JP4956207B2 - Rear shape classification judgment device - Google Patents

Rear shape classification judgment device Download PDF

Info

Publication number
JP4956207B2
JP4956207B2 JP2007015450A JP2007015450A JP4956207B2 JP 4956207 B2 JP4956207 B2 JP 4956207B2 JP 2007015450 A JP2007015450 A JP 2007015450A JP 2007015450 A JP2007015450 A JP 2007015450A JP 4956207 B2 JP4956207 B2 JP 4956207B2
Authority
JP
Japan
Prior art keywords
back surface
surface shape
shape data
cluster
distance
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
JP2007015450A
Other languages
Japanese (ja)
Other versions
JP2008178605A (en
Inventor
美佐世 鈴木
ゆり 藤原
昌司 後藤
敏雄 下川
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Panasonic Corp
Panasonic Holdings Corp
Original Assignee
Panasonic Corp
Matsushita Electric Industrial 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 Panasonic Corp, Matsushita Electric Industrial Co Ltd filed Critical Panasonic Corp
Priority to JP2007015450A priority Critical patent/JP4956207B2/en
Publication of JP2008178605A publication Critical patent/JP2008178605A/en
Application granted granted Critical
Publication of JP4956207B2 publication Critical patent/JP4956207B2/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • A Measuring Device Byusing Mechanical Method (AREA)
  • Length Measuring Devices With Unspecified Measuring Means (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Description

本発明は、人体の背面形状を分類する面形状分類判定装置に関するものである。 The present invention relates to rear shape classification judgment unit for classifying the human body back shape.

人体の背面形状を分類する方法としては、従来、所謂Staffelの分類法という方法がある。この方法は、人体の背面形状を視覚的、審美眼的観点から、S字型(脊柱が生理的に自然な湾曲をした形状)、平背型(首〜腰にかけて凹凸がなく平坦な形状)、凹背型(背中が凹んで臀部が突出した形状)、円背型(首〜腰にかけて丸く突出した形状)、凹円背型(S字型の各部の凹凸が大きい形状)の五種類に分類する方法である。   As a method for classifying the shape of the back of the human body, there is conventionally a so-called Staffel classification method. In this method, the back shape of the human body is visually and aesthetically pleasing from the S-shape (the shape of the spinal column is physiologically natural), the flat back (the shape is flat with no irregularities from the neck to the waist). , Concave back type (shape where the back is recessed and the buttocks protrude), round back type (shape which protrudes round from neck to waist), and concave back type (shape where the unevenness of each part of the S-shape is large) It is a method of classification.

また、視覚的分類を定量的に分類する方法もある。この方法は、図15(a)に示すような背面形状計測装置100を用いて、以下のような手順により背面形状を分類する方法である。   There is also a method for quantitatively classifying visual classification. This method is a method of classifying the back surface shape by the following procedure using the back surface shape measuring apparatus 100 as shown in FIG.

尚背面形状計測装置100は、水平方向に変位可能なプローブ101を例えば上下方向に一定間隔を開けて複数備えたもので、図15(b)に示すように被測定者Mの背面にプローブ101を押し当てそのときのプローブ101の変位量によって図16に示す被測定者Mの背面正中線Xの形状を計測する。   The back surface shape measuring apparatus 100 is provided with a plurality of probes 101 that can be displaced in the horizontal direction at regular intervals in the vertical direction, for example, as shown in FIG. The shape of the back midline X of the measurement subject M shown in FIG. 16 is measured according to the displacement amount of the probe 101 at that time.

さて、この分類方法は、背面形状測定後、背面形状の凹凸部の度合い距離と角度などの特徴点を用いて関数近似し、その後近似関数の数値及び変曲点を算出し、背面形状に関する各種パラメータを導出し、このパラメータを基に、計数型樹木構成法など、各種統計的分類手法を用いて背面形状を分類する方法である。   In this classification method, after measuring the back surface shape, function approximation is performed using feature points such as the degree distance and angle of the back surface irregularities, and then the numerical value and inflection point of the approximate function are calculated, and various types of back surface shape are calculated. In this method, parameters are derived, and the back surface shape is classified using various statistical classification methods such as a counting tree construction method based on the parameters.

また人体の姿勢データを予め規定した姿勢パラメータに変換し、この姿勢パラメータを用いて行い、姿勢のゆがみを人体模式図に適用して視覚化して提示する姿勢診断方法等も提供されている(例えば特許文献1)
特開2003−256568号公報
There are also provided posture diagnosis methods that convert posture data of a human body into predefined posture parameters, use the posture parameters, visualize postures by applying posture distortion to a human body schematic diagram, and the like (for example, Patent Document 1)
JP 2003-256568 A

ところで、上述のStaffelの分類法を用いる場合、分類者が背面形状を視覚的主観により分類したものであるため、分類基準が明確でないという問題があった。   By the way, when the above-mentioned Staffel classification method is used, there is a problem that the classification standard is not clear because the classifier classifies the back surface shape by visual subjectivity.

また、視覚的分類を定量的に分類する方法は、背面形状の凹凸部の距離と角度などの特徴点を用いているが、その距離と角度が背面形状の曲線近似関数から算出されたものであるため、特徴点算出時の誤差などにより情報量が低下する恐れがあった。また、被測定者の身長差などを考慮しておらず、精度の良い背面形状の判定を行うことができなかった。   In addition, the method for quantitatively classifying visual classification uses feature points such as distance and angle of the back surface irregularities, and the distance and angle are calculated from the back surface curve approximation function. For this reason, there is a risk that the amount of information may decrease due to an error in calculating the feature points. In addition, the height difference of the person to be measured is not taken into account, and it is not possible to accurately determine the back surface shape.

更に、分類後、S字型は理想とされているが、その他に分類された姿勢がどの程度理想から離れているか等の情報を得ることができず、またS字型と判定された場合においても頭が前方に出ていて理想的な姿勢には見えないという問題点もあった。   Furthermore, after the classification, the S-shape is considered to be ideal, but it is not possible to obtain information such as how far the other classified postures are from the ideal, and when it is determined as the S-shape However, there was also a problem that the head was in front and it did not look like an ideal posture.

本発明は、上述の点に鑑みて為されたもので、その目的とするところは、判定対象の背面形状に対して所定の分類中最も的確な分類を客観的且つ自動的に判定することができる面形状分類判定装置を提供することにある。 The present invention has been made in view of the above-described points, and the object of the present invention is to objectively and automatically determine the most accurate classification among predetermined classifications with respect to the back surface shape to be determined. and to provide a back surface shape classification determination apparatus capable.

上述の目的を達成するために、請求項の背面形状分類判定装置に係る発明では、人体背面の凹凸を関数化した背面形状データを複数のクラスタに分けて記憶した背面形状データベースと、判定対象の背面形状を測定して当該判定対象の背面の凹凸を関数化した背面形状データを取得する背面形状取得手段と、前記判定対象の背面形状データと前記複数のクラスタに含まれる背面形状データとの間の距離に基づいて前記判定対象の背面形状が属するクラスタを決定する判定手段とを備え、前記判定手段は、前記判定対象の背面形状データと前記各クラスタの背面形状データの代表値との距離を比較して距離が最小となるクラスタに属するように判定することを特徴とする。 In order to achieve the above object, in the invention relating to the back surface shape classification determination apparatus according to claim 1, a back surface shape database in which back surface shape data obtained by functionalizing unevenness of the back of the human body is stored in a plurality of clusters, and a determination target Back shape acquisition means for measuring the back surface shape and acquiring back surface shape data obtained by functionalizing the unevenness of the back surface of the determination target, the back surface shape data of the determination target and the back surface shape data included in the plurality of clusters A determination unit that determines a cluster to which the determination target back surface shape belongs based on a distance between the determination target and the determination unit, the distance between the determination target back surface shape data and the representative value of the back surface shape data of each cluster Are determined so as to belong to the cluster having the smallest distance .

