JPH05242221A - Method for constituting inspection picture data base of building material - Google Patents

Method for constituting inspection picture data base of building material

Info

Publication number
JPH05242221A
JPH05242221A JP4045022A JP4502292A JPH05242221A JP H05242221 A JPH05242221 A JP H05242221A JP 4045022 A JP4045022 A JP 4045022A JP 4502292 A JP4502292 A JP 4502292A JP H05242221 A JPH05242221 A JP H05242221A
Authority
JP
Japan
Prior art keywords
picture data
inspection
memory
inspection picture
building material
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
JP4045022A
Other languages
Japanese (ja)
Inventor
Yoshisuke Watanabe
義介 渡邊
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.)
Kubota Corp
Original Assignee
Kubota 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 Kubota Corp filed Critical Kubota Corp
Priority to JP4045022A priority Critical patent/JPH05242221A/en
Publication of JPH05242221A publication Critical patent/JPH05242221A/en
Pending legal-status Critical Current

Links

Landscapes

  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Image Analysis (AREA)
  • Processing Or Creating Images (AREA)
  • Image Processing (AREA)

Abstract

PURPOSE:To cope with constitution of a data base with a small-capacity memory and to simplify the retrieval work during preservation by classifying inspection picture data into plural items and compressing pictures to store them. CONSTITUTION:Inspection picture data from picture processors 3A and 3B are stored in a memory 5 through a host computer 4. In this case, the host computer 4 takes in inspection picture data and classifies these inspection picture data to prescribed items. For example, in the case of the existence of a break of a 'Colorbest-M(R)' in inspection picture data, the break is extracted as the feature quantity, and an optimum classification directory (register address) of the memory 5 is selected by this feature quantity. Further, inspection picture data is subjected to picture (data) processing and is stored and reserved in the pertinent classification directory of the memory 5, thus constituting the data base.

Description

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

【0001】[0001]

【産業上の利用分野】本発明は、カラーベストや瓦のよ
うに一定形状に製作されている屋根材や壁材等の建材の
欠けの有無を判別する際に用いられる建材の検査画像デ
ータベースの構築方法に関する。
BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an inspection image database for building materials used to determine whether or not there is a lack of building materials such as roofing materials and wall materials manufactured in a fixed shape such as color vests and roof tiles. Regarding the construction method.

【0002】[0002]

【従来の技術】一般に、建材、たとえばカラーベストの
製造工程では、40m/分程度で順次搬送されるカラー
ベストに対して作業者が目視検査により欠けの有無の判
別を行なっていたが、これは極めて非能率的である。こ
のため、最近では、上記搬送されるカラーベストを撮影
装置、たとえばCCDカメラで撮影し、このCCDカメ
ラからの画像を画像処理装置により、画像処理するとと
もに、カラーベストの画像を構成する画素数(面積)と
基準画素数(基準面積)とを比較して欠けの有無を自動
的に判別する方法が開発されている。
2. Description of the Related Art Generally, in a manufacturing process of building materials, for example, color vests, an operator visually checks the color vests sequentially conveyed at a rate of about 40 m / min to determine whether or not there is a chip. It is extremely inefficient. Therefore, recently, the conveyed color vest is photographed by a photographing device, for example, a CCD camera, and the image from the CCD camera is image-processed by an image processing device, and the number of pixels forming the color vest image ( A method has been developed in which the area is compared with a reference number of pixels (reference area) to automatically determine the presence or absence of a chip.

【0003】[0003]

【発明が解決しようとする課題】ところで、このような
検査において、検査画像データを検査ライン毎や欠けの
種別毎に項分けしてデータベース化しておけば、不良原
因を統計的に分析したり、その分析結果を建材の製造工
程にフィードバックして品質保証体制の強化を図ったり
する際の資料として有用である。しかし、従来では、検
査時の画像データをそのまま記憶させているだけである
ので、検査画像データベースを構築するには、大容量の
メモリを必要となる。すなわち、検査画像データは非常
にデータ容量が大きく、たとえば1枚の検査画像データ
で、512×512=262144バイトの容量が必要
で、1枚のフロッピーディスクでも、5枚の画像データ
しか記憶させることができず、したがって、検査画像デ
ータの効率的な保存・検索が行なえないのが現状であ
る。
By the way, in such an inspection, if the inspection image data is divided into a database for each inspection line or each type of chip, it is possible to analyze the cause of the defect statistically, It is useful as a material when the analysis results are fed back to the building material manufacturing process to strengthen the quality assurance system. However, conventionally, since the image data at the time of inspection is simply stored as it is, a large-capacity memory is required to construct the inspection image database. That is, the inspection image data has a very large data capacity, for example, one inspection image data needs a capacity of 512 × 512 = 262144 bytes, and one floppy disk can store only five image data. Therefore, it is the current situation that inspection image data cannot be efficiently stored and retrieved.

