JPH04290185A - Vertical/lateral writing discriminating method - Google Patents

Vertical/lateral writing discriminating method

Info

Publication number
JPH04290185A
JPH04290185A JP3054866A JP5486691A JPH04290185A JP H04290185 A JPH04290185 A JP H04290185A JP 3054866 A JP3054866 A JP 3054866A JP 5486691 A JP5486691 A JP 5486691A JP H04290185 A JPH04290185 A JP H04290185A
Authority
JP
Japan
Prior art keywords
vertical
character
horizontal
character spacing
writing
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.)
Withdrawn
Application number
JP3054866A
Other languages
Japanese (ja)
Inventor
Michihiko Kawazoe
川添 三千彦
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.)
Omron Corp
Original Assignee
Omron Corp
Omron Tateisi Electronics Co
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 Omron Corp, Omron Tateisi Electronics Co filed Critical Omron Corp
Priority to JP3054866A priority Critical patent/JPH04290185A/en
Publication of JPH04290185A publication Critical patent/JPH04290185A/en
Withdrawn legal-status Critical Current

Links

Landscapes

  • Character Input (AREA)

Abstract

(57)【要約】本公報は電子出願前の出願データであるた
め要約のデータは記録されません。
(57) [Summary] This bulletin contains application data before electronic filing, so abstract data is not recorded.

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、縦書あるいは横書で
数行にわたり一定の情報を表すように記載された文字の
文字認識を行い、認識後の文字列が一定情報を表すよう
に縦書であるか横書であるかを判別する縦書横書判別方
法に関する。
[Industrial Application Field] This invention performs character recognition of characters written vertically or horizontally over several lines to express certain information. The present invention relates to a vertical/horizontal writing discrimination method for determining whether the text is Japanese or horizontal.

【0002】0002

【従来の技術】従来の縦書横書判別は、OCR等により
読み取った文字データをパターンマッチング等により文
字認識し、その認識後の文字列を、データベースに格納
してある例えば「東京都」や、「××××会社」、「×
×大学」、「野球」、「コンピュータ」等の一定の意味
をなす情報(熟語)と照合して、文字列と一致する情報
があるか否かで行っている。
[Background Art] Conventional vertical/horizontal writing discrimination involves character recognition of character data read by OCR, etc., by pattern matching, etc., and the recognized character string is stored in a database, such as "Tokyo", etc. , “×××× Company”, “×
This is done by checking whether there is any information that matches the character string by comparing it with information (idioms) that have a certain meaning, such as "×University", "Baseball", and "Computer".

【0003】つまり、縦書である文書を例えば横書であ
ると判断した場合には、文字単体自体を認識できたとし
ても、各文字列が一定の情報を形成せず、その情報を分
類してデータベース化等の利用ができなくなるので、縦
書横書判別を行う。
[0003] In other words, if a vertically written document is determined to be horizontally written, even if individual characters themselves can be recognized, each string of characters does not form a certain amount of information, and it is difficult to classify that information. Since this makes it impossible to use it for database creation, etc., vertical and horizontal writing will be determined.

【0004】0004

【発明が解決しようとする課題】しかし、このような従
来の縦書横書判別では、文字認識後の文字列を、データ
ベースに格納した一定の意味をなす情報、つまり熟語と
照合するため、その照合処理に時間がかかり、全体とし
てのデータ処理速度が遅くなるという問題がある。
[Problem to be Solved by the Invention] However, in such conventional vertical/horizontal writing discrimination, the character string after character recognition is compared with information that has a certain meaning stored in a database, that is, an idiom. There is a problem that the verification process takes time and the overall data processing speed becomes slow.

【0005】また、その照合処理の一致する割合をより
増大させたい場合や、文書にどのような情報が記載され
ているか分からない場合には、データベースの容量を増
大させる必要があるので、処理速度がより遅くなると共
に、データベースのためのメモリ容量が増大してしまう
という問題がある。
[0005] Furthermore, if you want to increase the matching rate in the matching process or if you do not know what kind of information is written in the document, it is necessary to increase the capacity of the database, so the processing speed will increase. The problem is that it becomes slower and the memory capacity for the database increases.