請求項の背面形状分類判定装置に係る発明によれば、判定対象の背面形状データと前記複数のクラスタに含まれる背面形状データとの距離により数値的に分類(クラスタ)を判定するので、その結果明確な基準で精度良く最も的確な分類を客観的に自動的に判定することができる。しかも、前記判定手段が、前記判定対象の背面形状データと前記各クラスタの背面形状データの代表値との距離を比較して距離が最小となるクラスタに属するように判定することにより、分類判定を高速に判定することができる。 According to the invention relating to the back surface shape classification determination apparatus of claim 1 , the classification (cluster) is numerically determined by the distance between the back surface shape data to be determined and the back surface shape data included in the plurality of clusters. As a result, it is possible to objectively automatically determine the most accurate classification with high accuracy based on clear criteria. Moreover, the determination unit compares the distance between the back surface shape data to be determined and the representative value of the back surface shape data of each cluster, and determines that the distance belongs to the cluster having the smallest distance, thereby determining the classification. Judgment can be made at high speed.

上述の目的を達成するために、請求項の背面形状分類判定装置に係る発明では、人体背面の凹凸を関数化した背面形状データを複数のクラスタに分けて記憶した背面形状データベースと、判定対象の背面形状を測定して当該判定対象の背面の凹凸を関数化した背面形状データを取得する背面形状取得手段と、前記判定対象の背面形状データと前記複数のクラスタに含まれる背面形状データとの間の距離に基づいて前記判定対象の背面形状が属するクラスタを決定する判定手段とを備え、前記判定手段は、前記判定対象の背面形状データと前記各クラスタの背面形状データの全てとの距離を比較して距離が最小となるクラスタに属するように判定することを特徴とする。 In order to achieve the above object, in the invention relating to the back surface shape classification determination apparatus according to claim 2, a back surface shape database in which back surface shape data obtained by functionalizing the unevenness of the back of the human body is stored in a plurality of clusters, and a determination target Back shape acquisition means for measuring the back surface shape and acquiring back surface shape data obtained by functionalizing the unevenness of the back surface of the determination target, the back surface shape data of the determination target and the back surface shape data included in the plurality of clusters Determining means for determining a cluster to which the back surface shape of the determination target belongs based on a distance between, and the determination means calculates a distance between the back shape data of the determination target and all of the back surface data of each cluster. The comparison is characterized in that it is determined to belong to the cluster having the smallest distance.

請求項の背面形状分類判定装置に係る発明によれば、判定対象の背面形状データと前記複数のクラスタに含まれる背面形状データとの距離により数値的に分類(クラスタ)を判定するので、その結果明確な基準で精度良く最も的確な分類を客観的に自動的に判定することができ、さらに、クラスタの大きさやクラスタ内のデータ分散を考慮した判定を行うことができる。 According to the invention related to the back surface shape classification determination apparatus of claim 2 , since the classification (cluster) is numerically determined by the distance between the back surface shape data to be determined and the back surface shape data included in the plurality of clusters, As a result, it is possible to objectively automatically determine the most accurate classification with high accuracy based on clear criteria, and to perform determination in consideration of the size of clusters and data distribution within the clusters.

上述の目的を達成するために、請求項の背面形状分類判定装置に係る発明では、人体背面の凹凸を関数化した背面形状データを複数のクラスタに分けて記憶した背面形状データベースと、判定対象の背面形状を測定して当該判定対象の背面の凹凸を関数化した背面形状データを取得する背面形状取得手段と、前記判定対象の背面形状データと前記複数のクラスタに含まれる背面形状データとの間の距離に基づいて前記判定対象の背面形状が属するクラスタを決定する判定手段とを備え、前記判定手段は、各クラスタの背面形状データの代表値と、当該クラスタ内の各背面形状データとの距離に基づいて算出した分散度合いを表す指標により前記判定対象の背面形状データを除した値を比較して距離が最小となるクラスタに属するように判定することを特徴とする。 In order to achieve the above object, in the invention relating to the back surface shape classification determination apparatus of claim 3, a back surface shape database in which back surface shape data obtained by functionalizing unevenness of the back of the human body is stored in a plurality of clusters, and a determination target Back shape acquisition means for measuring the back surface shape and acquiring back surface shape data obtained by functionalizing the unevenness of the back surface of the determination target, the back surface shape data of the determination target and the back surface shape data included in the plurality of clusters Determining means for determining a cluster to which the back surface shape to be determined belongs based on a distance between them, and the determining means includes a representative value of the back surface shape data of each cluster and each back surface shape data in the cluster. A value obtained by dividing the back surface shape data of the determination target by an index indicating the degree of dispersion calculated based on the distance is compared to determine that the distance belongs to the smallest cluster. And wherein the Rukoto.

請求項の背面形状分類判定装置に係る発明によれば、判定対象の背面形状データと前記複数のクラスタに含まれる背面形状データとの距離により数値的に分類(クラスタ)を判定するので、その結果明確な基準で精度良く最も的確な分類を客観的に自動的に判定することができ、さらに、少ない計算量でクラスタの大きさやクラスタ内のデータ分散を考慮した判定を行うことができる。 According to the invention related to the back surface shape classification determination apparatus of claim 3 , since the classification (cluster) is numerically determined by the distance between the back surface shape data to be determined and the back surface shape data included in the plurality of clusters, As a result, it is possible to objectively automatically determine the most accurate classification with high accuracy based on clear criteria, and to perform determination in consideration of the size of the cluster and data distribution within the cluster with a small amount of calculation.

上述の目的を達成するために、請求項の背面形状分類判定装置に係る発明では、人体背面の凹凸を関数化した背面形状データを複数のクラスタに分けて記憶した背面形状データベースと、判定対象の背面形状を測定して当該判定対象の背面の凹凸を関数化した背面形状データを取得する背面形状取得手段と、前記判定対象の背面形状データと前記複数のクラスタに含まれる背面形状データとの間の距離に基づいて前記判定対象の背面形状が属するクラスタを決定する判定手段とを備え、前記判定手段は、理想の背面形状を示す曲線と、前記判定対象の背面形状データとの距離に基づいて理想状態からの前記判定対象の背面形状の乖離状態を評価することを特徴とする。 In order to achieve the above object, in the invention according to the back surface shape classification determination apparatus of claim 4, a back surface shape database in which back surface shape data obtained by functionalizing unevenness of the back of the human body is stored in a plurality of clusters, and a determination target Back shape acquisition means for measuring the back surface shape and acquiring back surface shape data obtained by functionalizing the unevenness of the back surface of the determination target, the back surface shape data of the determination target and the back surface shape data included in the plurality of clusters A determination unit that determines a cluster to which the back surface shape of the determination target belongs based on a distance between the determination unit, the determination unit based on a distance between a curve indicating an ideal back surface shape and the back surface shape data of the determination target Then, the deviation state of the back surface shape of the determination target from the ideal state is evaluated.

請求項の背面形状分類判定装置に係る発明によれば、判定対象の背面形状データと前記複数のクラスタに含まれる背面形状データとの距離により数値的に分類(クラスタ)を判定するので、その結果明確な基準で精度良く最も的確な分類を客観的に自動的に判定することができ、さらに、予め定められた理想の背面形状や、理想状態の背面形状を示す示すクラスタの代表値との間の距離を求めて理想の背面形状に対する判定対象の背面形状の乖離を評価することができる。 According to the invention related to the back surface shape classification determination apparatus of claim 4 , since the classification (cluster) is numerically determined by the distance between the back surface shape data to be determined and the back surface shape data included in the plurality of clusters, As a result, it is possible to automatically and objectively determine the most accurate classification accurately and accurately, and with the predetermined ideal back surface shape and the representative value of the cluster indicating the back surface shape in the ideal state. By determining the distance between them, the deviation of the back surface shape to be determined from the ideal back surface shape can be evaluated.

上述の目的を達成するために、請求項の背面形状分類判定装置に係る発明では、人体背面の凹凸を関数化した背面形状データを複数のクラスタに分けて記憶した背面形状データベースと、判定対象の背面形状を測定して当該判定対象の背面の凹凸を関数化した背面形状データを取得する背面形状取得手段と、前記判定対象の背面形状データと前記複数のクラスタに含まれる背面形状データとの間の距離に基づいて前記判定対象の背面形状が属するクラスタを決定する判定手段とを備え、前記判定手段の判定結果を表示する表示部を備え、該表示部は、前記各クラスタの代表値間の距離に基づいて座標系に各クラスタを配置し、前記判定対象の背面形状をクラスタ間の距離に基づいて前記座標系内に表示することを特徴とする。 In order to achieve the above object, in the invention according to the back surface shape classification determination apparatus of claim 5, a back surface shape database in which back surface shape data obtained by functionalizing unevenness of the back of the human body is stored in a plurality of clusters, and a determination target Back shape acquisition means for measuring the back surface shape and acquiring back surface shape data obtained by functionalizing the unevenness of the back surface of the determination target, the back surface shape data of the determination target and the back surface shape data included in the plurality of clusters A determination unit that determines a cluster to which the back surface shape of the determination target belongs based on a distance between the display unit, and a display unit that displays a determination result of the determination unit, the display unit between representative values of the clusters Each cluster is arranged in a coordinate system based on the distance, and the back surface shape of the determination target is displayed in the coordinate system based on the distance between the clusters.

