JP2001239221A - Image forming device and assorting/classifying/judging device used for assorting of agricultural product - Google Patents

Image forming device and assorting/classifying/judging device used for assorting of agricultural product

Info

Publication number
JP2001239221A
JP2001239221A JP2000056104A JP2000056104A JP2001239221A JP 2001239221 A JP2001239221 A JP 2001239221A JP 2000056104 A JP2000056104 A JP 2000056104A JP 2000056104 A JP2000056104 A JP 2000056104A JP 2001239221 A JP2001239221 A JP 2001239221A
Authority
JP
Japan
Prior art keywords
image
agricultural product
area
determination
appearance
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.)
Granted
Application number
JP2000056104A
Other languages
Japanese (ja)
Other versions
JP3962525B2 (en
Inventor
Seiji Nakamura
誠司 仲村
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.)
Maki Manufacturing Co Ltd
Original Assignee
Maki 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 Maki Manufacturing Co Ltd filed Critical Maki Manufacturing Co Ltd
Priority to JP2000056104A priority Critical patent/JP3962525B2/en
Publication of JP2001239221A publication Critical patent/JP2001239221A/en
Application granted granted Critical
Publication of JP3962525B2 publication Critical patent/JP3962525B2/en
Anticipated expiration legal-status Critical
Expired - Fee Related legal-status Critical Current

Links

Abstract

PROBLEM TO BE SOLVED: To provide an image forming device for agricultural products which improves the reliability of grade decision in assorting the agricultural products. SOLUTION: This device has a camera 202 for picking up the images of at least the flanks of the agricultural products P which are placed on agricultural product loading surfaces having recesses and are transported and an arithmetic controller 3 which determines the regions of the appearance decision images for making decision relating to the appearance of the agricultural products P by removing the pickup image information within the prescribed width along the contours of the resulted lateral pickup images of the agricultural products. The arithmetic controller 3 is constituted to have removal width changing sections 302 which are capable of dividing the blocks along the image contours and changing the same by dividing the blocks to the blocks of the lateral pickup images dividing the sizes of the prescribed widths to be removed.

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】本発明は、みかん、リンゴ、
トマト、西瓜、メロン等の農産物を仕分けするための選
果場等において用いられる装置に関し、詳しくは、仕分
情報の一つとして利用される農産物の外観を計測する農
産物の仕分けに用いる画像生成装置、及びこれを用いた
仕分区分判定装置に関するものである。
TECHNICAL FIELD The present invention relates to tangerines, apples,
Tomato, watermelon, related to devices used in sorting facilities and the like for sorting agricultural products such as melon, specifically, an image generation device used for sorting agricultural products that measures the appearance of agricultural products used as one of the sorting information, And a sorting classification determining apparatus using the same.

【0002】[0002]

【従来の技術】一般に、野菜や果物などの農産物を選果
場等において個々の品質に応じて仕分けることが行わ
れ、その仕分けの適正さが重要視されている。これは、
需要者や取引市場における品質に係わる評価が農産物生
産者への対価に直接結びつくからである。
2. Description of the Related Art Generally, agricultural products such as vegetables and fruits are sorted according to their individual qualities in a sorting place or the like, and the appropriateness of the sorting is regarded as important. this is,
This is because quality evaluations in consumers and trading markets are directly linked to the price paid to agricultural producers.

【0003】そして、農産物の仕分けのための要素とし
ては、一般的には階級要素(重量や大きさ)と、等級要
素(表面の疵,色等の外観的なものと、糖度,熟度等の
内部品質的なもの)とされ、種々の農産物における特徴
的な性質などが考慮されて、階級や等級の要素をカメラ
やその他の機器により計測してMPU(マイクロ プロ
セッサ ユニット)等を用いて仕分区分が判定され、あ
るいは一部は作業者の熟練性に依存して判定されている
が、これらのうちの農産物の外観に係わる要素は、技術
が発達して客観性の面で安定し、生産性,能率性の面で
優れている機器計測が主に行われている。
[0003] Elements for sorting agricultural products are generally classified into class elements (weight and size), grade elements (appearance such as surface flaws and colors, sugar content, ripeness, etc.). In consideration of the characteristic properties of various agricultural products, class and grade elements are measured with a camera or other equipment, and sorted using an MPU (microprocessor unit) or the like. The classification is determined, or partly determined depending on the skill of the worker. Among these, the factors related to the appearance of agricultural products are the ones that are stable in terms of objectivity and Equipment measurement that is excellent in terms of efficiency and efficiency is mainly performed.

【0004】このような外観計測のための機器は、例え
ば、複数のカメラを農産物を搬送するコンベア等の周囲
に配置したり、ミラーとカメラの組合わせで構成され、
平面、及び搬送路の側方、斜め前方、斜め後方などから
立体的外観を撮像することが行われる。
[0004] Such a device for measuring the appearance is constituted, for example, by arranging a plurality of cameras around a conveyor or the like for transporting agricultural products, or by combining a mirror and a camera.
An image of a three-dimensional appearance is taken from a flat surface, from the side of the transport path, diagonally forward, diagonally rear, and the like.

【0005】上記のように撮像された農産物の外観情
報、例えば大きさの階級要素や色や疵等の等級要素の情
報は、所定の判定プログラム等に従って農産物の仕分区
分を判定することに用いられる。
[0005] The appearance information of the agricultural product imaged as described above, for example, the information of the class element of the size, the information of the grade element such as the color and the flaw, etc. is used to determine the sorting category of the agricultural product according to a predetermined determination program or the like. .

【0006】ところで、上記撮像画像は、対象が農産物
という例えば球塊状のものであるために、照明や撮像方
式を工夫しても画像中に不確かな部分の情報も含まれる
ことは避けられないのが普通である。具体的には、輪郭
部のハレーション、ボケ、照明不足による画像欠け等で
ある。そこで特開平4−307357号公報により、農
産物の撮像画像のうち輪郭から所定幅の範囲(周辺部
分)を判定に用いる画像情報の中から除去するという画
像処理についての提案がされている。
[0006] By the way, since the above-mentioned captured image is an agricultural product, for example, a spherical mass, it is inevitable that information of an uncertain part is included in the image even if the lighting and the imaging method are devised. Is common. Specifically, there are halation and blurring of the contour portion, image missing due to insufficient illumination, and the like. Therefore, Japanese Patent Application Laid-Open No. Hei 4-307357 proposes an image processing for removing a range (peripheral portion) of a predetermined width from a contour in a captured image of an agricultural product from image information used for determination.

【0007】上記提案のようにすることで、撮像画像の
うちの不確かな部分に含まれる異常情報によって農産物
が不適切に判定・評価される不具合が防がれる。
[0007] By adopting the above-mentioned proposal, it is possible to prevent a problem that an agricultural product is inappropriately determined and evaluated by abnormal information included in an uncertain portion of a captured image.

【0008】[0008]

【発明が解決しようとする課題】上記のような撮像画像
の中に含まれる不確かな部分を除去する画像処理におい
ては、必要な範囲でできるだけ小さくする(確かな部分
の範囲を大きくする)ことが、農産物の仕分区分をでき
るだけ正確に評価分類するために望ましい。
In the image processing for removing an uncertain part included in a captured image as described above, it is necessary to make the area as small as possible (increase the area of the certain part). It is desirable to evaluate the classification of agricultural products as accurately as possible.

