JP2001022929A - Method and device for detecting colony microorganism - Google Patents

Method and device for detecting colony microorganism

Info

Publication number
JP2001022929A
JP2001022929A JP11192494A JP19249499A JP2001022929A JP 2001022929 A JP2001022929 A JP 2001022929A JP 11192494 A JP11192494 A JP 11192494A JP 19249499 A JP19249499 A JP 19249499A JP 2001022929 A JP2001022929 A JP 2001022929A
Authority
JP
Japan
Prior art keywords
hue
microorganism
microorganisms
edge
image
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Withdrawn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
JP11192494A
Other languages
Japanese (ja)
Inventor
Makoto Niwakawa
誠 庭川
Masahide Ichikawa
雅英 市川
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.)
Meidensha Corp
Meidensha Electric Manufacturing Co Ltd
Original Assignee
Meidensha Corp
Meidensha Electric Manufacturing Co Ltd
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 Meidensha Corp, Meidensha Electric Manufacturing Co Ltd filed Critical Meidensha Corp
Priority to JP11192494A priority Critical patent/JP2001022929A/en
Publication of JP2001022929A publication Critical patent/JP2001022929A/en
Withdrawn legal-status Critical Current

Links

Classifications

    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02WCLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
    • Y02W10/00Technologies for wastewater treatment
    • Y02W10/10Biological treatment of water, waste water, or sewage

Abstract

PROBLEM TO BE SOLVED: To count microorganisms having a characteristic shape such as a circular shape, a curved shape and a linear shape which are to become a colony. SOLUTION: The microscopic image of a microorganism is fetched, a hue being close to a circular microorganism is extracted from an input image, by using a hue model for the circular microorganism and is made variable density, so as to easily detect a change point (S11 to S13). The changed point (edge) of variable density is extracted, by performing second derivative of the variable density for every pixel (S14), a circle or a circular arc composed of three points being endpoints and a midpoint of an edge point detected as a point sequence, and the color components of an area in the circular arc are taken by each pixel (S15). The upper and lower limit allowable values of the average value of hue of an erroneous area are calculated, the area (area of characteristic microorganism) A of the hues of an input image entered within the allowable range of the average value of the hue is calculated (S16), the area A and the single body area (a) of the microorganism are acquired experimentally, and the number of microorganisms is calculated, by using a coefficient (k) compensating the thickness of the microorganisms (S17).

Description

【発明の詳細な説明】DETAILED DESCRIPTION OF THE INVENTION

【0001】[0001]

【発明の属する技術分野】この発明は、顕微鏡による微
生物の観察を画像処理で自動化した、特に群体になる微
生物の検出をする群体微生物検出方法および装置に関す
るものである。
BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method and an apparatus for detecting microbial organisms, in which microbial observation by a microscope is automated by image processing, particularly for detecting microbial organisms.

【0002】[0002]

【従来の技術】画像処理技術によって微生物を観察し、
その出現個数を出力する装置として「ろ過障害微生物監
視装置」(特願平8−180250)がある。
2. Description of the Related Art Microorganisms are observed by image processing technology,
As a device for outputting the number of appearances, there is a "filtration-failure microorganism monitoring device" (Japanese Patent Application No. 8-180250).

【0003】上記装置は浄水場の流入水や着水井の原水
を、装置水槽に導入し、またはサンプリングしてプレパ
ーラートを作成し、顕微鏡ITVカメラによって撮像す
る。そして藻類などの微生物を顕微鏡画像から画像処理
手法の「モデルベーストマッチング方式」を用いて固定
し微生物を検出し、微生物数の計数を行うものである。
水質管理のため、従来人手によって目視計数されていた
微生物の監視作業がこの装置により自動化された。
[0003] In the above-mentioned apparatus, inflow water from a water purification plant and raw water from a landing well are introduced into a water tank of the apparatus or sampled to prepare a preparation, which is imaged by a microscope ITV camera. Then, microorganisms such as algae are fixed from the microscope image using a “model-based matching method” of an image processing method, the microorganisms are detected, and the number of microorganisms is counted.
In order to control water quality, the monitoring work of microorganisms, which has been visually counted manually, has been automated by this apparatus.

【0004】モデルベーストマッチング方式はあらかじ
め微生物の形状をモデルとして登録しておき、検出時に
は顕微鏡画像にエッジ検出と特徴抽出を行って、円弧群
や直線群を抽出する。そしてこれら円弧・直線群とモデ
ルとのマッチングによりモデルと一致する微生物を検出
するものである。
In the model-based matching method, the shape of a microorganism is registered in advance as a model, and at the time of detection, edge detection and feature extraction are performed on a microscope image to extract a group of arcs and lines. Then, by matching the group of arcs and straight lines with the model, microorganisms that match the model are detected.

【0005】上記モデルベーストマッチング方式の処理
手順を図15に示す。画像入力処理(S101)では顕
微鏡ITVカメラからのモノクロ濃淡画像を取り込む。
エッジ検出処理(S102)では、入力画像から輝度が
大きく変化する点の集合(エッジ)を抽出する。エッジ
抽出法として、例えばガウス分布関数で重み付けした平
滑化二次微分法を使用するとノイズに強く、入力画像の
輝度の変化に影響されないエッジ検出が可能である。次
に、エッジ画像の特徴抽出処理(S103)では、抽出
したエッジ画像から直線成分と同弧成分を抽出し、これ
ら成分の集合をエッジ画像の特徴データとする。
FIG. 15 shows a processing procedure of the model-based matching method. In the image input process (S101), a monochrome gray-scale image from the microscope ITV camera is captured.
In the edge detection processing (S102), a set (edge) of points where the luminance changes greatly is extracted from the input image. As an edge extraction method, for example, when a smoothed second derivative method weighted by a Gaussian distribution function is used, it is possible to detect an edge which is resistant to noise and is not affected by a change in luminance of an input image. Next, in the feature extraction process of the edge image (S103), straight-line components and arc components are extracted from the extracted edge image, and a set of these components is used as feature data of the edge image.

【0006】特徴マッチング処理(S104)では、予
め登録された微生物種の特徴モデル(内部モデル)と特
徴抽出処理(S103)で抽出した特徴データとの照合
(マッチング)を行い、入力画像中に撮影された微生物
種を特定し、その個数を認識する。
[0006] In the feature matching process (S104), the feature model (internal model) of the microorganism species registered in advance is compared (matched) with the feature data extracted in the feature extraction process (S103), and photographing is performed in the input image. The identified microorganism species is identified and its number is recognized.

【0007】モデル作成処理(S105)は、既知の微
生物種を対象として処理(S101〜S103)の処理
を予め行い、当該微生物種を円弧の成分の集合になる内
部モデルとしてそれぞれ作成・登録しておく。
In the model creation process (S105), the processes (S101 to S103) are performed in advance for known microorganism species, and the microorganism species is created and registered as an internal model which is a set of arc components. deep.