【0006】そこで、本発明は上記問題に鑑みなされた
もので、文字認識後の縦書横書判別の際にはデータベー
スによる照合を行わず、処理速度を迅速化させた縦書横
書判別方法を提供することを目的とする。
[0006]The present invention has been made in view of the above problem, and provides a method for distinguishing between vertical and horizontal writing, which speeds up the processing speed by not performing database comparison when distinguishing between vertical and horizontal writing after character recognition. The purpose is to provide

【0007】[0007]

【課題を解決するための手段】上記目的を達成するため
本発明は、縦書あるいは横書で数行にわたり一定の情報
を表すように記載された文字の文字認識を行い、認識後
の文字列が上記一定情報を表すように縦書であるか横書
であるかを判別する縦書横書判別方法において、横方向
あるいは縦方向の一定方向から上記文字を読取り、その
読取りデータにより文字認識を行うと共に、文字認識不
可の場合には読取データを90度回転させて再度上記文
字認識を行い、文字認識可の場合には、上記読取データ
に基づき縦方向および横方向の文字間隔を算出して、両
方向の文字間隔の一定である割合の大小を比較すると共
に、両方向の文字間隔の大小を比較し、上記比較結果に
基づいて縦書横書の判別を行うことを特徴とする。
[Means for Solving the Problems] In order to achieve the above object, the present invention performs character recognition of characters written vertically or horizontally over several lines to express certain information, and the recognized character strings are In the vertical/horizontal writing discrimination method for determining whether the character is written vertically or horizontally so that it represents the above-mentioned certain information, the above-mentioned character is read from a certain direction, either horizontally or vertically, and character recognition is performed based on the read data. At the same time, if character recognition is not possible, the read data is rotated 90 degrees and the above character recognition is performed again.If character recognition is possible, the character spacing in the vertical and horizontal directions is calculated based on the above read data. , is characterized in that it compares the size of a constant ratio of character spacing in both directions, and also compares the size of character spacing in both directions, and determines whether it is vertical or horizontal writing based on the comparison results.

【0008】[0008]

【作用】上記構成では、まずは横方向あるいは縦方向の
一定方向から文字を読取って文字認識を行い、文字認識
可の場合には読取データに基づき縦方向および横方向の
文字間隔を算出して、両方向の文字間隔の一定である割
合を比較すると共に、両方向の文字間隔の大小を比較し
、上記両比較結果に基づいて縦書横書の判別を行うよう
にしたので、文字認識時の文字間隔から縦書横書を判別
することができ、データベースとの照合処理の必要がな
くなる。
[Operation] In the above configuration, characters are first read from a fixed direction in the horizontal or vertical direction, character recognition is performed, and if character recognition is possible, the character spacing in the vertical and horizontal directions is calculated based on the read data. In addition to comparing the constant ratio of the character spacing in both directions, we also compared the size of the character spacing in both directions, and based on the above comparison results, we determined whether it was vertical or horizontal writing, so the character spacing during character recognition It is possible to distinguish between vertical and horizontal writing, eliminating the need for comparison with a database.

【0009】[0009]

【実施例】以下、この発明を図面に基づいて説明する。DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be explained below based on the drawings.

【0010】図1は、この発明に係る縦書横書判別方法
を採用した名刺データの読取り・分類装置を簡略化して
示す説明図である。
FIG. 1 is a simplified explanatory diagram of a business card data reading/classifying device that employs the vertical/horizontal writing discrimination method according to the present invention.

