JPS63184886A - Binarizing system for picture processing - Google Patents
Binarizing system for picture processingInfo
- Publication number
- JPS63184886A JPS63184886A JP62016729A JP1672987A JPS63184886A JP S63184886 A JPS63184886 A JP S63184886A JP 62016729 A JP62016729 A JP 62016729A JP 1672987 A JP1672987 A JP 1672987A JP S63184886 A JPS63184886 A JP S63184886A
- Authority
- JP
- Japan
- Prior art keywords
- picture
- image
- density
- memory
- written
- 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
Links
- 238000000034 method Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 235000006732 Torreya nucifera Nutrition 0.000 description 1
- 244000111306 Torreya nucifera Species 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Landscapes
- Character Input (AREA)
- Image Input (AREA)
- Facsimile Image Signal Circuits (AREA)
Abstract
Description
【発明の詳細な説明】 〔概要） 〔産業上の利用分野〕 本発明は画像処理における画像の２値化方式に関する。[Detailed description of the invention] 〔overview) [Industrial application field] The present invention relates to an image binarization method in image processing.
画像処理は視覚認識において前処理として行われる。Image processing is performed as preprocessing in visual recognition.
この場合において農淡画像を直接扱うと計算量が増え処
理時間が増加する。また、視覚ｇ識には濃淡情報が直接
必要となる場合は少なく、図形の形や大きさ、線の曲が
り具合等の特徴的情報ｔ−２値画像から取りだして調べ
る処理が重要である。In this case, if the agricultural images are handled directly, the amount of calculation will increase and the processing time will increase. In addition, visual g-sensitivity rarely requires shading information directly, and it is important to extract and examine characteristic information such as the shape and size of figures, the degree of bending of lines, etc. from the t-binary image.
処理対象となる画像には様々な濃度から構成されており
、その中から認識の対象となる特定の濃度値を抽出する
方法が必要とされる。An image to be processed is composed of various densities, and a method is required to extract a specific density value to be recognized from among the images.
従来の２値化処理の方法を第４図に示す。 A conventional binarization processing method is shown in FIG.
第４図（ａ）図中３１は入力画像の濃度値、ｔは２値化
の基準となる闇値、第４図（ｂ）図中３２は２値化処理
後の出力画像の濃度値である。In Fig. 4(a), 31 is the density value of the input image, t is the darkness value which is the standard for binarization, and 32 in Fig. 4(b) is the density value of the output image after the binarization process. be.
従来の２値化処理は、入力画像をＦ＝（ｆｌｊ）。In conventional binarization processing, the input image is F=(flj).
出力画像ｆ：Ｇ＝（ｇｌｊ ）閾値１−１としたときと
表わされる。Output image f: is expressed as when G=(glj) threshold value 1-1.
以上の操作により、すべての濃度値を闇値を基準に白レ
ベル、黒レベルに分離する。Through the above operations, all density values are separated into white level and black level based on the darkness value.
従来の２値化方式は闇値以上の＃度と閾値未満の１１度
に分前しているため、処理対象となる画像が中間濃度で
あった場合、それ以上の濃度値の不用な画像を同時に抽
出してしまうといった問題を生じていた。Conventional binarization methods have a difference between # degrees above the dark value and 11 degrees below the threshold, so if the image to be processed has an intermediate density, unnecessary images with higher density values are removed. This caused the problem that they were extracted at the same time.
本発明の２値化方式を第１図に示す。図中１１は入力画
像の濃度値、ｔｌ、ｔＩはそれぞれ２値化の基準となる
閾値、１２は出力画像の濃度値、１３は抽出したい濃度
値を持つ画素である。FIG. 1 shows the binarization method of the present invention. In the figure, 11 is the density value of the input image, tl and tI are respectively threshold values serving as standards for binarization, 12 is the density value of the output image, and 13 is a pixel having the density value to be extracted.
本発明はｔ！以上かつｔ、以下の濃度とそれ以外の１１
１度を白レベル、黒レベルに分離する２値化方方式であ
る。The present invention is t! Concentrations greater than and equal to t, and other 11
This is a binarization method that separates each level into a white level and a black level.