請求項の背面形状分類判定装置に係る発明によれば、判定対象の背面形状データと前記複数のクラスタに含まれる背面形状データとの距離により数値的に分類(クラスタ)を判定するので、その結果明確な基準で精度良く最も的確な分類を客観的に自動的に判定することができ、さらに、各クラスタからどの程度離れているかということを表示部によってグラフ上に表示することができる。 According to the invention relating to the back surface shape classification determination apparatus of claim 5 , since the classification (cluster) is numerically determined by the distance between the back surface shape data to be determined and the back surface shape data included in the plurality of clusters, As a result, it is possible to objectively automatically determine the most accurate classification with high accuracy based on clear criteria, and to display how far from each cluster the graph is displayed on the graph.

請求項の背面形状分類判定装置に係る発明では、請求項の発明において、前記表示部は、前記座標系の軸が背面形状についての特徴を示す指標と相関を持つように軸の設定を行うことを特徴とする。 In the invention related to the back surface shape classification determination apparatus according to claim 6, in the invention according to claim 5 , the display unit sets the axis so that the axis of the coordinate system has a correlation with an index indicating a feature of the back surface shape. It is characterized by performing.

請求項の背面形状分類判別測定装置に係る発明によれば、背面形状についてより見易く且つ理解し易いレポートとすることができる。 According to the invention relating to the back surface shape classification determination and measurement apparatus of the sixth aspect , it is possible to obtain a report that makes the back surface shape easier to see and understand.

請求項の背面形状分類判定装置に係る発明では、請求項の発明において、前記表示部は、前記座標系の軸が背面形状についての特徴を示す指標と相関を持つように軸を回転させることを特徴とする。 In the invention according to the back shape classification determination apparatus according to claim 7, characterized in that in the invention of claim 5, wherein the display unit rotates the shaft to have a correlation with index axes of the coordinate system showing the characteristics for the rear shape It is characterized by that.

請求項の背面形状分類判定装置に係る発明によれば、クラスタ間の距離により乖離度合いを表現しつつ、軸に意味を持たせることができる。 According to the invention related to the back surface shape classification determination apparatus of the seventh aspect , it is possible to give meaning to the axis while expressing the degree of deviation by the distance between the clusters.

請求項の背面形状分類判定装置に係る発明では、請求項1乃至7の何れかの発明において、前記背面形状は、頭頂部から臀部下端までを上限値及び下限値とするための拡大縮小を行う身長補正と、凹凸方向の基準値を一定にする立ち位置補正をしたものであることを特徴とする。 In the invention related to the back surface shape classification judging device according to claim 8 , in any of the inventions according to claim 1 to 7 , the back surface shape is enlarged / reduced so as to have an upper limit value and a lower limit value from the top of the head to the lower end of the buttocks. It is characterized by performing height correction to be performed and standing position correction to make the reference value in the uneven direction constant.

請求項の背面形状分類判定装置に係る発明によれば、精度の高い判定を行うことができる。 According to the invention related to the back surface shape classification determination apparatus according to the eighth aspect , it is possible to perform highly accurate determination.

本発明は、判定対象の背面形状データと前記複数のクラスタに含まれる背面形状データとの距離により数値的に分類(クラスタ)を判定するので、その結果明確な基準で精度良く最も的確な分類を客観的且つ自動的に判定することできる背面形状分類判定装置を提供できるという効果がある。 In the present invention, the classification (cluster) is determined numerically based on the distance between the back surface shape data to be determined and the back surface shape data included in the plurality of clusters, and as a result, the most accurate classification can be performed with high accuracy on a clear basis. there is an effect that it provides the back surface shape classification judging device that can be determined objectively and automatically.

以下本発明の背面形状分類判定装置を実施形態により説明する。 Hereinafter will be described the back shape classification-size TeiSo location of the present invention by the embodiment.

(実施形態1)
図1に示す本実施形態の背面形状分類判定装置1は、マイクロコンピュータ等から構成され、演算処理とハードウェアの制御とを行う演算処理部10と、読み書き自在の記憶部11と、グラフィック表示が可能な表示部12と、インターネット等のネットワーク2上に存在する背面形状計測装置3で計測した判定対象の背面形状データや、データベース4に格納されている判定対象の背面形状のデータを外部から取得するための通信部13とを備えている。通信部13はネットワーク2からデータ取得を行わない場合は設けなくても良い。尚図1では演算処理部10と、記憶部11,表示部12,通信部13との間のインターフェースについては図示を省略している。
(Embodiment 1)
A back surface shape classification determination apparatus 1 according to the present embodiment shown in FIG. 1 includes a microcomputer and the like, and includes an arithmetic processing unit 10 that performs arithmetic processing and hardware control, a readable / writable storage unit 11, and a graphic display. Obtains the back surface data of the determination target measured by the display unit 12 and the back surface shape measuring device 3 existing on the network 2 such as the Internet, and the back shape data of the determination target stored in the database 4 from the outside. And a communication unit 13 for doing so. The communication unit 13 may not be provided when data acquisition from the network 2 is not performed. In FIG. 1, the interface between the arithmetic processing unit 10 and the storage unit 11, the display unit 12, and the communication unit 13 is not shown.

さて、記憶部11は、判定処理を行うのに必要な人体背面の凹凸を関数化した背面形状データを複数のクラスタに分けて基本データ11aとしてデータベース(背面形状データベース)化して記憶する。この基本データ11aはユーザーにより容易に書き換え可能なものである。また他に、背面形状の分類の判断基準となる数値や後述する点数換算用のマトリクス表(表3参照)なども基本データ11aとして記憶する。   Now, the storage unit 11 divides back shape data obtained by converting the unevenness of the back of the human body necessary for performing the determination processing into a plurality of clusters and stores it as a database (back shape database) as basic data 11a. The basic data 11a can be easily rewritten by the user. In addition, numerical values that are criteria for determining the classification of the back surface shape, a matrix table for point conversion described later (see Table 3), and the like are also stored as basic data 11a.

更に記憶部11は、通信部13を介してネットワーク2上の背面形状計測装置3やデータベース4から対象となる背面形状の計測データを取得して記憶したり、或いは当該背面形状分類判定装置1に備えている入力手段(図示せず)を用いて入力された判定対象の背面形状の計測データや、解析対象とする範囲を定める始点(頭頂部)/終点(臀部下端)などのデータを計測データ11bとして記憶する。   Further, the storage unit 11 acquires and stores the measurement data of the target back surface shape from the back surface shape measurement device 3 and the database 4 on the network 2 via the communication unit 13, or stores the measurement data in the back surface shape classification determination device 1. Measurement data of the back surface measurement data to be judged input using the input means (not shown) and data such as the start point (top) / end point (bottom end) that define the range to be analyzed 11b is stored.

演算処理部10は、分類判定の演算処理のための機能として、判定対象の計測データと、複数のクラスタに分けた判断基準となる背面形状データとの距離を算出する距離演算機能10aと、距離演算機能10aで算出された距離データを基に、判定対象の背面形状データがどのクラスタに属するかを判定する判定処理機能10bと、両処理機能10a,10bの処理結果を受けて、2次元座標マップの座標の計算や姿勢点数の変換などの処理を行う出力用演算機能10cとを備えている。   The arithmetic processing unit 10 includes a distance calculation function 10a for calculating the distance between the measurement data to be determined and the back surface shape data serving as a determination reference divided into a plurality of clusters, as a function for the calculation processing of classification determination, Based on the distance data calculated by the calculation function 10a, the determination processing function 10b for determining which cluster the determination target back surface shape data belongs to and the processing results of both the processing functions 10a and 10b are received, and the two-dimensional coordinates An output calculation function 10c that performs processing such as calculation of map coordinates and conversion of the number of posture points is provided.

表示部12は、判定処理機能10bにより判定された結果や、出力用演算機能10cで算出された算出結果に基づいたレポートを後述するように表示する。   The display unit 12 displays a report based on the result determined by the determination processing function 10b and the calculation result calculated by the output calculation function 10c as described later.