【0011】この図において、名刺1は名刺搬送装置2
により自動的に一枚ずつ順次送られ、その送られた名刺
1上に印字された「社名」、「氏名」、「部課名」およ
び「電話番号」等の漢字や数字等の文字が読取り部3に
より読取られる。読取り部3で読取られた文字は、RS
 232C 等のケーブル4を介してデータ処理装置で
あるパソコン(パーソナルコンピュータ)本体5に読取
りデータとして入力し、そこで文字認識されると共に本
発明に係る方法により縦書横書の判別が行われる。その
結果はCRT6やプリンタ7から出力される。
In this figure, a business card 1 is transferred to a business card conveying device 2.
The cards are automatically sent one by one, and characters such as kanji and numbers such as "company name,""name,""department/sectionname," and "telephone number" printed on the sent business card 1 are read on the reader. 3. The characters read by the reading section 3 are RS
The read data is input as read data to a personal computer main body 5, which is a data processing device, via a cable 4 such as 232C, where characters are recognized and whether vertical or horizontal writing is determined by the method according to the present invention. The results are output from the CRT 6 or printer 7.

【0012】尚、この文字読取り・分類装置および搬送
装置自体の構成は従来から周知のものであり、文字認識
もパターンマッチング等の従来からの手法を用いている
。また、本発明に係る縦書横書判別方法は、パソコン本
体5内に内蔵されるCPU(図示せず)と、ROMある
いはRAM等のメモリ(図示せず)とによるプログラム
処理により行われる。
[0012] The configurations of this character reading/classifying device and the conveyance device themselves are conventionally known, and character recognition uses conventional techniques such as pattern matching. Further, the vertical writing/horizontal writing discrimination method according to the present invention is performed by program processing by a CPU (not shown) built into the personal computer main body 5 and a memory (not shown) such as ROM or RAM.

【0013】次に、上記の如く構成された文字読取り・
分類装置において実施される本発明に係る縦書横書判別
方法の一実施例を、図2に示すフローチャートに基づい
て説明する。
[0013] Next, the character reading system configured as described above
An embodiment of the vertical/horizontal writing discrimination method according to the present invention, which is implemented in a classification device, will be described based on the flowchart shown in FIG.

【0014】まず最初に横方向に読取り部3をスキャン
させて名刺1上に印字された文字を読取り(ST10)
、パターンマッチング等の方法により文字認識を行う(
ST20)。
First, the reading section 3 is scanned in the horizontal direction to read the characters printed on the business card 1 (ST10).
, perform character recognition using methods such as pattern matching (
ST20).

【0015】認識不可の場合には(ST30“No ”
)、読取った文字データ、つまり読取りデータを時計回
りに90度回転させた後に(ST40)、再度認識を行
い(ST10)、認識できるか否かを判断し(ST30
)、また認識付加の場合には(ST30“No ”)、
読取りデータの90度回転、文字認識および認識判断の
処理(ST40,10,30)を少なくとも3回読取り
データが一回転するまで繰り返す。読取りデータを90
度回転させる方法は公知で、例えばパターンマッチング
の読取りデータ、つまり二値化したマトリクス状の読取
りデータの場合には、各“行”の要素をそれぞれ対応す
る各“列”に変換する方法等により行われる。
[0015] If recognition is not possible (ST30 “No”)
), the read character data, that is, the read data, is rotated 90 degrees clockwise (ST40), then recognized again (ST10), and it is determined whether or not it can be recognized (ST30).
), and in the case of recognition addition (ST30 “No”),
The process of rotating the read data by 90 degrees, character recognition, and recognition judgment (ST40, 10, 30) is repeated at least three times until the read data has rotated once. Read data 90
The method of rotating by degrees is well known. For example, in the case of pattern matching read data, that is, binary matrix-like read data, there is a method of converting each "row" element into a corresponding "column". It will be done.

【0016】認識可能となれば(ST30“Yes”)
、次に縦書横書の判別を行うため、まずは縦方向および
横方向の各文字の文字間隔を算出して、両方向の文字間
隔の一定である割合の大小、つまりその割合がどちらの
方向のほうが大きいか、あるいはほぼ同じかの判別を行
う(ST50)。この文字間隔の算出は、例えば文字読
取り時における文字の切り出し間隔等により行う。
[0016] If it can be recognized (ST30 “Yes”)
, Next, in order to distinguish between vertical and horizontal writing, first calculate the character spacing between each character in the vertical and horizontal directions, and then determine the size of the constant ratio of character spacing in both directions, that is, which direction the ratio is. It is determined whether the two values are larger or approximately the same (ST50). This character spacing is calculated based on, for example, the character cutout spacing during character reading.

