JPH0739820A - Street zone recognizing device and address reading and classifying machine - Google Patents

Street zone recognizing device and address reading and classifying machine

Info

Publication number
JPH0739820A
JPH0739820A JP5187973A JP18797393A JPH0739820A JP H0739820 A JPH0739820 A JP H0739820A JP 5187973 A JP5187973 A JP 5187973A JP 18797393 A JP18797393 A JP 18797393A JP H0739820 A JPH0739820 A JP H0739820A
Authority
JP
Japan
Prior art keywords
character
block
address
recognizing
reading
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
JP5187973A
Other languages
Japanese (ja)
Inventor
Koreyoshi Takanashi
是是 高梨
Kazuo Kudo
和男 工藤
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Toshiba Corp
Toshiba Software Engineering Corp
Original Assignee
Toshiba Corp
Toshiba Software Engineering Corp
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
Application filed by Toshiba Corp, Toshiba Software Engineering Corp filed Critical Toshiba Corp
Priority to JP5187973A priority Critical patent/JPH0739820A/en
Publication of JPH0739820A publication Critical patent/JPH0739820A/en
Pending legal-status Critical Current

Links

Abstract

PURPOSE:To lessen the erroneous recognition of street zone parts and to improve the efficiency of classification processing by collating the recognized characters supplied from a character recognizing means with a street zone dictionary and constituting this device by recognizing the street zones when the kinds of the characters of respective hierarchies coincide. CONSTITUTION:Postal matter P to be transported by each one piece is scanned thereon by a photoelectric conversion section 4a of a reading section 4, where pattern signals are obtd. by executing photoelectric conversion. These pattern signals are outputted to an address region detecting section 42 and a character recognizing section 43. A street name recognizing section 44 stores the respective character discriminating candidate matrices from the character recognizing section 43 into an internal memory and determines the scores by the characters of the respective hierarchies of an address dictionary 45 for combinations of the respective characters by the stored character discriminating candidate matrices and outputs the candidate characters of the highest score as the results of the town name recognition to a Chome and street zone recognizing section 46 and an address recognizing section 48. This address recognizing section 48 outputs the classification assigning data for the addresses and controls a classifying gate, thereby collecting the postal matter P into the pockets corresponding to this address information.

Description

【発明の詳細な説明】Detailed Description of the Invention

【0001】[0001]

【産業上の利用分野】この発明は、搬送される郵便物か
らその上に記載されている住所等の宛名を読取り、この
読取った宛名内の街区を認識する街区認識装置と、この
街区認識装置で認識した街区を用いて区分を行う宛名読
取区分機に関する。
BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention reads a mailing address such as an address written on a mail to be conveyed, and recognizes a block in the read address, and a block recognition device. The present invention relates to an address reading / sorting machine that performs sorting using the blocks recognized in.

【0002】[0002]

【従来の技術】郵便区分業務を大別すると、取集めた郵
便物を相手先の郵便局に送るための区分作業である差立
区分業務と、到着した郵便物を配達するための区分業務
である配達区分業務がある。
2. Description of the Related Art The mail sorting work is roughly divided into a sorting work for sending collected mail to a destination post office and a sorting work for delivering arrived mail. There is a delivery division business.

【0003】従来、差立区分業務については、郵便番号
自動読取区分機により大幅に自動化が図られてきたが、
配達区分業務については自動化が遅れていた。ところが
近年、郵便番号自動読取区分機の機能に加え、郵便物に
記載された町名、丁目、街区符号の漢字などの宛名つま
り住所を直接OCRで読取ることによって、郵便物を配
達区レベルまでの区分を自動化(配達区分業務の自動
化)するものが開発されている。
Conventionally, as for the sorting work, the postal code automatic reading and sorting machine has been largely automated.
Automation was delayed for delivery division work. However, in recent years, in addition to the function of the automatic zip code reading / sorting machine, the postal items can be sorted up to the delivery district level by directly reading the address, that is, the address such as the town name, chome, or the kanji of the block code written on the postal item by OCR. Have been developed (automatic delivery classification work).

【0004】このような装置では、街区部数字もしくは
デミリタの認識方法は、文字検切り結果に応じて文字識
別部より、記載方向や階層ごとの数字の種類に関係なく
認識されていた。
In such a device, the method of recognizing the block district number or demilita is recognized by the character identifying unit according to the result of character inspection regardless of the writing direction or the type of number for each layer.

【0005】郵便物の記載方向や階層ごとの数字種に関
係なく、文字識別部により文字認識していたため、組み
合わせに矛盾があったり、極めて可能性の低い組み合わ
せでも誤った数字やデミリタと判断してしまって誤認識
することがあった。
Characters are recognized by the character identification section regardless of the direction of writing of mail and the number type of each layer. Therefore, there is a contradiction in the combination, and it is determined that the combination is erroneous even if the combination is extremely unlikely. There was a case that it was mistakenly recognized.

【0006】[0006]

【発明が解決しようとする課題】この発明は、上記した
ように、組み合わせに矛盾があったり、極めて可能性の
低い組み合わせでも誤った数字やデミリタと判断してし
まって誤認識することがあり、街区部の誤認識が発生
し、宛名の読取率が悪く、またその類似する宛名から区
分処理を行うことができず、区分処理の効率が悪いとい
う欠点を除去するもので、街区部の誤認識の減少が図
れ、宛名の読取率の向上が図れ、かつ区分処理の効率向
上が図れる街区認識装置および宛名読取区分機を提供す
ることを目的とする。
As described above, the present invention may have a contradiction in a combination, or even a combination with an extremely low possibility may be erroneously recognized as an incorrect number or demilita. Erroneous recognition of the city block is performed because it eliminates the disadvantage that the efficiency of the classification process is poor because the recognition rate of the city block is incorrect, the address reading rate is poor, and the classification process cannot be performed from similar addresses. It is an object of the present invention to provide a block recognizing device and an address reading / sorting device that can reduce the number of addresses, improve the address reading rate, and improve the efficiency of classification processing.