次に本実施形態の背面形状分類判定装置1の分類判定の動作を図2に示すフローチャートに沿って説明する。   Next, the classification determination operation of the back surface shape classification determination apparatus 1 according to the present embodiment will be described with reference to the flowchart shown in FIG.

まず、演算処理部10は、通信部13を通じてネットワーク2上の背面形状計測装置3やデータベース4から判定対象とする背面形状の計測データを取得するか、或いは記憶部11の計測データ11bから判定対象とする背面形状の計測データを取得する(S1)。   First, the arithmetic processing unit 10 acquires the measurement data of the back surface to be determined from the back surface shape measuring device 3 and the database 4 on the network 2 through the communication unit 13, or the determination target from the measurement data 11 b of the storage unit 11. The measurement data of the back surface shape is acquired (S1).

ここで被測定者から判定対象の背面形状を計測する背面形状計測装置(ネットワーク2の背面形状計測装置3を含む)は、図15に示す背面形状計測装置100と同じものであって、例えば上下方向のプローブの数が例えば41本でその間隔を備え夫々のプローブの変位量(突出量)を出力するようになっている。尚ここではプローブ間隔を30mmとしたものを用いる。   Here, the back surface shape measuring device (including the back surface shape measuring device 3 of the network 2) that measures the back surface shape to be determined from the measurement subject is the same as the back surface shape measuring device 100 shown in FIG. The number of probes in the direction is 41, for example, and there is an interval between them to output the displacement amount (protrusion amount) of each probe. Here, the probe spacing is 30 mm.

図3(a)は、各プローブ毎の突出量を示す計測データの一例であり、この計測データ値を、縦軸(y軸)にプローブの位置(Noで示す)を、横軸(x軸)に突出量(mm)としたグラフ化したものであり、このグラフの曲線が対象背面の曲線を示すことになる。   FIG. 3A is an example of measurement data indicating the amount of protrusion for each probe. The measurement data value is plotted on the vertical axis (y-axis) with the probe position (indicated by No) and on the horizontal axis (x-axis). ) In the form of a projection amount (mm), and the curve of this graph represents the curve on the back of the object.

ここで被測定者の身長や計測に用いる背面形状計測装置3に対する被測定者の立ち位置の違いなどを補正するために、事前処理S2を行う。   Here, a pre-process S2 is performed in order to correct the height of the measurement subject and the difference in the standing position of the measurement subject with respect to the back surface shape measuring device 3 used for measurement.

この事前処理S2では、計測データとともに取得した解析対象とする範囲を定める始点(頭頂)/終点(臀部下端)のデータに基づいて計測データから始点から臀部下端の範囲の計測データのみを切り出す。図4(a)は切り出したプローブ毎の突出量を示し、図4(b)は切り出したデータをグラフ化したものを示す。   In this pre-processing S2, only measurement data in the range from the start point to the lower end of the buttock is cut out from the measurement data based on the start point (top) / end point (lower end of the buttock) that defines the range to be analyzed acquired together with the measurement data. FIG. 4A shows the protruding amount for each cut out probe, and FIG. 4B shows a graph of the cut out data.

この切り出し後、この切り出したデータを規定の長さ(y軸)に拡大又は縮小し、また横方向(突出量)についても拡大又は縮小することで、身長補正を行う。例えば100の長さで身長補正を行う場合には、y軸=(プローブNo−始点)/(100/(終点−始点))、突出量/(100/(終点−始点))と補正する。図5(a)はこの100で身長補正した後のプローブ毎の突出量を示し、図5(b)はそのデータをグラフ化したものを示す。   After the cutout, the cutout data is enlarged or reduced to a specified length (y-axis), and the horizontal direction (projection amount) is also enlarged or reduced to correct the height. For example, when height correction is performed with a length of 100, correction is made as y-axis = (probe number−start point) / (100 / (end point−start point)), protrusion amount / (100 / (end point−start point)). FIG. 5A shows the protrusion amount for each probe after the height is corrected by 100, and FIG. 5B shows a graph of the data.

この身長補正後、立ち位置の前後の誤差を補正するために身長補正したデータの中央値を0に持ってくるようにx軸処理を行う。この場合x軸=突出量−突出量の中央値という形で補正を行う。図6(a)は立ち位置補正後のプローブ毎の突出量を示し、図6(b)はそのデータをグラフ化したものを示す。   After this height correction, in order to correct the error before and after the standing position, the x-axis processing is performed so that the median value of the height-corrected data is brought to zero. In this case, correction is performed in the form of x axis = protrusion amount−median value of the protrusion amount. FIG. 6A shows the amount of protrusion for each probe after the standing position correction, and FIG. 6B shows a graph of the data.

さて、事前処理S2を終えたデータを用いて滑らかな曲線を得るための近似曲線を求める処理を行う(S3)。この処理S3では例えば9次関数近似を用いて近似式を求め、この近似式から予測値を求める。この予測値を以後の処理において判定対象の背面計測データとして用いる。尚被測定者毎に何次関数近似が最適かを、生の計測データ、又はスプライン近似曲線等との差を見て自動判断を行っても良い。   Now, processing for obtaining an approximate curve for obtaining a smooth curve is performed using the data that has undergone the pre-processing S2 (S3). In this process S3, an approximate expression is obtained using, for example, ninth-order function approximation, and a predicted value is obtained from this approximate expression. This predicted value is used as back surface measurement data to be determined in subsequent processing. It should be noted that automatic determination may be made by referring to the difference between the raw measurement data, the spline approximation curve, or the like as to what order function approximation is optimal for each person to be measured.

ここまでが演算処理装置1の背面形状データ取得手段としての演算処理部10の機能の働きとなる。   Up to this point, the operation of the arithmetic processing unit 10 as the back surface shape data acquisition unit of the arithmetic processing device 1 is performed.

さてこの処理S3を終了した後、演算処理部10は距離演算機能10aによって、記憶部11から基本データ11aを読み出し、各クラスタの背面形状データと判定対象の背面形状データとの距離を演算し、この演算結果を用いて判定処理機能10bにより判定対象の背面形状データがどの分類(クラスタ)に所属するかを判定する(S4)。   Now, after this process S3 is complete | finished, the arithmetic processing part 10 reads the basic data 11a from the memory | storage part 11 by the distance calculation function 10a, calculates the distance of the back surface shape data of each cluster, and the back surface shape data of judgment object, Using this calculation result, the determination processing function 10b determines to which classification (cluster) the back surface shape data to be determined belongs (S4).

この場合、例えば記憶部11の基本データ11aから各クラスタに所属するn名の背面形状データにおけるx軸方向の平均値、又は中央値からなる各クラスタの代表値と、判定対象の背面形状データとの距離(ユークリッド距離、ユークリッド平方距離、市街地距離等)を算出し、距離が最も小さい分類(クラスタ)を選択する。   In this case, for example, the average value in the x-axis direction in the n back surface shape data belonging to each cluster from the basic data 11a of the storage unit 11 or the representative value of each cluster consisting of the median value, and the back surface shape data to be determined Distance (Euclidean distance, Euclidean square distance, city area distance, etc.) is calculated, and the classification (cluster) with the smallest distance is selected.

図7は各クラスタ、例えばクラスタ”1”〜”4”の代表値(黒点で示す)と、判定対象のデータαとの距離のイメージを示しており、この図7の例ではクラスタ”3”が選択されることになる。   FIG. 7 shows an image of the distance between each cluster, for example, the representative values (indicated by black dots) of the clusters “1” to “4” and the determination target data α. In the example of FIG. Will be selected.

次にクラスタを選択した後、距離演算機能10aにより、当該判定対象の背面形状と理想の背面形状との離れ値を算出する処理を行う(S5)。   Next, after selecting a cluster, the distance calculation function 10a performs a process of calculating a separation value between the determination target back surface shape and the ideal back surface shape (S5).