【0017】横方向の文字間隔が一定である割合が縦方
向の文字間隔が一定である割合より大きいと判別された
場合には(ST50“横>縦”)、横書きと判断する一
方(ST60)、縦方向の文字間隔が一定である割合が
横方向の文字間隔が一定である割合より大きいと判別さ
れた場合には(ST50“横<縦”)、縦書きと判断し
(ST70)、さらに横方向の文字間隔が一定である割
合と縦方向の文字間隔が一定である割合が同じであると
判別されれば(ST50“横=縦”)、次の判別ステッ
プに移行する。ここでの判別は、名刺等のように、「社
名」や「氏名」、「部課名」のような熟語を構成する文
字がその熟語毎に大きさを変えていたり、改行されて行
頭の文字の位置がずれ、あるいは段落のずれが大きいも
のの場合に有効な判別である。
If it is determined that the proportion of constant character spacing in the horizontal direction is greater than the proportion of constant character spacing in the vertical direction (ST50 "horizontal>vertical"), horizontal writing is determined (ST60) If it is determined that the proportion of constant character spacing in the vertical direction is greater than the proportion of constant character spacing in the horizontal direction (ST50 "horizontal <vertical"), it is determined that the writing is vertical (ST70), and If it is determined that the ratio of constant character spacing in the horizontal direction and the ratio of constant character spacing in the vertical direction are the same (ST50 "horizontal=vertical"), the process moves to the next determination step. The distinction here is that, like on business cards, the characters that make up the phrases such as "company name,""name," or "department/section name" change in size for each phrase, or if the letters at the beginning of the line are broken. This is an effective determination when the position of the page is misaligned or there is a large misalignment of paragraphs.

【0018】次のステップでは縦方向の文字間隔と横方
向の文字間隔との大小を比較し(ST80)、縦方向の
文字間隔が横方向の文字間隔より大きいと判別された場
合には(ST80“横<縦”)、横書きと判断する一方
(ST90)、横方向の文字間隔が縦方向の文字間隔よ
り大きいと判別された場合には(ST80“横>縦”)
、縦書きと判断する(ST100)。ここでの判別は、
通常の文書では文字間より行間の方が大、つまり縦書き
のものでは横方向の文字間隔のほうが大きいのに対し、
横書きのものでは縦方向の文字間隔が大きいことに着目
したものである。
In the next step, the vertical character spacing is compared with the horizontal character spacing (ST80), and if it is determined that the vertical character spacing is larger than the horizontal character spacing (ST80). "Horizontal <Vertical"), it is determined that the writing is horizontal (ST90), while if it is determined that the character spacing in the horizontal direction is larger than the character spacing in the vertical direction (ST80 "Horizontal >Vertical")
, it is determined that the writing is vertical (ST100). The determination here is
In normal documents, the line spacing is larger than the character spacing; in other words, in vertically written documents, the horizontal character spacing is larger.
This focuses on the fact that horizontal writing has large vertical character spacing.

【0019】以上ここまでが、文字読取り・分類装置お
よびこの装置において実施される本発明に係る縦書横書
判別方法の説明で、次にこの装置に図3(a)〜(c)
に示すような縦書き、あるいは横書きの名刺を使用した
場合の縦書横書判別を図2に基づいて説明する。
The above is a description of the character reading/classifying device and the vertical/horizontal writing discrimination method according to the present invention implemented in this device.
The vertical and horizontal writing determination when using a business card with vertical writing or horizontal writing as shown in FIG. 2 will be explained based on FIG.