【0007】[0007]

【課題を解決するための手段】この発明の街区認識装置
は、郵便物に記載されている文字の読取りを行う読取手
段、この読取手段による読取内容に応じて文字認識する
文字認識手段、およびこの文字認識手段から供給される
認識文字に対して街区辞書と照合し、各階層の数字の種
類が一致する場合に、街区を認識する街区認識手段から
構成されている。
A block recognition device of the present invention is a reading means for reading characters written on a mail piece, a character recognition means for recognizing characters according to the contents read by the reading means, and The block recognition means is configured to match the recognized character supplied from the character recognition means with a block dictionary and recognize the block when the types of the numbers in each layer match.

【0008】この発明の街区認識装置は、郵便物に記載
されている文字の読取りを行う読取手段、この読取手段
による読取内容に応じて文字認識する文字認識手段、お
よびこの文字認識手段から供給される認識文字に対して
街区辞書と照合し、街区を区切る複数のデリミタに矛盾
がない場合に、街区を認識する街区認識手段から構成さ
れている。
The block recognition device of the present invention is supplied from the reading means for reading the characters written in the mail, the character recognizing means for recognizing the characters according to the contents read by the reading means, and the character recognizing means. It comprises a block recognition means for matching a recognition character with a block dictionary and recognizing a block when there is no contradiction in a plurality of delimiters separating the block.

【0009】この発明の宛名読取区分機は、搬送される
郵便物からその上に記載されている宛名を読取り、この
読取った宛名を用いて区分を行うものにおいて、郵便物
に記載されている文字の読取りを行う読取手段、この読
取手段による読取内容に応じて文字認識する文字認識手
段、この文字認識手段から供給される認識文字に対して
街区辞書と照合し、各階層の数字の種類が一致する場合
に、街区を認識する街区認識手段、およびこの街区認識
手段の認識結果に応じて区分を行う区分手段から構成さ
れている。
In the address reading / sorting machine of the present invention, the letters written on the mail are read in the case where the address written on the mail is read from the conveyed mail and the read address is used for sorting. Reading means for reading, character recognition means for recognizing characters according to the contents read by the reading means, and the recognized characters supplied from this character recognition means are collated with the city block dictionary to match the types of numbers in each layer. In the case of doing, it comprises a block recognizing means for recognizing the block, and a partitioning means for partitioning according to the recognition result of this block recognizing means.

【0010】この発明の宛名読取区分機は、搬送される
郵便物からその上に記載されている宛名を読取り、この
読取った宛名を用いて区分を行うものにおいて、郵便物
に記載されている文字の読取りを行う読取手段、この読
取手段による読取内容に応じて文字認識する文字認識手
段、この文字認識手段から供給される認識文字に対して
街区辞書と照合し、街区を区切る複数のデリミタに矛盾
がない場合に、街区を認識する街区認識手段、およびこ
の街区認識手段の認識結果に応じて区分を行う区分手段
から構成されている。
In the address reading / sorting machine of the present invention, the letters written on the mail are read in the case where the address written on the mail is read from the mail to be conveyed and the read address is used for sorting. Reading means for reading, a character recognizing means for recognizing characters according to the contents read by the reading means, and a recognition character supplied from the character recognizing means is collated with a city block dictionary and conflicts with a plurality of delimiters delimiting the city blocks. If there is no block, the block is configured to include a block recognizing unit that recognizes the block, and a partitioning unit that classifies the block according to the recognition result of the block recognizing unit.

【0011】[0011]

【作用】この発明は、上記のような構成において、郵便
物に記載されている文字の読取りを行い、この読取内容
に応じて文字認識し、この認識文字に対して街区辞書と
照合し、各階層の数字の種類が一致する場合に、街区を
認識するようにしたものである。
According to the present invention, in the above-mentioned structure, the characters written on the mail are read, the characters are recognized according to the read contents, and the recognized characters are collated with the city block dictionary. The block is recognized when the types of numbers in the layers match.

【0012】この発明は、上記のような構成において、
郵便物に記載されている文字の読取りを行い、この読取
内容に応じて文字認識し、この認識文字に対して街区辞
書と照合し、街区を区切る複数のデリミタに矛盾がない
場合に、街区を認識するようにしたものである。
According to the present invention, in the above structure,
The characters written on the mail are read, the characters are recognized according to the read contents, the recognized characters are compared with the block dictionary, and if there is no contradiction between the delimiters that separate the blocks, It is something that we recognize.

【0013】[0013]

【実施例】以下、この発明の一実施例について図面を参
照して説明する。図2はこの発明の街区認識装置を有す
るび宛名読取区分機としての郵便物自動区分機を示し、
次のような構成となっている。すなわち、供給部1には
一括かつ立位状態で葉書、封書などの郵便物P…がセッ
トされる。この供給部1の郵便物P…は、取出部2によ
り最前端の郵便物Pから順次1枚づつ取出し搬送され取
込搬送路3の途中に配置された読取部4によって郵便物
Pに付与された郵便番号、住所情報(宛名情報)が読取
られる。上記読取部4は郵便物P上の郵便番号、住所情
報を光電変換する光電変換部4a、この光電変換部4a
の出力に応じて文字パタ―ンの認識を行うことにより郵
便番号、住所情報を判別する判別部4bとからなる周知
のものである。
DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below with reference to the drawings. FIG. 2 shows an automatic mail sorting machine having a block recognition device of the present invention and as an address reading sorting machine,
It has the following structure. That is, the postal items P, such as postcards and sealed letters, are set in the supply unit 1 collectively and in a standing position. The postal matter P in the supply unit 1 is sequentially taken out and conveyed one by one from the frontmost postal matter P by the take-out unit 2 and given to the postal matter P by the reading unit 4 arranged in the middle of the take-in conveyance path 3. The postal code and address information (address information) are read. The reading unit 4 is a photoelectric conversion unit 4a for photoelectrically converting the zip code and address information on the postal matter P, and this photoelectric conversion unit 4a.
Is a well-known device including a discrimination unit 4b that discriminates a zip code and address information by recognizing a character pattern in accordance with the output of.