【0008】以上の処理になるモデルベーストマッチン
グ方式による微生物種の同定は、直線と円弧の集合とな
る特徴データと内部モデルとの照合になり、微生物種の
移動や変形等がある場合等においても認識が可能とな
る。
The identification of the microorganism species by the model-based matching method as described above is performed by collating the feature data, which is a set of straight lines and circular arcs, with the internal model. Recognition becomes possible.

【0009】このモデルベーストマッチング方式による
と、エッジ情報を利用した画像処理なので、一般的な画
像処理で使用されている二値化処理やパターンマッチン
グ処理に比べ、輝度の変化や背景の変化に影響されにく
い利点がある。また、現場の微生物から現物あわせでモ
デルを作製するため、微生物の見え方の変化などの現場
の環境に適応できる特徴がある。
According to this model-based matching method, since image processing is performed using edge information, it is more influential on luminance changes and background changes than binarization processing and pattern matching processing used in general image processing. There is an advantage that is hard to be. In addition, since the model is created from the microorganisms at the site, the characteristics can be adapted to the environment at the site, such as changes in the appearance of the microorganisms.

【0010】[0010]

【発明が解決しようとする課題】微生物には単体で生息
する種と、群体で生息する種がある。単体で存在する場
合、上記特願平8−180250の技術により微生物を
検出することができる。しかしながら群体で存在する場
合、微生物の検出ができなくなる問題がある。この原因
は、微生物が群体になると厚みができる。この厚みが顕
微鏡の焦点深度以上になると、焦点が合わずその部分が
惚るためである。
SUMMARY OF THE INVENTION Microorganisms include species that live alone and species that live in communities. When present alone, microorganisms can be detected by the technique of Japanese Patent Application No. 8-180250. However, when present in a colony, there is a problem that detection of microorganisms becomes impossible. The cause is that when the microorganisms are colonized, they become thicker. This is because if the thickness exceeds the depth of focus of the microscope, the part is out of focus and the part falls in love.

【0011】近年焦点深度の長い顕微鏡が開発されつつ
あるが、顕微鏡の高倍率化とのトレードオフの関係にあ
り、一般に高倍率の顕微鏡は、焦点深度が短い。
In recent years, microscopes with a long depth of focus have been developed. However, there is a trade-off relationship with increasing the magnification of the microscope, and a microscope with a high magnification generally has a short depth of focus.

【0012】したがって、特に小さな微生物が群体にな
る場合、焦点が合わない部分ができ微生物を正確に計数
できない問題がある。
[0012] Therefore, particularly when small microorganisms form a colony, there is a problem that a portion that is out of focus is formed and the microorganisms cannot be accurately counted.

【0013】この発明は、上記課題に鑑みてなされたも
のであり、その目的とするところは、群体になる円形状
又はカーブ状又は直線状の形状をした微生物を計数する
ことができる群体微生物検出方法および装置を提供する
ことにある。
SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and has as its object to detect a colony microorganism capable of counting microorganisms having a circular, curved, or linear shape. It is to provide a method and an apparatus.

【0014】[0014]

【課題を解決するための手段】この発明の群体微生物検
出方法は、画像入力素子より取り込んだ群体微生物入力
画像から検出対象とする円弧状又はカーブ状又は直線状
等の特徴を持った微生物の色相モデルに近い色相を抽出
し、抽出した色相を濃淡化した後エッジ処理して濃淡の
変化するエッジを抽出し、抽出したエッジの中から前記
検出対象微生物の特徴形状のエッジを求め、前記特徴形
状エッジ間の領域における色相平均の許容値を計算し、
前記入力画像から色相平均の許容値内にある微生物領域
を抽出し、前記微生物領域と検出対象微生物の単体面積
および実験的に得た微生物の厚み補償係数から検出対象
微生物数を計算により求めるものである。
SUMMARY OF THE INVENTION A method for detecting microbial microorganisms according to the present invention comprises the steps of: detecting a hue of a microorganism having an arc-shaped, curved or linear characteristic to be detected from a colony-microorganism input image captured from an image input device; A hue close to the model is extracted, and the extracted hue is shaded and then subjected to edge processing to extract an edge of varying shades, and from the extracted edges, an edge of the feature shape of the microorganism to be detected is obtained, and the feature shape is determined. Calculate the tolerance of hue average in the area between edges,
A microbial region that is within the permissible value of the hue average is extracted from the input image, and the number of the detection target microorganisms is calculated from the simplex area of the microorganism region and the detection target microorganism and the thickness compensation coefficient of the microorganism obtained experimentally. is there.

【0015】また、この発明の群体微生物検出装置は、
顕微鏡ITVカメラで撮影された画像を取り込む画像取
り込み手段と、この入力画像から検出対象とする円弧状
又はカーブ状又は直線状等の特徴を持った微生物の色相
モデルに近い色相を抽出する手段と、前記抽出した色相
を濃淡化する手段と、前記濃淡化された画像を画素毎に
二次微分演算して濃淡の変化するエッジを検出し、エッ
ジの中から前記検出対象微生物の特徴形状のエッジを抽
出する手段と、前記特徴形状エッジの間の領域における
色相平均の許容値を計算し、前記入力画像の色相平均の
許容値内にある微生物領域を抽出する手段と、前記微生
物領域と円弧状微生物の単体面積および実験的に得た微
生物の厚み補償係数から前記対象微生物数を計算する個
体数計算手段とを有するものである。
Further, the colony microorganism detecting apparatus of the present invention comprises:
Image capturing means for capturing an image captured by a microscope ITV camera; and means for extracting a hue close to a hue model of a microorganism having a characteristic such as an arc, a curve, or a straight line from the input image, Means for shading the extracted hue, and performing a second derivative operation on each of the shaded images to detect an edge whose shading changes, and among the edges, the edge of the characteristic shape of the microorganism to be detected. Means for extracting, calculating a permissible value of the hue average in the region between the feature shape edges, and means for extracting a microbial region within the permissible value of the hue average of the input image; and And a number calculating means for calculating the number of target microorganisms from the simplex area and the thickness compensation coefficient of the microorganisms obtained experimentally.

【0016】[0016]

【発明の実施の形態】実施例1(円弧による群体微生物
検出装置) この方式は、上記[発明が解決しようとする課題]であ
る微生物を顕微鏡ITVカメラによって撮った焦点の合
わない部分のある顕微鏡画像から微生物の個体数を計数
するため、焦点の合っている円弧状の特徴を持つ微生物
を検出し、その微生物の占める領域から群体全体の微生
物数を推定するものである。推定した微生物数データは
ベース化したり、上位装置や後段の処理装置へ渡され
る。
DESCRIPTION OF THE PREFERRED EMBODIMENTS Embodiment 1 (Apparatus for Detecting Microorganisms Using Arcs) This system uses a microscope having an out-of-focus portion obtained by photographing a microorganism, which is the above-mentioned problem to be solved by the microscope, with a microscope ITV camera. In order to count the number of microorganisms from an image, microorganisms having arc-shaped features that are in focus are detected, and the number of microorganisms in the entire colony is estimated from the area occupied by the microorganisms. The estimated microorganism count data is converted to a base or passed to a host device or a subsequent processing device.