【0009】このような観点から、上記撮像画像のうち
の輪郭から所定範囲の幅を不確かな部分として除去する
画像処理について更に検討したところ、ハレーション、
ボケ、画像欠け等が起こり易い部分というのは、農産物
の表面を仮に滑らかな曲面であると仮定したときに、農
産物表面上のある任意の点に立てた法線(曲面に垂直な
線)と、この点から撮像手段の受光部を結んだ線との間
でなす角度が所定の角度以上になることを目安にしてそ
の点の存在する領域が該当すると本発明者は考えた。つ
まり、斜視の角度が大きい領域の画像は、本来の農産物
表面に由来する情報以外のものの影響が大きいと思われ
るからである。
From such a viewpoint, the image processing for removing the width of a predetermined range from the contour of the captured image as an uncertain part was further studied.
The part where blur, image missing, etc. are likely to occur is defined as a normal line (a line perpendicular to the curved surface) established at an arbitrary point on the agricultural product surface, assuming that the surface of the agricultural product is a smooth curved surface. The inventor of the present invention considered that an area where the point is located corresponds to an angle formed between the point and a line connecting the light receiving unit of the imaging unit to a predetermined angle or more. In other words, it is considered that an image in a region where the oblique angle is large has a great influence on information other than the information derived from the original agricultural product surface.

【0010】この考えによれば、除去すべき幅の大きさ
は撮像方向と農産物の球塊状等の形状の関係によって一
定ではなく、例えば、農産物がラクビーボール型の形状
をなす場合の平面画像と側面画像とでは除去すべき幅の
大きさは同じでないし、また同じ側面画像であっても側
面域と上面域とでは同幅は必ずしも同じでない。また、
温州ミカンのような比較的偏平な農産物と上記ラクビー
ボール型の形状の農産物とでも、除去すべき幅の大きさ
は同じでない。
According to this idea, the size of the width to be removed is not constant depending on the relationship between the imaging direction and the shape of the agricultural product, such as a sphere, and, for example, a flat image when the agricultural product has a rugby ball shape. The size of the width to be removed is not the same in the side image, and the same width is not necessarily the same in the side region and the top region even for the same side image. Also,
The width of the width to be removed is not the same between relatively flat agricultural products such as Unshu Mandarin orange and the above-mentioned rugby ball type agricultural products.

【0011】また以上のこととは別に、近時において農
産物の仕分に用いられる場合が多いフリートレイと呼ば
れる受皿を使用した場合には、農産物は通常この受皿の
中央に設けた窪み部(凹部)にある程度沈み込んだ状態
で搬送されるので、この受皿に沈み込んだ部分は農産物
の画像としては撮像されない。にも拘わらず、この場合
も撮像された画像の輪郭から一定幅の範囲を除去する画
像処理を行えば、本来不確かな部分には該当しない領域
をも除去してしまう可能性があり、この領域に等級判定
に影響する疵等が存在していればこれを無視した判定を
行う結果になって、機器計測による判定・評価の信頼性
を損なうという問題がある。
Apart from the above, when a tray called a free tray, which is often used for sorting agricultural products in recent years, is used, the agricultural product is usually provided in a depression (recess) provided at the center of the tray. Is transported in a state in which it sinks to some extent, so that the part that sinks in the pan is not captured as an image of agricultural products. Nevertheless, even in this case, if image processing for removing a range of a fixed width from the outline of the captured image is performed, there is a possibility that a region that does not correspond to an originally uncertain portion may be removed. If there is a flaw or the like that affects the grade determination, the determination is ignored, and there is a problem that the reliability of the determination / evaluation by the instrument measurement is impaired.

【0012】本発明はこの様な従来の問題点を解消し、
判定・評価の信頼性を向上させることができる農産物の
画像生成装置及びこれを用いた仕分区分判定装置を提供
することを目的としてなされたものである。
The present invention solves such a conventional problem,
It is an object of the present invention to provide an agricultural product image generation device capable of improving the reliability of determination / evaluation and a sorting classification determination device using the same.

【0013】[0013]

【課題を解決するための手段】上記目的は、本願の特許
請求の範囲の各請求項に記載した下記(1)〜(8)の
発明により達成される。
The above object is achieved by the following inventions (1) to (8) described in the claims of the present application.

【0014】(1)の農産物の仕分け判定に用いる画像
生成装置の発明は、やや窪みをもった農産物載置面に載
って搬送される農産物の少なくとも側面を撮像する撮像
手段と、得られた農産物の側面撮像画像からその輪郭に
沿って所定の幅内の撮像画像情報を除去して農産物の等
級要素等の外観に係わる判定をするための外観判定画像
の領域を決める画像処理手段とを備え、この画像処理手
段は、画像輪郭に沿って区画を複数に分割し、少なくと
も農産物の側面撮像画像の下面域の除去幅をゼロとする
か、あるいは下面域の除去幅を上面域の除去幅よりも小
幅とすることを特徴とする。
(1) The invention of an image generating apparatus used for judging the sorting of agricultural products is provided by: an imaging means for imaging at least a side surface of the agricultural product conveyed on a slightly depressed agricultural product mounting surface; Image processing means for removing the captured image information within a predetermined width along the outline from the side captured image to determine the area of the appearance determination image for determining the appearance of the grade element of the agricultural product, This image processing means divides the section into a plurality of sections along the image outline, and sets the removal width of the lower surface area of at least the side captured image of the agricultural product to zero, or makes the removal width of the lower surface area smaller than the removal width of the upper surface area. It is characterized by having a small width.

【0015】上記構成において「やや窪みをもった農産
物載置面」というのは、コンベアに載せた農産物が移動
しないように安定載置する受部(凹部)をいい、コンベ
アに固定的に設けられたバケット式あるいはこれに類似
の形式のものや、コンベアとは機械的に連結されていな
い受皿に窪み(凹部)を設けたいわゆるフリートレイと
称されるものなどの農産物載置面が例示される。
In the above configuration, the term "slightly concave agricultural product mounting surface" refers to a receiving portion (recess) for stably mounting agricultural products placed on the conveyor so as not to move, and is fixedly provided on the conveyor. Agricultural product mounting surfaces such as a bucket type or a similar type, and a so-called free tray in which a recess (recess) is provided in a tray not mechanically connected to a conveyor are exemplified. .

【0016】「撮像手段」はCCD(チャージ カップ
ルド デバイス)カメラや、その他の撮像素子、あるい
はこれとミラーを組合わせにより構成され、画像処理を
画素毎に処理する好ましい態様のためには、X,Yマト
リックス状の配列の各画素信号として撮像する手段が用
いられる。照明ランプ等もこの撮像手段の一部を構成す
る。
The "imaging means" is constituted by a CCD (Charge Coupled Device) camera, another imaging device, or a combination of the imaging device and a mirror. , Y matrix is used as an image signal for each pixel signal. An illumination lamp and the like also constitute a part of the imaging means.

【0017】「画像処理手段」は、通常はMPU等のコ
ンピュータ技術を用いて構成され、画像処理は予め定め
たプログラムにより演算制御される。
The "image processing means" is usually constructed using a computer technology such as an MPU, and the image processing is arithmetically controlled by a predetermined program.

【0018】なお、上記構成は、農産物の外観に基づく
等級判定をするのに適当な領域である外観判定画像のう
ちの農産物側面の画像を生成するためのものを特定して
いるが、外観に基づく等級判定には平面画像を併せて用
いるのが普通であるから、この平面画像を撮像する手
段、平面撮像画像からその画像輪郭に沿って所定幅の不
確かな情報が含まれる可能性のある領域を除去する画像
処理手段を併有することを除外するものではなく、また
外観画像の生成とは別に、農産物の内部品質を計測する
手段やその他の階級要素を計測する手段を併有すること
を除外するものでもないことは言うまでもない。上記発
明(1)の構成による処理は、これらの他の仕分区分を
判定するための等級・階級要素を計測し、画像処理し、
判定する処理を、並行してあるいは順次に行うことがで
きるものである。
The above configuration specifies an image for generating an image of a side surface of an agricultural product in the appearance determination image, which is an area suitable for performing a grade determination based on the appearance of the agricultural product. Since it is common to use a plane image together for the grading judgment based on the area, means for capturing this plane image, an area from the plane captured image that may contain uncertain information of a predetermined width along the image contour It does not exclude having an image processing means for removing the image, and also excluding having a means for measuring the internal quality of agricultural products and a means for measuring other class elements separately from the generation of the appearance image. Needless to say, it is not a thing. In the processing according to the configuration of the above invention (1), a class / class element for determining these other sorting categories is measured, and image processing is performed.
The determination process can be performed in parallel or sequentially.