入力画像ｔ−Ｆ＝（ｆｉｊ ） 、 ２つの閾値をそれ
ぞれｔｌ＋ｔ！＋出力画像ｔ−ｃ＝（ｇｉｊ）とし九と
き、次の操作により中間濃度値を抽出する。Input image t-F=(fij), two thresholds respectively tl+t! +Output image t-c=(gij) When 9, the intermediate density value is extracted by the following operation.
第２図は本発明の実施例である。第２図（ａ）図中２０
はＩＣのパッケージを撮像した入力画像、２１はパッケ
ージのベース、２２はＩＣのビン、２３はパッケージに
捺印された文字を示す、第２図（ｂ）図中２４は出力画
像である。FIG. 2 shows an embodiment of the invention. Figure 2 (a) 20 in the figure
21 is an input image taken of an IC package, 21 is the base of the package, 22 is an IC bottle, 23 is a character stamped on the package, and 24 is an output image in FIG. 2(b).
ここでパッケージのベース２１は濃度値が低く、ＩＣの
ビン２２は鏝度値が高くなりている。また、パッケージ
に捺印された文字２３はパッケージのベース２１とＩＣ
のビン２２の中間の濃度を持っている。Here, the base 21 of the package has a low concentration value, and the IC bottle 22 has a high strength value. In addition, the characters 23 stamped on the package are the base 21 of the package and the IC.
It has an intermediate density of bin 22.
このとき、本発明の方式によりｚ値化処理全行えば、パ
ッケージに捺印された文字２３のみを抽出することがで
きる。At this time, if all z-value processing is performed using the method of the present invention, only the characters 23 stamped on the package can be extracted.
また、従来の方式で閾値１−１１ として２値化した場
合にはパッケージに捺印された文字２３と同時にＩＣの
ビン２２も抽出されるため、ＩＣのビン２２の出力画（
／１ｆｉ−除去する処理が必要となる。Furthermore, when binarizing with a threshold of 1-11 using the conventional method, the IC bin 22 is also extracted at the same time as the characters 23 stamped on the package, so the output image of the IC bin 22 (
/1fi-removal processing is required.
＃実宴樗キ
１４３図は本発明の一実施例による文字判定装置のプロ
、り図である。Figure 143 is a professional diagram of a character determination device according to an embodiment of the present invention.
図中、（Ｊｌ）はＣＣＤカメラ、伽）はＡ／Ｄ変換器、
（ｃ）は画像メモリ、（ｄ）は辞書と画像データとを比
較する比較器であり、（・）はその辞書メモリである。In the figure, (Jl) is a CCD camera, 伽) is an A/D converter,
(c) is an image memory, (d) is a comparator that compares the dictionary and image data, and (.) is the dictionary memory.
画像メモリは（ｆ）のダイレクトメモリーアクセス器に
よって、本発明に基づく二値化器（２））より出力され
た二値化データを書き込んでいる。The image memory is written with the binarized data output from the binarizer (2) based on the present invention by the direct memory access unit (f).
ＣＣＤカメラ（１）で撮像した画像信号をＡ／Ｄ変換器
缶）によりてディジタル化し、これを本発明を用い九二
値化器（ｘ）によって必要な画像だけを取抄出す。これ
をダイレクトメモリーアクセス器で画像メモリ（ｃ）へ
書き込む。書き込まれた画像データと辞書メモリ（＠）
の内容とを比較器（ｄ）で比較することによ妙辞臀メモ
リに記憶している文字かを判定する。An image signal captured by a CCD camera (1) is digitized by an A/D converter (can), and only necessary images are extracted by a nine-binarizer (x) using the present invention. This is written into the image memory (c) using a direct memory access device. Written image data and dictionary memory (@)
The comparator (d) compares the characters with the contents of the text to determine whether the characters are stored in the memory.
（ｈ）はＣＰＵのパスでありダイレクトメモリーアクセ
ス器（ｆ）１画像メモリ（Ｃ）、比較器（ｄ）、中央処
理装置ＣＰＵ等の各機能部の間でデータや命令の授受を
行うための共通の転送路である。(h) is the path of the CPU, which is used to exchange data and instructions between each functional unit such as the direct memory access device (f), the image memory (C), the comparator (d), and the central processing unit CPU. It is a common transfer path.
（発明の効果〕
本発明によれば、不用な画像を簡単に除去することが可
能となり、画像処理アルゴリズムを簡略化できる。(Effects of the Invention) According to the present invention, unnecessary images can be easily removed, and image processing algorithms can be simplified.
