Microsoft Technology Licensing, LLC

Daryl T Lawton

Ming Gang Liu

Mahmood Gulam Qadir

Kevyn Breca Collins-Thompson

Kristin Dahl Acker

Henry W Burgess

David L Bien

Alexandra W Loeb

John A Monson

Eric J Feigin

Tanuja A Joshi

Discriminating between documents scanned in a batch scanning process is achieved based on various analyses of the constituent document pages. The data provided by the various analyses are compared with each other to determine whether successive pages belong to the same document. Scanned documents result in a page sequence that is analyzed to extract one or more feature attributes for each page. The feature attributes are provided to a feature comparison process in order to assess the similarity of successive pages. If a sufficient likelihood of similarity is found, the compared pages are deemed to be from the same document; otherwise, they are deemed to be from different documents, indicating the existence of a document break. Based on the document breaks, separate scan files may be established. In this manner, the present invention represents eliminates the requirement of user intervention.

Method and apparatus for discriminating between documents in batch scanned document files

A system for retrieving information from a document. The system includes a document model representative of the document having a plurality of data structures representative of components within the document and a thumbnail image registered with the document model. The registration is accomplished by mapping selected coordinates within the thumbnail image to a data structure selected from the plurality of data structures. In this manner, a user can interact with the thumbnail image coordinates to retrieve data from the document as a function of the components mapped to those coordinates. In a further embodiment of the invention, the retrieved information may be streamed to a word-at-a-time display. This is particularly useful when used in connection with the display of low-resolution images on hand-held devices.

Method and system for browsing a low-resolution image

A method, apparatus, and article of manufacture provides a zero-crossing filtering region process for extracting data and related image elements from an input image. The input image is processed to generate connected component regions that correspond to image elements within the input image. The connected component regions are generated using a zero-crossing filter that attempts to identify pixels having a significant rate of change in value from their respective neighboring pixels. The connected components are then classified as being part of a foreground image or a background image that allows the image elements to be separated from the input image. Once the input image has been separated into multiple images, each separated image may be processed in a different manner depending upon the separate image's characteristics and uses.

Zero-crossing region filtering for processing scanned documents

Discriminating between documents scanned in a batch scanning process is achieved based on various analyses of the constituent document pages. The data provided by the various analyses are compared with each other to determine whether successive pages belong to the same document. Scanned documents result in a page sequence. The page sequence is then analyzed to extract one or more features attributes for each page. The feature attributes are provided to a feature comparison process in order to assess the similarity of successive pages. If a sufficient likelihood of similarity is found, then the compared pages are deemed to be from the same document; otherwise, they are deemed to be from different documents, indicating the existence of a document break. Through the display of the page sequence, a user may optionally modify the location of one or more document breaks. Based on the document breaks, separate scan files may be established. In this manner, the present invention represents eliminates the requirement of user intervention.

An apparatus including a method of digital image processing which allows a user to remove narrow, elongated areas of image distortion from a digitized image. According to the method, the user selects a portion of an image to be edited and, once the portion has been identified, the image distortion within the portion is automatically removed. The procedure for removing the distortion includes the steps of delineating the distortion within the portion of the image selected and replacing the delineated area with a correction image which is created as a function of the attributes of the neighboring portions of the image.

Automated removal of narrow, elongated distortions from a digital image

A technique of editing a digital image provides for the automatic removal of blotchy areas. From a user interface of a computer system, a user of the computer system identifies a location of a blotchy area to be removed in the digital image in response to prompting by the user interface. Based on the location provided by the user, the technique automatically determines the location of the blotchy area. Attributes of pixels comprising the digital image in a neighborhood around the blotchy area are automatically collected, while excluding the pixels comprising the blotchy area. The corrupted values of the pixels of the blotchy area are replaced with values derived at least in part from the attributes of the neighboring pixels Several different embodiments are described with various degrees of automation, including one embodiment in which all blotches of a character similar to the one selected by the user are automatically identified and removed.

User directed dust and compact anomaly remover from digital images

An apparatus and method is disclosed for automatically editing a digital color image to remove discoloration of the image, known as a 'red eye' effect, by parsing the discoloration into regions and re-coloring the area of the discoloration based on the attributes of the discoloration. The editing process according to the invention automatically creates a bitmap that is a correction image, which is composited with the source image or a copy of it and displayed as the source image with the red eye effect corrected.

Automated removal of red eye effect from a digital image

A system and method is described for automatically editing digital images. An image to be edited is selected and registered with a model that is an abstract of features and attributes common to a category of images to which the selected image belongs. In the illustrated embodiment, a human face is used as an example of an image to be edited and the matching model is a representation of features and attributes common to all human faces. Many other images of objects may also be edited using the techniques of the invention, as long as a general class of objects to which an image belongs is amenable to being represented by a model comprising a set of common features or attributes. A library of different models is available to the user for selecting the model matching the image to be edited. The library includes different models of the same object in different orientations and may also include models of different objects. After the appropriate model is selected, the user is prompted to register the details of the selected image with the generalized features and attributes of the selected model. Editing processes or tools, which are linked to the model, are then automatically appled to the image in order to perform a desired editing function. In addition to applying editing techniques to existing images in a larger image, the invention enables a user to paste and blend images into another, larger image--e.g., create a morphing effect by pasting one persons head over the head of another in an original image.

Model based image editing and correction

A method and apparatus for modifying a sprite containing a cutout feature for compositing with a background image modifies colors of pixels in the sprite according to their distances from the edge of the cutout feature to achieve desired visual effects such as edge softening. A distance mask for the sprite is generated which stores distance values representing distances of corresponding pixels in the sprite from the edge of the cutout feature. The distance mask can be efficiently generated by a chamfering technique. A clamping function is applied to the distance mask to determine scaling values for the respective pixels in the sprite. A modified sprite is constructed from the original sprite by modifying the colors of the pixels of the input sprite according to their respective scaling values. The modified sprite is then composited with the backgorund image to form a composite image.

Growing community of inventors

Bellevue, WA, United States of America

Daryl T Lawton