International Business Machines Corporation

Ronen Shevach

Aviad Zlotnick

Sergey Krutyolkin

Eyal Yair

Eugene Wallach

Oren Kagan

A method for processing a plurality of input images containing variable content that is filled into respective, fixed templates. The method includes comparing the images to collect a group of the images having a high degree of similarity therebetween, and combining the images in the group so as to distinguish the variable content from a fixed portion common to a preponderant number of the images in the group. The fixed portion is processed to reconstruct the fixed template that is common to at least some of the images among the preponderant number, and information is extracted from the images using the reconstructed template.

Automatic template and field definition in form processing

A method for displaying data includes receiving an input image of alphanumeric characters appearing on first and second lines. The characters are concatenated into a single line so as to generate an output image in which the characters from the second line follow the characters from the first line substantially without interruption therebetween, while maintaining a visual distinction between the characters from the first line and the characters from the second line.

Displaying multi-line fields for key-in

A method for processing an input image includes applying one or more transformations to the input image, whereby different shifts are applied to different pixels in the input image, so as to generate an output image. A region containing content of interest is selected in the output image, and the region corresponding to the selected region in the output image is located in the input image. The content of the located region in the input image is substituted for the content of the selected region in the output image.

Correction of distortions in form processing

This invention discloses a key-in method including a manual keying in phase, and an automatic accuracy enhancement phase, wherein at least one of the manual phase, the automatic phase and the interaction therebetween is dependent, at least one dataflow point, on data generated previous to said dataflow point.

Interactive verification of OCRed characters

Apparatus and a method is described for correcting a set of stored digital representations of numbers having an estimable error probability distribution where there is at least one known arithmetic relation between the numbers which can be expressed as a sum, difference or equality. The invention finds particular, but not exclusive, application to the correction of optical character recognition (OCR) results. Hidden Markov Model optimization logic is employed for finding the most likely path through a set of states in accordance with probability functions recording the likelihood of transitions between the states giving rise to a set of event-related observations. The system is arranged so that the states are possible accumulated totals generated by adding or subtracting ones of the numbers to or from an initial accumulated total, addition or subtraction of the numbers to or from an accumulated total or equality of an accumulated total with the numbers are the events causing transitions from state to state, the digital representations are the event-related observations, and the error probability distributions are the probability functions, the apparatus comprising means to correct the digital representations in accordance with events giving rise to the most likely path through the states.

Growing community of inventors

Netanya, Israel

Ronen Shevach