| 摘要 |
In the prior art, in character recognition of a language having many characters, such as Japanese, a feature vector is extracted from an input pattern, distance between the feature vector and reference vectors are calculated, and a character corresponding to a reference vector having the smallest distance value is selected as a recognized character. However, in the character recognition of a language having many characters, since the number of the reference vectors to be compared is large, there is a limit in improvement of processing speed of the character recognition. In the present invention, reference vectors corresponding to target characters are classified into plurality of classes based on occurrence frequencies of characters (15). When distances between the feature vector and the reference vectors are calculated (14), a comparison is sequentially made from the reference vectors of a class having a high character occurrence frequency, so that the processing speed of the character recognition is improved (16).
|
