JP4843766B2 - Method and apparatus for determining the degree of flowering of cut flowers - Google Patents

Method and apparatus for determining the degree of flowering of cut flowers Download PDF

Info

Publication number
JP4843766B2
JP4843766B2 JP2005241083A JP2005241083A JP4843766B2 JP 4843766 B2 JP4843766 B2 JP 4843766B2 JP 2005241083 A JP2005241083 A JP 2005241083A JP 2005241083 A JP2005241083 A JP 2005241083A JP 4843766 B2 JP4843766 B2 JP 4843766B2
Authority
JP
Japan
Prior art keywords
flowering
degree
cut flower
flower
cut
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related
Application number
JP2005241083A
Other languages
Japanese (ja)
Other versions
JP2007053933A (en
Inventor
照史 仲
将志 香川
修一 渡辺
雅丈 藤野
あかね 竹崎
敏弘 濱田
由利子 松本
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.)
National Agriculture and Food Research Organization
Kagawa Prefectural Government
Original Assignee
National Agriculture and Food Research Organization
Kagawa Prefectural Government
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 National Agriculture and Food Research Organization, Kagawa Prefectural Government filed Critical National Agriculture and Food Research Organization
Priority to JP2005241083A priority Critical patent/JP4843766B2/en
Publication of JP2007053933A publication Critical patent/JP2007053933A/en
Application granted granted Critical
Publication of JP4843766B2 publication Critical patent/JP4843766B2/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Description

本発明は、切り花の開花程度を判断して切り花の選別を可能にする切り花の開花程度判断方法及び開花程度判断装置に関する。   The present invention relates to a method for determining the degree of flowering of a cut flower and a device for determining the degree of flowering that enable the selection of cut flowers by determining the degree of flowering of the cut flower.

切り花の生産地では、高齢化による生産者が減少する一方で、企業的農家による規模拡大が進んでおり、またホームユースの需要に合わせた短茎切り花の栽培技術が開発されつつある。   In the area where cut flowers are produced, the number of producers is decreasing due to aging, while the scale of enterprise farmers is increasing, and cultivation techniques for short-cut flowers that meet the needs of home use are being developed.

このような生産地においては、品質が高く且つ鮮度の良い切り花を消費者に提供するために、所望の開花程度(咲き前)の花を収穫して出荷することが行われている。このため、開花程度(咲き前)の判断は、花の収穫調製において重要な作業である。   In such a production area, in order to provide consumers with cut flowers with high quality and good freshness, harvesting and shipping flowers of a desired flowering degree (before blooming) is performed. For this reason, the determination of the degree of flowering (before blooming) is an important task in the flower harvest preparation.

この開花程度(咲き前)の判断は、花色の変化、花直径の増加、花弁の開度、茎葉と花のボリウムのバランスや、小ギク等の多花性の切り花では花房全体が評価対象になる。つまり、開花程度の判断は、これらを代表するような単一の指標によって行われるのではなく、これらの判断要素を総合的に判断して行われる。このため、開花程度の定量手法は全く開発されておらず、生産段階において熟練した作業者が開花程度を判断するしかないのが現状である。   Judgment of the degree of flowering (before blooming) is based on changes in flower color, increase in flower diameter, petal opening, balance between stems and leaves, and multifloral cut flowers such as small chrysanthemum. Become. That is, the determination of the degree of flowering is not performed by a single index that represents them, but by comprehensively determining these determination factors. For this reason, no quantitative method for the degree of flowering has been developed, and the current situation is that a skilled worker can only determine the degree of flowering in the production stage.

また花の収穫作業は、生産者が圃場で開花程度(咲き前)を判断しながら数回に分けて行っているが、切り花生産の省力化を考えると、熟練を要する収穫作業は非効率的であり、規模拡大の最大の障害になっている。   In addition, the harvesting work of the flower is divided into several times while the producer determines the degree of flowering (before blooming) in the field, but considering labor-saving of cut flower production, the harvesting work that requires skill is inefficient. It is the biggest obstacle to scale expansion.

そこで、開花程度(咲き前)の判断を非熟練者でも可能にするため、熟練者が行った開花程度(咲き前)の総合判断を写真にして被判断物と見比べたり、実物と見比べたりする方法や、非特許文献1に記載されているような開花程度(咲き前)の写真を載せた刊行物を発行して、この写真と見比べる方法が取られてきた。   Therefore, in order to make it possible for non-experts to judge the degree of flowering (before blooming), the overall judgment of the degree of flowering (before blooming) made by a skilled person can be compared with the judged object or compared with the actual thing. Methods and methods of issuing publications with photos of the degree of flowering (before blooming) as described in Non-Patent Document 1 and comparing them with these photos have been taken.

「改訂版 花の切り前」,誠文堂新光社,1994年"Revised version before cutting flowers", Seibundo Shinkosha, 1994

このような開花程度(咲き前)を写真や実物と見比べる従来の方法では、これらを見る者の主観が入って判断基準が異なる場合が生じ、判断基準の客観性や再現性に欠けるという問題がある。   In the conventional method of comparing the degree of flowering (before blooming) with a photograph or the real thing, there are cases where the judgment criteria are different due to the subjectivity of the viewer, and there is a problem that the judgment criteria are not objective and reproducible. is there.

さらに従来の判断手法は、判断基準が数値化されていないので、機械や非熟練者による開花程度の判断や切り花の選別への応用が困難であり、また花数や茎葉のボリウム等の個体間差を考慮することができないので、写真や実物で示された以外の切り花の適用には限界があるという問題がある。   Furthermore, since conventional judgment methods are not quantified, it is difficult to apply to the degree of flowering and selection of cut flowers by machines and non-experts. Since the difference cannot be taken into account, there is a problem that there is a limit to the application of cut flowers other than those shown in photographs and real objects.

