JPH0373915B2 - - Google Patents
Info
- Publication number
- JPH0373915B2 JPH0373915B2 JP57083993A JP8399382A JPH0373915B2 JP H0373915 B2 JPH0373915 B2 JP H0373915B2 JP 57083993 A JP57083993 A JP 57083993A JP 8399382 A JP8399382 A JP 8399382A JP H0373915 B2 JPH0373915 B2 JP H0373915B2
- Authority
- JP
- Japan
- Prior art keywords
- input
- fourier transformation
- character
- input screen
- dimensional fourier
- 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.)
- Expired - Lifetime
Links
- 238000000034 method Methods 0.000 claims description 26
- 239000011159 matrix material Substances 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims 11
- 238000000926 separation method Methods 0.000 claims 3
- 238000003384 imaging method Methods 0.000 claims 1
- 230000001131 transforming effect Effects 0.000 claims 1
- 238000007796 conventional method Methods 0.000 description 2
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/413—Classification of content, e.g. text, photographs or tables
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Character Input (AREA)
- Image Analysis (AREA)
Description
【発明の詳細な説明】
この発明は、書籍や印刷文書中の情報を自動的
に入力する装置において、記述されている文字列
の領域と図形領域とを切り分けする方法に関する
ものである。DETAILED DESCRIPTION OF THE INVENTION The present invention relates to a method for separating a written character string area and a graphic area in a device for automatically inputting information in a book or a printed document.
従来の文字・図形領域を切り分けする方法で
は、入力画面を縦横方向に投影し、濃度のヒスト
グラムを作成し、ヒストグラムの極端に変化する
場所を判別することにより文字領域と図形領域の
切り分けを行つている。すなわち、第１図で、１
は入力画面で、文字領域２と図形領域３とに文字
と図形が印刷されている。４は縦方向の濃度のヒ
ストグラム、５は同じく横方向の濃度のヒストグ
ラムである。そして濃度の極端に変化する部分４
Ａ，５Ａを文字領域２と図形領域３の切り分え部
分とする。しかしこの方法では入力画面１が傾い
ている場合には縦横の濃度のヒストグラム４，５
は第２図のようになり周辺分布を正確に取ること
不可能である。 In the conventional method of separating text and graphic areas, the input screen is projected vertically and horizontally, a density histogram is created, and the text and graphic areas are separated by determining where the histogram changes extremely. There is. That is, in Figure 1, 1
is an input screen, and characters and figures are printed in a character area 2 and a figure area 3. 4 is a histogram of density in the vertical direction, and 5 is a histogram of density in the horizontal direction. And the part 4 where the concentration changes extremely
Let A and 5A be the parts where the character area 2 and the graphic area 3 are separated. However, with this method, if the input screen 1 is tilted, the vertical and horizontal density histograms 4 and 5
is as shown in Figure 2, and it is impossible to accurately obtain the marginal distribution.
また文字、図形の黒ラン、白ランのラン・レン
グスの統計的性質または黒画素の密度を加算する
ことにより第３図の曲線６をつくり文字および図
形領域の切り分けを行う方式もある。この方式で
は、処理時間が大きくなり、かつ文字・図形を切
り分けるしきい値の設定がむずかしいという問題
がある。 There is also a method of creating the curve 6 in FIG. 3 by adding the statistical properties of the run lengths of black runs and white runs of characters and figures, or the density of black pixels, and dividing the character and figure areas. This method has problems in that it takes a long time to process and it is difficult to set a threshold for separating characters and figures.
この発明は、上記した従来方式の欠点を解決す
るため、文書画像全体の濃淡情報を空間的２次元
フーリエ変換を行い、そのフーリエ変換された情
報をもとにして、あるいはあらかじめ行間隔がわ
かつているときにはその値をもとにして局所領域
（SMALL MATRIX）のスモール・マトリツク
ス・サイズを決定し、そのスモール・マトリツク
ス・サイズをもとにして文書全体を走査し、２次
元フーリエ変換のピーク値の絶対値の変化により
文字列領域と文書領域を切り分ける方法である。
以下、図面についてこの発明を詳細に説明する。 In order to solve the above-mentioned drawbacks of the conventional method, this invention performs a spatial two-dimensional Fourier transform on the shading information of the entire document image, and uses the Fourier-transformed information or when the line spacing is known in advance. When the small matrix size of the local region (SMALL MATRIX) is determined based on that value, the entire document is scanned based on the small matrix size, and the peak value of the two-dimensional Fourier transform is calculated. This is a method of separating character string areas and document areas based on changes in absolute values.