【0004】本発明は上記実情に鑑みてなされたもの
で、検査画像データを小容量のメモリに記憶・保存する
ことができ、検索も容易な建材の検査画像データベース
の構築方法を提供することを目的としている。
The present invention has been made in view of the above circumstances, and it is an object of the present invention to provide a method for constructing an inspection image database of a building material, which allows inspection image data to be stored / stored in a small-capacity memory and can be easily searched. Has an aim.

【0005】[0005]

【課題を解決するための手段】上記目的を達成するため
に本発明は、一方向へ搬送される建材を撮影する撮影装
置からの画像を処理して該建材の欠けの有無を判別する
際に、検査画像データを複数の所定項目に分類するとと
もに、画像圧縮を行なってメモリに対して該当する項目
毎に記憶させるようにしたものである。
In order to achieve the above object, the present invention provides a method for processing an image from a photographing device for photographing a building material conveyed in one direction to determine whether or not the building material is chipped. The inspection image data is classified into a plurality of predetermined items, and the image is compressed and stored in the memory for each corresponding item.

【0006】[0006]

【作用】上記構成により、検査画像データが複数の項目
に分類されるとともに、画像圧縮されて記憶されるの
で、小容量のメモリで対応でき、保存中の検索作業も簡
易に行なえる。
With the above construction, the inspection image data is classified into a plurality of items, and the images are compressed and stored. Therefore, a small-capacity memory can be used, and the search operation during storage can be easily performed.

【0007】[0007]

【実施例】以下、本発明の一実施例を図面にしたがって
説明する。図1は本発明の一実施例による建材の検査デ
ータベースの構築方法が適用される建材の欠け判別検査
工程の概略説明図である。
DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below with reference to the drawings. FIG. 1 is a schematic explanatory view of a building material defect determination inspection process to which a method of constructing a building material inspection database according to an embodiment of the present invention is applied.

【0008】図1において、1(1A,1B)は、建材
としてのカラーベストMを一方向へ一定速度で搬送させ
る複数ラインの搬送体、たとえばベルトコンベア、2
(2A,2B)は上記両コンベア1上の各カラーベスト
Mを撮影する複数の撮影装置としてCCDカメラであ
る。3(3A,3B)は上記各CCDカメラ2からの画
像を処理して、その画素数と基準画素数とを比較してカ
ラーベストMの欠けの有無を判別する画像処理装置であ
る。
In FIG. 1, reference numeral 1 (1A, 1B) denotes a plurality of lines of conveying bodies for conveying the color vest M as a building material in one direction at a constant speed, for example, a belt conveyor, 2
(2A, 2B) are CCD cameras as a plurality of photographing devices for photographing the color vests M on both the conveyors 1. An image processing device 3 (3A, 3B) processes the image from each CCD camera 2 and compares the number of pixels with the reference number of pixels to determine whether or not the color vest M is missing.

【0009】上記各画像処理装置3からの検査画像デー
タはホストコンピュータ4を介してメモリ5に記憶させ
る。この場合、ホストコンピュータ4では、図2のよう
に検査画像データを取り込み(ステップS1)、この検
査画像データから所定の項目に分類する。たとえば、検
査画像データでカラーベストMに欠けが存在しているも
のでは、欠けを特徴量として抽出し(ステップS2)、
この特徴量からメモリ5の最適な分類ディレクトリー
(登録番地)を選択する(ステップS3)。さらに、上
記検査画像データを画像(データ)圧縮してメモリ5の
該当する分類ディレクトリーに記憶・保存させてデータ
ベースを構築する。画像データの項目は、欠けの特徴量
によるものだけでなく、カラーベストMの不良品を検査
ライン毎や日付毎に分類することも並行して行なうとよ
い。
The inspection image data from each image processing apparatus 3 is stored in the memory 5 via the host computer 4. In this case, the host computer 4 takes in the inspection image data as shown in FIG. 2 (step S1) and classifies the inspection image data into predetermined items. For example, in the inspection image data in which the color best M has a defect, the defect is extracted as a feature amount (step S2),
The optimum classification directory (registered address) of the memory 5 is selected from this feature amount (step S3). Further, the inspection image data is image (data) compressed and stored / stored in a corresponding classification directory of the memory 5 to construct a database. The items of the image data are not limited to those based on the missing feature amount, and it is preferable to classify the defective products of the color vest M for each inspection line or each date in parallel.

【0010】上記のように、データベースを構築する際
に検査画像データを複数項目に分類するとともに、画像
圧縮して記憶させるので、ビット数が低減され、小容量
のメモリ5でデータ保存に対応することができる。ま
た、検査画像データの保存後に、このデータを読み出し
て歩留り等の分析を行ないたい場合には、上記検査画像
データを伸張させればよいので、その検索も簡単に行な
える。
As described above, when the database is constructed, the inspection image data is classified into a plurality of items, and the image is compressed and stored. Therefore, the number of bits is reduced, and the memory 5 having a small capacity can store the data. be able to. Further, when it is desired to read out the inspection image data and analyze the yield after storing the inspection image data, the inspection image data can be expanded so that the retrieval can be easily performed.

