Microsoft Technology Licensing, LLC

Zhigu Holdings Limited

Sasa Galic

Bogdan Radakovic

Bodin Dresevic

Aleksandar Uzelac

Djordje Nijemcevic

Milan Vugdelija

Mircea Cimpoi

Nikola Todic

A method and system is provided for identifying a page layout of an image that includes textual regions. The textual regions are to undergo optical character recognition (OCR). The system includes an input component that receives an input image that includes words around which bounding boxes have been formed and a text identifying component that groups the words into a plurality of text regions. A reading line component groups words within each of the text regions into reading lines. A text region sorting component that sorts the text regions in accordance with their reading order.

Page layout determination of an image undergoing optical character recognition

An image processing apparatus for detecting paragraphs in a textual image includes an input component for receiving an input image in which textual lines and words have been identified and a page classification component for classifying the input image as a first or second page type. The apparatus also includes a paragraph detection component for classifying all textual lines on the input image as a beginning paragraph line or a continuation paragraph line. The apparatus is also provided with a paragraph creation component for creating paragraphs that include textual lines between two successive beginning paragraph lines, including a first of the two successive beginning paragraph lines. The paragraphs that have been identified may be classified by the type of alignment they exhibit. For instance, paragraphs may be classified according to whether they are left aligned, right aligned, center aligned or justified.

Paragraph recognition in an optical character recognition (OCR) process

A method for enhancing a textual image for undergoing optical character recognition begins by receiving an image that includes native lines of text. A background line profile is determined which represents an average background intensity along the native lines in the image. Likewise, a foreground line profile is determined which represents an average foreground background intensity along the native lines in the image. The pixels in the image are assigned to either a background or foreground portion of the image based at least in part on the background line profile and the foreground line profile. The intensity of the pixels designated to the background portion of the image is adjusted to a maximum brightness so as to represent a portion of the image that does not include text.

Text enhancement of a textual image undergoing optical character recognition

Page segmentation in an optical character recognition process is performed to detect textual objects and/or image objects. Textual objects in an input gray scale image are detected by selecting candidates for native lines which are sets of horizontally neighboring connected components (i.e., subsets of image pixels where each pixel from the set is connected with all remaining pixels from the set) having similar vertical statistics defined by values of baseline (the line upon which most text characters 'sit') and mean line (the line under which most of the characters 'hang'). Binary classification is performed on the native line candidates to classify them as textual or non-textual through examination of any embedded regularity. Image objects are indirectly detected by detecting the image's background using the detected text to define the background. Once the background is detected, what remains (i.e., the non-background) is an image object.

Document page segmentation in optical character recognition

A system and method is provided which rescales a received image to an optimal size to undergo an optical character recognition (OCR) process. The system includes an optimal size determination component that determines an optimum size for the image such that processing time of the received image is minimized without affecting accuracy. The optimal size determination component determines the optimum size of the image based at least in part on a dominant interline spacing of text and a dominant text height. The system also includes a rescaling component that resizes the received image to the determined optimum size.

Resolution adjustment of an image that includes text undergoing an OCR process

Line segmentation in an OCR process is performed to detect the positions of words within an input textual line image by extracting features from the input to locate breaks and then classifying the breaks into one of two break classes which include inter-word breaks and inter-character breaks. An output including the bounding boxes of the detected words and a probability that a given break belongs to the identified class can then be provided to downstream OCR or other components for post-processing. Advantageously, by reducing line segmentation to the extraction of features, including the position of each break and the number of break features, and break classification, the task of line segmentation is made less complex but with no loss of generality.

Detecting position of word breaks in a textual line image

An image deskew system and techniques are used in the context of optical character recognition. An image is obtained of an original set of characters in an original linear (horizontal) orientation. An acquired set of characters, which is skewed relative to the original linear orientation by a rotation angle, is represented by pixels of the image. The rotation angle is estimated, and a confidence value may be associated with the estimation, to determine whether to deskew the image. In connection with rotation angle estimation, an edge detection filter is applied to the acquired set of characters to produce an edge map, which is input to a linear hough transform filter to produce a set of output lines in parametric form. The output lines are assigned scores, and based on the scores, at least one output line is determined to be a dominant line with a slope approximating the rotation angle.

Growing community of inventors

Seattle, WA, United States of America

Sasa Galic