【0020】まず、図3(a)に示すような横書の名刺
の場合には、横方向に読取った際に文字認識が可能なた
め、図2において、ST10,ST20,ST30,S
T50と進む。そして、このST50で縦方向の文字間
隔と横方向の文字間隔とのどちらの文字間隔が一定であ
る割合が大きいか否かの判別が行われ、図3(a)から
明らかなように横方向の文字間隔の一定である割合が、
縦方向の文字間隔の一定である割合より大きいので(S
T50“横>縦”)、横書きであると判断される(ST
60)。
First, in the case of a horizontally written business card as shown in FIG. 3(a), character recognition is possible when read horizontally, so in FIG.
Proceed to T50. Then, in ST50, it is determined whether the proportion of constant character spacing is greater, the vertical character spacing or the horizontal character spacing, and as is clear from FIG. 3(a), The constant rate of character spacing is
Since it is larger than the constant ratio of vertical character spacing (S
T50 “Horizontal > Vertical”), it is determined that the writing is horizontal (ST
60).

【0021】一方、図3(b)に示すような縦書の名刺
の場合には、横方向に読取った際には文字認識不可能な
ため、図2において、ST10、ST20、ST30、
ST40と進み、このST40で上述のように読取りデ
ータを時計回りに90度反転させる。
On the other hand, in the case of a vertically written business card as shown in FIG. 3(b), since characters cannot be recognized when read horizontally, ST10, ST20, ST30,
The process proceeds to ST40, and in ST40, the read data is reversed 90 degrees clockwise as described above.

【0022】そして、再度文字認識すれば(ST20)
、認識可能と判断できるので(ST30“Yes”)、
ST50へ進み、ここで縦方向の文字間隔と横方向の文
字間隔とのどちらの文字間隔が一定である割合が大きい
か否かの判別が行われる。この場合には、図3(b)か
ら明らかなように縦方向の文字間隔の一定である割合が
、横方向の文字間隔の一定である割合より大きいので(
ST50“横<縦”)、縦書きであると判断される(S
T70)。
[0022] Then, if the characters are recognized again (ST20)
, it can be determined that it is recognizable (ST30 "Yes"),
Proceeding to ST50, it is determined whether the proportion of constant character spacing between the vertical character spacing and the horizontal character spacing is greater. In this case, as is clear from Figure 3(b), the proportion of constant character spacing in the vertical direction is greater than the proportion of constant character spacing in the horizontal direction;
ST50 “Horizontal < Vertical”), it is determined that the writing is vertical (S
T70).

【0023】さらに、図3(c)に示すような縦書の名
刺の場合には、横方向に読取った際でも認識可能なため
、図2において、ST10,ST20,ST30,ST
50と進む。そしてこのST50で縦方向の文字間隔と
横方向の文字間隔とのどちらの文字間隔が一定である割
合が大きいか否かの判別が行われるが、図3(c)から
も明らかなように縦方向の文字間隔と、横方向の文字間
隔とがほぼ一定であるため(ST50“縦=横”)、つ
ぎの判断ステップであるST80に移行する。このST
80では縦方向の文字間隔と横方向の文字間隔との大小
を比較し、この場合には、図3(c)からも明らかなよ
うに横方向の文字間隔のほうが縦方向の文字間隔より大
きいので(ST80“横>縦”)、縦書きと判断される
(ST100)。
Furthermore, in the case of a vertically written business card as shown in FIG. 3(c), it can be recognized even when read horizontally, so in FIG.
Proceed to 50. Then, in ST50, it is determined whether the proportion of constant character spacing is greater, the vertical character spacing or the horizontal character spacing.As is clear from FIG. 3(c), Since the character spacing in the direction and the character spacing in the horizontal direction are almost constant (ST50 "vertical=horizontal"), the process moves to the next determination step, ST80. This ST
80, the character spacing in the vertical direction and the character spacing in the horizontal direction are compared, and in this case, as is clear from FIG. 3(c), the character spacing in the horizontal direction is larger than the character spacing in the vertical direction. Therefore, (ST80 "horizontal>vertical"), it is determined that the text is written vertically (ST100).