本発明は、開花程度(咲き前)の判断基準が客観性且つ再現性を有し、機械や非熟練者による切り花の選別作業が可能となり、花数や茎葉のボリウム等の個体間差を考慮した開花程度(咲き前)の判断が可能な切り花の開花程度判断方法及び開花程度判断装置を提供することを目的とする。   The present invention has an objective and reproducible judgment standard for the degree of flowering (before blooming), and enables selection of cut flowers by machines and non-experts, taking into account individual differences such as the number of flowers and the volume of leaves and leaves. It is an object of the present invention to provide a method and apparatus for determining the degree of flowering of a cut flower that can determine the degree of flowering (before blooming).

このような課題を解決するため、本発明の切り花の開花程度判断方法は、切り花の頂部より該切り花の茎と反対側から可視光で切り花を照射して該反対側から切り花を撮影し、撮影された切り花のデジタル画像を走査してRGB信号に変換し、変換されたRGB信号を所定の変換情報に基づいて色相、彩度、輝度を構成要素とするHSI表色系の画像情報に変換し、該HSI表色系に変換された画像情報から所定の変換情報に基づいて切り花の茎葉部分及び蕾花部分を識別し、識別された茎葉部分及び蕾花部分に基づいて切り花の開花程度を判断するための開花程度値を算出することを特徴とする。   In order to solve such problems, the method for determining the degree of flowering of a cut flower according to the present invention is to shoot a cut flower from the opposite side of the cut flower by irradiating the cut flower with visible light from the opposite side to the stem of the cut flower. The digital image of the cut flowers is scanned and converted into RGB signals, and the converted RGB signals are converted into HSI color system image information having hue, saturation, and luminance as constituent elements based on predetermined conversion information. , Identifying the stem and leaf portion of cut flowers based on predetermined conversion information from the image information converted to the HSI color system, and determining the degree of flowering of the cut flowers based on the identified stem and leaf portions and spikelets It is characterized by calculating a flowering degree value for performing.

この発明によれば、切り花を撮影したデジタル画像をRGB信号に変換し、このRGB信号を色相、彩度、輝度を構成要素とするHSI表色系の画像情報に変換することにより、撮影した切り花のデジタル画像を人間の眼が感じている状態に近い画像情報に変換することができる。またHSI表色系に変換された画像情報から切り花の茎葉部分及び蕾花部分を識別することにより、人間が感じるこれらの部分に合った識別が可能となる。その結果、花数や茎葉のボリウムのような個体間差を考慮した切り花の開花程度の判断が可能となり、例外的な品種を除けば、殆どの切り花品目や品種に適用することができる。また識別された茎葉部分及び蕾花部分に基づいて切り花の開花程度が数値化されるので、切り花の開花程度の判断を客観的に且つ再現性を有して行うことができる。このため、機械や非熟練者による開花程度の判断や切り花の選別への応用を可能にすることができる。   According to the present invention, a digital image obtained by photographing a cut flower is converted into an RGB signal, and the RGB signal is converted into image information of an HSI color system having hue, saturation, and luminance as constituent elements, whereby the photographed cut flower is obtained. This digital image can be converted into image information that is close to the state that human eyes feel. Further, by identifying the stem and leaf portions and cut flower portions of cut flowers from the image information converted into the HSI color system, it is possible to identify these portions that humans feel. As a result, it becomes possible to determine the degree of flowering of cut flowers in consideration of individual differences such as the number of flowers and the volume of stems and leaves, and it can be applied to most cut flower items and varieties except for exceptional varieties. Further, since the degree of flowering of cut flowers is quantified based on the identified stem and leaf parts and spikelets, it is possible to objectively and reproducibly determine the degree of flowering of cut flowers. For this reason, it is possible to determine the degree of flowering by a machine or an unskilled person and to apply to selection of cut flowers.

また本発明は、HSI表色系に変換された画像情報が、輝度が所定値以上で且つ色相が緑系であるときに切り花の茎葉部分と識別され、輝度が所定値以上で且つ色相が緑系以外であるときに蕾花部分と識別されることを特徴とする。   Further, according to the present invention, when the image information converted into the HSI color system has a luminance of a predetermined value or more and the hue is green, it is identified as a cut-and-leave part of a cut flower, and the luminance is a predetermined value or more and the hue is green. It is characterized in that it is identified as a cocoon part when it is other than a system.

この発明によれば、HSI表色系に変換された画像情報の輝度が所定値以上で且つ色相が緑系であるときに切り花の茎葉部分と識別され、輝度が所定値以上で且つ色相が緑系以外であるときに蕾花部分と識別されることにより、この識別方法は殆どの切り花品目や品種に適用可能であり、汎用性に優れる。また花弁の伸長や展開に先だって起こる「蕾の白色化」や「顎の展開」といった「緑色が失われる」開花過程を考慮した切り花の開花程度の判断を可能にすることができる。   According to the present invention, when the luminance of the image information converted into the HSI color system is equal to or higher than a predetermined value and the hue is green, it is identified as a cut-and-leave part of a cut flower, and the luminance is equal to or higher than the predetermined value and the hue is green. By identifying the flower portion when it is other than the system, this identification method is applicable to most cut flower items and varieties, and is excellent in versatility. In addition, it is possible to judge the degree of flowering of cut flowers in consideration of flowering processes such as “whitening of the eyelids” and “development of the jaw” that occur before the expansion and development of the petals.

また本発明に係わる開花程度値は、識別された蕾花部分の画素数と茎葉部分の画素数の比を対数変換して算出することを特徴とする。   The flowering degree value according to the present invention is calculated by logarithmically converting the ratio of the number of pixels of the identified spikelet portion and the number of pixels of the foliage portion.

この発明によれば、開花程度値が識別された蕾花部分の画素数と茎葉部分の画素数の比を対数変換して算出されることにより、茎葉部分の画素数と蕾花部分の画素数が指数関数的な差があっても、この差を圧縮してグラフ化を容易にして、数値化される開花程度値を所定の範囲内にすることができる。   According to the present invention, the ratio of the number of pixels of the bud portion and the number of pixels of the foliage portion, for which the flowering degree value has been identified, is calculated by logarithmically transforming the number of pixels of the foliage portion and the number of pixels of the bud portion. Even if there is an exponential difference, the difference can be compressed to facilitate graphing, and the flowering degree value to be digitized can be within a predetermined range.

