JPH04111186A - Character recognition result correction method for address character string - Google Patents

Character recognition result correction method for address character string

Info

Publication number
JPH04111186A
JPH04111186A JP23092790A JP23092790A JPH04111186A JP H04111186 A JPH04111186 A JP H04111186A JP 23092790 A JP23092790 A JP 23092790A JP 23092790 A JP23092790 A JP 23092790A JP H04111186 A JPH04111186 A JP H04111186A
Authority
JP
Grant status
Application
Patent type
Prior art keywords
place name
character
name word
word
address
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
JP23092790A
Inventor
Hideyuki Isoyama
Original Assignee
N T T Data Tsushin Kk
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date

Links

Abstract

PURPOSE: To shorten correction processing time and to improve processing accuracy by selecting the place name of a candidate while utilizing a place name word table and an index table expressing the hierarchical relation of the place name word and the character composing of an address character string, further estimating the distance of candidate place name words.
CONSTITUTION: A place name word table and the index table indicating the character composing of the place name word, and provided to express the hierarchical relation. From the recognition result of each character of the address character string, for example, a ten pairs of an address character string candidates are obtained. The above-mentioned index table is referred to, and a character coincident for each column is retrieved. The record number group of the place name word where the coincident character exists is determined to sort this record number group, and the record number with high appearance frequency is selected. Next, the place name word which can correctly connected to the place name word of high-order hierarchy is selected. The place name word with the highest similarity is decided against the elected place name by the estimation value calculated based on the distance value for each character.
COPYRIGHT: (C)1992,JPO&Japio
JP23092790A 1990-08-31 1990-08-31 Character recognition result correction method for address character string Pending JPH04111186A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP23092790A JPH04111186A (en) 1990-08-31 1990-08-31 Character recognition result correction method for address character string

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP23092790A JPH04111186A (en) 1990-08-31 1990-08-31 Character recognition result correction method for address character string

Publications (1)

Publication Number Publication Date
JPH04111186A true true JPH04111186A (en) 1992-04-13

Family

ID=16915466

Family Applications (1)

Application Number Title Priority Date Filing Date
JP23092790A Pending JPH04111186A (en) 1990-08-31 1990-08-31 Character recognition result correction method for address character string

Country Status (1)

Country Link
JP (1) JPH04111186A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08167007A (en) * 1994-12-14 1996-06-25 Nec Corp Symbol string reader
US5754671A (en) * 1995-04-12 1998-05-19 Lockheed Martin Corporation Method for improving cursive address recognition in mail pieces using adaptive data base management

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08167007A (en) * 1994-12-14 1996-06-25 Nec Corp Symbol string reader
US5754671A (en) * 1995-04-12 1998-05-19 Lockheed Martin Corporation Method for improving cursive address recognition in mail pieces using adaptive data base management

Similar Documents

Publication Publication Date Title
US5890103A (en) Method and apparatus for improved tokenization of natural language text
US5960430A (en) Generating rules for matching new customer records to existing customer records in a large database
US5982929A (en) Pattern recognition method and system
US5774588A (en) Method and system for comparing strings with entries of a lexicon
Knight et al. Translation with finite-state devices
US5195034A (en) Method for quasi-key search within a National Language Support (NLS) data processing system
US6581034B1 (en) Phonetic distance calculation method for similarity comparison between phonetic transcriptions of foreign words
US6308149B1 (en) Grouping words with equivalent substrings by automatic clustering based on suffix relationships
US4641264A (en) Method for automatic translation between natural languages
Fung et al. A technical word-and term-translation aid using noisy parallel corpora across language groups
US5754847A (en) Word/number and number/word mapping
US5640488A (en) System and method for constructing clustered dictionary for speech and text recognition
US20050120017A1 (en) Efficient retrieval of variable-length character string data
US7139712B1 (en) Speech synthesis apparatus, control method therefor and computer-readable memory
Ekbal et al. Language independent named entity recognition in Indian languages
US5384702A (en) Method for self-correction of grammar in machine translation
US6587819B1 (en) Chinese character conversion apparatus using syntax information
US6738741B2 (en) Segmentation technique increasing the active vocabulary of speech recognizers
JPS6175957A (en) Mechanical translation processor
EP0271664A2 (en) A morphological/phonetic method for ranking word similarities
Nagata A part of speech estimation method for Japanese unknown words using a statistical model of morphology and context
US5742706A (en) Method and apparatus for comparison of data strings
JPS5839377A (en) Character recognizing device
JPS5858647A (en) Index generating processor
US20050015237A1 (en) Process, computerized device and computer program for assisting the vowelization of Arabic language words