JPH067388B2 - Human phase data measuring device - Google Patents

Human phase data measuring device

Info

Publication number
JPH067388B2
JPH067388B2 JP57121749A JP12174982A JPH067388B2 JP H067388 B2 JPH067388 B2 JP H067388B2 JP 57121749 A JP57121749 A JP 57121749A JP 12174982 A JP12174982 A JP 12174982A JP H067388 B2 JPH067388 B2 JP H067388B2
Authority
JP
Japan
Prior art keywords
contour
face
signal
image signal
coordinate system
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 - Lifetime
Application number
JP57121749A
Other languages
Japanese (ja)
Other versions
JPS5911471A (en
Inventor
弦 柳沢
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.)
Sony Corp
Original Assignee
Sony Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Sony Corp filed Critical Sony Corp
Priority to JP57121749A priority Critical patent/JPH067388B2/en
Publication of JPS5911471A publication Critical patent/JPS5911471A/en
Publication of JPH067388B2 publication Critical patent/JPH067388B2/en
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G07CHECKING-DEVICES
    • G07CTIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C9/00Individual registration on entry or exit
    • G07C9/20Individual registration on entry or exit involving the use of a pass
    • G07C9/22Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder
    • G07C9/25Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder using biometric data, e.g. fingerprints, iris scans or voice recognition
    • G07C9/253Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder using biometric data, e.g. fingerprints, iris scans or voice recognition visually
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168Feature extraction; Face representation
    • GPHYSICS
    • G07CHECKING-DEVICES
    • G07CTIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C9/00Individual registration on entry or exit
    • G07C9/20Individual registration on entry or exit involving the use of a pass
    • G07C9/22Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder
    • G07C9/25Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder using biometric data, e.g. fingerprints, iris scans or voice recognition

Landscapes

  • Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Collating Specific Patterns (AREA)
  • Image Analysis (AREA)

Description

【発明の詳細な説明】 本発明は人相データ測定装置に関し、例えば2つの人相
像を比較して同一人物か否かを判定する場合に適用でき
るものである。
The present invention relates to a human phase data measuring device, and can be applied to the case of comparing two human phase images to determine whether they are the same person or not.

例えば身分証明書等の証明書に添附された写真に写って
いる人物の人相と証明書を持参している人物の人相とが
同一か否かを判断する場合、従来人手による判断に任せ
られていた。因みに人相から定量的なデータを得ること
は困難であるので、従来は人相が同一か否かの判断がで
きるような専門的訓練を受けた監定人の総合判断に頼る
のが現実的な解決手法であると考えられていたからであ
る。
For example, when determining whether the person's appearance in the photograph attached to a certificate such as an identification card is the same as the person's appearance in the photograph, leave it to the conventional manual judgment. It was being done. By the way, it is difficult to obtain quantitative data from the human face, so it is practical to rely on the comprehensive judgment of the auditors who have received specialized training to judge whether the human face is the same. It was considered to be a solution method.

人相の同一性を判断する際に障害になる条件としては次
の事項が考えられる。
The following items can be considered as the obstacles when judging the identity of human appearance.

第1に、顔を観察する向き(左右方向、上下方向の角度
の程度)、装身具の有無、調髪状態、ひげの有無、化粧
の有無などのように対象となる人物の素顔に対して外部
から加えられた外観的要因が相違すると、全体として把
握される人相は相違し易い。
First, from the outside with respect to the true face of the target person, such as the direction in which the face is observed (horizontal direction, degree of vertical angle), the presence or absence of jewelry, the condition of hair, the presence or absence of beard, the presence or absence of makeup, etc. If the added appearance factors are different, the personalities perceived as a whole are likely to be different.

また第2に喜怒哀楽の差異、健康状態の変化、年令差な
どのように対象となる人物の内面から生じた原因(いわ
ば内面的要因)によって外観上の差異が生ずると、人相
にかなりの影響が出る。
Secondly, if there is a difference in appearance due to internal causes (so-called internal factors) of the target person, such as differences in emotions, changes in health status, age differences, etc. It has a considerable impact.

さらに第3に顔に外傷がついたり、整形手術を施した場
合のように、対象となる人物の素顔に永久的変形を加え
たような場合(いわば永久的変形要因)には、人相上に
差異が生ずるのを避けられない。
Thirdly, when the face of the target person is permanently deformed (so-called permanent deformation factor), such as when the face is traumatized or plastic surgery is performed, the human appearance It is unavoidable that there will be a difference.

これらの条件を検討するに、対象となる人物の素顔は顔
面骨格や顔面筋肉に基づいて個人的特徴として決まって
いると考えられるので、顔の外観をなす眼、口、鼻、眉
等の構成部分の形状ないし位置の特徴を直接把握し易い
ような電気的データを得るようにすると共に、人相の同
一性を判断する際の障害となる要素をノイズとして除去
するようにすれば、2つの人相像の比較や、同一性の判
断(同一であるか否かを判断すること)を電子的データ
処理技術を用いて実現できると考えられる。
Considering these conditions, it is considered that the true face of the target person is determined as a personal feature based on the facial skeleton and facial muscles, so the configuration of the eyes, mouth, nose, eyebrows, etc. that make up the facial appearance. It is possible to obtain electrical data that makes it easy to directly grasp the characteristics of the shape or position of a part, and to eliminate the factors that hinder the determination of the identity of human phases as noise. It is considered that the comparison of the human image and the determination of the identity (determining whether they are the same) can be realized by using the electronic data processing technique.