また本発明の切り花の開花程度判断装置は、切り花の頂部より該切り花の茎と反対側から撮影した切り花のデジタル画像を走査してRGB信号を出力するカラー画像読取手段(例えば、実施形態におけるCCDカメラ30)と、該カラー画像読取手段によって出力されたRGB信号を所定の変換情報に基づいて色相、彩度、輝度を構成要素とするHSI表色系の画像情報に変換する表色系変換手段(例えば、実施形態における表示系変換部41)と、該表色系変換手段によって変換されたHSI表色系の画像情報から所定の変換情報に基づいて切り花の茎葉部分及び蕾花部分を識別し、この識別された茎葉部分及び蕾花部分に基づいて切り花の開花程度を判断するための開花程度値を算出する識別演算手段(例えば、実施形態における識別演算部43)とを有することを特徴とする。   The apparatus for determining the degree of flowering of a cut flower according to the present invention is a color image reading means that scans a digital image of a cut flower taken from the top of the cut flower from the side opposite to the stem of the cut flower and outputs an RGB signal (for example, the CCD in the embodiment). Color system conversion means for converting RGB signals output by the camera 30) and the color image reading means into HSI color system image information having hue, saturation, and luminance as constituent elements based on predetermined conversion information. (For example, the display system conversion unit 41 in the embodiment) and the stem and leaf portions and cut flower portions of cut flowers are identified based on predetermined conversion information from the HSI color system image information converted by the color system conversion means. And an identification calculation means for calculating a flowering degree value for determining the degree of flowering of the cut flower based on the identified stem and leaf part and spiked flower part (for example, the identification performance in the embodiment). Characterized in that it has a part 43) and.

この発明によれば、カラー画像読取手段により撮影された切り花のデジタル画像をRGB信号に変換し、表色系変換手段によりこのRGB信号を色相、彩度、輝度を構成要素とするHSI表色系の画像情報に変換することにより、撮影された切り花のデジタル画像を人間の眼が感じている状態に近い画像情報に変換することができる。また識別演算手段によりHSI表色系に変換された画像情報から切り花の茎葉部分及び蕾花部分を識別することにより、人間が感じるこれらの部分に合った識別が可能となる。その結果、花数や茎葉のボリウムのような個体間差を考慮した切り花の開花程度の判断が可能となり、例外的な品種を除けば、殆どの切り花品目や品種に適用することができる。また識別された茎葉部分及び蕾花部分に基づいて切り花の開花程度が数値化されるので、切り花の開花程度の判断を客観的に且つ再現性を有して行うことができ、非熟練者による開花程度の判断や切り花の選別への応用を可能にすることができる。   According to the present invention, a digital image of cut flowers photographed by the color image reading unit is converted into an RGB signal, and the RGB signal is converted by the color system conversion unit into the HSI color system having hue, saturation, and luminance as components. By converting to the image information, it is possible to convert the captured digital image of the cut flower into image information that is close to the state that the human eye feels. Further, by identifying the stems and leaves of cut flowers from the image information converted into the HSI color system by the identification calculation means, it becomes possible to identify these parts that humans feel. As a result, it becomes possible to determine the degree of flowering of cut flowers in consideration of individual differences such as the number of flowers and the volume of stems and leaves, and it can be applied to most cut flower items and varieties except for exceptional varieties. In addition, since the degree of flowering of cut flowers is quantified based on the identified stem and leaf part and spiked flower part, it is possible to objectively and reproducibly determine the degree of flowering of cut flowers, and by an unskilled person It can be applied to judge the degree of flowering and to select cut flowers.

本発明に係わる切り花の開花程度判断方法及び開花程度判断装置によれば、撮影された切り花のデジタル画像をRGB信号に変換し、これを色相、彩度、輝度を構成要素とするHSI表色系の画像情報に変換し、この画像情報から切り花の茎葉部分及び蕾花部分を識別し、識別された茎葉部分及び蕾花部分に基づいて切り花の開花程度を判断するための開花程度値を算出することにより、開花程度(咲き前)の判断が客観的に且つ再現性を有して行うことができ、機械や非熟練者による切り花の選別作業が可能となり、花数や茎葉のボリウム等の個体間差を考慮した開花程度(咲き前)の判断が可能な切り花の開花程度判断方法及び開花程度判断装置を提供することができる。   According to the method and apparatus for determining the degree of flowering of a cut flower according to the present invention, a digital image of a photographed cut flower is converted into an RGB signal, and this is an HSI color system having hue, saturation, and luminance as components. The image information is converted into the image information, and the stem and leaf portion and the spike portion of the cut flower are identified from the image information, and the flowering degree value for determining the flowering degree of the cut flower based on the identified stem and leaf portion and the spike flower portion is calculated. Therefore, the degree of flowering (before blooming) can be determined objectively and reproducibly, and the selection of cut flowers by machines and non-experts is possible. Individuals such as the number of flowers and the volume of leaves It is possible to provide a method for determining the degree of flowering of a cut flower and a device for determining the degree of flowering that can determine the degree of flowering (before blooming) in consideration of the difference between the two.

以下、本発明に係わる切り花の開花程度判断方法及び開花程度判断装置の好ましい実施の形態を図1から図7に基づいて説明する。先ず、本発明に係わる切り花の開花程度判断方法を説明する前に開花程度判断装置を説明する。   Hereinafter, preferred embodiments of a method and apparatus for determining the degree of flowering of cut flowers according to the present invention will be described with reference to FIGS. First, before explaining the method for judging the degree of flowering of cut flowers according to the present invention, a device for judging the degree of flowering will be explained.

開花程度判断装置1は、図1(構成図)に示すように、切り花Fを収容して光をあてる照明装置10と、切り花Fの天頂側から切り花Fを撮影するCCDカメラ30と、CCDカメラ30により撮影された切り花Fの画像を処理して切り花Fの開花程度を判断するための開花程度値を算出するパーソナルコンピュータ40とを有してなる。   As shown in FIG. 1 (configuration diagram), the degree of flowering determination device 1 includes an illumination device 10 that houses cut flowers F and applies light, a CCD camera 30 that captures the cut flowers F from the zenith side of the cut flowers F, and a CCD camera. And a personal computer 40 that calculates the flowering degree value for determining the degree of flowering of the cut flower F by processing the image of the cut flower F photographed by 30.