【0024】従って、本実施例の方法では、縦書横書の
判別を縦方向および横方向の文字間隔に着目して判別す
るようにしたので、文字認識後の文字列をデータベース
に格納してある一定情報あるいは熟語と照合する等の照
合処理がなくなり、縦書横書の判別速度が迅速化し、全
体としてデータ処理速度が高速化されると共に、その照
合処理するためのデータベースのメモリ容量が減縮され
る。
Therefore, in the method of this embodiment, since vertical and horizontal writing are determined by focusing on the character spacing in the vertical and horizontal directions, the character strings after character recognition are stored in the database. Collation processing such as matching certain information or phrases is eliminated, speeding up the discrimination between vertical and horizontal writing, speeding up the overall data processing speed, and reducing the memory capacity of the database used for the collation process. be done.

【0025】尚、本実施例では、縦方向および横方向の
文字間隔の一定である割合の大小を比較し、その割合が
等しいと判断された場合のみ縦方向および横方向の文字
間隔の大小を比較するようにしたが、本発明では、縦方
向および横方向の文字間隔の一定である割合の大小と、
縦方向および横方向の文字間隔の大小とを同時に行い、
その結果により、上記本実施例のように縦書横書を判別
するようにしてもよい。また、本実施例では名刺につい
て説明したが、本発明では名刺に限らずに一般の文書が
記載された書類等でも勿論よい。
[0025] In this embodiment, the magnitude of the constant ratio of the character spacing in the vertical and horizontal directions is compared, and only when the ratios are determined to be equal, the magnitude of the character spacing in the vertical and horizontal directions is changed. However, in the present invention, the size of the constant ratio of the character spacing in the vertical and horizontal directions,
Simultaneously increase and decrease the character spacing in the vertical and horizontal directions,
Based on the results, vertical writing and horizontal writing may be determined as in the above embodiment. Further, in this embodiment, a business card has been described, but the present invention is not limited to a business card, and of course, a document in which a general document is written may be used.

【0026】[0026]

【発明の効果】以上説明したように、この発明では、縦
書横書の判別を縦方向および横方向の文字間隔に着目し
て判断するようにしたので、文字認識後の文字列をデー
タベースに格納してある文字列をデータベースに格納し
てある熟語と照合する等の照合処理がなくなり、縦書横
書の判別速度が迅速化し、全体としてデータ処理速度が
高速化されると共に、その照合処理するためのデータベ
ースのためのメモリ容量は減縮される。
[Effects of the Invention] As explained above, in this invention, since the discrimination between vertical and horizontal writing is made by focusing on the character spacing in the vertical and horizontal directions, character strings after character recognition are stored in a database. This eliminates the need for matching processes such as comparing stored character strings with phrases stored in the database, which speeds up the discrimination between vertical and horizontal writing, speeds up data processing overall, and improves the matching process. The memory capacity for the database is reduced.

【図面の簡単な説明】[Brief explanation of the drawing]

【図1】この発明に係る縦書横書判別方法を採用した名
刺データの読取り・分類装置を簡略化して示す説明図。
FIG. 1 is a simplified explanatory diagram showing a business card data reading/classifying device that employs a vertical/horizontal writing discrimination method according to the present invention.

【図2】この発明に係る縦書横書判別方法の一例を示す
フローチャート。
FIG. 2 is a flowchart showing an example of a vertical writing/horizontal writing discrimination method according to the present invention.

【図3】(a)〜(c)はそれぞれ名刺における縦書あ
るいは横書の状態を示す説明図。
FIGS. 3(a) to 3(c) are explanatory diagrams each showing a state of vertical writing or horizontal writing on a business card.

【符号の説明】[Explanation of symbols]

1    名刺 2    名刺搬送装置 3    読取り部 4    ケーブル 5    パソコン本体 6    CRT 7    プリンタ 1 Business card 2 Business card conveyance device 3 Reading section 4 Cable 5  PC body 6 CRT 7 Printer

Claims (1)

