in the normalized character image superimposed on the original character image is determined from the values of the pixels in the original image lying within an elliptical neighborhood surrounding the normalized character image pixel and having major and minor elliptical axes proportional to A and B.

Growing community of inventors

Rochester, NY, United States of America

Louis J Beato