【0011】[0011]

【発明の効果】以上のように本発明によれば、建材の欠
けの有無を判別する際の検査画像データを複数の所定項
目に分類するとともに、画像圧縮を行なって該当項目に
記憶させるようにしたので、メモリ容量の増大化が抑制
されて検査画像データの検索や分析を効率的に行なえ、
高度の品質保証体制を確立することが可能となる。
As described above, according to the present invention, the inspection image data for determining the presence / absence of a chip in the building material is classified into a plurality of predetermined items, and the image is compressed and stored in the corresponding item. As a result, the increase in memory capacity is suppressed, and inspection image data can be searched and analyzed efficiently,
It is possible to establish a high quality assurance system.

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

【図1】本発明の一実施例による建材の検査データベー
スの構築方法が適用される建材の欠け判別検査工程の概
略説明図である。
FIG. 1 is a schematic explanatory diagram of a building material defect determination inspection process to which a method for building a building material inspection database according to an embodiment of the present invention is applied.

【図2】検査画像のデータベースの構築法の一例を示す
ブロック図である。
FIG. 2 is a block diagram showing an example of a method of constructing a database of inspection images.

【符号の説明】[Explanation of symbols]

2A,2B 撮影装置 3A,3B 画像処理装置 5 メモリ 2A, 2B Imaging device 3A, 3B Image processing device 5 Memory

Claims (1)

【特許請求の範囲】[Claims] 【請求項1】 一方向へ搬送される建材を撮影する撮影
装置からの画像を処理して該建材の欠けの有無を判別す
る際に、検査画像データを複数の所定項目に分類すると
ともに、画像圧縮を行なってメモリに対して該当する項
目毎に記憶させることを特徴とする建材の検査画像デー
タベースの構築方法。
1. Inspection image data is classified into a plurality of predetermined items when an image from a photographing device that photographs a building material conveyed in one direction is processed to determine whether or not the building material has a chip, and the image is classified into a plurality of predetermined items. A method for constructing an inspection image database of a building material, which is characterized by compressing and storing each corresponding item in a memory.
JP4045022A 1992-03-03 1992-03-03 Method for constituting inspection picture data base of building material Pending JPH05242221A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP4045022A JPH05242221A (en) 1992-03-03 1992-03-03 Method for constituting inspection picture data base of building material

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP4045022A JPH05242221A (en) 1992-03-03 1992-03-03 Method for constituting inspection picture data base of building material

Publications (1)

Publication Number Publication Date
JPH05242221A true JPH05242221A (en) 1993-09-21

Family

ID=12707714

Family Applications (1)

Application Number Title Priority Date Filing Date
JP4045022A Pending JPH05242221A (en) 1992-03-03 1992-03-03 Method for constituting inspection picture data base of building material

Country Status (1)

Country Link
JP (1) JPH05242221A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2002023480A1 (en) * 2000-09-18 2002-03-21 Olympus Optical Co., Ltd. System and method for managing image data file

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2002023480A1 (en) * 2000-09-18 2002-03-21 Olympus Optical Co., Ltd. System and method for managing image data file
JPWO2002023480A1 (en) * 2000-09-18 2004-01-22 オリンパス株式会社 Image data file management system and method
US7289660B2 (en) 2000-09-18 2007-10-30 Olympus Optical Co., Ltd. Image data file management system and method

Similar Documents

Publication Publication Date Title
WO2004036197A1 (en) Glass bottle inspection device
WO2006012194B1 (en) Method and apparatus for monitoring and detecting defects in plastic package sealing
KR100319469B1 (en) Image Processing Apparatus
US20020009218A1 (en) Directional lighting and method to distinguish three dimensional information
JP2002214153A (en) Foreign matter inspecting device and method in liquid filled vessel
JPH05242221A (en) Method for constituting inspection picture data base of building material
CN108615232A (en) Detection method, device and the detection platform of enamel coating defect
CN113518998B (en) Counting system, counting device, machine learning device, counting method, component arrangement method, and recording medium
US20230152781A1 (en) Manufacturing intelligence service system connected to mes in smart factory
CN115138596A (en) Visual detection method and device
JP2000118637A (en) Entry for storing device to decide item in accordance with shape of entered article
JP2605581B2 (en) How to discharge falling cans, etc.
JPH06294633A (en) Method and equipment for automatically inspecting fastener
CN111553911A (en) Global positioning method and device for industrial particle continuous product
JP3174732B2 (en) Classification equipment
JPH04364449A (en) Fruit defect detecting apparatus
JPH0767577B2 (en) Sheet metal processing line system
WO2006013563A2 (en) A system for distributing objects
JPH0886621A (en) Method for inspecting appearance of construction material
JPH02303579A (en) Method and apparatus for discriminating color of vegetables and fruit
JPH06102204A (en) Inspecting method for construction material
JPH0785253A (en) Conveyance processing system
JP3003229B2 (en) Work posture determination method
CN116993701A (en) Image processing and counting method and system for battery piece and tablet machine
JP2001148013A (en) Device for inspecting quality by image