【0019】この発明(1)によれば、農産物の種類に
より異なる形状に応じて、等級判定の際に、異常な情報
が含まれる可能性のある領域(不確かな部分)を適切に
除外して判定・評価することができるので、判定の精度
が向上し、信頼性の高い農産物の仕分けが実現できる。
特に側面と共に平面を撮像することにより、更には必要
に応じて底面を撮像することにより、外観判定画像の領
域をより適した撮像画像(側面,平面,底面)に振り分
けるようにすれば、判定の信頼性をより高めることがで
きる。
According to the present invention (1), a region (uncertain portion) that may contain abnormal information is appropriately excluded at the time of class determination according to different shapes depending on the types of agricultural products. Since determination and evaluation can be performed, the accuracy of the determination is improved, and highly reliable sorting of agricultural products can be realized.
In particular, by imaging the plane together with the side surface, and further imaging the bottom surface as needed, the area of the appearance determination image can be allocated to more appropriate captured images (side surface, plane surface, and bottom surface). Reliability can be further improved.

【0020】また、一つの農産物のうちでも、異常な情
報が含まれる可能性のある領域の幅(輪郭からの幅)が
その形状により同じでない場合も、例えば法線と受光線
の間がなす上記除去目安角度に応じて除去幅を部分的に
適切に変更できるので、判定の精度が高く、信頼性の高
い農産物の仕分けを実現できる。なお、画像輪郭に沿っ
て除去幅を変更する範囲を複数の区画に分割するという
のは、例えば、側面撮像画像において、上面域、側面
域、底面域に分ける場合などのことをいう。
Further, even if the width (width from the contour) of a region where abnormal information may be included in one agricultural product is not the same due to its shape, for example, the distance between the normal line and the light receiving line is formed. Since the removal width can be partially and appropriately changed according to the above-mentioned removal reference angle, highly accurate sorting of agricultural products with high determination accuracy can be realized. Note that dividing the range in which the removal width is changed along the image contour into a plurality of sections means, for example, a case where the side captured image is divided into a top area, a side area, and a bottom area.

【0021】(2)の農産物の仕分け判定に用いる画像
生成装置の発明は、やや窪みをもった農産物載置面に載
って搬送される農産物の少なくとも側面を撮像する撮像
手段と、得られた農産物の側面撮像画像からその輪郭に
沿って所定の幅内の撮像画像情報を除去して農産物の外
観に係わる判定をするための外観判定画像の領域を決め
る画像処理手段とを備え、この画像処理手段は、画像輪
郭に沿って区画を複数に分割し、除去する前記所定幅の
大きさを前記分割した側面撮像画像の区画に分けて変更
可能とする除去幅変更手段を有することを特徴とする。
(2) The invention of an image generating apparatus used for judging the sorting of agricultural products is provided by an image pickup means for imaging at least a side surface of the agricultural product conveyed on a slightly recessed agricultural product mounting surface, and an obtained agricultural product. Image processing means for determining a region of an appearance determination image for making a determination relating to the appearance of the agricultural product by removing captured image information within a predetermined width along the contour from the side captured image of the image processing means; Is characterized by having a removal width changing unit that divides a section into a plurality of sections along an image outline, and that can change the size of the predetermined width to be removed by dividing the section into the divided side captured image.

【0022】この発明において、画像処理に含まれる
「除去幅変更手段」は、選別する農産物の種類等に応じ
て経験的にあるいは実験的に、除去することが適当な幅
を決めるものであり、一般的には、上述したように、農
産物の表面を滑らかな曲面と仮定したときに、農産物表
面上の任意の点に立てた法線(曲面に垂直な線)と、こ
の点から撮像手段の受光部を結んだ線(以下便宜的に
「受光線」という)との間でなす角度が所定の角度(以
下「除去目安角度」という)以上になることを目安にし
て、除去幅を決めることができる。なお、該除去目安角
度は農産物の種類等によっても一律ではないが、一般的
には40゜〜50°の範囲を目安とすることができ、一
例的に言えば45°以上の範囲で経験的、あるいは繰り
返しの試験によって決めることができる。
In the present invention, the "removal width changing means" included in the image processing determines an appropriate width to be removed empirically or experimentally in accordance with the kind of the agricultural product to be selected. In general, as described above, when the surface of an agricultural product is assumed to be a smooth curved surface, a normal line (line perpendicular to the curved surface) set at an arbitrary point on the agricultural product surface, and the point of Determining the removal width based on the fact that the angle formed between the line connecting the light receiving parts (hereinafter referred to as “light receiving line” for convenience) is equal to or greater than a predetermined angle (hereinafter referred to as “removal guide angle”). Can be. The removal target angle is not uniform depending on the type of agricultural products, but can be generally set in a range of 40 ° to 50 °, for example, empirically in a range of 45 ° or more. Or by repeated testing.

【0023】この発明(2)によれば、除去幅を変更す
ることで、対象とする農産物毎に適した不確かな部分を
適切に選択することができる。
According to the invention (2), by changing the removal width, an uncertain portion suitable for each target agricultural product can be appropriately selected.

【0024】(3)の発明は、上記(2)の発明におい
て、除去幅変更手段が、少なくとも農産物の側面撮像画
像の下面域の除去幅をゼロとするか、あるいは下面域の
除去幅を上面域の除去幅よりも小幅とするものであるこ
とを特徴とする。
According to the invention of (3), in the invention of (2), the removal width changing means sets at least the removal width of the lower surface area of the side image of the agricultural product to zero, or sets the removal width of the lower surface area to the upper surface. The width is smaller than the removal width of the area.

【0025】上記において下面域の除去幅をゼロにする
のは、例えば農産物を平面上に載置した場合の下面域の
除去幅より受皿等の凹部に沈み込む長さが大きければ、
受皿上に現れている下面域の部分は上記除去目安角度以
下の除去する必要がない部分(除去するとむしろ判定精
度を低下させる)となるからであり、この下面域では側
面撮像画像を除去しない。また、下面域の除去幅を上面
域の除去幅よりも小幅にするのは、上記農産物の凹部へ
の沈み込み量が小さく、除去目安角度以上の面が側面撮
像画像内の下面域に一定程度存在する場合である。この
場合には、必要な小さい幅範囲で側面撮像画像の下面域
を除去すればよいことになる。
In the above description, the reason why the removal width of the lower surface area is set to zero is that, for example, if the length of sinking in a concave portion such as a saucer is larger than the removal width of the lower surface area when the agricultural product is placed on a flat surface.
This is because the portion of the lower surface area appearing on the pan is a portion that does not need to be removed below the above removal reference angle (removal rather reduces the determination accuracy), and the side surface captured image is not removed in this lower surface area. In addition, the removal width of the lower surface area is made smaller than the removal width of the upper surface area because the amount of the agricultural product sinking into the concave portion is small, and the surface equal to or larger than the removal reference angle is fixed to the lower surface area in the side surface image. If it exists. In this case, it is sufficient to remove the lower surface area of the side surface captured image in a necessary small width range.

【0026】この発明(3)によれば、限定されるもの
ではないが、フリートレイの中央凹部に沈み込むように
載置された農産物の外観に基づく等級判定に有効な領域
を広く利用できるので、精度が高く、信頼性の高い農産
物の仕分けを実現できる。
According to the invention (3), although not limited, an area effective for determining the grade based on the appearance of the agricultural product placed so as to sink into the central recess of the free tray can be widely used. It can realize highly accurate and reliable sorting of agricultural products.

【0027】(4)の発明は、上記の各発明において、
除去幅変更手段が、農産物の側面撮像画像と、該側面撮
像画像を複数の方向に所定画素数ずらせたシフト画像の
複数とを用い、各画素のアンド処理で外観判定画像の領
域を決めるものであることを特徴とする。
The invention of (4) is based on each of the above inventions.
The removal width changing means uses the side image of the agricultural product and a plurality of shift images obtained by shifting the side image by a predetermined number of pixels in a plurality of directions, and determines an area of the appearance determination image by AND processing of each pixel. There is a feature.

