A method of performing character isolation in an optical character recognition process, the method comprising receiving image data representing one or more character columns, determining a number of black pixels in each column of the image data, defining a vertical separation threshold which is a maximum number of black pixels in a column, dividing the columns into different pixel groups and groups of excluded columns by excluding any columns with a number of black pixels below the vertical separation threshold, identifying the pixel group representing the left most character column in the image data, determining whether there are one or two pixel groups representing character columns in the image data and, if it is determined that there are two pixel groups representing character columns, using a predetermined width value for a right most character column in order to identify a right hand boundary of the right most character column.

A local connectivity feature transform (LCFT) is applied to binary document images containing text characters, to generate transformed document images which are then input into a bi-directional Long Short Term Memory (LSTM) neural network to perform character/word recognition. The LCFT transformed image is a gray scale image where the pixel values encode local pixel connectivity information of corresponding pixels in the original binary image. The transform is one that provides a unique transform score for every possible shape represented as a 33 block. In one example, the transform is computed using a 33 weight matrix that combines bit coding with a zigzag pattern to assign weights to each element of the 33 block, and by summing up the weights for the non-zero elements of the 33 block shape.

Complete removal of an underline which intersects a character may cause problems in a subsequent character recognition or conversion process, when parts of the character which coincided with the underline are also removed. To help reduce the problems, parts of underline may be removed from an image while parts of the character that coincide with the underline are maintained in the image. Areas where the character coincides with the underline are defined from a reduced version of the underline. When the underline is removed, the areas where the character coincide with the underline are maintained in a second image. The second image may then be subjected to a character recognition or conversion process with potentially fewer problems.

Disclosed are a method and apparatus for storing and/or digitizing documents that preserves the confidentiality of the documents. The technology includes a process, referred to herein as shredding, that extracts portions of a digitized document, such as a scanned document or an image file, to create shreds. A shred can be, for example, a field of a form, a portion of a photo, etc. In some embodiments where the source document includes confidential information, each individual shred does not include the confidential information and, with information of only one shred, a person cannot obtain the confidential information. As a result, while the source document needs to be stored in a secure fashion to prevent disclosure of the confidential information, the shreds can be stored in a non-secure fashion without risking disclosure of the confidential information.

An NC-program conversion device includes an OCR processing unit that recognizes a character string from an input image; a first storage unit that stores one alphabetic letter and the number of digits of a number subsequent to the alphabetic letter, in an associated manner; a second storage unit that stores a program code that is composed of a combination of one alphabetic letter and a two-character number and an effective character that is composed of one alphabetic letter subsequent to the program code, in an associated manner; and a character-string segmenting unit that refers to the first storage unit and the second storage unit, to segment each line of the character string, which is recognized by the OCR processing unit, as program codes stored in the first storage unit in an associated manner.

A method for character recognition. The method includes: obtaining a plurality of character segments extracted from an image; determining a first character bounding box including a first set of the plurality of character segments and a second character bounding box including a second set of the plurality of character segments; determining an ordering for the first set based on a plurality of texture properties for the first set; determining a plurality of directions of the first set based on a plurality of brush widths and a plurality of intensities for the first set; and executing character recognition for the first character bounding box by sending the first set, the plurality of directions for the first set, and the ordering for the first set to an intelligent character recognition (ICR) engine.

Systems and methods for extracting and digitizing information from a sheet of material to facilitate organization of information are provided. An example system includes a sheet of material such as that from a planner, notebook, a stack of repositionable notes, or another similar writing surface, and a device for scanning the sheet with an optical sensor. The sheet of material includes markings thereupon and computer readable indicators. The device includes a processor operably coupled to the optical sensor for causing the optical sensor to scan the sheet, send the scan to a server computer, and receive scanned text from the server computer. Upon receiving the scanned text, a ruleset may be applied to format the text and the formatted information is presented on a display of the device.

This image processing apparatus performs image processing on image data, and includes an edit-region identifying section identifying a user-specified region in the image data as an edit region, a character-position identifying section identifying the positions of individual characters in the image data, a character-region generating section generating a character region for each of the characters whose positions have been identified by the character-position identifying section, an edit-character-string identifying section identifying an edit character string based on candidate characters identified by determining the degree of overlay between the edit region and character region, and an image processing unit performing image processing on the edit character string identified by the edit-character-string identifying section.

Using a convolutional neural network, a method for digitizing and extracting meaning from graphic objects such as bar and pie charts, decomposes a chart into its sub-parts (pie and slices or bars, axes and legends) with significant tolerance to the wide range of variations in shape and relative position of pies, bars, axes and legends. A linear regression calibration allows properly reading values even when there are many OCR failures.

A method of performing character isolation in an optical character recognition process, the method comprising receiving image data representing one or more character columns, determining a number of black pixels in each column of the image data, defining a vertical separation threshold which is a maximum number of black pixels in a column, dividing the columns into different pixel groups and groups of excluded columns by excluding any columns with a number of black pixels below the vertical separation threshold, identifying the pixel group representing the left most character column in the image data, determining whether there are one or two pixel groups representing character columns in the image data and, if it is determined that there are two pixel groups representing character columns, using a predetermined width value for a right most character column in order to identify a right hand boundary of the right most character column.