この処理では、基本データ11aとして登録されている理想の背面形状データ[最良のクラスタ(例えば近似直線の傾きが垂直に近く、凹凸の少ない形状)の代表値(当該クラスタに所属する所属するn名の背面形状データにおけるx軸方向の平均値、又は中央値)又は姿勢に関する研究者等の専門家から理想形状と認定された一個人の背面形状データ]と、判定対象の背面形状データとの距離(ユークリッド距離、ユークリッド平方距離、市街地距離等)を理想形状との差(離れ値)として算出する。この算出によって理想の背面形状に対する当該判定対象の背面形状の乖離状態を評価するのである。   In this processing, the ideal back surface shape data [the best cluster (for example, the shape of the approximate straight line is nearly vertical and the shape of the unevenness) representative value (n names belonging to the cluster) registered as the basic data 11a. The distance between the back surface shape data to be judged and the back surface shape data of an individual determined as an ideal shape by a researcher or other expert regarding the posture) Euclidean distance, Euclidean square distance, city area distance, etc.) are calculated as the difference (separated value) from the ideal shape. By this calculation, the deviation state of the determination target back surface shape with respect to the ideal back surface shape is evaluated.

この算出後、演算処理部10は出力用演算機能10aによって背面形状データを2次元データに落とし、座標を算出するとともに、x軸に特徴となる指標との相関を持たせるために回転をかける処理を行って、マップ座標算出の処理を行う(S6)。   After this calculation, the arithmetic processing unit 10 uses the output arithmetic function 10a to drop the back surface shape data into two-dimensional data, calculates the coordinates, and applies a rotation to correlate with an index that is characteristic of the x axis. To calculate map coordinates (S6).

この場合各クラスタの代表値(各クラスタに所属する所属するn名の背面形状データにおけるx軸方向の平均値、又は中央値)間の距離(ユークリッド距離、ユークリッド平方距離、市街地距離等)から座標を算出する。   In this case, the coordinates are based on the distance (Euclidean distance, Euclidean square distance, city area distance, etc.) between the representative values of each cluster (average value or median value in the x-axis direction in the n back surface shape data belonging to each cluster). Is calculated.

表1は、7分類(クラスタ)の中央値間のユークリッド平方距離を示しており、この表1に基づいて上述の座標の算出を詳説する。尚表の””内の数字はクラスタNoを示す。   Table 1 shows the Euclidean square distance between the medians of the seven classifications (clusters), and the calculation of the above-described coordinates will be described in detail based on Table 1. The numbers in “” in the table indicate the cluster numbers.

ここで、各クラスタ”1”〜”7”の位置Piを次のようにおく。   Here, the positions Pi of the clusters “1” to “7” are set as follows.

P1:(x1,y1)
P2:(x2,y2)
P3:(x3,y3)
P4:(x4,y4)
P5:(x5,y5)
P6:(x6,y6)
P7:(x7,y7)
また、理想背面形状のクラスタであるクラスタ”2”の座標を(0,0)と定め、もう一点をクラスタ”1”とし、y座標を0に固定すると、三平方の定理より、以下の連立方程式が成り立つ。
P1: (x1, y1)
P2: (x2, y2)
P3: (x3, y3)
P4: (x4, y4)
P5: (x5, y5)
P6: (x6, y6)
P7: (x7, y7)
If the coordinates of cluster “2”, which is an ideal back surface cluster, is defined as (0, 0), the other point is cluster “1”, and the y coordinate is fixed to 0, the following simultaneous equations are obtained from the three-square theorem. The equation holds.

x3+y3=d23 …(1)
x4+y4=d24 …(2)
x5+y5=d25 …(3)
x6+y5=d26 …(4)
x7+y7=d23 …(5)
(x3−√d12)+y3=d13 …(6)
(x4−√d12)+y4=d14 …(7)
(x5−√d12)+y5=d15 …(8)
(x6−√d12)+y6=d16 …(9)
(x7−√d12)+y7=d17 …(10)
尚x、yの後ろの数字はクラスタNoを、またdは2点間の距離を示し、後ろの2つの数字は対応する2点のクラスタNoを夫々示す。
x3 2 + y3 2 = d23 (1)
x4 2 + y4 2 = d24 (2)
x5 2 + y5 2 = d25 (3)
x6 2 + y5 2 = d26 (4)
x7 2 + y7 2 = d23 (5)
(X3-√d12) 2 + y3 2 = d13 (6)
(X4-√d12) 2 + y4 2 = d14 (7)
(X5-√d12) 2 + y5 2 = d15 (8)
(X6-√d12) 2 + y6 2 = d16 (9)
(X7−√d12) 2 + y7 2 = d17 (10)
The numbers after x and y indicate the cluster number, d indicates the distance between the two points, and the two numbers after the two indicate the corresponding cluster numbers of the two points.

さて、各クラスタ同士の距離dは、表1より明らかであるため、(1)〜(10)の連立方程式を解くと、全てのxとyが求まり、上記例では次のような座標が求められた。   Since the distance d between the clusters is clear from Table 1, all the x and y are obtained by solving the simultaneous equations (1) to (10). In the above example, the following coordinates are obtained. It was.

P1:(−1.1964,0)
P2:(0,0)
P3:(1.2862,0.76141)
P4:(2.1208,2.6698)
P5:(−0.67218,1.5764)
P6:(1.0087,1.9164)
P7:(0.24599,0.94683)
次に各クラスタの中央値の背面形状データにおける近似曲線の係数を求める。表2は求めた結果を示しており、この表2に示す係数は姿勢が後傾であればマイナス、前傾であればプラス、真っ直ぐに近ければ0に近い値となる。これによりx軸が傾きを表すとした場合は、クラスタ”2”とクラスタ”5”がy軸上にほぼ並ぶように位置すると言えることになる。
P1: (−1.1964, 0)
P2: (0, 0)
P3: (1.2862, 0.76141)
P4: (2.1208, 2.6698)
P5: (−0.67218, 1.5764)
P6: (1.00087, 1.9164)
P7: (0.24599, 0.94683)
Next, the coefficient of the approximate curve in the back shape data of the median value of each cluster is obtained. Table 2 shows the obtained results. The coefficients shown in Table 2 are negative if the posture is backward tilted, positive if the posture is forward tilted, and close to 0 if the posture is close to straight. As a result, when the x-axis represents an inclination, it can be said that the clusters “2” and “5” are positioned so as to be substantially aligned on the y-axis.

図8は、クラスタ”1”〜”7”の2次元座標のプロットを示し、各黒点は求められた座標であって、夫々に付した数字はクラスタNoを示す。尚図中の実線の曲線は各クラスタの背面形状の曲線、破線は理想の背面形状の曲線を示す。   FIG. 8 shows a plot of the two-dimensional coordinates of the clusters “1” to “7”, where each black dot is the obtained coordinate, and the number given to each indicates a cluster number. In the figure, the solid curve represents the back surface of each cluster, and the broken line represents the ideal back surface curve.

ここで、例えば図9に示すようにクラスタ”5”の座標P5:(x5,y5)をx=0のy軸上に持ってくるには、座標P2を中心として時計方向に回転させれば良く、この回転角θは、θ=cos−1 (y5/√d25)と表すことができ、これを解くとθ=23.1°が求まる。 Here, for example, as shown in FIG. 9, in order to bring the coordinates P5: (x5, y5) of the cluster “5” on the y axis where x = 0, the coordinates P2 should be rotated clockwise. The rotation angle θ can be expressed as θ = cos −1 (y5 / √d25), and by solving this, θ = 23.1 ° is obtained.

そして回転後の座標P5’:(x5’,y5’)は、
x5’=x5cosθ−y5sinθ
y5’=x5sinθ−y5cosθ
となる。
And the coordinates P5 ′ after rotation: (x5 ′, y5 ′) are
x5 ′ = x5 cos θ−y5 sin θ
y5 ′ = x5sin θ−y5 cos θ
It becomes.

そして座標P2を中心としてその他の全ての座標P1〜P7を上述のように時計方向に23.1°回転させたときの、新しい座標P1’〜P7’は次のようになる。   Then, new coordinates P1 'to P7' when the other coordinates P1 to P7 are rotated clockwise by 23.1 ° as described above with the coordinate P2 as the center are as follows.