【0028】上記において「所定画素数ずらせたシフト
画像」は、外観判定画像の領域を決めるためにだけ利用
するものであり、例えば、側面撮像画像に対してシフト
画像をその各画素の上下方向のアドレスを下方向に10
画素シフトしたとすれば、上記各画素のアンド処理によ
って、側面撮像画像の上10画素は外観判定画像の領域
から除去されることになる。ただし上記(1)又は
(3)の発明においては、側面撮像画像の下面域の除去
幅はゼロ又は小幅なものとされるので、外観判定画像に
おける下10画素の除去については、除去しないかシフ
トする画素数は少なくされる。
In the above description, the "shifted image shifted by a predetermined number of pixels" is used only for determining the area of the appearance determination image. For example, the shifted image is shifted from the side image in the vertical direction of each pixel. Address down 10
If the pixel is shifted, the upper 10 pixels of the side image are removed from the area of the appearance determination image by the AND processing of each pixel. However, in the invention of the above (1) or (3), since the removal width of the lower surface area of the side image is set to zero or small, the removal of the lower 10 pixels in the appearance determination image is not removed or shifted. The number of pixels to be processed is reduced.

【0029】この発明(4)によれば、画像処理技術に
おける収縮処理とこれに付加した補正処理によって、側
面撮像画像から、目的とする農産物の等級判定に適した
外観判定画像を生成する処理が容易に行えるという利点
がある。
According to the present invention (4), a process for generating an appearance judgment image suitable for judging the grade of a target agricultural product from the side image by the shrinking process and the correction process added thereto in the image processing technique. There is an advantage that it can be easily performed.

【0030】(5)の発明は、上記の各発明において、
除去幅変更手段が、撮像する農産物が側面から視て上下
方向が短尺な略楕円形状であるときに、側面撮像画像の
上面域の除去幅を、側面域の除去幅よりも大きく設定す
るものであることを特徴とする。
The invention of (5) is characterized in that, in each of the above inventions,
The removal width changing means sets the removal width of the upper surface area of the side captured image to be larger than the removal width of the side area when the agricultural product to be imaged has a substantially elliptical shape whose vertical direction is short when viewed from the side. There is a feature.

【0031】この発明によれば上記のような形状の農産
物、例えば温州みかん、トマト、柿等の農産物を仕分け
する場合に、異常な情報が含まれる可能性のある領域を
適切に除去(除外)することができる。
According to the present invention, when sorting agricultural products having the above shapes, for example, agricultural products such as Unshu mandarin oranges, tomatoes, persimmons, etc., appropriately remove (exclude) regions that may contain abnormal information. can do.

【0032】(6)の農産物の仕分区分判定装置の発明
は、外観判定画像の領域を決める上記(1)〜(5)の
いずれかの発明の画像処理手段を備えた画像生成装置
と、該領域内の外観判定画像を農産物の等級判定の一つ
として用いる等級判定手段とを備えたことを特徴とす
る。
(6) The invention of an apparatus for determining sorting of agricultural products according to the invention comprises an image generating apparatus comprising the image processing means according to any one of the above-mentioned inventions (1) to (5) for determining an area of an appearance determination image. Grade determining means for using the appearance determination image in the area as one of the grade determinations of the agricultural product.

【0033】上記における「等級判定手段」は、通常は
MPUを含むコンピュータ技術を用いて構成される。具
体的には、計測された画像中の輝度が予め定めた閾値と
の比較で低い部分の広がりが一定面積を越える場合には
当該面積の部分を「疵」と判定するとか、撮像手段にバ
ンドパスフィルタを配して所定波長の光が検出されるこ
とを通じて農産物の色を判定するとか、検出光を色ヒス
トグラム解析して色を判定するとか、農産物の種類に応
じて求められる等級要素に合致した等級評価をする手段
を用いることができる。
The above-mentioned "grade judging means" is usually constituted by using computer technology including MPU. Specifically, when the spread of the low portion exceeds a certain area by comparing the measured luminance in the image with a predetermined threshold value, the portion having that area is determined to be a “flaw”, A pass filter is arranged to determine the color of agricultural products through detection of light of a predetermined wavelength, or color histogram analysis of the detected light is used to determine the color, or it matches the grade factor required for the type of agricultural product Means for performing a grade evaluation can be used.

【0034】この発明によれば、農産物の側面の撮像画
像(通常は併せて平面の撮像画像)に基づく等級判定を
外観に関して行うことができ、しかもその信頼性は、適
切な範囲を必要十分に決めて行うことができるので高く
確保することができる。
According to the present invention, it is possible to make a grade judgment based on a captured image of a side surface of an agricultural product (usually, a captured image of a flat surface) with respect to the appearance, and the reliability of the product must be within an appropriate range. Since it can be decided, it can be secured high.

【0035】(7)の農産物の仕分区分判定装置の発明
は、上記(6)の発明に更に、画像処理前の撮像画像を
農産物の階級判定の一つとして用いる階級判定手段を備
えたことを特徴とする。
(7) The invention of the apparatus for classifying and sorting agricultural products according to the present invention is characterized in that the invention of (6) is further provided with a class determining means for using the taken image before image processing as one of the classes of agricultural products. Features.

【0036】この発明によれば、上記(6)の発明に加
えて、外観撮像画像を農産物の大きさ(階級要素)の判
定に利用できるという利点がある。
According to this invention, in addition to the above-mentioned invention (6), there is an advantage that the appearance captured image can be used for determining the size (class element) of the agricultural product.

【0037】(8)の発明は、上記(6)又は(7)の
発明の等級判定手段が、少なくとも農産物の色及び/又
は疵により等級を判定するものであることを特徴とす
る。
The invention of (8) is characterized in that the grade judging means of the invention of (6) or (7) judges the grade at least based on the color and / or the flaw of the agricultural product.

【0038】この発明によれば、農産物の側面の撮像画
像に基づく等級判定を、外観の中でも重要な色及び/又
は疵に関して信頼性高く行うことができる。
According to the present invention, a grade determination based on a picked-up image of a side surface of an agricultural product can be performed with a high degree of reliability regarding important colors and / or flaws in appearance.

【0039】[0039]

【発明の実施の形態】実施形態1 図1〜図9に示された本例において、図1は農産物選別
装置1の構成概要を示し、101は農産物Pを選別のた
めに搬送する搬送コンベアを示している。そしてその搬
送上流側には、農産物の外観を計測する計測ステージが
配置され、搬送下流側には各仕分区分別の分岐コンベア
102,102,・・・・が分岐接続された仕分ステー
ジが配置されている。なお、本例においては、説明の便
宜上、計測は外観撮像のための装置のみを図示している
が、他の内部品質等を計測する装置を併設することもで
きる。また本例における搬送コンベア101は、図4に
示すように、搬送横方向に沿って中央部が窪んだ搬送面
を形成するように構成されている。
BEST MODE FOR CARRYING OUT THE INVENTION Embodiment 1 In the present embodiment shown in FIGS. 1 to 9, FIG. 1 shows an outline of the configuration of an agricultural product sorting apparatus 1, and 101 shows a transport conveyor for transporting agricultural products P for sorting. Is shown. On the upstream side of the transport, a measuring stage for measuring the appearance of agricultural products is arranged, and on the downstream side of the transport, a sorting stage in which branch conveyors 102, 102,... ing. In this example, for the sake of convenience of description, only a device for external appearance imaging is shown for measurement, but another device for measuring internal quality or the like may be provided. Further, as shown in FIG. 4, the transport conveyor 101 in this example is configured to form a transport surface in which a central portion is depressed along the transport horizontal direction.