【0014】つぎに、読取部4を通過した郵便物Pは搬
送路3を介して区分部11に搬送されるようになってい
る。この区分部11は、図示しないゲ―ト機構部によっ
て鉛直方向に複数段設けられた区分搬送路5a、〜5g
に上記郵便番号、住所情報の読取結果等に基づいて選択
的に振分けられるようになっている。
Next, the postal matter P which has passed through the reading section 4 is conveyed to the sorting section 11 through the conveying path 3. The sorting section 11 is provided with a plurality of sorting transport paths 5a to 5g vertically provided by a gate mechanism section (not shown).
In addition, it can be selectively distributed based on the above-mentioned postal code, the reading result of the address information, and the like.

【0015】上記区分搬送路5a、〜5fの下方にはそ
の下面側に沿ってそれぞれ複数のポケット(集積箱)6
…が複数段(A段、〜G段)に配設されており、区分搬
送路5a、〜5gに送り込まれた郵便物Pは上記読取部
4の読取結果に基づいて所定のポケット6内に区分集積
されるようになっている。
A plurality of pockets (collection boxes) 6 are provided below the sectioned conveying paths 5a to 5f along the lower surface thereof.
.. are arranged in a plurality of stages (stages A to G), and the postal matter P sent to the sorting conveyance paths 5a to 5g is stored in a predetermined pocket 6 based on the reading result of the reading unit 4. It is designed to be collected separately.

【0016】なお、上記搬送路3、5a、…上には、そ
の搬送路上の郵便物Pの搬送を検知する搬送検知器群
(図示しない)が設けられている。上記郵便物Pの表面
には住所情報等が記載されている。上記住所情報は、そ
れぞれ複数行の文字情報によって構成されている。この
ような郵便物Pにおいて、住所情報として読取るべき
「区、市名」、「町名」、「番地」などの宛名(たとえ
ば図3に示すように、「松戸市松戸四−一」という地名
が記載されている。
A conveyance detector group (not shown) for detecting the conveyance of the postal matter P on the conveyance path is provided on the conveyance paths 3, 5a, .... Address information and the like are written on the surface of the mail P. The address information is composed of a plurality of lines of character information. In such a postal matter P, addresses such as “ward, city name”, “town name”, and “house number” that should be read as address information (for example, as shown in FIG. Have been described.

【0017】また、上記供給部1の上部には操作パネル
としてのオペレ―タパネル7が設けられている。図4は
電気回路を示すものである。すなわち、制御部31はメ
モリ32に記憶されている区分指定テ―ブルを用いて、
上記判別部4bから供給される住所情報に対応する区分
指定デ―タを読出し、この読出した区分指定デ―タ(ポ
ケット6、…のアドレス)に対応するポケット6、…に
上記郵便物Pを搬送せしめるものである。たとえば、搬
送路3の途中の搬送検知器(図示しない)からの搬送検
知信号に応じて区分ゲ―ト制御信号を出力することによ
り、ドライバ33を用いて区分ゲ―ト9、…を制御せし
めるようになっている。上記メモリ32には、区分指定
テ―ブルとして各郵便番号、各住所情報に対応するポケ
ット6、…のアドレス(区分指定デ―タ)が記憶されて
いる。
An operator panel 7 as an operation panel is provided above the supply unit 1. FIG. 4 shows an electric circuit. That is, the control unit 31 uses the classification designation table stored in the memory 32,
The sorting designation data corresponding to the address information supplied from the discrimination unit 4b is read out, and the mail P is placed in the pockets 6, ... Corresponding to the read sorting designation data (addresses of pockets 6, ...). It can be transported. For example, by outputting a sorting gate control signal in response to a transportation detection signal from a transportation detector (not shown) in the middle of the transportation path 3, the driver 33 is used to control the sorting gates 9. It is like this. The memory 32 stores addresses (classification designation data) of each postal code, pockets 6 corresponding to address information as classification designation tables.

【0018】さらに、上記制御部31はドライバ35に
より上記搬送路3等の搬送機構部36を駆動することに
より、搬送系全体の制御を行うようになっている。次
に、読取部4の光電変換部4aと判別部4bについて、
図1を用いて説明する。
Further, the control unit 31 controls the entire transport system by driving the transport mechanism unit 36 such as the transport path 3 with the driver 35. Next, regarding the photoelectric conversion unit 4a and the determination unit 4b of the reading unit 4,
This will be described with reference to FIG.

【0019】すなわち、光電変換部4aは、郵便物P上
を光学的に走査して光電変換することによりパタ―ン信
号を得るものであり、たとえば郵便物P上に光を照射す
る光源、およびその反射光を受けて電気信号に変換する
自己走査形のCCDイメ―ジセンサ等によって構成され
る。
That is, the photoelectric conversion unit 4a obtains a pattern signal by optically scanning the postal matter P and photoelectrically converting it. For example, a light source for irradiating the postal matter P with light, and It is composed of a self-scanning CCD image sensor which receives the reflected light and converts it into an electric signal.

【0020】上記光電変換部4aの出力は判別部4bに
供給されるようになっている。この判別部4bは、住所
領域検出部42、文字認識部43、町名認識部44、住
所辞書45、丁目、街区認識部(街区認識装置)46、
丁目、街区辞書47、および住所認識部48から構成さ
れている。
The output of the photoelectric conversion section 4a is supplied to the discrimination section 4b. The discriminating unit 4b includes an address area detecting unit 42, a character recognizing unit 43, a town name recognizing unit 44, an address dictionary 45, a chome, a block recognizing unit (block recognizing device) 46,
It is composed of a chome, a block dictionary 47, and an address recognition unit 48.

【0021】上記住所領域検出部42は、上記郵便物P
に記載されている各情報のなかから、領域の形、位置等
で、住所情報が記載されている領域を検出する周知のも
のである。
The address area detection unit 42 detects the mail P
It is well known that the area in which the address information is described is detected based on the shape, position, etc. of the area from among the information described in (1).

【0022】上記住所領域検出部42の判断結果、たと
えばその判断した領域の座標値が文字認識部43内の選
択回路51に出力されるようになっている。また、上記
光電変換部4aの出力は文字認識部43内の2値化回路
50に出力されるようになっている。
The judgment result of the address area detecting section 42, for example, the coordinate value of the judged area is output to the selecting circuit 51 in the character recognizing section 43. The output of the photoelectric conversion unit 4a is output to the binarization circuit 50 in the character recognition unit 43.