照明装置10は、直方体形状に形成されて内部に切り花Fを収容可能な空間部11aを有する収容部11と、収容部11内に設けられて切り花Fを載せる載置台15と、載置台15に載せられた切り花Fの天頂側から可視光を照射する照明部20とを有してなる。収容部11は、上板11b、左右の側板11c,11d及び後板11eの少なくともいずれかが開閉自在に設けられて空間部11aへの切り花Fの出し入れを容易にしている。載置台15に載せられた切り花Fの周辺に配置された上板11b、左右の側板11c,11d、後板11e及び底板11fの各内面には暗幕若しくは黒色の画用紙が張り付けられて、撮影対象となる切り花Fの背景部分からの反射光を抑制している。なお、上板11b、左右の側板11c,11d、後板11e及び底板11fの各内面を黒色に塗って、切り花Fの背景部分からの反射光を抑制したり、黒色のゴム板を張り付けてもよい。また照明部20は切り花Fの天頂側に配置される場合に限られるものではなく、切り花Fの頂部に対して斜め方向から可視光を照射するように配置されるようにしてもよい。前板11gの中央部にはCCDカメラ30を装着するための装着孔11g1が設けられている。   The illuminating device 10 is formed in a rectangular parallelepiped shape and includes a housing portion 11 having a space portion 11a in which the cut flower F can be housed, a mounting table 15 provided in the housing portion 11 on which the cut flower F is placed, and a mounting table 15 The illumination part 20 which irradiates visible light from the top | zenith side of the cut flower F mounted is comprised. The accommodating portion 11 is provided with at least one of an upper plate 11b, left and right side plates 11c and 11d, and a rear plate 11e so as to be freely opened and closed, thereby facilitating the insertion and removal of cut flowers F into the space portion 11a. On the inner surfaces of the top plate 11b, the left and right side plates 11c and 11d, the rear plate 11e, and the bottom plate 11f arranged around the cut flower F placed on the mounting table 15, a black curtain or black drawing paper is attached to the shooting object. The reflected light from the background portion of the cut flower F is suppressed. Even if the inner surfaces of the upper plate 11b, the left and right side plates 11c, 11d, the rear plate 11e, and the bottom plate 11f are painted black, the reflected light from the background portion of the cut flower F is suppressed, or a black rubber plate is attached. Good. Moreover, the illumination part 20 is not restricted to the case where it arrange | positions at the zenith side of the cut flower F, You may make it arrange | position so that visible light may be irradiated to the top part of the cut flower F from the diagonal direction. A mounting hole 11g1 for mounting the CCD camera 30 is provided at the center of the front plate 11g.

載置台15は、収容部11に沿って延びて下方が凸状に湾曲する載置部16を備える。載置部16の先端部は照明部20より空間部内側方向に所定距離を有した位置に配置されて、載置部16の先端部から切り花Fの頂部が突出した状態での切り花Fを載置可能にしている。このため、切り花Fの蕾や花(蕾花部分Fa)が互いに重なり合うことがなく、後述する切り花Fの開花程度値の信頼性を向上することができる。なお、載置台15の内面や外面を黒色にすることで、反射光の影響をより少なくすることができる。   The mounting table 15 includes a mounting portion 16 that extends along the housing portion 11 and has a downwardly curved convex shape. The tip of the placement unit 16 is disposed at a position having a predetermined distance inward of the space from the illumination unit 20, and the cut flower F in a state where the top of the cut flower F protrudes from the tip of the placement unit 16 is placed. It can be placed. For this reason, the buds and flowers (the bud portion Fa) of the cut flower F do not overlap each other, and the reliability of the flowering degree value of the cut flower F described later can be improved. In addition, the influence of reflected light can be reduced more by making the inner surface and outer surface of the mounting table 15 black.

照明部20は環状に形成されて前板11gの内面に装着孔11g1を囲むようにして取り付けられている。このため、照明部20は切り花Fの天頂側から切り花Fを照射することができる。照明部20は一定の照度を有した可視光を発光し、図示しない電源からの電力供給を受けて点灯するようになっている。   The illumination unit 20 is formed in an annular shape, and is attached to the inner surface of the front plate 11g so as to surround the mounting hole 11g1. For this reason, the illumination unit 20 can irradiate the cut flower F from the zenith side of the cut flower F. The illumination unit 20 emits visible light having a constant illuminance, and is lit by receiving power supply from a power source (not shown).

CCDカメラ30は、撮影したデジタル画像を走査してRGB信号を出力する。このRGB信号はケーブルKを介してパーソナルコンピュータ40に送られる。CCDカメラ30は図示しない電源からの電力供給を受けて撮影可能な状態になる。   The CCD camera 30 scans the captured digital image and outputs RGB signals. The RGB signals are sent to the personal computer 40 via the cable K. The CCD camera 30 is ready to take a picture by receiving power from a power source (not shown).

パーソナルコンピュータ40は、図2(ブロック図)に示すように、CCDカメラ30によって出力されたRGB信号を所定の変換情報に基づいて色相、彩度、輝度を構成要素とするHSI表色系の画像情報に変換する表色系変換部41と、表色系変換部41によって変換されたHSI表色系の画像情報から所定の変換情報に基づいて図1に示す切り花Fの蕾花部分Fa及び茎葉部分Fbを識別し、この識別された蕾花部分Fa及び茎葉部分Fbに基づいて切り花Fの開花程度を判断するための開花程度値を算出する識別演算部43と、識別演算部43で算出された開花程度値をディスプレイ46に表示させる表示部45とを有してなる。   As shown in FIG. 2 (block diagram), the personal computer 40 uses the RGB signal output from the CCD camera 30 based on predetermined conversion information as an HSI color system image having hue, saturation, and luminance as components. The color system conversion unit 41 that converts the information into information, and the spiked portion Fa and the foliage of the cut flower F shown in FIG. 1 based on the predetermined conversion information from the image information of the HSI color system converted by the color system conversion unit 41 An identification calculation unit 43 that identifies the part Fb and calculates a flowering degree value for determining the flowering degree of the cut flower F based on the identified spiked flower part Fa and stem and leaf part Fb, and is calculated by the identification calculation part 43 And a display unit 45 for displaying the flowering degree value on the display 46.

