International Business Machines Corporation

Yaakov Navon

Eugene Walach

Dan S Chevion

Andrei Heilper

Alexander Nisenboim

Asaf Tzadok

Ehud Dov Karnin

Eugeniusz Walach

Ella Barkan

Martin Tross

Israel Berger

Eugene Wallach

Eyal Yair

Ari Shotland

Dan Chevion

Method, system, and computer program product for tracing seismic sections to convert to digital format are provided. The method includes: receiving a scan of a seismic section having multiple overlapping traces measured at spot points; splitting the traces into segments; associating the segments with appropriate baselines; estimating the traces between segments using logical rules; and deriving amplitudes of the traces.

Tracing seismic sections to convert to digital format

A computer-implemented method for form generation includes capturing an image of a hard-copy form, and automatically processing the image to identify form fields in the image and text characters associated with each of the form fields. Geometrical coordinates of the form fields that define respective filling areas for entry of information into the fields are determined. Optical character recognition (OCR) is applied to the text characters in order to identify form field names. Associations are determined between the form field names and object names of corresponding data objects. The geometrical coordinates of the filling areas of the form fields are combined with the object names of the data objects corresponding to the form fields to generate a form definition.

Automated generation of form definitions from hard-copy forms

A method for segmentation of characters in text that segments text into lines, words and slices and determines at least one of fixed pitch and proportional pitch prior to segmentation. The method computes histograms of the lines and defines widths of lobes of the histograms of the lines as the character pitches. In addition, the method further analyzes the character pitches; segments lines into words; computes histograms of the words and aggregating the histograms of the words at predetermined points. Moreover, the method segments the words; slicing them words into an upper slice and lower slice and further segments the upper slice and the lower slice. The results are then combined to provide for both coarse and fine segmentation that enhance the performance of character OCR for documents scanned as at least one of gray-scale images and color images.

Character segmentation by slices

A method for computerized processing of paper forms includes receiving an electronic image of a paper form containing text information from a client having a telephone. The text information is extracted from the form using an optical character recognition (OCR) process. A field of the extracted text information that is suspected of containing an error is identified, and a first text message is automatically communicated to the telephone asking the client to verify the identified field. A second text message is received in response to the first text message, and the text information in the field is validated or corrected according to the response.

Data verification using text messaging

A method for image separation of an image, wherein the image includes pixels, and the method includes identifying kernels, whereby characteristics of the kernels are reflected by at least one of the following operators, P(x&#x2212;w,y)&#x2212;P(x,y)&#x3e;t AND P(x+w, y)&#x2212;P(x,y)&#x3e;t; or P(x, y&#x2212;w)&#x2212;P(x,y)&#x3e;t AND P(x, y+w)&#x2212;P(x,y)&#x3e;t; or P(x+d, y+d)&#x2212;P(x,y)&#x3e;t AND P(x&#x2212;d, y&#x2212;d)&#x2212;P(x,y)&#x3e;t; or P(x&#x2212;d, y+d)&#x2212;P(x,y)&#x3e;t AND P(x+d, y&#x2212;d)&#x2212;P(x,y)&#x3e;t, wherein the kernels include at least some of a first group of the pixels. The kernels are associated with a first layer, and pixels that are not associated with the first layer are classified as a second layer. The first layer may be text or graphics and the second layer may be a background. The first layer may be compressed with a high resolution compression technique and the second layer may be compressed with a high lossy compression technique.

Layer based compression of digital images

A method for locating symbols arranged in one or more rows in an image includes smearing the image, and fitting line segments through edge points of features in the smeared image. A group is found of the line segments that are in mutual proximity and are mutually substantially parallel. A region of the image that contains the group of the line segments is identified as a possible location of the symbols.

Segmentation of text lines in digitized images

A method for locating a barcode in an image includes dividing the image into a plurality of tiles, and scanning each of the tiles so as to detect a pattern of stripes associated with the barcode in at least one of the tiles. The pattern of stripes is analyzed so as to determine an angle of orientation of the barcode. Responsive to the determined angle, bounds of the barcode are defined in alignment with the pattern of the stripes.

Fast barcode search

A method for deskewing text is disclosed, in which a noisy digitized gray scale image is preprocessed by binarization, noise removal, and then by smearing in three patterns. A selected smeared image having minimal runs is sampled, and the resulting sampled image subjected to the Hough process using a search technique at two angular resolutions. A dominant text line is chosen from the output of the Hough process, and the image deskewed accordingly. The method is suitable for detecting skew at any angle, and is capable of detecting multiple skew text lines.

Skew detection of text in a noisy digitized image

A method for finding a predefined object in an image includes selecting a line belonging to the object, the line having a known stroke width and defining a maximum width and a minimum width that together define a range of widths therebetween that contains the stroke width. A feature in the image is found having a feature width within the range, and the feature is processed to determine whether it is a part of the object.

Finding objects in an image

A method of binarization used in an OCR system involves in determining text pixels by checking, for each pixel, that the difference between its value and the values of a plurality of pixels located at a predetermined distance therefrom is greater than a relative threshold corresponding to the difference in intensities between the text and the background of the image, subsampling the image at a rate corresponding to at least two pixels in order to detect kernels of text, and then binarizing the image pixels only in tiles of several stroke width sides containing text kernels by using in each tile, an absolute threshold estimated in that tile. The determining of text pixels includes, for each analyzed pixel, checking that either one of the differences between the value of the analyzed pixel and the value of the two pixels located at each intersection of a circle with each one of the row line, column line and both lines at the angle of 45 degrees, is greater than the relative threshold where that circle is centered at the location of the analyzed pixel and has a radius equal to the stroke width.

Method of binarization in an optical character recognition system

A method for automatic sorting includes receiving an item in a sequence of items to be sorted, each such item marked with a respective machine-readable identifying code and with respective characters in a location relative to the code that varies from one item to another in the sequence. A position of the code on the item is determined and, responsive to the position of the code, the location of the characters on the item is found. The characters are processed to determine a destination of the item.

Growing community of inventors

Ein Vered, Israel

Yaakov Navon