【特許請求の範囲】[Claims] 【請求項1】縦書あるいは横書で数行にわたり一定の情
報を表すように記載された文字の文字認識を行い、認識
後の文字列が上記一定情報を表すように縦書であるか横
書であるかを判別する縦書横書判別方法において、横方
向あるいは縦方向の一定方向から上記文字を読取り、そ
の読取りデータにより文字認識を行うと共に、文字認識
不可の場合には読取データを90度回転させて再度上記
文字認識を行い、文字認識可の場合には、上記読取デー
タに基づき縦方向および横方向の文字間隔を算出して、
両方向の文字間隔の一定である割合の大小を比較すると
共に、両方向の文字間隔の大小を比較し、上記比較結果
に基づいて縦書横書の判別を行うことを特徴とする縦書
横書判別方法。
Claim 1: Character recognition is performed for characters written vertically or horizontally over several lines to represent certain information, and the character string after recognition is written vertically or horizontally so as to represent the certain information. In the vertical/horizontal writing discrimination method, the above-mentioned characters are read from a certain direction, either horizontally or vertically, character recognition is performed based on the read data, and if character recognition is not possible, the read data is The characters are rotated once and the character recognition is performed again. If the characters can be recognized, the character spacing in the vertical and horizontal directions is calculated based on the read data.
Vertical/horizontal writing discrimination characterized by comparing the size of a constant ratio of character spacing in both directions, comparing the size of character spacing in both directions, and determining vertical writing/horizontal writing based on the above comparison results. Method.
JP3054866A 1991-03-19 1991-03-19 Vertical/lateral writing discriminating method Withdrawn JPH04290185A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP3054866A JPH04290185A (en) 1991-03-19 1991-03-19 Vertical/lateral writing discriminating method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP3054866A JPH04290185A (en) 1991-03-19 1991-03-19 Vertical/lateral writing discriminating method

Publications (1)

Publication Number Publication Date
JPH04290185A true JPH04290185A (en) 1992-10-14

Family

ID=12982511

Family Applications (1)

Application Number Title Priority Date Filing Date
JP3054866A Withdrawn JPH04290185A (en) 1991-03-19 1991-03-19 Vertical/lateral writing discriminating method

Country Status (1)

Country Link
JP (1) JPH04290185A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH04352295A (en) * 1991-05-30 1992-12-07 Toshiba Corp System and device for identifing character string direction

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS61272138A (en) * 1985-05-28 1986-12-02 鈴木 貞夫 Resin foam composite heat-insulating material

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS61272138A (en) * 1985-05-28 1986-12-02 鈴木 貞夫 Resin foam composite heat-insulating material

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH04352295A (en) * 1991-05-30 1992-12-07 Toshiba Corp System and device for identifing character string direction

Similar Documents

Publication Publication Date Title
Ng et al. Learning to recognize tables in free text
US7298903B2 (en) Method and system for separating text and drawings in digital ink
Pal et al. Automatic separation of machine-printed and hand-written text lines
JPH0430070B2 (en)
Sareen et al. Gurmukhi handwritten word conversion using feature extraction using deep learning
Pal On the developement of an optical character recognition (ocr) system for printed bangla script
JPS6132187A (en) Character recognition system
JPS592191A (en) Recognizing and processing system of handwritten japanese sentence
Chen et al. On-line signature verification using direction sequence string matching
JPH10302025A (en) Handwritten character recognition device and program recording medium thereof
JP2972443B2 (en) Character recognition device
JPH09114926A (en) Method and apparatus for classifying input characters in online character recognition
JPS59158482A (en) Character recognizing device
JP3217442B2 (en) Optical character reader
JPS60169984A (en) Composition reader
JP2749425B2 (en) Article extraction method
JPH05210635A (en) Input device
KR100234028B1 (en) Character Area Classification Method of Character Recognition System
JPS6095689A (en) Optical character reader
JPS6061875A (en) Generation system of standard pattern
JPS6139175A (en) Optical character reading device
JPS63282586A (en) Character recognition device
JPS62281082A (en) character recognition device
JPS62177686A (en) Optical character reader
JPH04320573A (en) Character data sorting device

Legal Events

Date Code Title Description
A300 Application deemed to be withdrawn because no request for examination was validly filed

Free format text: JAPANESE INTERMEDIATE CODE: A300

Effective date: 19980514