表色系変換部41によって変換されるHSI表色系の画像情報は、図3(模式図)に示すように、色相情報、彩度情報及び輝度情報から構成されており、人間の視覚に近い画像情報である。   As shown in FIG. 3 (schematic diagram), the HSI color system image information converted by the color system conversion unit 41 is composed of hue information, saturation information, and luminance information, and is close to human vision. Image information.

また図2に示す識別演算部43は、HSI表色系に変換された画像情報の輝度が所定値(設定値)より小さいときに切り花の背景部分と認識し、輝度が所定値以上で色相が緑系であり彩度が所定範囲内にあるときに切り花の茎葉部分と識別し、輝度が所定値以上で且つ色相が緑系以外であるときに蕾花部分と識別する。なお、背景部分と認識するための輝度の上限値(閾値)は、任意の値に設定可能である。   2 recognizes the background portion of cut flowers when the luminance of the image information converted into the HSI color system is smaller than a predetermined value (set value), and the hue is higher than the predetermined value and the hue is higher than the predetermined value. When the color is green and the saturation is within a predetermined range, the cut flower is identified as a stem and leaf part, and when the luminance is not less than a predetermined value and the hue is other than green, the flower part is identified. Note that the upper limit value (threshold value) of the luminance for recognizing the background portion can be set to an arbitrary value.

ここで、識別演算部43によって処理された画像の変換例を図4に示す。図4の上段に示す3つの画像は、開花程度の異なる3つの切り花(図では目視区分1,5,9と記載)のそれぞれを切り花の天頂側から撮影した画像の絵であり、図の下段に示す3つの画像は、これらの撮影画像を識別処理した画像の絵である。撮影画像の絵は背景部分が黒色(図面ではドットで示した明るい灰色)で表わされ、茎葉部分が緑色(図面では不定形の実線で囲まれた部分を示す白色)で表わされ、蕾花部分が白色又は紫色(図面では円形及び楕円形の実線で囲まれた部分を示す白色又は暗い灰色)で表わされている。一方、識別処理された下段の画像の絵は、切り花の背景部分が黒色(図面ではドットで示した明るい灰色)で表わされ、花の茎葉部分が緑色(図面では不定形の実線で囲まれた部分を示す白色)で表わされ、切り花の蕾花部分が赤色(図面では不定形の実線で囲まれた部分を示す暗い灰色)で表わされている。このように黒色を除いて緑色とそれ以外(実施例では赤色)という識別方法を採ることにより、開花程度の低い蕾は緑色(茎葉部分)と識別することができ、花弁の伸長や展開に先だって起こる「蕾の白色化」や「顎の展開」といった「緑色が失われる」開花過程を有した部分(図中のa、bが示す部分)は赤色(蕾花部分)と識別することができる。このため、例外的な品種を除けば、この識別方法は殆どの切り花品目や品種に適用可能であり、汎用性に優れている。   Here, FIG. 4 shows an example of conversion of the image processed by the identification calculation unit 43. The three images shown in the upper part of FIG. 4 are pictures of images taken from the zenith side of the cut flowers of the three cut flowers having different degrees of flowering (shown as visual classifications 1, 5, and 9 in the figure). These three images are pictures of images obtained by identifying these captured images. The picture of the photographed image is represented by a black background (light gray indicated by dots in the drawing), a foliage portion by green (in the drawing, white indicating a portion surrounded by an infinite solid line), The flower part is represented in white or purple (in the drawing, white or dark gray indicating a part surrounded by a circular and elliptical solid line). On the other hand, in the picture of the lower image after the identification processing, the background portion of the cut flower is represented by black (light gray indicated by dots in the drawing), and the stem and leaf portion of the flower is surrounded by green (indefinite solid line in the drawing). The white portion indicating the portion of the cut flower is represented by red (the dark gray portion indicating the portion surrounded by an indefinite solid line in the drawing). Thus, by adopting a method of distinguishing between green and others (red in the examples) except for black, buds with a low flowering degree can be identified as green (stems and leaves), and prior to the expansion and development of petals. The part (the part indicated by a and b in the figure) that has a flowering process of “green is lost” such as “whitening of the eyelid” or “development of the jaw” can be distinguished from red (the part of the iris). . Therefore, except for exceptional varieties, this identification method can be applied to most cut flower items and varieties, and is excellent in versatility.

また図2に示す識別演算部43は、識別した蕾花部分の画素数と茎葉部分の画素数の比を対数変換して開花程度値(以下、「F/G値」と記す)を算出する。即ち、F/G値は次式によって表わされる。F/G値=log(100×(蕾花部分の画素数/茎葉部分の画素数))。ここで、蕾花部分の画素数とは、蕾花部分と識別された部分を撮影したCCDの画素数(ピクセル数)をいい、茎葉部分の画素数とは、茎葉部分と識別された部分を撮影したCCDの画素数(ピクセル数)をいう。 2 calculates a flowering degree value (hereinafter, referred to as “F / G value”) by logarithmically converting the ratio of the number of pixels of the identified spikelet portion and the number of pixels of the foliage portion. . That is, the F / G value is expressed by the following equation. F / G value = log e (100 × (number of pixels in bud portion / number of pixels in foliage portion)). Here, the number of pixels of the bud portion refers to the number of pixels (pixel number) of the CCD that has captured the portion identified as the bud portion, and the number of pixels of the foliage portion refers to the portion identified as the foliage portion. This refers to the number of pixels (number of pixels) of the imaged CCD.