【0017】図1に実施例1にかかる群体微生物検出装
置のブロック構成図を示す。図1について、画像取り込
み手段1は顕微鏡ITVカメラで撮った顕微鏡画像(図
4)を画像入力素子等により取り込む。色相抽出手段2
は入力画像を色相の3値(H、S、L)に変換し、この
色相を対象微生物の色相モデルと比較して入力画像の対
象する微生物に近い色相だけを抽出する。色相濃淡化手
段3はこの抽出した色相を濃淡化する。
FIG. 1 is a block diagram showing a colony microorganism detecting apparatus according to the first embodiment. Referring to FIG. 1, an image capturing means 1 captures a microscope image (FIG. 4) taken by a microscope ITV camera using an image input device or the like. Hue extraction means 2
Converts the input image into ternary hues (H, S, L), compares the hue with the hue model of the target microorganism, and extracts only the hue close to the target microorganism in the input image. Hue shading means 3 shades the extracted hue.

【0018】円弧抽出手段4aは、上記濃淡化した画像
をエッジ処理し画像のエッジを抽出し、このエッジを円
弧近似により円または円弧を抽出し円弧(図5)を求め
る。円弧間の色抽出手段5aは抽出された円弧の接線間
に囲まれた斜線領域(図3)を求め、斜線領域の色相の
平均値を計算する。
The arc extracting means 4a performs edge processing on the gray-scaled image to extract an edge of the image, and extracts a circle or an arc from the edge by arc approximation to obtain an arc (FIG. 5). The color extracting means 5a between the arcs obtains a shaded area (FIG. 3) surrounded between the tangents of the extracted arcs, and calculates the average value of the hues of the shaded area.

【0019】領域A抽出手段6は色相の下限許容値と上
限許容値を計算し、上記入力画像の色相と比較し、許容
値内に入っている色相の領域、即ち対象微生物の存在す
る領域Aを求める。個体数計算手段7は領域Aと微生物
の単体面積aおよび計数hから微生物数を計算し微生物
数を推定する。このデータは出力手段8を介して上位装
置等に渡される。
The area A extraction means 6 calculates the lower limit and the upper limit of the hue, compares the calculated hue with the hue of the input image, and determines the area of the hue within the allowable value, that is, the area A where the target microorganism exists. Ask for. The population calculation means 7 estimates the number of microorganisms by calculating the number of microorganisms from the region A, the single area a of the microorganisms, and the count h. This data is passed to the host device via the output means 8.

【0020】上記実施例1の動作を図2を用いて詳細に
説明する。ステップS11で画像取り込み手段1が顕微
鏡画像を取り込み、ステップS12で色相抽出手段2が
色相を抽出する。この色相の抽出方法について説明する
(図7)。まずオフラインで対象とする微生物に近い色
相の下限許容値(HL、SL、IL)と上限許容値(HH
H、IH)を実験的に取得し、色相モデルとする。そし
てオンラインで入力画像の色相が許容値内であれば通過
させ、対象とする微生物に近い色相だけ抽出する。次に
ステップS13で色相濃淡化手段3が色相抽出手段2を
通過した色相を濃淡画像にする。
The operation of the first embodiment will be described in detail with reference to FIG. In step S11, the image capturing unit 1 captures a microscope image, and in step S12, the hue extracting unit 2 extracts a hue. This hue extraction method will be described (FIG. 7). First, the lower limit (H L , S L , I L ) and the upper limit (H H ,
S H , I H ) are obtained experimentally and used as a hue model. Then, if the hue of the input image is within the allowable value, the input image is passed through, and only the hue close to the target microorganism is extracted. Next, in step S13, the hue shading means 3 converts the hue passing through the hue extracting means 2 into a shaded image.

【0021】藻類は概して緑色であるが、種別ごとに微
妙に色が異なっている。したがってテンプレートの色相
でなく現場から取得した特定の色相とする。これによ
り、1)ゴミと微生物と判別がしやすい、2)微生物の
種別を判別しやすい、といった利点がある(色相につい
ては「画像解析ハンドブック」参照)。
Algae are generally green, but the color is slightly different for each type. Therefore, a specific hue obtained from the site is used instead of the hue of the template. This has the advantage that 1) it is easy to distinguish between dust and microorganisms, and 2) it is easy to distinguish the type of microorganisms (for the hue, see "Image Analysis Handbook").

【0022】微生物の色相がモノクロだったり、顕微鏡
画像がモノクロにしか入力できない場合は、上記色相の
3値(H、S、I)を使用する代わりに濃淡の1値を使
用すればよい。
When the hue of the microorganism is monochrome or when the microscope image can be input only in monochrome, instead of using the above three values of the hue (H, S, I), one value of shading may be used.

【0023】ステップS14で円弧抽出手段4aが画像
の円弧を抽出して微生物の円弧群を求める。この円弧抽
出で円弧群を求める方法について説明する。まずステッ
プS13で得た濃淡画像を、後述のエッジ抽出処理によ
りエッジを抽出し、このエッジを円弧近似により円また
は円弧を求める。画像中に微生物が群体で存在する場
合、近似される円弧も多くなるため円弧群と呼ぶ。
In step S14, the arc extracting means 4a extracts the arcs of the image to obtain arc groups of microorganisms. A method for obtaining a group of arcs by this arc extraction will be described. First, an edge is extracted from the grayscale image obtained in step S13 by an edge extraction process described later, and a circle or arc is obtained from the edge by arc approximation. When microorganisms are present in a group in the image, the number of approximated arcs is also large, and thus the group is called an arc group.

【0024】上記エッジ抽出処理は、画像中の濃淡の変
化を求める手法で、画像の画素毎に二次微分演算を行っ
て、この演算結果が0を交差する点をエッジとする処理
である(特願平6−149246号参照)。
The edge extraction processing is a method for obtaining a change in shading in an image, and is a processing in which a second differential operation is performed for each pixel of an image, and a point where the operation result crosses zero is set as an edge ( See Japanese Patent Application No. 6-149246).

【0025】また上記円弧近似は、画像処理において画
像中のエッジを円、または円弧に近似する手法で、点列
として検出されたエッジ点の端点と中間点の3点を決
め、この3点から半径や中心座標を計算し円弧を求める
ものである(特願平6−113218号参照)。
The arc approximation is a method of approximating an edge in an image to a circle or an arc in image processing. The end point and the intermediate point of the edge points detected as a point sequence are determined. The radius and center coordinates are calculated to obtain a circular arc (see Japanese Patent Application No. Hei 6-113218).