P1’:(−1.1005,0.46926)
P2’:(0,0)
P3’:(1.4818,0.19593)
P4’:(2.998,1.6242)
P5’:(0,1.7138)
P6’:(1.6795,1.3672)
P7’:(0.59764,0.77448)
図10(a)はこの回転後の座標をプロットしたものである。図10(b)は各クラスタ”1”〜”7”の回転後のx座標と近似直線との傾きがどの程度の相関があるかを見るために作成した散布図である。この散布図には正の相関が見られ、相関係数は0.998と非常に強い相関関数であることが分かる。
P1 ′: (−1.1005, 0.46926)
P2 ': (0, 0)
P3 ′: (1.4818, 0.19593)
P4 ′: (2.998, 1.6242)
P5 ′: (0, 1.7138)
P6 ′: (1.6795, 1.3672)
P7 ′: (0.59764, 0.77448)
FIG. 10A plots the coordinates after the rotation. FIG. 10B is a scatter diagram created to see the degree of correlation between the x-coordinates after rotation of the clusters “1” to “7” and the approximate line. This scatter diagram shows a positive correlation, and it can be seen that the correlation coefficient is 0.998, which is a very strong correlation function.

同様にしてクラスタ”1”と、クラスタ”2”からの判定対象のデータに対する距離を用いて座標を求めることが可能である。   Similarly, the coordinates can be obtained by using the distance from the cluster “1” and the data to be determined from the cluster “2”.

上述のようにしてマップ座標の算出処理(S6)が終了したのち、演算処理部10は出力用演算機能10cにより、姿勢点数の算出処理を行う(S7)。   After the map coordinate calculation process (S6) is completed as described above, the calculation processing unit 10 performs the posture point calculation process using the output calculation function 10c (S7).

この算出処理は、まず判定対象の背面形状データの近似曲線の傾きをx軸、S5で求めた理想からの離れ値(距離)をy軸とし、離れ値から、記憶部11に基本データ11aとして記憶している距離と姿勢点数の関係を示すマトリクス表(表3)を用いて姿勢点数を算出する。   In this calculation process, first, the slope of the approximate curve of the back surface shape data to be determined is the x-axis, the departure value (distance) from the ideal obtained in S5 is the y-axis, and from the separation value, the basic data 11a is stored in the storage unit 11. The posture score is calculated using a matrix table (Table 3) showing the relationship between the stored distance and the posture score.

尚頭や腰、臀部などの部位別の項目毎に重み付けして点数を付けるようにしても良い。    It should be noted that points may be assigned by weighting each item such as the head, waist and buttocks.

而して、演算処理部10は、判定処理機能10bでの分類(クラスタ)判定の結果や、出力用演算機能10cでの2次元座標や姿勢点数の算出結果に基づいて表示部12を通じてユーザーに提示するレポート排出の処理を行う(S8)。   Thus, the arithmetic processing unit 10 notifies the user through the display unit 12 based on the result of classification (cluster) determination by the determination processing function 10b and the calculation result of the two-dimensional coordinates and the number of posture points by the output arithmetic function 10c. The report discharge process to be presented is performed (S8).

図11は表示部12で表示したレポートを示しており、図示するように被測定者の姿勢点数や被測定者の背面形状データの補正・近似後の背面形状と理想の背面形状を重ね表示しあり、被測定者の背骨に対する評価のコメント、Strffelによる分類結果、更に被測定者の姿勢(背面形状)を、各クラスタ間の距離に基づいて2次元座標系内で表示したり、更に各種コメントが表示される。   FIG. 11 shows a report displayed on the display unit 12. As shown in the figure, the back shape after correction / approximation of the posture number of the subject and the back shape data of the subject and the ideal back shape are displayed in an overlapping manner. Yes, comments on evaluation of the subject's spine, classification results by Strffel, and the posture (rear shape) of the subject to be measured in a two-dimensional coordinate system based on the distance between each cluster, and various comments Is displayed.

このレポートを見た被測定者は自己の姿勢と理想の姿勢との離れ具合などが直感的に分かることになる。   The measured person who sees this report can intuitively understand the degree of separation between his / her ideal posture and the ideal posture.

尚上述の座標の算出の代わりに、背面形状データの曲線の特徴となる指標を軸に対応付けた座標を算出するようにしても良い。   Instead of calculating the above-described coordinates, coordinates in which an index that is a characteristic of the curve of the back surface shape data is associated with the axis may be calculated.

つまり、この算出によれば、x軸、y軸が共に特徴となる指標と一致した座標を算出することができ、算出時間も短縮できる。   That is, according to this calculation, it is possible to calculate coordinates where the x-axis and the y-axis coincide with the characteristic index, and the calculation time can be shortened.

この場合、例えは背面形状の近似直線の傾きをx軸とし、理想の背面形状とのユークリッド距離をy軸とする座標を算出するのである(尚背面形状の凹凸量などをy軸としても良い)。図12はこの算出した1000名分の座標をプロットした例を示しており、グレースケールの違いがクラスタの違いを示している。
(実施形態2)
本実施形態では、図2に示すフローチャートの判別の処理(S4)において、判定対象の背面形状のデータと各クラスタに属する全てのデータとの距離(ユークリッド距離、ユークリッド平方距離、市街地距離等)の平均を算出し、この平均値の最も小さい分類(クラスタ)を選択する点で実施形態1と相違する。
In this case, for example, coordinates are calculated with the inclination of the approximate straight line of the back surface as the x axis and the Euclidean distance from the ideal back surface as the y axis (note that the unevenness of the back surface shape may be used as the y axis). ). FIG. 12 shows an example in which the calculated coordinates for 1000 people are plotted, and the difference in gray scale indicates the difference in cluster.
(Embodiment 2)
In the present embodiment, in the discrimination process (S4) of the flowchart shown in FIG. 2, the distance (Euclidean distance, Euclidean square distance, city area distance, etc.) between the back face shape data to be judged and all data belonging to each cluster is determined. The difference from the first embodiment is that an average is calculated and a classification (cluster) having the smallest average value is selected.

例えば判定対象のデータと、あるクラスタ”N”に属する背面形状データとの距離をd1〜dnとしたとき、クラスタ”N”の該当データとの距離平均は、数1で示す式のように表せる。   For example, when the distance between the data to be determined and the back surface shape data belonging to a certain cluster “N” is d1 to dn, the distance average between the corresponding data of the cluster “N” can be expressed by the equation shown in Equation 1. .

この距離平均値が最も小さい分類(クラスタ)を選択する判定を行うのある。図13はこの判定のイメージを示しており、該当データαと各クラスタ、例えば”1”〜”4”に属する各データ(黒点)との間の距離を求めてその平均値の最も小さい分類(クラスタ)を選択するのである。   There is a determination to select a classification (cluster) having the smallest distance average value. FIG. 13 shows an image of this determination. The distance between the corresponding data α and each data (black dot) belonging to each cluster, for example, “1” to “4” is obtained, and the classification with the smallest average value ( Cluster).

尚その他の構成や動作は実施形態1と同じであるので説明は省略する。   Since other configurations and operations are the same as those in the first embodiment, description thereof is omitted.

而して本実施形態は、各分類(クラスタ)に属する全てのデータを用いることにより、各分類(クラスタ)の大きさや分散度合いなども考慮にいれた精度の良い判定を行うことができる。
(実施形態3)
本実施形態では、図2に示すフローチャートの判別の処理(S4)において、判定対象の背面形状のデータと各分類(クラスタ)の代表値(各クラスタに属するn名の背面形状データにおけるx軸の平均値又は中央値)と、その分類(クラスタ)に属する背面形状データとの距離平均で、判定対象データと各分離(クラスタ)の代表値の距離で除することにより、分布の大きさで規準化した指標を作成し、この指標が最も小さい分類(クラスタ)を選択する点で実施形態12と相違する。
Thus, in the present embodiment, by using all data belonging to each classification (cluster), it is possible to make a highly accurate determination in consideration of the size and the degree of dispersion of each classification (cluster).
(Embodiment 3)
In the present embodiment, in the discrimination process (S4) of the flowchart shown in FIG. 2, the back face shape data to be judged and the representative value of each classification (cluster) (the x axis in the n back face shape data belonging to each cluster). The average value or median value) and the distance average between the back surface shape data belonging to the classification (cluster), and dividing by the distance between the data to be judged and the representative value of each separation (cluster), the standard of distribution size This is different from the twelfth embodiment in that a digitized index is created and a classification (cluster) having the smallest index is selected.