Hereinafter, the invention will be explained in detail with reference to the drawings.
ｆ（ｘ，ｙ）を入力された画像の濃度分布とす
ると空間周波数成分ｇ（ωx，ωy）は次のようにあ
らわすことができる。 When f(x, y) is the density distribution of the input image, the spatial frequency component g(ω x , ω y ) can be expressed as follows.
ｇ（ωx，ωy） ＝∬ｆ（ｘ，ｙ）e-i(〓x g(ω x , ω y ) =∬f(x, y)e -i( 〓 x
Claims (1)
の文字領域と図形領域を切り分ける方法におい
て、処理すべき入力画面の文字列の行間隔の値を
もとにして局所領域を走査するためのスモール・
マトリツクス・サイズを決定する処理と、このス
モール・マトリツクス・サイズで前記入力画面全
体を走査しながら２次元フーリエ変換を行う処理
と、このフーリエ変換面での原点に近いピーク点
の値をもとにして文字領域と図形領域を切り分け
る処理とからなることを特徴とする文字・図形切
り分け方法。 ２ ２次元フーリエ変換を行う処理において、入
力画面の濃度情報をデイジタル的に入力し、フー
リエ変換面でのピーク点を検出することを特徴と
する特許請求の範囲第１項記載の文字・図形切り
分け方法。 ３ ２次元フーリエ変換を行う処理において、入
力画面の濃度情報を光学的に入力し、瞬時にフー
リエ変換を行い、そのフーリエ変換面での情報を
撮像素子を用いて入力し、ピーク点を検出するこ
とを特徴とする特許請求の範囲第１項記載の文
字・図形切り分け方法。 ４ 画像入力装置から入力された印刷文書画像中
の文字領域と図形領域を切り分ける方法におい
て、処理すべき入力画面全体の濃淡情報を空間的
２次元フーリエ変換を行う処理と、この変換され
た平面において、原点に近いピーク点を見い出す
ことにより、文字列の行間隔を求める処理と、こ
の行間隔の値をもとにして局所領域を走査するた
めのスモール・マトリツクス・サイズを決定する
処理と、このスモール・マトリツクス・サイズで
前記入力画面全体を走査しながら２次元フーリエ
変換を行う処理と、このフーリエ変換面での原点
に近いピーク点の値をもとにして文字領域と図形
領域を切り分ける処理とからなることを特徴とす
る文字・図形切り分け方法。 ５ ２次元フーリエ変換を行う処理において、入
力画面の濃度情報をデイジタル的に入力し、フー
リエ変換面でのピーク点を検出することを特徴と
する特許請求の範囲第４項記載の文字・図形切り
分け方法。 ６ ２次元フーリエ変換を行う処理において、入
力画面の濃度情報を光学的に入力し、瞬時にフー
リエ変換を行い、そのフーリエ変換面での情報を
撮像素子を用いて入力し、ピーク点を検出するこ
とを特徴とする特許請求の範囲第４項記載の文
字・図形切り分け方法。[Claims] 1. A method for separating character areas and graphic areas in a printed document image input from an image input device, in which a local area is divided based on the line spacing value of a character string on an input screen to be processed. Small for scanning
The process of determining the matrix size, the process of performing two-dimensional Fourier transform while scanning the entire input screen using this small matrix size, and the process of performing two-dimensional Fourier transform based on the value of the peak point near the origin on this Fourier transform surface. 1. A method for separating characters and figures, comprising the steps of separating a character area and a figure area. 2. Character/figure separation according to claim 1, characterized in that in the process of performing two-dimensional Fourier transformation, density information on an input screen is digitally input and peak points on the Fourier transformation plane are detected. Method. 3. In the process of performing two-dimensional Fourier transformation, the density information on the input screen is optically input, Fourier transformation is instantaneously performed, and the information on the Fourier transformation plane is input using an image sensor to detect the peak point. A method for separating characters and figures according to claim 1. 4. In a method for separating character areas and graphic areas in a printed document image input from an image input device, a process of spatially two-dimensional Fourier transforming the grayscale information of the entire input screen to be processed, and a process of performing spatial two-dimensional Fourier transformation on the transformed plane. , a process to find the line spacing of a character string by finding a peak point close to the origin, a process to determine the small matrix size for scanning a local area based on this line spacing value, and A process of performing a two-dimensional Fourier transform while scanning the entire input screen in a small matrix size, and a process of dividing a character area and a figure area based on the value of a peak point near the origin on this Fourier transform surface. A character/figure separation method characterized by consisting of the following. 5. Character/figure separation according to claim 4, characterized in that in the process of performing two-dimensional Fourier transformation, density information on an input screen is digitally input and peak points on the Fourier transformation plane are detected. Method. 