図5に示すグラフは、F/G値と目視区分との関係を示したものである。このグラフは、横軸が1から10の等級区分によって示される目視区分(目視判定)を示し、縦軸がF/G値×10及び切り花の着色輪数の割合(%)等を示している。このグラフ内の実線が示すように、目視区分に対してF/G値が広いレンジで安定した直線性を示していることが判る。他の測定値(花弁長、花径、花高、着色輪数の割合)では、目視区分に対する直線性はなく、目視区分を代表することができない。   The graph shown in FIG. 5 shows the relationship between the F / G value and the visual classification. In this graph, the horizontal axis indicates the visual classification (visual determination) indicated by the grade classification of 1 to 10, and the vertical axis indicates the F / G value × 10, the ratio (%) of the number of colored flowers of cut flowers, and the like. . As shown by the solid line in this graph, it can be seen that the F / G value shows a stable linearity in a wide range with respect to the visual classification. Other measured values (petal length, flower diameter, flower height, ratio of number of colored rings) have no linearity with respect to the visual classification and cannot represent the visual classification.

また図6に示すグラフは、F/G値と開花程度の進行過程との関係を、3品種(広島紅、みのる、やよい)について示したものであり、グラフの横軸は採花後の開花液処理の日数を示し、縦軸はF/G値を示している。このグラフからいずれの品種においてもF/G値は一貫して単調増加し、極端に硬い蕾(処理0日目)や消費者段階で満開時(処理8〜10日目)を除くと、十分な直線性を有し、F/G値が開花程度の進行を示す客観的指標となり得ることが判る。   The graph shown in FIG. 6 shows the relationship between the F / G value and the progress of flowering for three varieties (Hiroshima Beni, Minoru and Yayoi). The horizontal axis of the graph represents the flowering solution after flowering. The number of days of processing is shown, and the vertical axis shows the F / G value. From this graph, the F / G value consistently monotonically increased for all varieties, and it is sufficient to exclude extremely hard rice cakes (treatment day 0) and full bloom at the consumer stage (treatment days 8 to 10). It can be seen that the F / G value can be an objective index indicating the progress of the degree of flowering.

さらに図7に示すグラフは、F/G値と生産者の目視による開花程度(咲き前)の判断との関係を示したものであり、グラフの横軸はF/G値を示し、縦軸は生産者が出荷最適時期或いは出荷可能時期であると回答した比率(%)を示している。このグラフにおいて、F/G値を独立の変数とし、このF/G値と出荷可能(若しくは出荷最適)であると判断した生産者の比率との間には、実線及び破線で示すようなロジスティック回帰による近似モデルが推定可能である。そして、例えば、近似モデルの50%の回答比率を出荷可能若しくは出荷最適な開花程度(咲き前)とすると、グラフ中央の矢印が示すように、生産者の判断をF/G値によって数値化することができる。例えば、出荷可能な開花程度をF/G値(2.0〜4.0)と数値化したり、出荷最適な開花程度をF/G値(2.6〜3.5)と数値化することができる。   Furthermore, the graph shown in FIG. 7 shows the relationship between the F / G value and the judgment of the degree of flowering (before blooming) by the producer. The horizontal axis of the graph shows the F / G value, and the vertical axis Indicates the percentage (%) at which the producer replied that it was the optimal shipping time or the shipping time. In this graph, the F / G value is an independent variable, and between this F / G value and the ratio of producers determined to be shippable (or shipping optimal), a logistic as shown by a solid line and a broken line is shown. An approximate model by regression can be estimated. Then, for example, assuming that the response ratio of 50% of the approximate model is the degree of flowering that can be shipped or is optimal for shipment (before blooming), as shown by the arrow at the center of the graph, the producer's judgment is quantified by the F / G value. be able to. For example, the degree of flowering that can be shipped is digitized as an F / G value (2.0 to 4.0), or the flowering degree that is optimal for shipment is digitized as an F / G value (2.6 to 3.5). Can do.

このように算出された開花程度値は、図2に示す表示部45によってディスプレイ46に表示される。このため、作業者はディスプレイ46に表示された開花程度値を目視するだけで切り花の開花程度を容易に判断することができる。   The flowering degree value calculated in this way is displayed on the display 46 by the display unit 45 shown in FIG. For this reason, the operator can easily determine the degree of flowering of cut flowers simply by visually observing the degree of flowering displayed on the display 46.

次に、切り花の開花程度判断方法について説明する。先ず、図1に示すように、開閉自在に構成された上板11b等を開け、切り花Fの頂部が照明部20側に向くように切り花Fの姿勢を変えた状態で切り花Fを載置台15上に置く。このとき、蕾や花が互いに重ならないようにするため、切り花Fの頂部を載置台15の先端部から突出させた状態にする。そして、開けた上板11b等を閉じ、照明部20を点灯し、パーソナルコンピュータ40及びCCDカメラ30を作動させる。   Next, a method for determining the degree of flowering of cut flowers will be described. First, as shown in FIG. 1, the upper plate 11b configured to be openable and closable is opened, and the cut flower F is placed on the mounting table 15 in a state where the posture of the cut flower F is changed so that the top of the cut flower F faces the illumination unit 20 side. put on top. At this time, the top of the cut flower F is projected from the tip of the mounting table 15 so that the buds and flowers do not overlap each other. Then, the opened upper plate 11b is closed, the illumination unit 20 is turned on, and the personal computer 40 and the CCD camera 30 are operated.

そして、CCDカメラ30によって切り花Fを撮影する。撮影された切り花Fの画像は、RGB信号に変換されてCCDカメラ30から出力される。RGB信号はケーブルKを通ってパーソナルコンピュータ40に送られる。パーソナルコンピュータ40は、RGB信号をHSI表色系の画像情報に変換し、このHSI表色系に変換した画像情報から切り花Fの茎葉部分Fb、蕾花部分Fa及び背景部分を識別し、この識別した茎葉部分Fb及び蕾花部分Faの画像情報に基づいて切り花Fの開花程度値を算出し、ディスプレイ46に開花程度値を表示する。   Then, the cut flower F is photographed by the CCD camera 30. The photographed image of cut flower F is converted into RGB signals and output from the CCD camera 30. The RGB signals are sent to the personal computer 40 through the cable K. The personal computer 40 converts the RGB signal into image information of the HSI color system, identifies the foliage portion Fb, the spike portion Fa and the background portion of the cut flower F from the image information converted into the HSI color system, and this identification The flowering degree value of the cut flower F is calculated based on the image information of the stem and leaf part Fb and the spiked flower part Fa, and the flowering degree value is displayed on the display 46.