【0026】ステップS15で円弧間の色抽出手段5a
が図3に示すように円弧の接線間で囲まれた領域からな
る斜線領域の色成分を求める。この斜線領域の色成分を
求める方法について説明する。まず、斜線領域を上記円
弧近似処理により求められる円弧の中心座標や半径と、
一般的な幾何計算で求め、次いで色成分を斜線領域中の
画素毎取得する。
At step S15, the color extracting means 5a between the arcs is used.
Calculates a color component of a shaded area composed of areas surrounded by arc tangents as shown in FIG. A method for obtaining the color components of the hatched area will be described. First, the center coordinates and radius of the arc obtained by performing the above-described arc approximation processing on the hatched area are
The color component is obtained by general geometric calculation, and then the color component is obtained for each pixel in the shaded area.

【0027】ステップS16で領域A抽出手段6が対象
微生物が存在する領域Aを求める。この領域Aを求める
方法について説明する(図8)。
In step S16, the area A extraction means 6 determines the area A where the target microorganism exists. A method for obtaining the area A will be described (FIG. 8).

【0028】[0028]

【数1】 (Equation 1)

【0029】まず斜線領域(図3)の色相の平均値を計
算する。次に入力画像の色相の平均値を計算する。そし
て式1にて下限許容値(HML、SML、IML)と上限許容
値(HMH、SMH、IMH)を計算する。そして入力画像の
色相が、許容値内であれば1、そうでなければ0として
2値画像を求め、1の領域を膨張・縮退処理にてノイズ
除去し、領域Aを求める。
First, the average value of the hues in the shaded area (FIG. 3) is calculated. Next, the average value of the hue of the input image is calculated. Then, the lower limit allowable values (H ML , S ML , and I ML ) and the upper limit allowable values (H MH , S MH , and I MH ) are calculated by Expression 1. Then, if the hue of the input image is within the allowable value, 1 is set, otherwise 0 is set to obtain a binary image, and the area 1 is subjected to dilation / reduction processing to remove noise and obtain an area A.

【0030】斜線領域は円弧間の領域で、焦点が合って
いない微生物の領域である。この領域の色相の平均値を
使うことにより、焦点の合っていない微生物を判別でき
る利点がある。
The shaded area is the area between the arcs, which is the area of microorganisms that are out of focus. By using the average value of the hues in this region, there is an advantage that a microorganism that is out of focus can be identified.

【0031】ステップ17で個体数計算手段7が領域A
から微生物の個体数を求める。この個体数を求める方法
について説明する。プレパラートを使用して顕微鏡画像
を取得すると群体が平坦化されるため、個体数=h・A
/aとして計算する。hは係数、aは微生物の単体面積
である。検水から直接顕微鏡画像を取得すると、群体は
球状に近いため、固体数=h・(R・r)3として計算
する。Rは領域Aの重心から周囲までの平均半径、rは
微生物の単体半径である。hは実験的に取得し、微生物
の厚みを補償する。一般に微生物の増殖傾向を未然に把
握できればよいので、簡単なhの乗算で支障ない。上記
ステップ11〜27を繰り返して群体微生物数のデータ
を得る。
In step 17, the number of individuals calculation means 7
From the number of microorganisms. A method for obtaining the number of individuals will be described. When a microscope image is obtained using a preparation, the colony is flattened, so that the number of individuals = hA
/ A. h is a coefficient and a is a single area of a microorganism. When a microscope image is directly obtained from a sample, the number of solids is calculated as h · (R · r) 3 because the colony is nearly spherical. R is the average radius from the center of gravity of the region A to the periphery, and r is the single radius of the microorganism. h is obtained experimentally and compensates for microbial thickness. Generally, it is sufficient to be able to grasp the growth tendency of microorganisms beforehand, so simple multiplication of h does not hinder. Steps 11 to 27 are repeated to obtain data on the number of colony microorganisms.

【0032】実施例1の方式によれば、群体になる円形
状の特徴を持った微生物、例えば、ミクロキスチス種
(Microcystis)の計数ができる。また現場
から特定の色相をモデルとして取得するため、ゴミと微
生物との判別性が良い。微生物の種別の判別性が良い。
そして円弧間の平均の色相を使うため焦点の合わない微
生物を判別できる利点がある。 実施例2(カーブによる群体微生物検出装置) この方式は、顕微鏡画像の焦点の合っているカーブ状の
特徴を持つ微生物を検出し、検出された微生物の占める
領域から群体全体の微生物数を推定する。そして得られ
た時系列的な微生物数データは、報告書化したり、上位
装置や後段の処理装置へ渡すものである。
According to the method of the first embodiment, it is possible to count microorganisms having a characteristic of a circular shape, such as microcystis, which form a colony. Further, since a specific hue is obtained as a model from the site, discrimination between dust and microorganisms is good. Good discrimination of the type of microorganism.
In addition, since the average hue between the arcs is used, there is an advantage that the microorganism that is out of focus can be identified. Example 2 (Corporate Microbial Detector by Curve) This method detects a microorganism having a curved characteristic in focus on a microscope image, and estimates the number of microorganisms in the entire colony from an area occupied by the detected microorganisms. . The obtained time-series data on the number of microorganisms is written into a report or passed to a host device or a subsequent processing device.

【0033】図9に実施例2にかかる群体微生物検出装
置のブロック構成図を示す。なお、図1(実施例1)と
同一構成部分には同一符号を付してその重複する説明を
省略する。
FIG. 9 is a block diagram showing a colony microorganism detecting apparatus according to the second embodiment. The same components as those in FIG. 1 (Example 1) are denoted by the same reference numerals, and redundant description is omitted.

【0034】図9において、カーブ抽出手段4bは色相
抽出手段2で抽出した微生物に近い色相を濃淡化手段3
で濃淡化された画像をエッジ処理し画像のエッジを抽出
し、このエッジからカーブを抽出しカーブを求める。カ
ーブ間の色抽出手段5bは入力画像の上記抽出されたカ
ーブの接線間に囲まれた斜線領域(図11)を求め、斜
線領域の色相の平均値を計算する。その他の構成は図1
のものと変わりがない。
In FIG. 9, the curve extracting means 4b converts the hue close to the microorganism extracted by the hue extracting means 2 into the light and shade means 3
The edge of the image is extracted by performing edge processing on the image shaded by the above, and a curve is extracted from this edge to obtain a curve. The color extracting means 5b between the curves obtains a shaded area (FIG. 11) surrounded by the tangents of the extracted curves in the input image, and calculates the average value of the hues of the shaded area. Other configurations are shown in FIG.
There is no difference from the one.

【0035】上記実施例2の動作を図10を用いて説明
する。ステップ21〜23で上記図2のステップ11〜
13と同様に顕微鏡画像を取り込み、対象とする微生物
に近い色相だけ抽出し、抽出した色相を濃淡画像にす
る。
The operation of the second embodiment will be described with reference to FIG. Steps 21 to 23 in FIG.
Microscopic images are captured in the same manner as in 13, and only the hues close to the target microorganism are extracted, and the extracted hues are converted into gray-scale images.