【0023】上記文字認識部43は、上記光電変換部4
aからの読取信号を2値化する2値化回路20、上記住
所領域検出部42から供給される座標情報に対応する上
記2値化回路20からの2値化信号を選択的に出力する
選択回路51、この選択回路51から供給される住所領
域に対応する住所情報の行画像の文字を1文字ずつ検出
切出しする、つまり住所に対応する文字情報を検出切出
しする文字検出切出回路52、この文字検出切出回路5
2から供給されるつまり検出切出された文字情報を正規
化し、サンプリングする正規化回路53、および正規化
回路53から供給される文字情報を、たとえば辞書55
内の英字、数字に対する基準パタ―ンとのマッチング法
などによって英字、数字等の文字を認識する認識回路5
4によって構成されている。
The character recognizing unit 43 includes the photoelectric conversion unit 4
a binarization circuit 20 for binarizing the read signal from a, and a selection for selectively outputting the binarization signal from the binarization circuit 20 corresponding to the coordinate information supplied from the address area detection unit 42. A circuit 51, a character detection cutout circuit 52 for detecting and cutting out the characters of the line image of the address information corresponding to the address area supplied from the selection circuit 51 one by one, that is, for detecting and cutting out the character information corresponding to the address. Character detection / cutout circuit 5
2, the normalization circuit 53 that normalizes and samples the character information that is detected and cut out, and the character information supplied from the normalization circuit 53, for example, the dictionary 55.
Recognition circuit 5 that recognizes letters such as letters and numbers by the matching method with the reference pattern for letters and numbers in
It is composed of four.

【0024】上記文字認識部43つまり認識回路54の
出力は町名認識部44、丁目、街区認識部46に供給さ
れる。上記町名認識部44は、上記文字認識部43から
供給される認識文字に対して住所辞書45から読出され
る住所により町名(松戸市松戸)を認識するものであ
り、この認識結果は丁目、街区認識部46、住所認識部
48に出力される。
The output of the character recognition unit 43, that is, the recognition circuit 54 is supplied to the town name recognition unit 44, the chome, and the block recognition unit 46. The town name recognition unit 44 recognizes the town name (Matsudo, Matsudo city) from the address read from the address dictionary 45 with respect to the recognized characters supplied from the character recognition unit 43. The recognition result is chome, block. It is output to the recognition unit 46 and the address recognition unit 48.

【0025】上記丁目、街区認識部46は、上記町名認
識部44から供給される町名認識結果により特定される
町名以降の上記文字認識部43から供給される認識文字
に対して丁目、街区辞書47から読出される数字および
区切文字(丁目、番、号、の、−、〜等)を認識するも
のであり、この認識結果は住所認識部48に出力され
る。
The chome and block recognition unit 46 recognizes the recognition characters supplied from the character recognition unit 43 after the town name specified by the town name recognition result supplied from the town name recognition unit 44 and recognizes the chome and block dictionary 47. It recognizes the numbers and delimiters (chome, number, number,-,-, etc.) read from, and the recognition result is output to the address recognition unit 48.

【0026】上記丁目、街区辞書47は、数字および区
切文字(丁目、番、号、の、−、〜等)の街区、数字に
対応する標準パターンが記憶されているものである。上
記住所認識部48は、上記町名認識部44から供給され
る町名と上記丁目、街区認識部46から供給される丁
目、街区により住所を認識し、住所に対する区分指定デ
―タつまり後段の区分部11におけるポケット6、…を
示すデ―タを出力するものである。
The chome / block dictionary 47 stores standard patterns corresponding to blocks and numbers of numbers and delimiters (chome, number, number,-, ..., etc.). The address recognition unit 48 recognizes the address by the town name and the chome supplied from the town name recognition unit 44, the chome and the chome supplied from the block recognition unit 46, and the classification designation data for the address, that is, the subsequent classification unit. The data indicating the pockets 6, ... In 11 are output.

【0027】次に、上記のような構成において動作を説
明する。たとえば今、操作パネル7の図示しないスター
トスイッチの投入に応じて、制御部31が搬送機構部3
6を駆動制御することにより、供給部1に集積されてい
る郵便物Pが1通ずつ取出部2で取出され、搬送路3を
搬送される。この搬送途中でその郵便物P上の住所情報
が読取部4で読取られる。すると、制御部31は読取部
4から供給される住所情報に対応する区分指定デ―タを
読出し、この区分指定デ―タに対応するポケット6、…
に郵便物Pを搬送制御する。
The operation of the above arrangement will be described below. For example, when the start switch (not shown) of the operation panel 7 is turned on, the control unit 31 causes the transport mechanism unit 3 to operate.
By controlling the drive of 6, the postal matter P accumulated in the supply unit 1 is taken out one by one by the take-out unit 2 and is conveyed through the conveying path 3. The address information on the postal matter P is read by the reading unit 4 during the transportation. Then, the control unit 31 reads out the classification designation data corresponding to the address information supplied from the reading unit 4, and the pocket 6 corresponding to the classification designation data, ...
The conveyance of the postal matter P is controlled.

【0028】すなわち、光電変換部4aは、郵便物P上
を光学的に走査して光電変換することによりパタ―ン信
号を得、住所領域検出部42および文字認識部43に出
力する。住所領域検出部42は上記郵便物Pに記載され
ている各情報のなかから、領域の形、位置等で、住所情
報が記載されている領域を検出し、この検出結果を文字
認識部43に出力する。
That is, the photoelectric conversion section 4a obtains a pattern signal by optically scanning the postal matter P and photoelectrically converting it, and outputs it to the address area detection section 42 and the character recognition section 43. The address area detection unit 42 detects the area in which the address information is described from the information described in the postal matter P, such as the shape and position of the area, and the detection result is sent to the character recognition unit 43. Output.

【0029】文字認識部43は住所領域検出部42から
供給される領域の検出結果を用いて光電変換部4aから
供給されるパタ―ン信号の2値化、文字検出、文字認識
を順次行い、その文字認識の結果を町名認識部44、丁
目、街区認識部46に出力する。
The character recognition unit 43 sequentially performs binarization, character detection, and character recognition of the pattern signal supplied from the photoelectric conversion unit 4a using the detection result of the area supplied from the address area detection unit 42, The result of the character recognition is output to the town name recognition unit 44, the chome, and the block recognition unit 46.

