Word string collating apparatus, word string collating method and address recognition apparatus
First Claim
1. An address recognition apparatus for recognizing an address written on a sheet of paper, comprising:
- input means for receiving an image of the written address and transforming the image into computer-processable digital data;
character recognizing means for recognizing a word string in the digital data on a unit character basis;
word extracting means for extracting characters recognized by the character recognizing means on a unit word basis;
an address word string dictionary for storing a plurality of first word strings each constructing an address in which a word arrangement order is determined; and
address word string recognizing means having executable instructions for;
(a) collating a second word string including a plurality of words extracted by said word extracting means and the first various word strings in said address word string dictionary,(b) determining words of the second word string respectively corresponding to the words of the first word string based on similarities between the words of the first word string and the words of the second word string,(c) evaluating each of the first word strings based on the number of words between the words of the second word string thus determined and the similarities between the words of the first word string and the words of the second word string determined,(d) recognizing one of the first word strings as the address word string; and
(e) outputting the recognized first word string as the address word string representing the written address.
1 Assignment
0 Petitions
Accused Products
Abstract
The present invention is directed to an address recognition apparatus for recognizing a written address. The apparatus includes an input device that receives a scanned image of the written address and transforms the image into digital data, a character recognizing section that recognizes a word string in the digital data on a unit character basis, a word extracting section that extracts characters recognized by the character recognizing section on a unit word basis, and an address word string dictionary that previously stores a plurality of first word strings. The apparatus further includes and an address word string recognizing section that collates a second word string, determines words of the second word string respectively corresponding to the words of the first word string, evaluates each of the first word strings, and recognizes one of the first word strings as the address word string.
23 Citations
2 Claims
-
1. An address recognition apparatus for recognizing an address written on a sheet of paper, comprising:
-
input means for receiving an image of the written address and transforming the image into computer-processable digital data; character recognizing means for recognizing a word string in the digital data on a unit character basis; word extracting means for extracting characters recognized by the character recognizing means on a unit word basis; an address word string dictionary for storing a plurality of first word strings each constructing an address in which a word arrangement order is determined; and address word string recognizing means having executable instructions for; (a) collating a second word string including a plurality of words extracted by said word extracting means and the first various word strings in said address word string dictionary, (b) determining words of the second word string respectively corresponding to the words of the first word string based on similarities between the words of the first word string and the words of the second word string, (c) evaluating each of the first word strings based on the number of words between the words of the second word string thus determined and the similarities between the words of the first word string and the words of the second word string determined, (d) recognizing one of the first word strings as the address word string; and (e) outputting the recognized first word string as the address word string representing the written address.
-
-
2. An address recognition apparatus for recognizing an address written on a sheet of paper, comprising:
-
an input device configured to receive a scanned image of the written address and transforming the image into computer-processable digital data; a character recognizing section configured to recognize a word string in the digital data on a unit character basis; a word extracting section configured to extract characters recognized by the character recognizing section on a unit word basis; an address word string dictionary configured to previously store a plurality of first word strings each constructing an address in which a word arrangement order is determined; and an address word string recognizing section configured with executable instructions to; (a) collate a second word string including a plurality of words extracted by the word extracting section and the first various word strings in the address word string dictionary, (b) determine words of the second word string respectively corresponding to the words of the first word string based on the word arrangement order and similarities between the words of the first word string and the words of the second word string, (c) evaluate each of the first word strings based on the number of words between the respective words in the second word string thus determined and the similarities between the words of the first word string and the words of the second word string determined, (d) recognize one of the first word strings as the address word string, and (e) output the recognized first word string as the address word string representing the written address.
-
Specification