【0036】ステップS24でカーブ抽出手段4bが画
像のカーブを抽出して微生物のカーブ群を求める。この
カーブ抽出で円弧群を求める方法は、まず、ステップS
23で得た濃淡画像を、前述のエッジ抽出処理によりエ
ッジを抽出し、点列として検出されたエッジの端点と中
間点の3点を決め、この3点から閉曲線や閉じていない
C型の自由曲線であるカーブを抽出する。画像中に微生
物が群体で存在する場合、C型のカーブは多くなるため
カーブ群と呼ぶ。
At step S24, the curve extracting means 4b extracts a curve of the image to obtain a curve group of microorganisms. The method of obtaining the arc group by this curve extraction is as follows.
An edge is extracted from the grayscale image obtained in step 23 by the above-described edge extraction processing, and three points, ie, an end point and an intermediate point of the edge detected as a point sequence, are determined. Extract a curve that is a curve. When the microorganisms are present in a group in the image, the number of C-shaped curves increases, and thus the group is referred to as a curve group.

【0037】次にステップS25でカーブ間の色抽出手
段5bが図11に示すように検出されたカーブ間の領域
からなる斜線領域の色成分を求める。この斜線領域の色
成分を求める方法は、まず、斜線領域は実施例1の場合
と同様にカーブの中心座標や半径と、一般的な幾何計算
で求め、次いで色成分を斜線領域中の画素毎取得する。
Next, in step S25, the color extracting means 5b between the curves obtains the color components of the hatched area consisting of the detected areas between the curves as shown in FIG. The method for obtaining the color components of the hatched area is as follows. First, the hatched area is obtained by a general geometric calculation and the center coordinates and radius of the curve as in the first embodiment. get.

【0038】そして、実施例1のステップS16,S1
7と同様にステップS26,S27で微生物の領域Aを
求め、領域Aの微生物の数を計算する。そしてステップ
S21〜27をくり返して群体微生物数のデータを得
る。
Then, steps S16 and S1 of the first embodiment are performed.
As in the case of 7, the region A of the microorganism is obtained in steps S26 and S27, and the number of microorganisms in the region A is calculated. Steps S21 to S27 are repeated to obtain data on the number of microbial communities.

【0039】実施例2の方式は、カーブを使用している
ので、半径が短い円弧を上記実施例1の方式のように手
間をかけて円弧抽出処理するより、そのままカーブで取
り扱っているので、信頼性がある。この方式によると、
群体になるカーブ状の特徴をもった微生物、例えばミク
ロキスチス種(Microcystis)の計数が可能
となる。 実施例3(直線による群体微生物検出装置) この方式は、顕微鏡画像の焦点の合っている直線状の特
徴を持つ微生物を検出し、その微生物の占める領域から
群体全体の微生物数を推定する。
Since the method of the second embodiment uses a curve, an arc having a short radius is handled as a curve as it is, instead of performing the arc extraction processing with much effort as in the method of the first embodiment. Reliable. According to this scheme,
Microorganisms having curved characteristics, such as microcystis species, can be counted. Example 3 (A colony microorganism detection apparatus using a straight line) In this method, a microorganism having a linear feature that is in focus in a microscope image is detected, and the number of microorganisms in the entire colony is estimated from an area occupied by the microorganism.

【0040】図12に実施例3にかかる群体微生物のブ
ロック構成図を示す。なお、図1(実施例1)と同一構
成部分には同一符号を付してその重複する説明を省略す
る。
FIG. 12 shows a block diagram of a colony microorganism according to the third embodiment. The same components as those in FIG. 1 (Example 1) are denoted by the same reference numerals, and redundant description is omitted.

【0041】図12において、直線抽出手段4Cは、色
抽出手段2で微生物に近い色相が抽出され濃淡化手段3
で濃淡化された、微生物の濃淡化画像をエッジ処理し画
像のエッジを抽出し、このエッジから直線を求める。直
線近傍の色抽出手段5Cは入力画像の上記直線の近傍の
斜線領域(図14)を求め、斜線領域の色相の平均値を
計算する。その他の構成は図1のものと変わりがない。
In FIG. 12, the straight line extracting means 4C extracts the hue close to the microorganism by the color extracting means 2 and
Edge processing is performed on the gray-scale image of the microorganism, which is gray-scaled in step (1), to extract an edge of the image, and a straight line is obtained from the edge. The color extracting means 5C near the straight line obtains a shaded area (FIG. 14) near the straight line in the input image and calculates an average value of the hues of the shaded area. Other configurations are the same as those in FIG.

【0042】上記実施例2の動作を図13を用いて説明
する。ステップ31〜33で上記図2のステップ11〜
13と同様に顕微鏡画像を取り込み、対象とする微生物
に近い色相だけ抽出し、抽出した色相を濃淡画像にす
る。
The operation of the second embodiment will be described with reference to FIG. Steps 31 to 33 in FIG.
Microscopic images are captured in the same manner as in 13, and only the hues close to the target microorganism are extracted, and the extracted hues are converted into gray-scale images.

【0043】ステップ24でカーブ抽出手段4bが画像
の直線部分を抽出して微生物の直線群を求める。この直
線抽出で直線群を求める方法は、まず、ステップS23
で得た濃淡画像を、前述のエッジ抽出処理により濃淡画
像のエッジを抽出し、点列として検出されたエッジの端
点と中間点の3点を決め、この3点が一直線となる直線
を抽出する。画像中に微生物が群体で存在する場合、直
線は多くなるため直線群と呼ぶ。
In step 24, the curve extracting means 4b extracts a straight line portion of the image to obtain a straight line group of microorganisms. A method of obtaining a straight line group by this straight line extraction is as follows.
From the grayscale image obtained in the above, the edge of the grayscale image is extracted by the above-described edge extraction processing, and three points of the end point and the intermediate point of the edge detected as a point sequence are determined, and a straight line in which the three points are straight is extracted. . When the microorganisms are present in a group in the image, the number of straight lines increases, and thus the group is referred to as a group of straight lines.

【0044】次にステップS25で直線間の色抽出手段
5Cが図14に示すように検出された直線から一定幅の
近傍の領域からなる斜線領域の色成分を求める。この斜
線領域の色成分を求める方法は、一般的な幾何学的計算
で求め、次いで色成分を斜線領域中の画素毎取得する。
Next, in step S25, the color extracting means 5C between the straight lines obtains the color components of the shaded area consisting of the area near the fixed width from the detected straight line as shown in FIG. The method of obtaining the color components of the hatched area is obtained by a general geometric calculation, and then the color components are obtained for each pixel in the hatched area.