【0040】上記搬送コンベア1の上流側に配置される
計測ステージにおいては、画像生成装置2の計測部を構
成する照明ランプ201と撮像カメラ(例えばRGBカ
メラ)202とが設けられ、これらの詳細は図2,図3
に示される。3はマイクロコンピュータからなる演算制
御装置であり、本例では、上記撮像カメラ202で撮像
した農産物Pの側面撮像画像と、平面撮像画像とから、
側面と平面の各外観判定画像の領域を決める画像処理部
301、及びこの画像処理手段301による撮像画像の
輪郭に沿った除去幅を変更する除去幅変更部302とが
設けられて、これらが上記カメラ202等と共に仕分区
分の判定に用いる画像生成装置2を構成する。なお、図
では画像処理手段301及び除去幅変更手段302をブ
ロックダイヤグラムで示しているが、実際にはコンピュ
ータプログラムとして設定される。また、除去幅変更部
302は、後述するシフト画像のシフト量を変更する手
段として構成されるが、一品種用に特化した農産物選別
装置等では省略することもできる。
On the measurement stage arranged on the upstream side of the conveyor 1, an illumination lamp 201 and an imaging camera (for example, an RGB camera) 202 which constitute a measurement section of the image generating apparatus 2 are provided. Figures 2 and 3
Is shown in Numeral 3 denotes an arithmetic and control unit composed of a microcomputer. In this example, the arithmetic and control unit 3 includes a side image of the agricultural product P imaged by the imaging camera 202 and a planar image.
An image processing unit 301 that determines the area of each appearance determination image on the side surface and the plane, and a removal width changing unit 302 that changes the removal width along the contour of the captured image by the image processing unit 301 are provided. Together with the camera 202 and the like, the image generation device 2 used for determining the sorting classification is configured. Although the image processing unit 301 and the removal width changing unit 302 are shown in the block diagram in the figure, they are actually set as computer programs. The removal width changing unit 302 is configured as a means for changing a shift amount of a shift image, which will be described later, but may be omitted in an agricultural product sorting apparatus specialized for one type.

【0041】又、上記演算制御装置3には、画像処理し
ない外観撮像画像に基づいて農産物の大きさを判定・評
価し、また画像処理後の平面の外観判定画像及び側面の
外観判定画像に基づいて農産物の等級を判定・評価する
判定部303が設けられていて、これらの判定結果によ
り農産物の仕分区分が決められる。
Further, the arithmetic and control unit 3 determines and evaluates the size of the agricultural product based on the appearance captured image that is not subjected to the image processing, and based on the plane appearance determination image after the image processing and the side appearance determination image. A judgment unit 303 for judging and evaluating the grade of the agricultural product is provided, and the classification of the agricultural product is determined based on these determination results.

【0042】等級の判定・評価は、例えば明度の低い部
分が所定の大きさ以上であるときにこれを疵と判定した
り、色解析により農産物の色を判定したりする場合を挙
げることができる。
The evaluation and evaluation of the grade include, for example, a case where a low-brightness portion is larger than a predetermined size, which is judged as a flaw, or a case where the color of an agricultural product is judged by color analysis. .

【0043】得られた各農産物の仕分区分情報は、搬送
下流側に分岐接続されている分岐コンベア102,10
2,・・・・に連係した排出装置の制御部4,4,・・
・に送られ、判定された仕分区分に対応する分岐コンベ
ア102に排出される。
The obtained sorting classification information of each agricultural product is stored in the branch conveyors 102 and 10 branch-connected to the downstream side of the transportation.
Control unit of discharge device linked to 2,.
And is discharged to the branch conveyor 102 corresponding to the determined sorting category.

【0044】図2及び図3は、画像生成装置2の計測部
を示しており、搬送コンベア101の搬送路の両側に縦
長の斜置きミラー203が一対に配置されていて、照明
ランプ201からの光が農産物Pの両側面に反射して該
ミラー203による反射光を上方のカメラ202が撮像
して側面撮像画像とされる。また農産物の上面で反射し
た反射光は同様に上方のカメラで撮像して平面撮像画像
とされる。
FIGS. 2 and 3 show a measuring section of the image generating apparatus 2, wherein a pair of vertically long inclined mirrors 203 are arranged on both sides of the transport path of the transport conveyor 101, The light is reflected on both side surfaces of the agricultural product P, and the reflected light from the mirror 203 is imaged by the upper camera 202 to be a side image. Similarly, the reflected light reflected on the upper surface of the agricultural product is imaged by the upper camera to be a plane image.

【0045】このような撮像において、側面撮像画像に
ついては、図4に示すように、搬送コンベア101の窪
みに沈み込んだ部分(斜線部)は撮像できない。かかる
場合に撮像画像の輪郭に沿って図11に示したように一
定幅で除去(除去領域B´)を行うと、本来は色や疵等
を検出することが適当な領域が、その撮像画像の下面域
の除去部分に含まれてしまうことになる。
In such imaging, as shown in FIG. 4, a portion (a hatched portion) sinking into the dent of the conveyor 101 cannot be imaged. In such a case, if the removal (removal area B ′) is performed along the contour of the captured image with a constant width as shown in FIG. Is included in the removed portion of the lower surface area.

【0046】そこで本例においては、側面の外観判定画
像の領域Aを決める際に、図5に示したように、左右方
向及び下方向に所定画素数だけ画像をずらせたシフト画
像S1,S2,S3(例えば側方に9mm(S1,S
2)、シフト幅を下方に11mm(S3)ずらせたシフ
ト画像)を作成し、各画素毎に本来の撮像画像と三つの
シフト画像(S1〜S3)のアンド信号出力がある領域
を、側面の外観判定画像の領域Aとした。したがって撮
像画像を上方向にずらせたシフト画像を使用していない
ので、撮像画像の輪郭に沿った一定幅の除去(除去領域
B)は該画像の下面域では行われず、図6に示したよう
に、撮像画像の側面域及び上面域で輪郭から一定幅の除
去が行われた側面の外観判定画像の領域Aが決定される
ことになる。なお、平面の外観判定画像aについては、
側面撮像画像のようなコンベアによる撮像域のカットと
いう問題がないので、図8に示すように撮像画像の輪郭
から一定幅(例えば7mm)の部分を除去した除去領域
bを除いた内側を該平面の外観判定画像aとした。
Therefore, in this example, when determining the area A of the side-surface appearance judgment image, as shown in FIG. 5, the shifted images S1, S2, which are shifted by a predetermined number of pixels in the horizontal and downward directions. S3 (for example, 9 mm laterally (S1, S
2) A shift image in which the shift width is shifted downward by 11 mm (S3)) is created, and an area where the original captured image and the AND signal output of the three shift images (S1 to S3) are provided for each pixel is defined as a side surface. It was set as the area A of the appearance determination image. Therefore, since a shifted image in which the captured image is shifted upward is not used, removal of a fixed width along the contour of the captured image (removal region B) is not performed in the lower surface area of the image, as shown in FIG. Then, the area A of the side surface appearance determination image from which the fixed width is removed from the outline in the side surface area and the upper surface area of the captured image is determined. It should be noted that, regarding the planar appearance determination image a,
Since there is no problem of cutting the imaging area by the conveyor as in the case of the side image, the inside of the outline of the image except for the removal area b in which a portion of a fixed width (for example, 7 mm) has been removed from the outline of the image is shown in FIG. Was determined as the appearance determination image a.

【0047】図7は以上の操作によって得られる側面の
撮像画像、外観判定画像の領域A及び農産物の外観に存
在する疵、ハレーション等による誤検出部などの関係を
図解的に示したものであり、この図中の下面域に近い位
置に存在する疵は、本例によれば側面の外観判定画像の
領域Aに含まれるので確実に検出できるが、図11のよ
うに下面域を一定幅で除去するようにして生成された側
面の外観判定画像の領域A´の場合には、同疵が除去領
域B´内に含まれることになる虞れがあるので、疵があ
るにも拘わらず高い等級の仕分区分に判定されて判定装
置の信頼性を損なう結果となってしまう。
FIG. 7 schematically shows the relationship between the captured image of the side surface obtained by the above operation, the area A of the appearance judgment image, the flaws present in the appearance of the agricultural product, and the erroneous detection part due to halation and the like. According to this example, the flaw existing at a position close to the lower surface area in this figure can be reliably detected because it is included in the area A of the side surface appearance judgment image, but as shown in FIG. In the case of the region A ′ of the side surface appearance determination image generated by removing, there is a possibility that the same flaw may be included in the removed area B ′, so that it is high despite the presence of the flaw. It is determined that the classification is of a grade, and the reliability of the determination device is impaired.