【0030】町名認識部44は文字認識部43から供給
される各文字の文字識別候補行列を内部メモリに記憶
し、この内部メモリに記憶した文字識別候補行列による
各文字の組合わせ(候補文字)に対する住所辞書45の
各階層の文字による得点を求め、一番得点の高い候補文
字を町名の認識結果として、丁目、街区認識部46、住
所認識部48へ出力する。
The town name recognizing unit 44 stores the character identification candidate matrix of each character supplied from the character recognizing unit 43 in the internal memory, and combines each character by the character identification candidate matrix stored in this internal memory (candidate character). The score by the character of each layer of the address dictionary 45 is calculated, and the candidate character with the highest score is output to the chome, the block recognition unit 46, and the address recognition unit 48 as the recognition result of the town name.

【0031】丁目、街区認識部46は、上記町名認識部
44から供給される町名認識結果により特定される町名
以降の文字認識部43から供給される認識文字に対して
丁目、街区辞書47から読出される数字および区切文字
(丁目、番、号、の、−、〜等)を認識し、この認識結
果を住所認識部48に出力する。
The chome and block recognition unit 46 reads from the chome and block dictionary 47 the recognition characters supplied from the character recognition unit 43 after the town name specified by the town name recognition result supplied from the town name recognition unit 44. The recognized numbers and delimiters (chome, number, number, of-,-, etc.) are recognized, and the recognition result is output to the address recognition unit 48.

【0032】住所認識部48は、町名認識部44から供
給される町名と丁目、街区認識部46から供給される丁
目、街区により住所を認識し、住所に対する区分指定デ
―タつまり後段の区分部11におけるポケット6、…を
示すデ―タを出力する。
The address recognition unit 48 recognizes the address by the town name and chome supplied from the town name recognition unit 44, the chome and the block supplied from the block recognition unit 46, and the classification designation data for the address, that is, the subsequent classification unit. The data indicating the pockets 6 in 11 are output.

【0033】そして、制御部31は、読出した区分指定
デ―タと搬送検知器の検知信号に対応して区分ゲ―ト9
…を制御することにより、上記郵便物Pがその住所情報
に対応するポケット6、…に集積される。
Then, the control section 31 responds to the read sorting designation data and the detection signal of the transport detector to sort the sorting gate 9
By controlling the ..., The mail P is accumulated in the pockets 6, ... Corresponding to the address information.

【0034】上記丁目、街区認識部46の認識処理につ
いて、図5に示すフローチャートを参照しつつ説明す
る。すなわち、まず、1階層目のデミリタとそれ以降の
デミリタを比較して、矛盾があるときや、可能性の低い
とき、街区部認識結果を否定し、誤読を防ぐ。
The recognition processing of the above-mentioned chome and block recognition unit 46 will be described with reference to the flowchart shown in FIG. That is, first, the delimiter of the first layer is compared with the delimiters of the subsequent layers, and when there is a contradiction or when there is a low possibility, the block recognition result is denied and misreading is prevented.

【0035】たとえば、図6の様な郵便物Pでbの文字
を「一」(横棒)と認識したとき、d、eの二文字で
「丁」、fの文字を「目」と認識して「3−2丁目」と
誤認識されたとき、街区認識結果に矛盾があるため否定
する。
For example, when the letter b is recognized as "one" (horizontal bar) in the postal matter P as shown in FIG. 6, two letters d and e are recognized as "cho" and the letter f is recognized as "eye". Then, when it is erroneously recognized as “3-2 chome”, it is denied because there is a contradiction in the block recognition result.

【0036】また、同じように、図6に示す郵便物Pで
bの文字「番」と認識したときeの文字の「の」と認識
して「3番21の3」と誤認識されたとき、街区認識結
果に矛盾があるため否定する。
Similarly, when the letter "b" of b is recognized in the postal matter P shown in FIG. 6, it is recognized as "no" of the letter e and is erroneously recognized as "3-2 1 3". At this time, it is denied because there is a contradiction in the block recognition result.

【0037】また、郵便物Pの記載方法で通常は、図7
のように1階層と2階層で数字の種類(算数字又は漢数
字)は、一致する。しかし、街区部の文字認識結果は、
七丿870と、漢数字と算数字で認識し、1階層と2階
層とで矛盾が生じるため、街区部の認識結果は採用しな
いようにする。
In addition, the method of describing the postal matter P is usually as shown in FIG.
As described above, the types of numbers (mathematical numbers or Chinese numbers) in the first and second layers match. However, the character recognition result of the block is
The recognition result of the block is not adopted because it is recognized as the Nanachi 870 and the Chinese and arithmetic numbers and there is a contradiction between the first layer and the second layer.

【0038】また、図8の場合、検切り結果により“1
−11”と“1−八”の2種類の認識結果が得られた。
従来ではそのような場合、文字認識の点数で高い方を優
先していた為、誤読の危険性が高かった。そこで、1階
層目の数字種と2階層目の比較を行うと、“1−11”
は1階層目:算数時、2階層目:算数字で一致し、“1
−八”は1階層目:算数字に2階層目:漢数字で不一致
となり、矛盾が生じる。よって、文字種の一致した“1
−11”を採用する。
Further, in the case of FIG. 8, "1" is obtained according to the inspection result.
Two kinds of recognition results, "-11" and "1-8", were obtained.
Conventionally, in such a case, the higher the character recognition score, the higher the priority, so the risk of misreading was high. Therefore, when comparing the numeral type of the first layer and the second layer, "1-11"
Is the 1st layer: when mathematics, the 2nd layer: matches with the arithmetic number, "1
-"8" is inconsistent in the first layer: mathematics and in the second layer: Chinese numerals, resulting in a contradiction.
-11 "is adopted.