第１図（ａ）（ｂ）は本発明の詳細な説明する図、第２
図（ａ）（ｂ）は本発明の実施例を示す図、第３図は本
発明の実施例による文字判定装置のプロ、り図、第４図
（ａ）（ｂ）は従来の原理を説明する図工ある。
２１：ＩＣバ、ケージのベース、
２２：ＩＣバ、ケージのビン、
２３：ＩＣバ、ケージに捺印された文字。
代理人弁理上 井 桁 貞 −゛、 ′（ｅｌ
茅３ 図
第４図FIGS. 1(a) and 1(b) are diagrams explaining the present invention in detail, and FIG.
Figures (a) and (b) are diagrams showing an embodiment of the present invention, Figure 3 is a professional diagram of a character recognition device according to an embodiment of the present invention, and Figures 4 (a) and (b) are diagrams showing the conventional principle. There are illustrations to explain. 21: IC bar, base of cage, 22: IC bar, bottle of cage, 23: IC bar, characters stamped on cage. Attorney Patent Attorney Sada Igeta -゛、'(el Kaya 3 Figure 4)
Claims (1)
換を行い、処理対象画像を抽出することを特徴とする画
像処理における２値化方式。A binarization method in image processing characterized by performing density conversion on a grayscale image based on two threshold values in image processing and extracting a processing target image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP62016729A JPS63184886A (en) | 1987-01-27 | 1987-01-27 | Binarizing system for picture processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP62016729A JPS63184886A (en) | 1987-01-27 | 1987-01-27 | Binarizing system for picture processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| JPS63184886A true JPS63184886A (en) | 1988-07-30 |
Family
ID=11924350
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP62016729A Pending JPS63184886A (en) | 1987-01-27 | 1987-01-27 | Binarizing system for picture processing |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JPS63184886A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04343249A (en) * | 1991-05-20 | 1992-11-30 | Disco Abrasive Syst Ltd | Image processing system and camera means |
| JP2009124715A (en) * | 1998-11-09 | 2009-06-04 | Silverbrook Research Pty Ltd | Dither unit, and halftone method |
-
1987
- 1987-01-27 JP JP62016729A patent/JPS63184886A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04343249A (en) * | 1991-05-20 | 1992-11-30 | Disco Abrasive Syst Ltd | Image processing system and camera means |
| JP2009124715A (en) * | 1998-11-09 | 2009-06-04 | Silverbrook Research Pty Ltd | Dither unit, and halftone method |
| JP2009188985A (en) * | 1998-11-09 | 2009-08-20 | Silverbrook Research Pty Ltd | System for multiple simultaneous access to resource held in computer memory, and method for operating same |
| JP4621766B2 (en) * | 1998-11-09 | 2011-01-26 | シルバーブルック リサーチ プロプライエタリイ、リミテッド | Halftoning method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2940936B2 (en) | Tablespace identification method | |
| KR880702027A (en) | Binarization processing method for images with multiple luminance levels | |
| JP2004272798A (en) | Image reading device | |
| JP2004280334A (en) | Image reading device | |
| JPS63184886A (en) | Binarizing system for picture processing | |
| JPS61193277A (en) | Document reader | |
| JP2548386B2 (en) | License plate usage code recognition method | |
| JP3850488B2 (en) | Character extractor | |
| JPH08123901A (en) | Character extraction device and character recognition device using this device | |
| JP2590099B2 (en) | Character reading method | |
| JP2795860B2 (en) | Character recognition device | |
| JPS62147584A (en) | Character reader | |
| JPS62221783A (en) | Area extracting system | |
| JP2853140B2 (en) | Image area identification device | |
| JPS62247473A (en) | Picture processor | |
| JPH11306282A (en) | Method and device for extracting character string area | |
| Nakao et al. | Product Discrimination system using deep learning | |
| JP2001175808A (en) | Image processor and computer-readable recording medium with recorded image processing program | |
| JPH04142676A (en) | Binary image conversion method | |
| JPH0660220A (en) | Area extracting method for document image | |
| JP2004240500A (en) | Device and program for processing image, and storing medium | |
| JP2963807B2 (en) | Postal code frame detector | |
| JPS62160593A (en) | Character reader | |
| JPH03188587A (en) | Binarizing system | |
| JPH0652355A (en) | Character segmenting and character recognizing device |