【0048】図9は上記の演算制御装置3で行われる信
号処理の一例を図示したものであり、カメラ202で撮
像された各画素のRGB輝度信号(ディジタル信号)か
らなる撮像画像情報を画像入力し、これを一つの処理と
しては二値化して、所定の閾値との比較により農産物の
外形形状を演算算出し、その大きさを求めて階級判定を
行う。また、変形の度合を求めて、等級判定の一つの情
報とする。更に二値化した信号は、上述したシフト画像
を使用した方法により、撮像画像の輪郭に沿って不確か
な部分を除去して、側面の外観判定画像の領域Aを生成
し、また平面の外観判定画像については、平面撮像画像
の輪郭から一定の幅の部分を除去して平面の外観判定画
像の領域aを生成する。
FIG. 9 shows an example of the signal processing performed by the arithmetic and control unit 3 described above. The captured image information comprising the RGB luminance signals (digital signals) of each pixel captured by the camera 202 is input to the image input device. Then, this is binarized as one process, and the outer shape of the agricultural product is calculated and calculated by comparison with a predetermined threshold value, and the size thereof is obtained to determine the class. Also, the degree of deformation is obtained and used as one piece of information for class determination. Further, the binarized signal is subjected to the above-described method using the shifted image to remove an uncertain portion along the outline of the captured image, to generate a region A of the side surface appearance determination image, and to determine the planar appearance determination. As for the image, the area a of the planar appearance determination image is generated by removing a portion having a constant width from the outline of the planar captured image.

【0049】演算制御装置3における撮像画像情報を使
用したもう一つの処理は、各画素信号を色変換し、例え
ば明度の低い部分が上記外観判定画像の領域A,a内に
存在しているか否かにより傷害の有無として等級判定の
もう一つの情報とする。更に色変換した情報を用いて色
ヒストグラム解析により着色度を求め、これを更にもう
一つの等級判定の情報とする。
Another processing using the captured image information in the arithmetic and control unit 3 is to perform color conversion on each pixel signal, for example, to determine whether a low brightness portion exists in the areas A and a of the appearance determination image. According to this, it is regarded as another information of the grade judgment as the presence or absence of injury. Further, the degree of coloring is obtained by color histogram analysis using the information obtained by the color conversion, and this is used as further information for class determination.

【0050】以上の三つの等級情報に基づいて農産物の
等級判定を行う。
The grade of the agricultural product is determined based on the above three grade information.

【0051】そして、得られた階級判定の結果と等級判
定の結果から仕分区分を求め、仕分出力として図1で説
明した排出装置の制御部4に送られる。
Then, a classification is obtained from the obtained result of the class judgment and the result of the class judgment, and is sent to the control unit 4 of the discharge device described in FIG.

【0052】なお、以上説明した本例の構成によれば、
農産物の判定は平面撮像画像と側面撮像画像のみによっ
て行っているが、これには底面撮像画像を加味すること
も出来、このためには例えば、特許第2812466号
公報に記載されているように、農産物がコンベアを乗り
移る際にその乗り移り部の隙間の下方から撮像する方法
を用いることができる。
According to the configuration of the present embodiment described above,
Although the determination of agricultural products is performed only by the plane captured image and the side captured image, it is also possible to add a bottom captured image to this, for example, as described in Japanese Patent No. 2812466, When the agricultural product moves on the conveyor, a method of imaging from below the gap of the transfer portion can be used.

【0053】また、農産物Pの側面の撮像は、上記例で
は対向一対のミラー203を利用してこの間を通過する
農産物を撮像するようにしているが、図10に示すよう
に農産物の側面を4分割し(4分割した側面は図中にP
1,P2,P3,P4で示した)、搬送コンベアの両側
斜め前及び両側斜め後からこれらの各分割面を撮像する
ようにして、側面画像の側面域における不確かな部分を
実質的になくすようにすることもできる(特公平7−9
9326号公報参照)。なおP5は平面撮像される上面
を示している。
In the above example, the side of the agricultural product P is imaged using the pair of mirrors 203 facing each other to image the agricultural product passing therethrough. However, as shown in FIG. Divide (the four divided sides are P
1, P2, P3, and P4), and each of these divided planes is imaged obliquely in front of and on both sides of the conveyor, so as to substantially eliminate uncertainty in the side area of the side image. (Tokuhei 7-9)
9326). Note that P5 indicates the upper surface on which planar imaging is performed.

【0054】[0054]

【発明の効果】本願の発明によれば、農産物の種類によ
り異なる形状に応じて、等級判定の際に、異常な情報が
含まれる可能性のある領域(不確かな部分)を適切に除
外して判定・評価することができるので、判定の精度が
向上し、信頼性の高い農産物の仕分けが実現できる。
According to the invention of the present application, a region (uncertain portion) that may contain abnormal information is appropriately excluded at the time of class determination according to the shape that varies depending on the type of agricultural product. Since determination and evaluation can be performed, the accuracy of the determination is improved, and highly reliable sorting of agricultural products can be realized.

【0055】また、本願の発明(2)によれば、一つの
農産物のうちでも、異常な情報が含まれる可能性のある
領域の幅(輪郭からの幅)がその形状により同じでない
場合も、例えば法線と受光線の間がなす上記除去目安角
度に応じて除去幅を部分的に適切に変更できるので、判
定の精度が高く、信頼性の高い農産物の仕分けを実現で
きる。
Further, according to the invention (2) of the present application, even if the width (width from the contour) of a region where abnormal information may be included in one agricultural product is not the same due to its shape, For example, the removal width can be partially and appropriately changed according to the above-mentioned removal reference angle formed between the normal line and the light receiving line, so that highly accurate sorting of agricultural products with high determination accuracy can be realized.

【0056】本願の発明(3)によれば、フリートレイ
の中央凹部に沈み込むように載置された農産物の外観に
基づく等級判定に有効な領域を広く利用できるので、精
度が高く、信頼性の高い農産物の仕分けを実現できる。
According to the invention (3) of the present application, an effective area for the grade judgment based on the appearance of the agricultural product placed so as to sink into the central recess of the free tray can be widely used, so that the accuracy and the reliability are high. High-quality agricultural products can be sorted.

【0057】本願の発明(4)によれば、画像処理技術
における収縮処理とこれに付加した補正処理によって、
側面撮像画像から、目的とする農産物の等級判定に適し
た外観判定画像を生成する処理が容易に行えるという利
点がある。
According to the invention (4) of the present application, the contraction processing in the image processing technique and the correction processing added thereto enable the
There is an advantage that a process of generating an appearance determination image suitable for determining the grade of a target agricultural product can be easily performed from the side surface captured image.

【0058】本願の発明(5)によれば、特定の農産物
を仕分けする場合に、不確かな情報が含まれる可能性の
ある領域を、当該農産物の形状に応じて部分的に適切に
除去することができる。
According to the invention (5) of the present application, when sorting a specific agricultural product, an area that may contain uncertain information is appropriately and partially removed according to the shape of the agricultural product. Can be.

【0059】本願の発明(6)によれば、農産物の側面
の撮像画像(通常は併せて平面の撮像画像)に基づく等
級判定を外観に関して行うことができ、しかもその信頼
性は、適切な範囲を必要十分に決めて行うことができる
ので高く確保することができる。
According to the invention (6) of the present application, it is possible to make a grade determination based on a captured image of a side surface of an agricultural product (usually a captured image of a flat surface) with respect to the appearance, and the reliability is within an appropriate range. Can be determined as necessary and sufficiently, so that it can be secured at a high level.

