Xerox Corporation

Other

Peter C Wayner

Daniel P Huttenlocher

Michael J Hopcroft

Todd A Cass

A processor measures skew of lines in an image by obtaining a first, coarse approximation to skew direction and then using the first approximation to obtain a second, fine approximation that is more precise than the first. A third, even more precise approximation can be obtained using the second approximation, and further successive approximations can be similarly obtained. In an image of text, the first approximation can be obtained by finding the direction in which characters are closest together, since intercharacter distances are typically smaller than interline distances. This direction can be determined by measuring distances from selected pixels at edges of connected components across white pixels to edges of other connected components. The measured distances in each direction can be combined to obtain a central value for the direction, such as an average. The central values form a profile indicating central value as a function of direction. The minima separated by 180&deg; within the profile indicate the direction of intercharacter spacing, which provides a first approximation of the skew direction. Alternatively, the first approximation can be obtained by finding a direction that has the largest variance in black pixels per line, because the lines in the direction of skew either have many black pixels due to characters in a line or few black pixels due to spaces between lines. The second approximation can then be obtained by determining which one of a number of directions close to the first approximation has the largest variance in black pixels per line. The range of directions used to obtain the second approximation can be based on the angle separating directions used in obtaining the first approximation.

Coarse and fine skew measurement

A method for determining the boundaries of a symbol or word string within an image, including the steps of determining page orientation, isolating symbol strings from adjacent symbol strings, establishing a set of boundaries or references with respect to which measurements about, or further processing of, the symbol string may be made.

Method for determining boundaries of words in text

A device for creating and displaying a graph describing the dynamic of a game. The graph is created by displaying the a curve representing the score of the game at significant moments in the process of the game. This is superimposed upon information describing these significant moments. Markers that connect these significant instances with the score are also shown. These graphical forms may be displayed in an animated production.

Method and device for graphical display of a sporting contest

An image is analyzed by random or pseudorandom sampling. Information about attributes such as skew, typeface, and character size and spacing is obtained by measuring a characteristic at a number of sampled locations and combining the results to obtain a measure of the characteristic for the image. The number of sampled locations is smaller than the number of locations in the image, but is large enough to achieve a degree of statistical significance. The sampled locations can be selected by obtaining a random or pseudorandom number indicating a candidate location and then applying a criterion to determine whether the candidate location is an appropriate starting point for the measurement. For example, the criterion can be that the location must be a pixel within a character or must be a pixel of a given color at an edge. The measurement can indicate a distance from each sampled location in each of a number of directions, such as the distance to an edge. The distances can be combined to obtain data indicating a distribution, such as by averaging. An image can be divided into segments, each of which has a prominent value for a characteristic being measured, by first dividing the image into starting segments, then sampling the starting segments to measure the characteristic, and then grouping the starting segments into larger segments based on the measurements. The starting segments can be rectangles or, for an image with words, can be segments that each include a word or a paragraph.

Image analysis based on location sampling

Dominant typeface, including point size, of text in an image is identified by measuring distances across connected components in each of plural directions to obtain distribution data. The distribution data indicate a distribution of distances across connected components in each direction for the image. The distribution data are then used to obtain typeface data indicating the dominant typeface of characters in the text. Distance can be measured from each of a set of pixels that are inside or on edges of connected components to an edge of a connected component. The distances for each direction can be combined, such as by obtaining an average or other measure of central value, so that the combined distances indicate the distribution of distances in the direction. The distribution data can be used to form a profile that can be compared or clustered with other profiles to identify similar profiles or to find a matching profile. Skew can be obtained and used in forming profiles that are independent of skew. The comparisons can be independent of differences in character scale. A machine can store a set of model profiles of known typeface and point size in memory and can compare a profile for an image with each model profile to find the closest match, providing an identifier of its dominant typeface and point size. A machine could also store an input image in memory, obtain data indicating its dominant typeface, modify the stored data according to the dominant typeface, and provide an output image based on the modification. Profiles can be stored or transmitted, and a product can include a model profile together with code for operating a processor to obtain a profile for an image and code for operating the processor to compare the profile for the image with the model profile.

Image analysis to obtain typeface information

Characteristics of images such as skew of lines of text or dominant typeface of characters are detected by producing distance data. Distance data is produced for each of a number of starting pixels within an image. Each starting pixel meets a criterion, such as an edge pixel or a pixel inside a connected component. Each starting pixel's distance data indicates the distance in each of a number of directions from the starting pixel to another pixel at which the image meets another criterion. For example, to detect skew of lines of text, the distance data can indicate distance from a starting pixel at an edge across white pixels to another edge. To detect dominant typeface, the distance data can indicate distance from a starting pixel at an edge or inside a connected component across black pixels to another edge. The separating angle between adjacent directions can be small enough to detect features of an appropriate size at an appropriate distance, such as features of character size at the average intercharacter spacing. The distances at each direction from all the starting pixels can be averaged to obtain a combined distance at each direction. A sufficient number of starting pixels can be used so that the combined distance is approximately the same as if every pixel in the image were a starting pixel. The combined distances at all the directions form a profile.

Growing community of inventors

Ithaca, NY, United States of America

Peter C Wayner