Method and apparatus for recognizing a character

An apparatus for recognizing a character written in a document comprising:

• character rectangle producing means for extracting a plurality of black-pixel masses, respectively composed of a plurality of black pixels connected with each other, from an image of the document indicated by a plurality of black pixels and a plurality of white pixels and producing a plurality of character rectangles respectively circumscribed about one black-pixel mass;
• character pattern classifying means for comparing character images of the black-pixel masses, about which the character rectangles produced by the character rectangle producing means are circumscribed, with each other, and classifying one or more black-pixel masses, of which the character images have the same character pattern, into a character group for each character pattern to classify the black-pixel masses extracted by the character rectangle producing means into the character patterns;
• representative character image determining means for determining one of the character images of the black-pixel masses classified into the same character pattern by the character pattern classifying means as a representative character image of a representative black-pixel mass having a representative character pattern for each of the character patterns;
• figure feature detecting means for detecting a figure feature of one representative character image of one representative black-pixel mass determined by the representative pattern determining means, for each of the representative character patterns;
• referential figure feature storing means for storing a plurality of referential figure features of a plurality of referential character patterns which each express a character;
• character recognizing means for comparing one figure feature of one representative character image detected by the figure feature detecting means with each of the referential figure features of the referential character patterns stored in the referential figure feature storing means for each of the figure features of the representative character images, recognizing the representative character image as a particular character expressed by a particular referential character pattern selected from the referential character patterns for each of the representative character images in cases where a particular referential figure feature of the particular referential character pattern agrees with the figure feature of the representative character image and recognizing each of the character images of the black-pixel masses classified into one character pattern, which corresponds to one representative character image recognized as one particular character, as the particular character for each of the character patterns;
• noise removing means for selecting a specific character rectangle from the character rectangles producing means on condition that a specific character image of a specific black-pixel mass, about which the specific character rectangle is circumscribed, is not recognized as any character by the character recognizing means, removing the specific character rectangle as a noise from the group of the character rectangles produced by the character rectangle producing means in cases where the specific character rectangle exists in a position placed in an upper or lower direction of one character rectangle which is circumscribed about one character image of one black-pixel mass recognized as one particular character by the character recognizing means;
• word rectangle detecting means for reading out the character rectangles produced by the character rectangle producing means in which the specific character rectangle removed by the noise removing means is not included, detecting a region between each pair of character rectangles adjacent to each other as an inter-word space in cases where a distance between the pair of character rectangles adjacent to each other is longer than a predetermined character distance, detecting a region between each pair of character rectangles adjacent to each other as an inter-character space in cases where a distance between the pair of character rectangles adjacent to each other is equal to or shorter than the predetermined character distance, and detecting one character rectangle placed between two inter-word spaces or a plurality of character rectangles which are serially arranged through one or more inter-character spaces and are placed between two inter-word spaces as a word rectangle;
• word storing means for storing a plurality of words;
• word and character confirming means for specifying a series of black-pixel masses about which the word rectangle detected by the word rectangle detecting means is circumscribed collating a series of characters, which is indicated by a series of character images of the series of black-pixel masses recognized by the character recognizing means, with a spelling of each word stored in the word storing means, and confirming the series of characters as a particular word having a particular spelling in cases where the series of characters matches with the particular spelling of the particular word, and confirming each of the characters as a confirmed character in cases where the characters are confirmed as the particular word, further comprising:
• character rectangle unifying means for selecting a first character rectangle and a second character rectangle from the group of the character rectangles produced by the character rectangle producing means, on condition that either a first character image of a first black-pixel mass about which the first character rectangle is circumscribed or a second character image of a second black-pixel mass about which the second character rectangle is circumscribed is not recognized as any character by the character recognizing means and the first and second character rectangles are placed in a rectangular character area, unifying the first and second character rectangles to a unified character rectangle circumscribed about the first and second black-pixel masses while maintaining positions of the first and second character rectangles composing the unified character rectangle, deleting the first and second character rectangles from the group of the character rectangles produced by the character rectangle producing means, and adding the unified character rectangle to the group of the character rectangles, a unified black-pixel mass, about which the unified character rectangle is circumscribed, being classified into a unified character pattern by the character pattern classifying means for each unified black-pixel mass, one of unified character images of the unified black-pixel masses classified into the same unified character pattern being determined by the representative character image determining means as a representative unified character image of a representative unified black-pixel mass, and the unified character images of the unified black-pixel masses being recognized as one particular character by the character recognizing means.