このように、切り花Fの開花程度値が算出されてディスプレイ46上に表示されるので、開花程度(咲き前)の判断において作業者の主観を排除することができる。このため、開花程度の判断基準が客観的となるとともに、再現性をもたせることができ、その結果、機械や非熟練者による切り花Fの選別作業を可能にすることができる。また花数や茎葉のボリウムのある切り花Fでも、前述した開花程度値の算出方法によって開花程度が数値化されるので、花数等が異なる切り花でも開花程度(咲き前)の判断を行うことができる。   Thus, since the flowering degree value of the cut flower F is calculated and displayed on the display 46, the subjectivity of the operator can be excluded in determining the flowering degree (before blooming). For this reason, the judgment standard of the degree of flowering becomes objective and can be given reproducibility. As a result, it is possible to select the cut flowers F by a machine or an unskilled person. In addition, the degree of flowering is also quantified by the above-described method for calculating the degree of flowering of cut flowers F with the number of flowers and the volume of stems and leaves. it can.

なお、前述した実施例では、切り花Fの背景部分を認識するための輝度の上限値(閾値)を任意に設定可能としたが、この閾値設定を自動化してもよい。例えば、切り花を含まない背景だけの画像を予め取得しておき、開花程度を判断する切り花の画像の輝度値から予め取得した背景画像の輝度値を引き算した値を切り花の真の輝度値とすることにより、背景部分の攪乱を除去することができる。   In the above-described embodiment, the upper limit value (threshold value) of the luminance for recognizing the background portion of the cut flower F can be arbitrarily set. However, this threshold value setting may be automated. For example, an image of only a background that does not include a cut flower is acquired in advance, and a value obtained by subtracting the luminance value of the background image acquired in advance from the luminance value of the cut flower image that determines the degree of flowering is set as the true luminance value of the cut flower. Thus, disturbance of the background portion can be removed.

また輝度値の小さい順から順番に閾値候補と設定し、その閾値で分けられる2つのクラスのクラス間分散を最大化する輝度値を閾値と決定する大津の手法等を利用することによって、茎葉部分Fbと蕾花部分Faとを自動的に識別するようにしてもよい。   In addition, by setting the threshold candidates in order from the smallest luminance value, and using Otsu's method or the like that determines the luminance value that maximizes the variance between the two classes divided by the threshold as the threshold, the foliage part You may make it identify Fb and the flower part Fa automatically.

本発明の一実施の形態に係わる切り花の開花程度判断装置の概略構成図を示す。The schematic block diagram of the flowering degree judgment apparatus of the cut flower concerning one embodiment of this invention is shown. この開花程度判断装置の一部であるパーソナルコンピュータのブロック図を示す。The block diagram of the personal computer which is a part of this flowering degree judgment apparatus is shown. HSI表色系に変換された画像情報の模式図を示す。The schematic diagram of the image information converted into the HSI color system is shown. 切り花の撮影画像と処理画像を示す。The photographed image and processed image of cut flowers are shown. F/G値と目視区分との関係を示したグラフである。It is the graph which showed the relationship between F / G value and visual classification. 開花程度の進行とF/G値との関係を示すグラフである。It is a graph which shows the relationship between progress of a flowering grade, and F / G value. F/G値と生産者の目視による開花程度の判断との関係を示すグラフである。It is a graph which shows the relationship between F / G value and the judgment of the flowering degree by a producer's visual observation.

符号の説明Explanation of symbols

1 開花程度判断装置
30 CCDカメラ(カラー画像読取手段)
41 表示系変換部(表示系変換手段)
43 識別演算部(識別演算手段)
F 切り花
Fa 蕾花部分
Fb 茎葉部分
1 Flowering degree judging device 30 CCD camera (color image reading means)
41 Display system conversion unit (display system conversion means)
43. Identification calculation unit (identification calculation means)
F Cut flower Fa Camellia part Fb Stem and leaf part

Claims (4)