【0060】本願の発明(7)によれば、上記(6)の
発明に加えて、外観撮像画像を農産物の大きさ(階級要
素)の判定に利用できる。
According to the invention (7) of the present application, in addition to the invention of the above (6), the appearance captured image can be used for determining the size (class element) of the agricultural product.

【0061】本願の発明(8)によれば、農産物の側面
の撮像画像に基づく等級判定を、外観の中でも重要な色
及び/又は疵に関して信頼性高く行うことができる。
According to the invention (8) of the present application, the grading judgment based on the picked-up image of the side surface of the agricultural product can be performed with respect to the important color and / or flaw in the appearance with high reliability.

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

【図1】本願発明の画像生成装置が適用される農産物選
別装置の構成概要を示した図。
FIG. 1 is a diagram showing an outline of the configuration of an agricultural product selection device to which an image generation device of the present invention is applied.

【図2】図1の画像生成装置の画像計測部の正面図。FIG. 2 is a front view of an image measurement unit of the image generation device of FIG.

【図3】図2の画像計測部の側面図。FIG. 3 is a side view of the image measuring unit in FIG. 2;

【図4】農産物の側面の撮像画像の領域を説明するため
の図。
FIG. 4 is a diagram for explaining a region of a captured image of a side surface of an agricultural product.

【図5】側面撮像画像から外観判定画像を生成する操作
を説明する図。
FIG. 5 is a diagram illustrating an operation of generating an appearance determination image from a side captured image.

【図6】生成された側面の外観判定画像の領域を示した
図。
FIG. 6 is a diagram illustrating a region of a generated side surface appearance determination image.

【図7】側面の外観判定画像と農産物表面に存在する疵
等との関係を示した図。
FIG. 7 is a diagram showing a relationship between an appearance determination image on a side surface and a flaw or the like present on the surface of an agricultural product.

【図8】平面の外観判定画像の領域を示した図。FIG. 8 is a diagram showing a region of a planar appearance determination image.

【図9】農産物の外観撮像から仕分区分判定に至る手順
を説明する図。
FIG. 9 is a view for explaining a procedure from imaging of the appearance of agricultural products to determination of sorting.

【図10】農産物の外観撮像の他の例を示した図。FIG. 10 is a diagram showing another example of the appearance imaging of agricultural products.

【図11】従来法により側面撮像画像から生成された外
観判定画像の領域を示した図。
FIG. 11 is a diagram showing a region of an appearance determination image generated from a side surface captured image by a conventional method.

【符号の説明】[Explanation of symbols]

1・・・農産物選別装置 101・・・搬送コンベア 102・・・分岐コンベア 2・・・画像生成装置 201・・・照明ランプ 202・・・撮像カメラ 203・・・ミラー 3・・・演算制御装置 301・・・画像処理部 302・・・除去幅変更部 303・・・判定部 4・・・排出装置の制御部 P・・・農産物 S1,S2,S3・・・シフト画像 A,A´,a・・・外観判定画像の領域 B,B´,b・・・除去領域 P1,P2,P3,P4・・・撮像される4分割側面 P5・・・撮像される上面 DESCRIPTION OF SYMBOLS 1 ... Agricultural product sorting apparatus 101 ... Conveyer conveyor 102 ... Branch conveyor 2 ... Image generation apparatus 201 ... Illumination lamp 202 ... Imaging camera 203 ... Mirror 3 ... Calculation control apparatus Reference numeral 301: Image processing unit 302: Removal width changing unit 303: Determination unit 4: Control unit of the discharge device P: Agricultural products S1, S2, S3: Shift images A, A ', a: Area of appearance judgment image B, B ', b: Removal area P1, P2, P3, P4: Four divided side surfaces to be imaged P5: Upper surface to be imaged

───────────────────────────────────────────────────── フロントページの続き (51)Int.Cl.7 識別記号 FI テーマコート゛(参考) G06T 7/60 250 G01B 11/24 A H K Fターム(参考) 2F065 AA51 AA61 CC00 DD04 FF04 GG12 JJ26 KK02 LL12 PP15 QQ04 QQ21 QQ24 RR05 TT03 UU05 3F079 AC06 CA21 CA32 CA42 CB25 CB29 CB35 DA11 DA21 5B057 AA15 BA15 CA08 CA12 CA16 CB08 CB12 CB16 CC03 CE09 DA07 DA08 DB02 DB09 DC05 DC09 DC16 DC22 5L096 AA06 BA03 CA04 CA14 CA17 FA06 FA14 FA69 ──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. 7 Identification symbol FI Theme coat ゛ (Reference) G06T 7/60 250 G01B 11/24 AH K F Term (Reference) 2F065 AA51 AA61 CC00 DD04 FF04 GG12 JJ26 KK02 LL12 PP15 QQ04 QQ21 QQ24 RR05 TT03 UU05 3F079 AC06 CA21 CA32 CA42 CB25 CB29 CB35 DA11 DA21 5B057 AA15 BA15 CA08 CA12 CA16 CB08 CB12 CB16 CC03 CE09 DA07 DA08 DB02 DB09 DC05 DC09 DC16 DC22 5L0904 CA1417

Claims (8)