【0039】さらに、図3の場合も、検切り結果により
“四−1”と“12−1”の2種類の認識結果が得られ
たが、前の場合と同様に、正しく採用されるようになっ
た。したがって、郵便物の記載方向や階層ごとの数字種
を考慮して、文字識別部により、文字認識を行うように
したため、組み合わせに矛盾があったり、極めて可能性
の低い組み合わせの認識を防ぐことができ、街区部の誤
認識を低下させることができる。
Further, in the case of FIG. 3 as well, two types of recognition results, "4-1" and "12-1", were obtained by the inspection result, but it seems that they are correctly adopted as in the previous case. Became. Therefore, character recognition is performed by the character identification unit in consideration of the writing direction of the postal matter and the number type of each layer, so it is possible to prevent the recognition of combinations with inconsistencies or extremely unlikely combinations. Therefore, it is possible to reduce false recognition of the block.

【0040】上記したように、1階層目とそれ以降のデ
リミタの組み合わせを考慮して、街区部認識を行い、1
階層目で候補に上がった数字の種類が1種類で、それ以
降の階層で候補に上がった数字の種類も1種類のとき、
1階層目とそれ以降の数字の種類が異なった場合、認識
結果は否定され、1階層目の数字の種類が1つで1階層
目の数字の種類が2つの場合、1階層目の数字の種類に
2階層目の数字の種類が一致しているものを認識し、1
階層目の数字が2つで2階層目の数字の種類が1つの場
合、2階層目の数字の種類に1階層目の種類が一致して
いるものを認識するようにしたものである。
As described above, the block division is recognized in consideration of the combination of the delimiters of the first layer and the subsequent layers.
When there is only one type of number that has been selected as a candidate in the hierarchy and one type of number that has been selected as a candidate in subsequent layers,
If the type of the numbers on the first layer and subsequent numbers are different, the recognition result is denied, and if the number of types on the first layer is one and the number of types on the first layer is two, the numbers on the first layer Recognize that the type of the number on the second layer matches the type, and
When there are two numbers in the layer and one type of number in the second layer, the type in which the type in the first layer matches the type of numbers in the second layer is recognized.

【0041】すなわち、従来まで1階層目と2階層目と
で各々認識結果を採用していたが、1階層目と2階層目
で数字の種類が異なって認識され、誤読された例が多く
あったため、そのように認識された場合はリジェクトと
するようにしたものである。
That is, until now, the recognition results have been adopted for the first layer and the second layer respectively, but there are many cases in which different types of numbers are recognized and misread in the first layer and the second layer. Therefore, if it is recognized as such, it is rejected.

【0042】これにより、街区で記載される算数字及び
漢数字の組み合わせにより、誤読を減少させることがで
きる。なお、街区部を認識する際に、階層の数字の種類
に矛盾があるかを判定させ、誤読を防止するようにした
が、これに限らず、1つ目と2つ目のデリミタに矛盾が
あるかの判定、あるいは宛名が縦書きか横書きかに応じ
て横棒のデリミタを用いるか、縦棒のデリミタを用いる
かを特定し、これとの比較により、デミリタに矛盾があ
るかの判定をさせるようにしても良い。
As a result, it is possible to reduce erroneous reading due to the combination of arithmetic and Chinese numerals written in the block. In addition, when recognizing the block part, it is determined whether or not there is a contradiction in the type of numbers in the hierarchy, and misreading is prevented. However, the present invention is not limited to this, and there is a contradiction in the first and second delimiters. Depending on whether there is a vertical writing address or horizontal writing address, specify whether to use the horizontal bar delimiter or the vertical bar delimiter, and by comparing with this, determine whether there is a contradiction in the delimiter. It may be allowed to.

【0043】例えば、デミリタで1つ目が“一”(横
棒)の時は2つ目以降も“−”(横棒)の可能性が高い
ものでもし“|”(縦棒)が認識された場合はそれを
“|”(縦棒)と見なさないようにする。
For example, in the demilita, when the first is "one" (horizontal bar), the second and subsequent ones are highly likely to be "-" (horizontal bar), but "|" (vertical bar) is recognized. If so, do not consider it as a "|" (vertical bar).

【0044】図9のような横書きの文書の場合はデミリ
タを“一”(横棒)で使うが、一般的で“|”(縦棒)
はまず使わない。よって、横書きで“|”(縦棒)が認
識された場合はそれを“|”(縦棒)とみなさないよう
にさせる。
In the case of a horizontally written document as shown in FIG. 9, the delimiter is used as "one" (horizontal bar), but it is generally "|" (vertical bar).
I rarely use Therefore, when "|" (vertical bar) is recognized in horizontal writing, it is not considered as "|" (vertical bar).

【0045】縦書きの文書では、図10の場合ではデミ
リタが“|”(縦棒)で図11の場合は“一”(横棒)
となるので横書きのように定められない。そこで1つ目
のデミリタを“|”(縦棒)と認識した時は、それ以降
のデミリタも“|”(縦棒)として“一”(横棒)が認
識されてもそれを“一”(横棒)とみなさないようにす
る。“一”(横棒)においても同様に、2つ目以降に
“|”(縦棒)が検知されてもそれを“|”(縦棒)と
みなさない。以上のことよりデミリタの矛盾をさせない
ことにより、街区部の誤認識を低下させることができ
る。
In a vertically written document, the delimiter is "|" (vertical bar) in the case of FIG. 10 and "one" (horizontal bar) in the case of FIG.
Therefore, it cannot be defined like horizontal writing. Therefore, when the first demilita is recognized as "|" (vertical bar), even if the subsequent demilita recognizes "1" (horizontal bar) as "|" (vertical bar), it is "1". Do not regard it as a (horizontal bar). Similarly, in "one" (horizontal bar), even if "|" (vertical bar) is detected after the second one, it is not regarded as "|" (vertical bar). From the above, it is possible to reduce the misrecognition of the block by not making the contradiction of Demilita.

【0046】[0046]

【発明の効果】以上詳述したようにこの発明によれば、
街区部の誤認識の減少が図れ、宛名の読取率の向上が図
れ、かつ区分処理の効率向上が図れる街区認識装置およ
び宛名読取区分機を提供できる。
As described above in detail, according to the present invention,
It is possible to provide a block recognizing device and an address reading / sorting device that can reduce erroneous recognition of a block, improve the address reading rate, and improve the efficiency of classification processing.