例えば分類(クラスタ)の代表値と、その分類(クラスタ)に属するデータとの距離平均をdm(このdmは予め記憶部1の基準データ11aとして記憶されているものとする)とし、判定対象データと分類(クラスタ)の代表値との距離をdとしたとき、判定対象データとそのクラスタとの基準化した指標は、
d/dm
で表すことができ、この指標が最も小さい分類(クラスタ)を選択する判定を行うのである。図14はこの判定のイメージを示しており、各クラスタ、例えば”1”〜”4”に属する各背面形状データ(小黒点)とその代表値(大黒点)との間の距離の平均値dmを求めるとともに、判定対象のデータαと各代表値との距離dを求めて上述のように指標を算出し、その指標が最も小さい分類(クラスタ)を選択するのである。
For example, the distance average between the representative value of the classification (cluster) and the data belonging to the classification (cluster) is dm (this dm is stored in advance as the reference data 11a of the storage unit 1), and the determination target data And the distance between the representative value of the classification (cluster) and d, the standardized index between the determination target data and the cluster is
d / dm
The determination is made to select the classification (cluster) with the smallest index. FIG. 14 shows an image of this determination, and the average value dm of the distance between each back surface shape data (small black point) belonging to each cluster, for example, “1” to “4” and its representative value (large black point). And the distance d between the determination target data α and each representative value is calculated, the index is calculated as described above, and the classification (cluster) having the smallest index is selected.

尚その他の構成や動作は実施形態1と同じであるので説明は省略する。   Since other configurations and operations are the same as those in the first embodiment, description thereof is omitted.

実施形態1の背面形状分類判定装置のブロック図である。It is a block diagram of the back surface shape classification determination apparatus of Embodiment 1. 実施形態1の分類判定処理の動作説明用フローチャートである。5 is a flowchart for explaining operations of classification determination processing according to the first embodiment. 実施形態1に用いる判定対象の背面形状データ例図である。It is a back surface shape data example figure of the judgment object used for Embodiment 1. FIG. 実施形態1に用いる判定対象の背面形状データから切り出した後のデータ例図である。It is a data example figure after cutting out from the back surface shape data of the judgment object used for Embodiment 1. 実施形態1に用いる判定対象の背面形状データの身長補正後のデータ例図である。It is a data example figure after the height correction | amendment of the back shape data of the determination object used for Embodiment 1. FIG. 実施形態1に用いる判定対象の背面形状データの立ち位置補正後のデータ例図である。It is a data example figure after standing position correction of the back face shape data of the judgment object used for Embodiment 1. 実施形態1の判定対象の背面形状データと各クラスタの代表値との距離を示すイメージ図である。It is an image figure which shows the distance of the back surface shape data of the determination target of Embodiment 1, and the representative value of each cluster. 実施形態1の各クラスタの代表値の2次元座標のプロット例図である。FIG. 4 is a plot example diagram of two-dimensional coordinates of representative values of each cluster according to the first embodiment. 実施形態1の座標軸の回転設定の説明図である。FIG. 6 is an explanatory diagram of a coordinate axis rotation setting according to the first embodiment. (a)は実施形態1の座標軸の回転設定後の2次元座標のプロット例図、(b)は実施形態1の各クラスタのx座標と近似直線の傾きの散布例図である。(A) is a plot example diagram of the two-dimensional coordinates after setting the rotation of the coordinate axis of the first embodiment, and (b) is a scatter example diagram of the x-coordinate of each cluster and the inclination of the approximate line in the first embodiment. 実施形態1の表示部でのレポート表示例図である。6 is a report display example diagram on the display unit of Embodiment 1. FIG. 実施形態1の座標の別の算出法によって算出された結果の2次元座標のプロット例図である。FIG. 10 is a plot example diagram of two-dimensional coordinates as a result calculated by another coordinate calculation method according to the first embodiment. 実施形態2における分類判定に用いる各クラスタの代表となる背面形状データの値とクラスタ内の背面形状データとの距離を示すイメージ図である。FIG. 9 is an image diagram showing a distance between a back surface shape data value representing each cluster used for classification determination in Embodiment 2 and back surface shape data in the cluster. 実施形態3における分類判定に用いる判定対象の背面形状データと各クラスタ内の各背面形状データとの距離を示すイメージ図である。It is an image figure which shows the distance of the back surface shape data of the determination object used for the classification | category determination in Embodiment 3, and each back surface shape data in each cluster. (a)は背面形状計測装置の側面図、(b)は背面形状計測装置を用いて計測中の状態を示す側面図である。(A) is a side view of a back surface shape measuring device, (b) is a side view which shows the state under measurement using a back surface shape measuring device. 人体背面の背面正中線の説明図である。It is explanatory drawing of the back midline of a human body back surface.

符号の説明Explanation of symbols

1 背面形状分離判定装置
10 演算処理部
10a 距離演算機能
10b 判定処理機能
10c 出力用演算機能
11 記憶部
11a 基本データ
11b 計測データ
12 表示部
13 通信部
2 ネットワーク
3 背面形状計測装置
4 データベース
DESCRIPTION OF SYMBOLS 1 Back surface shape separation determination apparatus 10 Arithmetic processing part 10a Distance calculation function 10b Determination processing function 10c Output calculation function 11 Storage part 11a Basic data 11b Measurement data 12 Display part 13 Communication part 2 Network 3 Back surface shape measurement apparatus 4 Database

Claims (8)