【0045】そして、実施例1のステップS16,S1
7と同様にステップS36,S37で微生物の領域Aを
求め、領域Aの微生物の数を計算する。そしてステップ
S31〜S37をくり返して群体微生物数のデータを得
る。この方式によると群体になる糸状性の特徴を持った
微生物、例えばオシラドリア(Oscillatori
a)の計算ができる。
Then, steps S16 and S1 of the first embodiment are performed.
Similarly to 7, the region A of the microorganism is obtained in steps S36 and S37, and the number of microorganisms in the region A is calculated. Then, steps S31 to S37 are repeated to obtain data on the number of colony microorganisms. According to this method, microorganisms having a filamentous characteristic, such as oscillatria, are collected.
a) can be calculated.

【0046】上記実施例では、円弧状、カーブ状、直線
状の形状となる微生物数の検出例であるが、その他の形
状となる微生物があれば、それも同様に検出できること
はいうまでもない。
The above embodiment is an example of detecting the number of microorganisms having an arc shape, a curve shape, or a linear shape. However, it is needless to say that any microorganism having any other shape can be similarly detected. .

【0047】[0047]

【発明の効果】この発明は、上述のとおり構成されてい
るので、以下に記載する効果を奏する。 (1)モデルベーストマッチング法を使用しているた
め、入力画像の輝度変化や背景の変化などノイズに影響
されにくい。また、現場の微生物から現物あわせでモデ
ルを作製するため、微生物の見え方の変化などの現場環
境に適応できる。 (2)群体になる円形状の特徴を持った微生物を計数で
きる。 (3)群体になるカーブ状の特徴を持った微生物を計数
できる。 (4)群体になる糸状性の特徴を持った微生物を計数で
きる。 (5)現場から特定色相をモデルとして取得するため、
ゴミと微生物の判別性がよい。 (6)現場から特定色相をモデルとして取得するため、
微生物の種別の判別性がよい。 (7)現場の微生物の特徴(円形・閉曲線・直線)の近
傍の色相を取得するため、焦点の合っていない微生物を
判別できる。
Since the present invention is configured as described above, the following effects can be obtained. (1) Since the model-based matching method is used, it is hardly affected by noise such as a change in luminance of an input image and a change in background. In addition, since the model is prepared from the microorganisms at the site, the model can be adapted to the on-site environment such as a change in the appearance of the microorganisms. (2) Microorganisms having a circular characteristic can be counted. (3) It is possible to count microorganisms having a curve-like characteristic that forms a colony. (4) It is possible to count microorganisms having the characteristic of filamentousness that form a colony. (5) To obtain a specific hue as a model from the site,
Good discrimination between garbage and microorganisms. (6) To obtain a specific hue as a model from the site,
Good discrimination of the type of microorganism. (7) Since the hues near the characteristics (circle, closed curve, and straight line) of the microorganisms on the spot are acquired, the microorganisms that are out of focus can be identified.

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

【図1】実施例1にかかる群体微生物検出装置のブロッ
ク構成図。
FIG. 1 is a block diagram of a colony microorganism detection apparatus according to a first embodiment.

【図2】実施例1の動作を述べるフロー図。FIG. 2 is a flowchart illustrating the operation of the first embodiment.

【図3】円弧間の領域説明図。FIG. 3 is an explanatory diagram of an area between arcs.

【図4】群体微生物の顕微鏡画像を示す写真。FIG. 4 is a photograph showing a microscopic image of a colony microorganism.

【図5】円弧抽出画像を示す写真。FIG. 5 is a photograph showing an arc extraction image.

【図6】領域A抽出画像を示す写真。FIG. 6 is a photograph showing an area A extraction image.

【図7】色相抽出ブロック図。FIG. 7 is a block diagram of hue extraction.

【図8】領域A抽出ブロック図。FIG. 8 is an area A extraction block diagram.

【図9】実施例2にかかる群体微生物検出装置のブロッ
ク構成図。
FIG. 9 is a block diagram of a colony microorganism detection apparatus according to a second embodiment.

【図10】実施例2の動作を述べるフロー図。FIG. 10 is a flowchart illustrating the operation of the second embodiment.

【図11】カーブ間の領域説明図。FIG. 11 is an explanatory diagram of an area between curves.

【図12】実施例3にかかる群体微生物検出装置のブロ
ック構成図。
FIG. 12 is a block diagram of a colony microorganism detection apparatus according to a third embodiment.

【図13】実施例3の動作を述べるフロー図。FIG. 13 is a flowchart describing the operation of the third embodiment.

【図14】直線の近傍領域説明図。FIG. 14 is an explanatory diagram of a region near a straight line.

【図15】従来例にかかるモデルベーストマッチング方
式の処理フロー図。
FIG. 15 is a processing flowchart of a model-based matching method according to a conventional example.

【符号の説明】[Explanation of symbols]

1…画像取り込み手段 2…色相抽出手段 3…色相濃淡化手段 4a…円弧抽出手段 4b…カーブ抽出手段 4c…直線抽出手段 5a…円弧間の色相抽出手段 5b…カーブ間の色相抽出手段 5c…直線近傍の色相抽出手段 6…領域A抽出手段 7…個体数計算手段 8…出力手段 DESCRIPTION OF SYMBOLS 1 ... Image taking-in means 2 ... Hue extracting means 3 ... Hue shading means 4a ... Arc extracting means 4b ... Curve extracting means 4c ... Straight line extracting means 5a ... Hue extracting means between arcs 5b ... Hue extracting means between curves 5c ... Straight line Near hue extraction means 6 Area A extraction means 7 Individual number calculation means 8 Output means

───────────────────────────────────────────────────── フロントページの続き Fターム(参考) 4B029 AA07 BB01 CC03 CC07 FA03 FA10 FA11 4B063 QA01 QA18 QQ05 QS39 QX01 QX10 4D028 CC06 CE02 5B057 AA10 BA02 CA01 CA08 CA12 CA16 CB18 CC01 CE11 CE17 DA08 DB02 DB06 DB09 DC03 DC04 DC16  ────────────────────────────────────────────────── ─── Continued on the front page F term (reference) 4B029 AA07 BB01 CC03 CC07 FA03 FA10 FA11 4B063 QA01 QA18 QQ05 QS39 QX01 QX10 4D028 CC06 CE02 5B057 AA10 BA02 CA01 CA08 CA12 CA16 CB18 CC01 CE11 CE17 DA08 DB02 DC06 DC09 DC09

Claims (6)