【図面の簡単な説明】[Brief description of drawings]

【図1】この発明の一実施例における判別部の構成を示
すブロック図。
FIG. 1 is a block diagram showing a configuration of a discriminating unit in an embodiment of the present invention.

【図2】郵便物自動区分機の構成を示す断面図。FIG. 2 is a cross-sectional view showing the configuration of an automatic mail sorting machine.

【図3】図2の郵便物の住所記載例を示す図。FIG. 3 is a diagram showing an example of the address description of the mail piece in FIG.

【図4】郵便物自動区分機の全体の構成を示すブロック
図。
FIG. 4 is a block diagram showing the overall configuration of an automatic mail sorting machine.

【図5】丁目、街区認識部の動作を説明するためのフロ
ーチャート。
FIG. 5 is a flowchart for explaining the operation of the chome and block recognition unit.

【図6】図2の郵便物の住所記載例を示す図。FIG. 6 is a diagram showing an example of the address description of the mail of FIG.

【図7】図2の郵便物の住所記載例を示す図。FIG. 7 is a diagram showing an example of the address description of the mail piece in FIG.

【図8】図2の郵便物の住所記載例を示す図。FIG. 8 is a diagram showing an example of the address description of the mail of FIG.

【図9】他の実施例を説明するための郵便物の住所記載
例を示す図。
FIG. 9 is a diagram showing an address description example of a mail piece for explaining another embodiment.

【図10】他の実施例を説明するための郵便物の住所記
載例を示す図。
FIG. 10 is a diagram showing an example of an address description of a mail item for explaining another embodiment.

【図11】他の実施例を説明するための郵便物の住所記
載例を示す図。
FIG. 11 is a diagram showing an example of an address description of a mail item for explaining another embodiment.

【符号の説明】[Explanation of symbols]

1…供給部 P…郵便物 2…取出部 3…取出搬送路 4…読取部 4a…光電変換部 4b…判別部 5a、〜…区分搬送路 6、〜…ポケット 9〜…区分ゲート 11…区分部 31…制御部 43…文字認識部 44…町名認識部 45…住所辞書 46…丁目、街区認識部 47…丁目、街区辞書 48…住所認識部 DESCRIPTION OF SYMBOLS 1 ... Supplying part P ... Mail 2 ... Extracting part 3 ... Extracting conveying path 4 ... Reading part 4a ... Photoelectric converting part 4b ... Discriminating part 5a, ... Sorting conveying path 6, ... Part 31 ... Control part 43 ... Character recognition part 44 ... Town name recognition part 45 ... Address dictionary 46 ... Chome, block recognition part 47 ... Chome, block dictionary 48 ... Address recognition part

Claims (4)

【特許請求の範囲】[Claims] 【請求項1】 郵便物に記載されている文字の読取りを
行う読取手段と、 この読取手段による読取内容に応じて文字認識する文字
認識手段と、 この文字認識手段から供給される認識文字に対して街区
辞書と照合し、各階層の数字の種類が一致する場合に、
街区を認識する街区認識手段と、 を具備したことを特徴とする街区認識装置。
1. A reading means for reading a character described in a mail piece, a character recognizing means for recognizing a character according to the content read by the reading means, and a recognition character supplied from the character recognizing means. Collate with the block dictionary, and if the type of numbers in each layer match,
A block recognition device comprising: a block recognition unit that recognizes a block.
【請求項2】 郵便物に記載されている文字の読取りを
行う読取手段と、 この読取手段による読取内容に応じて文字認識する文字
認識手段と、 この文字認識手段から供給される認識文字に対して街区
辞書と照合し、街区を区切る複数のデリミタに矛盾がな
い場合に、街区を認識する街区認識手段と、 を具備したことを特徴とする街区認識装置。
2. A reading means for reading characters written on a mail piece, a character recognizing means for recognizing characters according to the contents read by the reading means, and a recognition character supplied from the character recognizing means. A block recognition device comprising: a block recognition unit that recognizes a block when there is no contradiction in a plurality of delimiters that divide the block by checking with a block dictionary.
【請求項3】 搬送される郵便物からその上に記載され
ている宛名を読取り、この読取った宛名を用いて区分を
行う宛名読取区分機において、 郵便物に記載されている文字の読取りを行う読取手段
と、 この読取手段による読取内容に応じて文字認識する文字
認識手段と、 この文字認識手段から供給される認識文字に対して街区
辞書と照合し、各階層の数字の種類が一致する場合に、
街区を認識する街区認識手段と、 この街区認識手段の認識結果に応じて区分を行う区分手
段と、 を具備したことを特徴とする宛名読取区分機。
3. An address reading / sorting machine that reads an address written on a mail to be conveyed and performs classification using the read address, and reads a character written on the mail. In the case where the reading means, the character recognizing means for recognizing the character according to the content read by the reading means, and the recognized character supplied from the character recognizing means are collated with the city block dictionary, and the types of numbers in each layer match. To
An address reading / sorting machine comprising: a block recognizing means for recognizing a block and a classifying means for classifying according to a recognition result of the block recognizing means.
【請求項4】 搬送される郵便物からその上に記載され
ている宛名を読取り、この読取った宛名を用いて区分を
行う宛名読取区分機において、 郵便物に記載されている文字の読取りを行う読取手段
と、 この読取手段による読取内容に応じて文字認識する文字
認識手段と、 この文字認識手段から供給される認識文字に対して街区
辞書と照合し、街区を区切る複数のデリミタに矛盾がな
い場合に、街区を認識する街区認識手段と、 この街区認識手段の認識結果に応じて区分を行う区分手
段と、 を具備したことを特徴とする宛名読取区分機。
4. An address reading / sorting machine, which reads an address written on a mail to be conveyed and classifies the read address, reads a character written on the mail. The reading means, the character recognizing means for recognizing characters according to the contents read by the reading means, and the recognized character supplied from the character recognizing means are collated with the block dictionary, and there is no contradiction between the delimiters separating the blocks. In this case, the address reading / sorting machine comprises: a block recognizing means for recognizing the block; and a classifying means for classifying according to the recognition result of the block recognizing means.
JP5187973A 1993-07-29 1993-07-29 Street zone recognizing device and address reading and classifying machine Pending JPH0739820A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP5187973A JPH0739820A (en) 1993-07-29 1993-07-29 Street zone recognizing device and address reading and classifying machine

