| Patent application number | Description | Published |
|---|
| 20080240582 | METHOD AND APPARATUS FOR CHARACTER STRING RECOGNITION - A method and an apparatus for character string recognition may be provided that enables prevention of a decrease in recognition accuracy for a character string even when distortion of an image appears in a direction perpendicular to a medium transfer direction. | 10-02-2008 |
| 20080285839 | METHOD AND APPARATUS FOR MAGNETIC CHARACTER RECOGNITION - A method for magnetic character recognition may include preparing standard array data of peak intervals; generating a regeneration waveform out of a character string of magnetic characters printed on a surface of an information data recording medium; segmenting a character waveform of each magnetic character out of the regeneration waveform; generating array data of peak intervals out of an array pattern of a plurality of intervals between peaks that are included in the character waveform; and comparing the array data of peak intervals with the standard array data of peak intervals; wherein, based on a comparison result of comparing the array data of peak intervals with the standard array data of peak intervals, a read character is identified with a character corresponding to an array data of peak intervals that shows the highest coincidence. | 11-20-2008 |
| 20080304746 | METHOD AND APPARATUS FOR CHARACTER STRING RECOGNITION - To provide a method and apparatus for character string recognition that enables improvement in accuracy of character recognition while maintaining high-speed operation performance in character recognition. | 12-11-2008 |
| 20090242643 | APPARATUS AND METHOD FOR SYMBOL INFORMATION READING - A symbol information reading apparatus may include an imaging element; an image memory structured to store image data; a position detecting processor structured to fetch the image data and structured to detect a position of symbol information. The position detecting processor may include a temporary area judgment unit that structured to calculate a variation of brightness, and structured to judge a temporary area having a possibility of corresponding to the symbol information; a correlation map creating unit that structured to calculate correlation between areas neighboring in a direction perpendicular to the scanning direction, and structured to create a map showing an area provided with large correlation values; a labeling unit that structured to check presence of a basic barcode on the correlation map, and structured to label an area judged as having the basic barcode; and a position determining unit that structured to detect a position of the symbol information recorded. | 10-01-2009 |
| 20090324106 | METHOD AND APPARATUS FOR MAGNETIC CHARACTER RECOGNITION - A method for magnetic character recognition may include: a peak detection process for detecting peak positions in a regeneration waveform; a character pitch measuring process for calculating an average character width and an average character period of each character according to a detection result of the peak detection process; a character segmentation process for calculating a peak interval array for each character according to the average character period; a peak searching process for searching for peak positions by using searching conditions, which are different from what the character segmentation process applies, on each waveform part segmented through the character segmentation process; a peak count evaluation process for choosing either a result of the character segmentation process or a result of the peak searching process, depending on whether the number of peaks in the waveform part agrees with a prescribed number of peaks; and a character determining process for a matching operation on a peak interval array, according to the peak interval array determined through the peak count evaluation process, to determine the character. | 12-31-2009 |
| 20100135578 | CHARACTER LINE RECOGNITION METHOD AND CHARACTER LINE RECOGNITION DEVICE - A character line recognition method for processing image data obtained by scanning a character line on a medium to recognize the character line may include processing the image data into monochrome binary format image data by using a predetermined binarization standard threshold; extracting character features from each character that composes the character line to calculate similarity with respect to standard character features; temporarily determining characters based on the similarity; calculating basic statistics of the similarity for all the characters which have been temporarily determined; and changing the binarization standard threshold based on the basic statistics and then returning to the processing the image data. | 06-03-2010 |
| 20110186637 | APPARATUS AND METHOD FOR READING SYMBOL INFORMATION - An apparatus and method for reading symbol information enabling improvement of decoding accuracy, not being affected by the condition of a reflection coefficient waveform of a reflected light beam and the kind of symbol information to be read. The method includes: reading a reflected light beam from symbol information irradiated with a light beam; detecting peak values in a reflection coefficient waveform of the reflected light beam; calculating a first peak value according to a peak value at a high reflection coefficient side (white level) among the peak values detected; calculating a second peak value according to a peak value at a low reflection coefficient side (black level) among the peak values detected; and calculating a binarization threshold based on the first peak value and the second peak value. | 08-04-2011 |
| 20110220721 | METHOD AND APPARATUS FOR READING BARCODE INFORMATION - Provided is a method and an apparatus for reading barcode information; the method and apparatus being able to read barcode information correctly without being influenced by the environmental conditions at the time of reading the barcode information. When a reading method according to a prescribed rule could not read a character, each element width is judged again to be either thin or thick according to structural characteristics of characters to convert again an element width matrix into a bit pattern, and then a character corresponding to the bit pattern as a result of the re-conversion is determined. | 09-15-2011 |