【特許請求の範囲】[Claims] 【請求項1】 画像入力素子より取り込んだ群体微生物
入力画像から検出対象とする円弧状の特徴を持った微生
物の色相モデルに近い色相を抽出し、抽出した色相を濃
淡化した後エッジ処理して濃淡の変化するエッジを抽出
し、抽出したエッジの中から円弧状エッジを求め、 前記円弧状エッジの間の領域における色相平均の許容値
を計算し、前記入力画像から色相平均の許容値内にある
微生物領域を抽出し、 前記微生物領域と円弧状微生物の単体面積および実験的
に得た微生物の厚み補償係数から円弧状微生物数を計算
により求めることを特徴とする群体微生物検出方法。
1. A hue close to a hue model of a microorganism having an arc-shaped feature to be detected is extracted from a colony microbial input image captured from an image input device, and the extracted hue is shaded and then subjected to edge processing. Extract the edge of changing shades, find the arc-shaped edge from the extracted edges, calculate the allowable value of the hue average in the region between the arc-shaped edges, from the input image within the allowable value of the hue average A method for detecting a colony of microorganisms, comprising extracting a certain microbial region, and calculating the number of arcuate microorganisms from a single area of the microbial region and the arcuate microorganism and a thickness compensation coefficient of the microorganism obtained experimentally by calculation.
【請求項2】 画像入力素子より取り込んだ群体微生物
入力画像から検出対象とするカーブ状の特徴を持った微
生物の色相モデルに近い色相を抽出し、 抽出した色相を濃淡化した後エッジ処理して濃淡の変化
するエッジを抽出し、抽出したエッジの中からカーブ状
エッジを求め、 前記カーブ状エッジの間の領域における色相平均の許容
値を計算し、前記入力画像から色相平均の許容値内にあ
る対象微生物領域を抽出し、 前記微生物領域とカーブ状微生物の単体面積および実験
的に得た微生物の厚み補償係数からカーブ状微生物数を
計算により求めることを特徴とする群体微生物検出方
法。
2. A hue close to a hue model of a microorganism having a curved characteristic to be detected is extracted from a colony microbial input image captured from an image input device, and the extracted hue is shaded and then subjected to edge processing. Extract the edge where the shading changes, find the curved edge from the extracted edges, calculate the allowable value of the hue average in the area between the curved edges, and within the allowable value of the hue average from the input image. A method of detecting a colony of microorganisms, comprising extracting a target microorganism region and calculating the number of curved microorganisms from the microorganism region, the single area of the curved microorganism, and the thickness compensation coefficient of the microorganism obtained experimentally.
【請求項3】 画像入力素子より取り込んだ群体微生物
入力画像から検出対象とする直線状の特徴を持った微生
物の色相モデルに近い色相を抽出し、 抽出した色相を濃淡化した後エッジ処理して濃淡の変化
するエッジを抽出し、抽出したエッジの中から直線状エ
ッジを求め、 前記直線状エッジの間の領域における色相平均の許容値
を計算し、前記入力画像から色相平均の許容値内にある
微生物領域を抽出し、 前記微生物領域と直線状微生物の単体面積および実験的
に得た微生物の厚み補償係数から直線状微生物数を計算
により求めることを特徴とする群体微生物検出方法。
3. A hue close to a hue model of a microorganism having a linear feature to be detected is extracted from a colony microbial input image captured from an image input device, and the extracted hue is shaded and then subjected to edge processing. Extract the edge where the shading changes, find a linear edge from the extracted edges, calculate the allowable value of the hue average in the region between the linear edges, and within the allowable value of the hue average from the input image. A method for detecting a colony of microorganisms, comprising extracting a certain microorganism region, and calculating the number of linear microorganisms from the single region of the microorganism region, the simple substance area of the linear microorganism, and the thickness compensation coefficient of the microorganism obtained experimentally.
【請求項4】 顕微鏡ITVカメラで撮影された画像を
取り込む画像取り込み手段と、 この入力画像から検出対象とする円弧状の特徴を持った
微生物の色相モデルに近い色相を抽出する手段と、 前記抽出した色相を濃淡化する手段と、 前記濃淡化された画像を画素毎に二次微分演算して濃淡
の変化するエッジを検出し、エッジの中から円弧状エッ
ジを抽出する手段と、 前記円弧状エッジの間の領域における色相平均の許容値
を計算し、前記入力画像の色相平均の許容値内にある微
生物領域を抽出する手段と、 前記微生物領域と円弧状微生物の単体面積および実験的
に得た微生物の厚み補償係数から円弧状の微生物数を計
算する個体数計算手段とを有することを特徴とする群体
微生物検出装置。
4. An image capturing means for capturing an image captured by a microscope ITV camera; a means for extracting a hue close to a hue model of a microorganism having an arc-shaped feature to be detected from the input image; Means for shading the shaded hue, means for second-order differentiation of the shaded image for each pixel to detect edges whose shading changes, and extraction of arc-shaped edges from the edges; Means for calculating a hue average allowable value in a region between edges, and extracting a microbial region within the hue average allowable value of the input image; And a population calculating means for calculating the number of arc-shaped microorganisms from the thickness compensation coefficient of the microorganisms.
【請求項5】 顕微鏡ITVカメラで撮影された画像を
取り込む画像取り込み手段と、 この入力画像から検出対象とするカーブ状の特徴を持っ
た微生物の色相モデルに近い色相を抽出する手段と、 前記抽出した色相を濃淡化する手段と、 前記濃淡化された画像を画素毎に二次微分演算して濃淡
の変化するエッジを検出し、エッジの中からカーブ状エ
ッジを抽出する手段と、 前記カーブ状エッジの間の領域における色相平均の許容
値を計算し、前記入力画像の色相平均の許容値内にある
微生物領域を抽出する手段と、 前記微生物領域とカーブ状微生物の単体面積および実験
的に得た微生物の厚み補償係数からカーブ状の微生物数
を計算する個体数計算手段とを有することを特徴とする
群体微生物検出装置。
5. An image capturing means for capturing an image captured by a microscope ITV camera, a means for extracting a hue close to a hue model of a microorganism having a curved characteristic to be detected from the input image, Means for shading the shaded hue, means for performing a second differential operation on the shaded image for each pixel to detect an edge whose shading changes, and extracting a curved edge from the edge; Means for calculating a hue average allowable value in a region between edges, extracting a microbial region that is within the hue average allowable value of the input image; A population calculating means for calculating the number of curved microorganisms from the thickness compensation coefficient of the microorganisms.
【請求項6】 顕微鏡ITVカメラで撮影された画像を
取り込む画像取り込み手段と、 この入力画像から検出対象とする直線状の特徴を持った
微生物の色相モデルに近い色相を抽出する手段と、 前記抽出した色相を濃淡化する手段と、 前記濃淡化された画像を画素毎に二次微分演算して濃淡
の変化するエッジを検出し、エッジの中から直線状エッ
ジを抽出する手段と、 前記直線状エッジの間の領域における色相平均の許容値
を計算し、前記入力画像の色相平均の許容値内にある微
生物領域を抽出する手段と、 前記微生物領域と直線状微生物の単体面積および実験的
に得た微生物の厚み補償係数から直線状の微生物数を計
算する個体数計算手段とを有することを特徴とする群体
微生物検出装置。
6. An image capturing means for capturing an image captured by a microscope ITV camera; a means for extracting a hue close to a hue model of a microorganism having a linear feature to be detected from the input image; Means for shading the shaded hue, means for performing a second differential operation on the shaded image for each pixel to detect an edge where the shading changes, and extracting a linear edge from the edge; Means for calculating a hue average allowance in an area between edges and extracting a microbial area within the hue average allowance of the input image; A population calculating means for calculating the number of linear microorganisms from the thickness compensation coefficient of the microorganisms.
JP11192494A 1999-07-07 1999-07-07 Method and device for detecting colony microorganism Withdrawn JP2001022929A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP11192494A JP2001022929A (en) 1999-07-07 1999-07-07 Method and device for detecting colony microorganism