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP5187973A JPH0739820A (en) 1993-07-29 1993-07-29 Street zone recognizing device and address reading and classifying machine

Publications (1)

Publication Number Publication Date
JPH0739820A true JPH0739820A (en) 1995-02-10

Family

ID=16215387

Family Applications (1)

Application Number Title Priority Date Filing Date
JP5187973A Pending JPH0739820A (en) 1993-07-29 1993-07-29 Street zone recognizing device and address reading and classifying machine

Country Status (1)

Country Link
JP (1) JPH0739820A (en)

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1998042285A1 (en) 1997-03-21 1998-10-01 The Procter & Gamble Company Absorbent article wrapper comprising a side flap fastener cover
WO1999025285A1 (en) 1997-11-14 1999-05-27 The Procter & Gamble Company Absorbent article wrapper comprising a side flap fastener cover
WO1999055268A1 (en) 1998-04-28 1999-11-04 The Procter & Gamble Company Absorbent article wrapper comprising a side flap fastener cover
US6015934A (en) * 1997-11-12 2000-01-18 Kimberly-Clark Worldwide, Inc. Individually wrapped absorbent article and method and apparatus for its production
WO2000019954A1 (en) 1998-10-05 2000-04-13 The Procter & Gamble Company Individually packaged absorbent article
WO2000019953A1 (en) 1998-10-05 2000-04-13 The Procter & Gamble Company Individually packaged absorbent article
US6074376A (en) * 1995-01-30 2000-06-13 The Procter & Gamble Company Absorbent article wrapper comprising side flap fastener cover
US6183587B1 (en) 1997-11-26 2001-02-06 The Procter & Gamble Company Method of making sanitary napkin comprising three dimensionally shaped tube of absorbent material
US6186993B1 (en) 1996-03-26 2001-02-13 Kao Corporation Wrapping construction of absorbent article
US6316688B1 (en) 1998-04-27 2001-11-13 The Procter & Gamble Company Sanitary napkin comprising three dimensionally shaped tube of absorbent material
US6383169B1 (en) * 1995-01-30 2002-05-07 The Procter & Gamble Company Releasable wrapper for absorbent articles such as sanitary napkins
US6475199B1 (en) 1998-04-27 2002-11-05 The Procter & Gamble Company Method of individually packaging a three dimensionally-shaped absorbent article
US6802833B2 (en) 2002-02-01 2004-10-12 Uni-Charm Corporation Hygiene product

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6074376A (en) * 1995-01-30 2000-06-13 The Procter & Gamble Company Absorbent article wrapper comprising side flap fastener cover
US6383169B1 (en) * 1995-01-30 2002-05-07 The Procter & Gamble Company Releasable wrapper for absorbent articles such as sanitary napkins
US6186993B1 (en) 1996-03-26 2001-02-13 Kao Corporation Wrapping construction of absorbent article
WO1998042285A1 (en) 1997-03-21 1998-10-01 The Procter & Gamble Company Absorbent article wrapper comprising a side flap fastener cover
US6015934A (en) * 1997-11-12 2000-01-18 Kimberly-Clark Worldwide, Inc. Individually wrapped absorbent article and method and apparatus for its production
WO1999025285A1 (en) 1997-11-14 1999-05-27 The Procter & Gamble Company Absorbent article wrapper comprising a side flap fastener cover
US6183587B1 (en) 1997-11-26 2001-02-06 The Procter & Gamble Company Method of making sanitary napkin comprising three dimensionally shaped tube of absorbent material
US6316688B1 (en) 1998-04-27 2001-11-13 The Procter & Gamble Company Sanitary napkin comprising three dimensionally shaped tube of absorbent material
US6475199B1 (en) 1998-04-27 2002-11-05 The Procter & Gamble Company Method of individually packaging a three dimensionally-shaped absorbent article
WO1999055268A1 (en) 1998-04-28 1999-11-04 The Procter & Gamble Company Absorbent article wrapper comprising a side flap fastener cover
WO2000019953A1 (en) 1998-10-05 2000-04-13 The Procter & Gamble Company Individually packaged absorbent article
WO2000019954A1 (en) 1998-10-05 2000-04-13 The Procter & Gamble Company Individually packaged absorbent article
US6802833B2 (en) 2002-02-01 2004-10-12 Uni-Charm Corporation Hygiene product

Similar Documents

Publication Publication Date Title
US6327373B1 (en) Mail address reading apparatus and mail sorting apparatus
JPH0739820A (en) Street zone recognizing device and address reading and classifying machine
JP2006263512A (en) Address recognition device
JPH01159088A (en) Automatic classifying machine for mail
JPH07271899A (en) Character recognition device
JP3710866B2 (en) Mail sorting apparatus, mail processing system, and mail processing method
JP3088036B2 (en) Address reading sorting machine
JP3088038B2 (en) Mail sorting device and mail sorting method
JPH0957199A (en) Address reading apparatus and mail-sorting apparatus
JPH0478475A (en) Automatic postal matter classifying machine
JPH0739819A (en) Address reading and classifying device
JPH0739822A (en) Word recognizing device and address reading and classifying device
JPH0739821A (en) Address reading device and address reading and classifying machine
JP4659947B2 (en) Reading device, reading method, sorting device, and sorting method
JP2988784B2 (en) Mail handling equipment
JPH10180192A (en) Sorting treatment device of sheet paper or the like, method therefor, sorting treatment device for postal item and method therefor
JP2003141443A (en) Recognizing device, sorter, recognizing method and sorting method
JPH0816717A (en) Mail sorting device
JPH0739816A (en) Address reading device
JP2868930B2 (en) Mail handling equipment
JP2007075761A (en) Sorting device and sorting method
JPH0584548B2 (en)
JPH0739817A (en) Address reading device
JPH0484289A (en) Pattern recognizing device
JPH0747334A (en) Address recognizing device and address reading and classifying machine