人体背面の凹凸を関数化した背面形状データを複数のクラスタに分けて記憶した背面形状データベースと、判定対象の背面形状を測定して当該判定対象の背面の凹凸を関数化した背面形状データを取得する背面形状取得手段と、前記判定対象の背面形状データと前記複数のクラスタに含まれる背面形状データとの間の距離に基づいて前記判定対象の背面形状が属するクラスタを決定する判定手段とを備え、前記判定手段は、前記判定対象の背面形状データと前記各クラスタの背面形状データの代表値との距離を比較して距離が最小となるクラスタに属するように判定することを特徴とする背面形状分類判定装置 Back surface shape database that stores back surface shape data that is a function of unevenness on the back of the human body divided into multiple clusters and back surface shape data that measures the back surface shape of the judgment target and functionalizes the back surface unevenness of the judgment target Back surface acquisition means for determining, and determination means for determining a cluster to which the back surface shape of the determination target belongs based on a distance between the back surface shape data of the determination target and back surface shape data included in the plurality of clusters. , the determining means, the back shape, wherein the determining to belong to the distance by comparing the distance between the representative value of the rear shape data of the determination target of the rear shape data and said each cluster is the minimum cluster Classification judgment device . 人体背面の凹凸を関数化した背面形状データを複数のクラスタに分けて記憶した背面形状データベースと、判定対象の背面形状を測定して当該判定対象の背面の凹凸を関数化した背面形状データを取得する背面形状取得手段と、前記判定対象の背面形状データと前記複数のクラスタに含まれる背面形状データとの間の距離に基づいて前記判定対象の背面形状が属するクラスタを決定する判定手段とを備え、前記判定手段は、前記判定対象の背面形状データと前記各クラスタの背面形状データの全てとの距離を比較して距離が最小となるクラスタに属するように判定することを特徴とする背面形状分類判定装置。 Back surface shape database that stores back surface shape data that is a function of unevenness on the back of the human body divided into multiple clusters and back surface shape data that measures the back surface shape of the judgment target and functionalizes the back surface unevenness of the judgment target Back surface acquisition means for determining, and determination means for determining a cluster to which the back surface shape of the determination target belongs based on a distance between the back surface shape data of the determination target and back surface shape data included in the plurality of clusters. The determination means compares the distance between the back surface shape data to be determined and all the back surface shape data of each cluster and determines that the distance belongs to the cluster having the smallest distance. Judgment device. 人体背面の凹凸を関数化した背面形状データを複数のクラスタに分けて記憶した背面形状データベースと、判定対象の背面形状を測定して当該判定対象の背面の凹凸を関数化した背面形状データを取得する背面形状取得手段と、前記判定対象の背面形状データと前記複数のクラスタに含まれる背面形状データとの間の距離に基づいて前記判定対象の背面形状が属するクラスタを決定する判定手段とを備え、前記判定手段は、各クラスタの背面形状データの代表値と、当該クラスタ内の各背面形状データとの距離に基づいて算出した分散度合いを表す指標により前記判定対象の背面形状データを除した値を比較して距離が最小となるクラスタに属するように判定することを特徴とする背面形状分類判定装置。 Back surface shape database that stores back surface shape data that is a function of unevenness on the back of the human body divided into multiple clusters and back surface shape data that measures the back surface shape of the judgment target and functionalizes the back surface unevenness of the judgment target Back surface acquisition means for determining, and determination means for determining a cluster to which the back surface shape of the determination target belongs based on a distance between the back surface shape data of the determination target and back surface shape data included in the plurality of clusters. The determination means is a value obtained by dividing the determination target back surface shape data by an index representing the degree of dispersion calculated based on the distance between the back surface shape data of each cluster and each back surface shape data in the cluster. rear shape classification judging device you wherein the determining to belong to a cluster distance is the minimum by comparing. 人体背面の凹凸を関数化した背面形状データを複数のクラスタに分けて記憶した背面形状データベースと、判定対象の背面形状を測定して当該判定対象の背面の凹凸を関数化した背面形状データを取得する背面形状取得手段と、前記判定対象の背面形状データと前記複数のクラスタに含まれる背面形状データとの間の距離に基づいて前記判定対象の背面形状が属するクラスタを決定する判定手段とを備え、前記判定手段は、理想の背面形状を示す曲線と、前記判定対象の背面形状データとの距離に基づいて理想状態からの前記判定対象の背面形状の乖離状態を評価することを特徴とする背面形状分類判定装置。 Back surface shape database that stores back surface shape data that is a function of unevenness on the back of the human body divided into multiple clusters and back surface shape data that measures the back surface shape of the judgment target and functionalizes the back surface unevenness of the judgment target Back surface acquisition means for determining, and determination means for determining a cluster to which the back surface shape of the determination target belongs based on a distance between the back surface shape data of the determination target and back surface shape data included in the plurality of clusters. , the determination unit shall be the features and the curve showing the ideal rear shape, to evaluate the divergence state of the rear surface shape of the determination target from the ideal state based on the distance between the back surface shape data of the determination target rear shape classification judgment unit. 人体背面の凹凸を関数化した背面形状データを複数のクラスタに分けて記憶した背面形状データベースと、判定対象の背面形状を測定して当該判定対象の背面の凹凸を関数化した背面形状データを取得する背面形状取得手段と、前記判定対象の背面形状データと前記複数のクラスタに含まれる背面形状データとの間の距離に基づいて前記判定対象の背面形状が属するクラスタを決定する判定手段とを備え、前記判定手段の判定結果を表示する表示部を備え、該表示部は、前記各クラスタの代表値間の距離に基づいて座標系に各クラスタを配置し、前記判定対象の背面形状をクラスタ間の距離に基づいて前記座標系内に表示することを特徴とする背面形状分類判定装置。 Back surface shape database that stores back surface shape data that is a function of unevenness on the back of the human body divided into multiple clusters and back surface shape data that measures the back surface shape of the judgment target and functionalizes the back surface unevenness of the judgment target Back surface acquisition means for determining, and determination means for determining a cluster to which the back surface shape of the determination target belongs based on a distance between the back surface shape data of the determination target and back surface shape data included in the plurality of clusters. the a display unit for displaying the determination result of the determining means, the display unit, the respective clusters are located on the coordinate system based on the distance between the representative value of each cluster, between the cluster and the back shape of the determination target rear shape classification judging device it means displays in the coordinate system based on the distance. 前記表示部は、前記座標系の軸が背面形状についての特徴を示す指標と相関を持つように軸の設定を行うことを特徴とする請求項記載の背面形状分類判定装置。 6. The rear shape classification determination apparatus according to claim 5 , wherein the display unit sets the axis such that the axis of the coordinate system has a correlation with an index indicating the characteristic of the rear shape. 前記表示部は、前記座標系の軸が背面形状についての特徴を示す指標と相関を持つように軸を回転させることを特徴とする請求項記載の背面形状分類判定装置。 The back surface shape classification determination apparatus according to claim 5 , wherein the display unit rotates the axis so that the axis of the coordinate system has a correlation with an index indicating characteristics of the back surface shape. 前記背面形状は、頭頂部から臀部下端までを上限値及び下限値とするための拡大縮小を行う身長補正と、凹凸方向の基準値を一定にする立ち位置補正をしたものであることを特徴とする請求項1乃至7の何れかの1項に記載の背面形状分類判定装置 The back surface shape is obtained by performing height correction for performing enlargement / reduction to set the upper limit value and the lower limit value from the top of the head to the lower end of the buttocks, and standing position correction for making the reference value in the uneven direction constant. The back shape classification determination apparatus according to any one of claims 1 to 7 .
JP2007015450A 2007-01-25 2007-01-25 Rear shape classification judgment device Expired - Fee Related JP4956207B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2007015450A JP4956207B2 (en) 2007-01-25 2007-01-25 Rear shape classification judgment device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2007015450A JP4956207B2 (en) 2007-01-25 2007-01-25 Rear shape classification judgment device

Publications (2)

Publication Number Publication Date
JP2008178605A JP2008178605A (en) 2008-08-07
JP4956207B2 true JP4956207B2 (en) 2012-06-20

Family

ID=39722945

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2007015450A Expired - Fee Related JP4956207B2 (en) 2007-01-25 2007-01-25 Rear shape classification judgment device

Country Status (1)

Country Link
JP (1) JP4956207B2 (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2016123586A (en) * 2014-12-26 2016-07-11 オムロン株式会社 Apparatus and method for acquiring body information
US11771958B2 (en) 2017-07-07 2023-10-03 Rika TAKAGI Instructing process management system for treatment and/or exercise, and program, computer apparatus and method for managing instructing process for treatment and/or exercise
JP7004218B2 (en) * 2018-05-14 2022-01-21 オムロン株式会社 Motion analysis device, motion analysis method, motion analysis program and motion analysis system
JP7428874B2 (en) * 2019-11-25 2024-02-07 ミツミ電機株式会社 Computing device, processor implementation method, and body type determination system for determining body type

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3829620B2 (en) * 2000-12-20 2006-10-04 松下電工株式会社 Cushion state diagnostic apparatus for cushion-divided bedding and diagnostic method

Also Published As

Publication number Publication date
JP2008178605A (en) 2008-08-07

Similar Documents

Publication Publication Date Title
Herzlinger et al. A new method for 3D geometric morphometric shape analysis: The case study of handaxe knapping skill
CN115082467B (en) Building material welding surface defect detection method based on computer vision
JP6740033B2 (en) Information processing device, measurement system, information processing method, and program
US20040109608A1 (en) Systems and methods for analyzing two-dimensional images
JP4956207B2 (en) Rear shape classification judgment device
KR20020091801A (en) A rules-based occupant classification system for airbag deployment
CN107610110B (en) Global and local feature combined cross-scale image quality evaluation method
JP5395470B2 (en) Shape recognition device
JP2009186338A (en) Flaw detector, flaw detection method and computer program
WO2019187341A1 (en) Index computation device, prediction system, progress prediction evaluation method, and program
EP3047455B1 (en) Method and system for spine position detection
KR20200022564A (en) Tooth segmentation system and method
CN115393351B (en) Method and device for judging cornea immune state based on Langerhans cells
CN113284090A (en) Scoliosis detection method and medical platform
Baek et al. Statistical foot-shape analysis for mass-customisation of footwear
JP2012132754A (en) Texture evaluation device, texture evaluation method
JP2017156170A (en) Object surface correction method and working method of workpiece
CN114419676A (en) Sitting posture analysis method and device based on artificial intelligence, computer equipment and medium
US20190117148A1 (en) Scoliosis diagnosis assistance device, scoliosis diagnosis assistance method, and program
US20210401361A1 (en) Method and device for correcting posture
KR102043092B1 (en) The method and apparatus for determining metamorphopsia based on user interaction
Lee et al. Anlysis methods of the variation of facial size and shape based on 3D face scan images
JP4971811B2 (en) Function database generation method and function database generation device
CN114414580B (en) Method for identifying and deducting impurities on scrap steel
JP4604762B2 (en) Method for comparing and evaluating feature diagrams and creating simulation model

Legal Events

Date Code Title Description
A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20090924

RD04 Notification of resignation of power of attorney

Free format text: JAPANESE INTERMEDIATE CODE: A7424

Effective date: 20100907

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20111130

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20111206

A711 Notification of change in applicant

Free format text: JAPANESE INTERMEDIATE CODE: A712

Effective date: 20120112

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20120206

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: 20120221

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: 20120316

R150 Certificate of patent or registration of utility model

Ref document number: 4956207

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150

Free format text: JAPANESE INTERMEDIATE CODE: R150

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

Free format text: PAYMENT UNTIL: 20150323

Year of fee payment: 3

LAPS Cancellation because of no payment of annual fees