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP11192494A JP2001022929A (en) 1999-07-07 1999-07-07 Method and device for detecting colony microorganism

Publications (1)

Publication Number Publication Date
JP2001022929A true JP2001022929A (en) 2001-01-26

Family

ID=16292249

Family Applications (1)

Application Number Title Priority Date Filing Date
JP11192494A Withdrawn JP2001022929A (en) 1999-07-07 1999-07-07 Method and device for detecting colony microorganism

Country Status (1)

Country Link
JP (1) JP2001022929A (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007190510A (en) * 2006-01-20 2007-08-02 Hitachi Zosen Corp Biological wastewater treatment method
KR100781239B1 (en) 2006-06-06 2007-11-30 재단법인서울대학교산학협력재단 Method for tracking bacteria swimming near the solid surface
JP2008212017A (en) * 2007-03-01 2008-09-18 Nikon Corp Apparatus for determining cell state, and method for determining cell state
WO2008149636A1 (en) 2007-06-04 2008-12-11 Kabushiki Kaisha N-Tech Method for counting colonies
JP2010044641A (en) * 2008-08-14 2010-02-25 Toshiba Corp Ultrasonic diagnostic apparatus, ultrasonic image processor and ultrasonic image processing program
JP2010104301A (en) * 2008-10-30 2010-05-13 Eiken Chem Co Ltd Method, apparatus, and program for detecting microorganism
JP2011232051A (en) * 2010-04-23 2011-11-17 Nagoya Univ Classification model generation device, cell classification device, incubator, method for cell culture, and program
JP2012075409A (en) * 2010-10-04 2012-04-19 Microbio Corp Colony detection method, colony detection system and colony detection program
EP2586873A1 (en) * 2010-06-23 2013-05-01 Kabushiki Kaisha N-Tech Method for detecting microorganisms, device for detecting microorganisms and program
WO2018230016A1 (en) * 2017-06-13 2018-12-20 株式会社Ihi Mobile body observation method

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007190510A (en) * 2006-01-20 2007-08-02 Hitachi Zosen Corp Biological wastewater treatment method
KR100781239B1 (en) 2006-06-06 2007-11-30 재단법인서울대학교산학협력재단 Method for tracking bacteria swimming near the solid surface
JP2008212017A (en) * 2007-03-01 2008-09-18 Nikon Corp Apparatus for determining cell state, and method for determining cell state
US8831326B2 (en) 2007-06-04 2014-09-09 Kabushiki Kaisha N-Tech Method for counting colonies
WO2008149636A1 (en) 2007-06-04 2008-12-11 Kabushiki Kaisha N-Tech Method for counting colonies
JP2010044641A (en) * 2008-08-14 2010-02-25 Toshiba Corp Ultrasonic diagnostic apparatus, ultrasonic image processor and ultrasonic image processing program
US8858442B2 (en) 2008-08-14 2014-10-14 Kabushiki Kaisha Toshiba Ultrasonic diagnostic apparatus and ultrasonic image processing apparatus
JP2010104301A (en) * 2008-10-30 2010-05-13 Eiken Chem Co Ltd Method, apparatus, and program for detecting microorganism
JP2011232051A (en) * 2010-04-23 2011-11-17 Nagoya Univ Classification model generation device, cell classification device, incubator, method for cell culture, and program
EP2586873A4 (en) * 2010-06-23 2013-12-18 N Tech Kk Method for detecting microorganisms, device for detecting microorganisms and program
US8831313B2 (en) 2010-06-23 2014-09-09 Kabushiki Kaisha N-Tech Method for detecting microorganisms, device for detecting microorganisms and program
EP2586873A1 (en) * 2010-06-23 2013-05-01 Kabushiki Kaisha N-Tech Method for detecting microorganisms, device for detecting microorganisms and program
JP2012075409A (en) * 2010-10-04 2012-04-19 Microbio Corp Colony detection method, colony detection system and colony detection program
WO2018230016A1 (en) * 2017-06-13 2018-12-20 株式会社Ihi Mobile body observation method
JPWO2018230016A1 (en) * 2017-06-13 2020-04-09 株式会社Ihi Mobile observation method

Similar Documents

Publication Publication Date Title
CN111368643B (en) Escherichia coli dynamic growth monitoring method
Salem et al. A comparative study of white blood cells segmentation using otsu threshold and watershed transformation
CN109636824A (en) A kind of multiple target method of counting based on image recognition technology
Nguyen et al. Cell splitting with high degree of overlapping in peripheral blood smear
CN107657209B (en) Template image registration mechanism based on finger vein image quality
JPH10506484A (en) Biological analysis self-calibration device
CN105205821A (en) Weld image segmentation method
US20170309017A1 (en) Device and method for finding cell nucleus of target cell from cell image
CN113537182B (en) Automatic identification method and system for metaphase mitosis microscopic image of chromosome
CN116758071B (en) Intelligent detection method for carbon electrode dirt under visual assistance
JP2001022929A (en) Method and device for detecting colony microorganism
CN113902713B (en) Image segmentation algorithm-based multi-colony counting method
CN109117703A (en) It is a kind of that cell category identification method is mixed based on fine granularity identification
JP2015181374A (en) Filamentous bacteria detection device and filamentous bacteria detection method
Razzak et al. Automatic detection of malarial parasite using microscopic blood images
Jenné et al. Towards on-line quantification of flocs and filaments by image analysis
CN111368669A (en) Nonlinear optical image recognition method based on deep learning and feature enhancement
CN109948544A (en) A kind of automatic positioning of target bacterium colony and recognition methods
CN109859220B (en) Linear image segmentation method
JP3431883B2 (en) Cell lineage extraction method
CN116485749A (en) Self-encoder-based method for identifying dirt in lens module
Cosio et al. Automatic counting of immunocytochemically stained cells
CN109523568A (en) A kind of gross specimen camera system based on Canny algorithm
CN109544513A (en) A kind of steel pipe end surface defect extraction knowledge method for distinguishing
CN115063340A (en) Bacterial colony counting method and bacterial colony counter

Legal Events

Date Code Title Description
A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20041117

A761 Written withdrawal of application

Free format text: JAPANESE INTERMEDIATE CODE: A761

Effective date: 20070228