【特許請求の範囲】[Claims] 【請求項1】 やや窪みをもった農産物載置面に載って
搬送される農産物の少なくとも側面を撮像する撮像手段
と、得られた農産物の側面撮像画像からその輪郭に沿っ
て所定の幅内の撮像画像情報を除去して農産物の外観に
係わる判定をするための外観判定画像の領域を決める画
像処理手段とを備え、この画像処理手段は、画像輪郭に
沿って区画を複数に分割し、少なくとも農産物の側面撮
像画像の下面域の除去幅をゼロとするか、あるいは下面
域の除去幅を上面域の除去幅よりも小幅とすることを特
徴とする農産物の仕分け判定に用いる画像生成装置。
An imaging means for imaging at least a side surface of an agricultural product carried on a slightly depressed agricultural product mounting surface, and a predetermined width along a contour from an obtained side image of the agricultural product. Image processing means for determining an area of an appearance determination image for removing the captured image information and making a determination relating to the appearance of the agricultural product, the image processing means dividing a section into a plurality of sections along the image outline, An image generating apparatus for use in agricultural product sorting determination, wherein a removal width of a lower surface area of a side image of a farm product is set to zero or a removal width of a lower surface area is made smaller than a removal width of an upper surface area.
【請求項2】 やや窪みをもった農産物載置面に載って
搬送される農産物の少なくとも側面を撮像する撮像手段
と、得られた農産物の側面撮像画像からその輪郭に沿っ
て所定の幅内の撮像画像情報を除去して農産物の外観に
係わる判定をするための外観判定画像の領域を決める画
像処理手段とを備え、この画像処理手段は、画像輪郭に
沿って区画を複数に分割し、除去する前記所定幅の大き
さを前記分割した側面撮像画像の区画に分けて変更可能
とする除去幅変更手段を有することを特徴とする農産物
の仕分け判定に用いる画像生成装置。
2. An imaging means for imaging at least a side surface of an agricultural product conveyed on a slightly recessed agricultural product mounting surface, and a predetermined width along a contour from an obtained side image of the agricultural product. Image processing means for determining an area of an appearance determination image for removing the captured image information and making a determination relating to the appearance of the agricultural product, wherein the image processing means divides the section into a plurality of sections along the image outline and removes the section. An image generating apparatus for use in agricultural product sorting determination, comprising: a removal width changing unit that allows the size of the predetermined width to be changed and divided into sections of the divided side captured image.
【請求項3】 前記除去幅変更手段は、少なくとも農産
物の側面撮像画像の下面域の除去幅をゼロとするか、あ
るいは下面域の除去幅を上面域の除去幅よりも小幅とす
るものであることを特徴とする請求項2に記載の農産物
の仕分け判定に用いる画像生成装置。
3. The removal width changing means sets at least the removal width of the lower surface area of the side image of the agricultural product to zero or makes the removal width of the lower surface area smaller than the removal width of the upper surface area. 3. The image generating apparatus according to claim 2, wherein the apparatus is used for determination of sorting of agricultural products.
【請求項4】 前記画像処理手段は、農産物の側面撮像
画像と、該側面撮像画像を複数の方向に所定画素数ずら
せたシフト画像の複数とを用い、各画素のアンド処理で
外観判定画像の領域を決めるものであることを特徴とす
る請求項1ないし3のいずれかに記載の農産物の仕分け
判定に用いる画像生成装置。
4. The image processing means uses an image of a side surface of an agricultural product and a plurality of shift images obtained by shifting the image of the side surface by a predetermined number of pixels in a plurality of directions. 4. The image generating apparatus according to claim 1, wherein the area is determined.
【請求項5】 前記画像処理手段は、撮像する農産物が
側面から視て上下方向が短尺な略楕円形状であるとき
に、側面撮像画像の上面域の除去幅を、側面域の除去幅
よりも大きく設定するものであることを特徴とする請求
項1ないし4のいずれかに記載の農産物の仕分け判定に
用いる画像生成装置。
5. The image processing means according to claim 1, wherein when the agricultural product to be imaged has a substantially elliptical shape whose vertical direction is short when viewed from the side, the removal width of the upper surface area of the captured side image is smaller than the removal width of the side area. 5. The image generating apparatus according to claim 1, wherein the image generating apparatus is set to a large value.
【請求項6】 外観判定画像の領域を決めるための請求
項1ないし5のいずれかに記載の前記画像処理手段を備
えた画像生成装置と、該領域内の外観判定画像を農産物
の等級判定の一つとして用いる等級判定手段とを備えた
ことを特徴とする農産物の仕分区分判定装置。
6. An image generating apparatus comprising the image processing means according to claim 1 for determining an area of an appearance determination image, and an image determination apparatus in the area for determining a grade of an agricultural product. An apparatus for classifying and classifying agricultural products, comprising: a grade judging means used as one.
【請求項7】 外観判定画像の領域を決めるための請求
項1ないし5のいずれかに記載の前記画像処理手段を備
えた画像生成装置と、該領域内の外観判定画像を農産物
の等級判定の一つとして用いる等級判定手段と、画像処
理前の撮像画像を農産物の階級判定の一つとして用いる
階級判定手段とを備えたことを特徴とする農産物の仕分
区分判定装置。
7. An image generating apparatus comprising the image processing means according to claim 1 for determining an area of an appearance determination image, and an image determination apparatus for determining a grade of an agricultural product in the area. An apparatus for classifying and classifying agricultural products, comprising: a class determining means used as one; and a class determining means using a captured image before image processing as one of the class determinations of agricultural products.
【請求項8】 前記等級判定手段は、少なくとも農産物
の色及び/又は疵により等級を判定するものであること
を特徴とする請求項6又は7に記載の農産物の仕分区分
判定装置。
8. The agricultural product sorting classification judging device according to claim 6, wherein the grade judging means judges the grade based on at least a color and / or a flaw of the agricultural product.
JP2000056104A 2000-03-01 2000-03-01 Image generation device and sorting classification determination device used for sorting agricultural products Expired - Fee Related JP3962525B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2000056104A JP3962525B2 (en) 2000-03-01 2000-03-01 Image generation device and sorting classification determination device used for sorting agricultural products

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2000056104A JP3962525B2 (en) 2000-03-01 2000-03-01 Image generation device and sorting classification determination device used for sorting agricultural products

Publications (2)

Publication Number Publication Date
JP2001239221A true JP2001239221A (en) 2001-09-04
JP3962525B2 JP3962525B2 (en) 2007-08-22

Family

ID=18577121

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2000056104A Expired - Fee Related JP3962525B2 (en) 2000-03-01 2000-03-01 Image generation device and sorting classification determination device used for sorting agricultural products

Country Status (1)

Country Link
JP (1) JP3962525B2 (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7545972B2 (en) 2002-10-31 2009-06-09 Teruaki Itoh Test tube type discrimination apparatus
CN110595385A (en) * 2019-09-30 2019-12-20 黄山职业技术学院 Method and device for quickly selecting standard indocalamus leaves
CN113522776A (en) * 2021-07-25 2021-10-22 安徽唯嵩光电科技有限公司 Fresh strawberry sorting method and device
CN114887926A (en) * 2022-05-10 2022-08-12 苏州天准科技股份有限公司 Electrode burr detection device, detection method and electrode comprehensive detection equipment
CN110595385B (en) * 2019-09-30 2024-05-03 黄山职业技术学院 Method and device for quickly selecting standard indocalamus leaves

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7545972B2 (en) 2002-10-31 2009-06-09 Teruaki Itoh Test tube type discrimination apparatus
CN110595385A (en) * 2019-09-30 2019-12-20 黄山职业技术学院 Method and device for quickly selecting standard indocalamus leaves
CN110595385B (en) * 2019-09-30 2024-05-03 黄山职业技术学院 Method and device for quickly selecting standard indocalamus leaves
CN113522776A (en) * 2021-07-25 2021-10-22 安徽唯嵩光电科技有限公司 Fresh strawberry sorting method and device
CN114887926A (en) * 2022-05-10 2022-08-12 苏州天准科技股份有限公司 Electrode burr detection device, detection method and electrode comprehensive detection equipment

Also Published As

Publication number Publication date
JP3962525B2 (en) 2007-08-22

Similar Documents

Publication Publication Date Title
Noordam et al. High-speed potato grading and quality inspection based on a color vision system
JP6152845B2 (en) Optical granular material sorter
JP5340717B2 (en) X-ray inspection equipment
Zhou et al. PC‐based machine vision system for real‐time computer‐aided potato inspection
EP1830176A1 (en) Device and method for optical measurement of small particles such as grains from cereals and like crops
KR20150119398A (en) Optical granular substance sorter
JPS5973089A (en) Electronic flaw scanner
JP5455409B2 (en) Foreign matter sorting method and foreign matter sorting equipment
Pearson et al. A machine vision system for high speed sorting of small spots on grains
ES2275107T3 (en) PRODUCT QUALITY ASSESSMENT IN GROSS FLOW.
JPH073517A (en) Method for sensing defective cocoon
Koh et al. Improving particle size measurement using multi-flash imaging
JP3614980B2 (en) Agricultural product appearance inspection method and apparatus
JP2000163579A (en) Appearance inspection method and device
JP2001239221A (en) Image forming device and assorting/classifying/judging device used for assorting of agricultural product
CN111602047B (en) Tablet inspection method and tablet inspection device
AU2008243688B2 (en) Method and apparatus for three dimensional image processing and analysis
JP2005031069A (en) X-ray inspection apparatus
KR102198917B1 (en) Grain grading system and method
JP2642107B2 (en) Automatic grading method and device for fruits and vegetables
JP4408358B2 (en) Grain sorting device
JP2005186053A (en) Particulate matter color sorting machine
WO2021177173A1 (en) Optical sorting machine
JPH08166380A (en) Automatic bruise detector for vegitable and fruit
Koh et al. Image segmentation of overlapping particles in automatic size analysis using multi-flash imaging

Legal Events

Date Code Title Description
A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20050201

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20070510

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20070515

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20070521

R150 Certificate of patent or registration of utility model

Ref document number: 3962525

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150

Free format text: JAPANESE INTERMEDIATE CODE: R150

S111 Request for change of ownership or part of ownership

Free format text: JAPANESE INTERMEDIATE CODE: R313113

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20100525

Year of fee payment: 3

R350 Written notification of registration of transfer

Free format text: JAPANESE INTERMEDIATE CODE: R350

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20100525

Year of fee payment: 3

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20110525

Year of fee payment: 4

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20120525

Year of fee payment: 5

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20130525

Year of fee payment: 6

LAPS Cancellation because of no payment of annual fees