6. In the process of performing two-dimensional Fourier transformation, the density information on the input screen is optically input, Fourier transformation is instantaneously performed, and the information on the Fourier transformation plane is input using an imaging device to detect the peak point. A method for separating characters and figures according to claim 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP57083993A JPS58201182A (en) | 1982-05-20 | 1982-05-20 | Character and graph demarcating method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP57083993A JPS58201182A (en) | 1982-05-20 | 1982-05-20 | Character and graph demarcating method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JPS58201182A JPS58201182A (en) | 1983-11-22 |
| JPH0373915B2 true JPH0373915B2 (en) | 1991-11-25 |
Family
ID=13818052
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP57083993A Granted JPS58201182A (en) | 1982-05-20 | 1982-05-20 | Character and graph demarcating method |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JPS58201182A (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0679349B2 (en) * | 1985-04-12 | 1994-10-05 | 住友電気工業株式会社 | Optical reader |
| JPH0535868A (en) * | 1991-07-31 | 1993-02-12 | Toppan Printing Co Ltd | Image cutting device |
| JP3733161B2 (en) * | 1995-08-01 | 2006-01-11 | キヤノン株式会社 | Image processing apparatus and method |
| JP2000339460A (en) * | 1999-05-26 | 2000-12-08 | Sharp Corp | Region of interest setting device and region of interest setting method |
| JP4616522B2 (en) * | 2001-07-12 | 2011-01-19 | 株式会社リコー | Document recognition apparatus, document image region identification method, program, and storage medium |
| JP5705611B2 (en) * | 2011-03-25 | 2015-04-22 | 株式会社日立ハイテクノロジーズ | Apparatus and method for detecting rotation angle from normal position of image |
-
1982
- 1982-05-20 JP JP57083993A patent/JPS58201182A/en active Granted
Also Published As
| Publication number | Publication date |
|---|---|
| JPS58201182A (en) | 1983-11-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US5563403A (en) | Method and apparatus for detection of a skew angle of a document image using a regression coefficient | |
| US9805281B2 (en) | Model-based dewarping method and apparatus | |
| US6738154B1 (en) | Locating the position and orientation of multiple objects with a smart platen | |
| Fan et al. | Marginal noise removal of document images | |
| JP4261005B2 (en) | Region-based image binarization system | |
| JP2003132358A (en) | Image processing method, device and system | |
| US5892854A (en) | Automatic image registration using binary moments | |
| US5075895A (en) | Method and apparatus for recognizing table area formed in binary image of document | |
| Meng et al. | Nonparametric illumination correction for scanned document images via convex hulls | |
| JPH0373915B2 (en) | ||
| EP0975146B1 (en) | Locating the position and orientation of multiple objects with a smart platen | |
| KR100537829B1 (en) | Method for segmenting Scan Image | |
| JPH05342412A (en) | Extracting system for gradient vector and feature extracting system for character recognition | |
| JP2960468B2 (en) | Method and apparatus for binarizing grayscale image | |
| JPH0490082A (en) | Device for detecting character direction in document | |
| JP2004048130A (en) | Image processing method, image processing apparatus, and image processing program | |
| JPH0797390B2 (en) | Character recognition device | |
| JP2006107018A (en) | Method and apparatus for image analysis, method and system for image processing, and operation program therefor | |
| JPS6246038B2 (en) | ||
| JP2001291056A (en) | Document picture recognizing device and recording medium | |
| JPH10222688A (en) | Picture processing method | |
| EP0974931A1 (en) | Method and apparatus for identifying a plurality of sub-images in an input image | |
| JPH0535914A (en) | Picture inclination detection method | |
| JP2843638B2 (en) | Character image alignment method | |
| JPS6327751B2 (en) |