切り花の頂部より該切り花の茎と反対側から可視光で前記切り花を照射して該反対側から前記切り花を撮影し、
撮影された前記切り花のデジタル画像を走査してRGB信号に変換し、
変換されたRGB信号を所定の変換情報に基づいて色相、彩度、輝度を構成要素とするHSI表色系の画像情報に変換し、
該HSI表色系に変換された画像情報から所定の変換情報に基づいて前記切り花の茎葉部分及び蕾花部分を識別し、
識別された茎葉部分及び蕾花部分の画像情報に基づいて前記切り花の開花程度を判断するための開花程度値を算出することを特徴とする切り花の開花程度判断方法。
Shooting the cut flower from the opposite side by irradiating the cut flower with visible light from the opposite side of the cut flower stem from the top of the cut flower,
Scan the digital image of the cut flower that was taken and convert it to RGB signal,
The converted RGB signal is converted into image information of an HSI color system having hue, saturation, and luminance as components based on predetermined conversion information,
Identifying the stem and leaf part and the spike part of the cut flower based on the predetermined conversion information from the image information converted to the HSI color system,
A method for determining the degree of flowering of a cut flower, wherein a flowering degree value for determining the degree of flowering of the cut flower is calculated based on image information of the identified stem and leaf part and spiked flower part.
前記HSI表色系に変換された前記画像情報は、前記輝度が所定値以上で且つ前記色相が緑系であるときに前記切り花の茎葉部分と識別され、前記輝度が所定値以上で且つ前記色相が緑系以外であるときに前記蕾花部分と識別されることを特徴とする請求項1に記載の切り花の開花程度判断方法。   The image information converted into the HSI color system is identified as a stem and leaf portion of the cut flower when the luminance is a predetermined value or more and the hue is a green system, and the luminance is a predetermined value or more and the hue The method for determining the degree of flowering of cut flowers according to claim 1, wherein when the flower is other than green, the flower part is identified. 前記開花程度値は、識別された前記蕾花部分の画素数と前記茎葉部分の画素数の比を対数変換して算出することを特徴とする請求項1又は2に記載の切り花の開花程度判断方法。   The degree of flowering degree of cut flowers according to claim 1 or 2, wherein the flowering degree value is calculated by logarithmically converting a ratio between the number of pixels of the identified spikelet part and the number of pixels of the foliage part. Method. 切り花の頂部より該切り花の茎と反対側から撮影した前記切り花のデジタル画像を走査してRGB信号を出力するカラー画像読取手段と、
該カラー画像読取手段によって出力されたRGB信号を所定の変換情報に基づいて色相、彩度、輝度を構成要素とするHSI表色系の画像情報に変換する表色系変換手段と、
該表色系変換手段によって変換されたHSI表色系の画像情報から所定の変換情報に基づいて前記切り花の茎葉部分及び蕾花部分を識別し、この識別された茎葉部分及び蕾花部分に基づいて前記切り花の開花程度を判断するための開花程度値を算出する識別演算手段とを有することを特徴とする切り花の開花程度判断装置。
A color image reading means for scanning a digital image of the cut flower taken from the opposite side of the cut flower stem from the top of the cut flower and outputting an RGB signal;
A color system conversion means for converting the RGB signal output by the color image reading means into image information of an HSI color system having hue, saturation, and luminance as components based on predetermined conversion information;
Based on predetermined conversion information from the HSI color system image information converted by the color system conversion means, the foliage part and the spike part of the cut flower are identified, and based on the identified foliage part and the spike part. And a discrimination calculation means for calculating a flowering degree value for judging the flowering degree of the cut flower.
JP2005241083A 2005-08-23 2005-08-23 Method and apparatus for determining the degree of flowering of cut flowers Expired - Fee Related JP4843766B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2005241083A JP4843766B2 (en) 2005-08-23 2005-08-23 Method and apparatus for determining the degree of flowering of cut flowers

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2005241083A JP4843766B2 (en) 2005-08-23 2005-08-23 Method and apparatus for determining the degree of flowering of cut flowers

Publications (2)

Publication Number Publication Date
JP2007053933A JP2007053933A (en) 2007-03-08
JP4843766B2 true JP4843766B2 (en) 2011-12-21

Family

ID=37917974

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2005241083A Expired - Fee Related JP4843766B2 (en) 2005-08-23 2005-08-23 Method and apparatus for determining the degree of flowering of cut flowers

Country Status (1)

Country Link
JP (1) JP4843766B2 (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108317960A (en) * 2018-04-20 2018-07-24 昆明理工大学 A kind of flowers grading plant
CN108647652B (en) * 2018-05-14 2022-07-01 北京工业大学 Cotton development period automatic identification method based on image classification and target detection
CN110178481B (en) * 2019-05-22 2020-08-21 青岛理工大学 Bulbil recognition and adjustment method in precise directional planting of gingers
WO2023085992A1 (en) * 2021-11-15 2023-05-19 Opticept Technologies Ab Image analysis of cut flowers

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH09262027A (en) * 1996-03-28 1997-10-07 Yazaki Corp Automatically diagnostic system for plant
JP2000315256A (en) * 1999-04-30 2000-11-14 Katsuji Uosaki Color sorting method for eggplant and vegetable selecting method for eggplant using the method
JP4276414B2 (en) * 2002-09-30 2009-06-10 浜松ホトニクス株式会社 Plant cultivation apparatus and method

Also Published As

Publication number Publication date
JP2007053933A (en) 2007-03-08

Similar Documents

Publication Publication Date Title
EP1842153B1 (en) Differentiation of illumination and reflection boundaries
TWI431549B (en) Image processing apparatus and method and computer program product
JP5764238B2 (en) Steel pipe internal corrosion analysis apparatus and steel pipe internal corrosion analysis method
JP4519708B2 (en) Imaging apparatus and method, and program
JP5761789B2 (en) Plant image region extraction method, plant image region extraction apparatus, and plant growth monitoring system
JP2019520632A (en) Weed recognition in the natural environment
CN104636759B (en) A kind of method and picture filter information recommendation system for obtaining picture and recommending filter information
JP6951753B2 (en) Information search system and program
JP2012505375A (en) Improved apparatus and method for gem assessment, evaluation and grading
KR20100029839A (en) Methods for recommending a personal care product and tools therefor
WO2016175234A1 (en) Color image processing method, color image processing program, and object recognition method and device
JP4843766B2 (en) Method and apparatus for determining the degree of flowering of cut flowers
JP2009134383A (en) Image processing device, method, and program
US8260005B2 (en) Portable tool for determining meat quality
CN108184286A (en) The control method and control system and electronic equipment of lamps and lanterns
JPWO2015102057A1 (en) Image processing method, image processing system, and program
JP2018200640A (en) Image processing device and image processing method
TWI255429B (en) Method for adjusting image acquisition parameters to optimize objection extraction
JP6323097B2 (en) Color measuring device, color measuring system, color measuring method, and program
CN108235831B (en) The control method and control system and electronic equipment of lamps and lanterns
US20150104108A1 (en) Data processor and computer-readable non-volatile recording medium for storing program for data processing
CA2862331C (en) Device and method for detecting a plant against a background
JP5266486B2 (en) Green visibility measuring apparatus, method and program
JPWO2006057314A1 (en) Image processing apparatus and image processing method
JP6165187B2 (en) Makeup evaluation method, makeup evaluation system, and makeup product recommendation method

Legal Events

Date Code Title Description
A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20080821

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A821

Effective date: 20080821

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20101101

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: 20110823

A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20110908

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

Free format text: PAYMENT UNTIL: 20141021

Year of fee payment: 3

R150 Certificate of patent or registration of utility model

Free format text: JAPANESE INTERMEDIATE CODE: R150

LAPS Cancellation because of no payment of annual fees