本発明は以上の点を考慮してなされたもので、顔の構成
部分の形状ないし位置を、両眼を結ぶ線(例えば両眼の
瞳孔の中心を結ぶ線)上の1/2の点を人相の計測基準点
とする極座標系で計測し、この計測データを直交座標系
に変換した後この変換データを相互に比較することによ
り人相の同一性を精度良く判断できるようにしようとす
るものである。
The present invention has been made in consideration of the above points, and the shape or position of a face constituent part is defined as a half point on a line connecting both eyes (for example, a line connecting the centers of pupils of both eyes). Measures in the polar coordinate system that is the measurement reference point of the human phase, transforms the measured data into the orthogonal coordinate system, and then compares the transformed data with each other, so that the identity of the human phase can be accurately determined. It is a thing.

以下図面について本発明の一実施例を詳述しよう。第1
図において、(1)は全体として人相認識装置を示し、人
相データ測定装置(2)を含んでなる。人相データ測定装
置(2)は対象となる人物の顔を撮影して電気的映像信号
S1を得るテレビジョンカメラ(3)と、このカメラ(3)か
ら得られる映像信号S1から輪郭強調画像信号S2を得
る輪郭強調処理回路(4)と、この輪郭強調画像信号S2
を極座標上に表出した画像と考えて計測データを得ると
共にこれを直交座標系のデータに変換して人相データ信
号S3として出力する極座標−直交座標変換装置(5)と
を有する。
An embodiment of the present invention will be described in detail with reference to the drawings. First
In the figure, (1) shows a human phase recognition device as a whole, and includes a human phase data measuring device (2). The human phase data measuring device (2) is a television camera (3) that captures an electric image signal S1 by photographing a face of a target person, and a contour enhanced image signal from the image signal S1 obtained from this camera (3). A contour emphasis processing circuit (4) for obtaining S2 and the contour emphasis image signal S2
Is regarded as an image expressed in polar coordinates, and measurement data is obtained, and this is converted into data in a rectangular coordinate system and is output as a human phase data signal S3.

輪郭強調処理回路(4)はカメラ(3)から得られる映像信号
S1を微分反転処理して2値化し、かくして第2図に示
す如く顔及びその構成部分の輪郭を黒レベルで表現した
輪郭強調画像に相当する画像処理信号でなる輪郭強調画
像信号S2を極座標−直交座標変換装置(5)に与える。
The contour enhancement processing circuit (4) performs differential inversion processing on the video signal S1 obtained from the camera (3) to binarize it, and thus contour enhancement of the face and its constituent parts represented by a black level as shown in FIG. An edge-enhanced image signal S2, which is an image processing signal corresponding to an image, is given to the polar coordinate-orthogonal coordinate converter (5).

ここで輪郭強調処理回路(4)は、人相の同一性を判断
する際に障害となる人物の素顔に対して外部から加えら
れた外観的要因(例えば眼鏡等の装身具の有無、調髪状
態、ひげの有無、化粧の有無)、又は人物の内面から生
じた原因(例えば喜怒哀楽、健康状態、年令差)、又は
人物の素顔に加えられた永久的変形(例えば外傷や整形
手術による人相上の差異)などの不要なデータを除去
し、同一性の判断に必要な人物の顔面骨格や顔面筋肉の
データ(例えば眼、鼻、口、眉、口から鼻にかけてのし
わの輪郭など)のみを抽出して輪郭強調画像信号S2と
して極座標−直交座標変換装置(5)に信号を与える。
Here, the contour emphasis processing circuit (4) externally applies external factors to the bare face of a person who becomes an obstacle in determining the identity of the human appearance (for example, the presence or absence of jewelry such as eyeglasses, a hair condition, With or without beard, with or without makeup), or causes caused by the inside of the person (for example, emotions, health, age difference), or permanent deformation (for example, due to trauma or plastic surgery) applied to the person's bare face. Data such as facial skeletons and facial muscles of a person necessary for determining the identity by removing unnecessary data (such as difference in appearance) (for example, eye, nose, mouth, eyebrow, wrinkle outline from mouth to nose) Only the signal is extracted and given as a contour-enhanced image signal S2 to the polar coordinate-rectangular coordinate transformation device (5).

極座標−直交座標変換装置(5)は先ず輪郭強調画像信号
S2を第2図に示す如く極座標上の画像として表出した
と等価な極座標信号に変換する。ここで極座標の原点P
(r=0,θ=0)は、輪郭強調画像信号S2の極座標
上の画像、すなわち輪郭線で表わされた顔及びその構成
部分のうち左及び右眼(11L)及び(11R)の例え
ば瞳孔の中心を結ぶ線分を2等分した点に設定される。
そして変換装置(5)はこの線分の延長線を基準として角
度θを第2図において反時計方向に0°〜360°まで
目盛り、各角度位置において原点を基準として輪郭線の
各部のr方向の長さを演算し、これを第3図に示す如く
x軸方向に角度θをとりかつy軸方向に長さrをとって
表わしたと等価な直交座標表示の画像信号に変換し、こ
の直交座標表示画像信号を人相データ測定装置(2)の人
相データ信号S3として送出する。
The polar coordinate-orthogonal coordinate converter (5) first converts the edge-enhanced image signal S2 into a polar coordinate signal equivalent to that represented as an image on polar coordinates as shown in FIG. Here, the origin P of polar coordinates
(R = 0, θ = 0) is, for example, the image on the polar coordinates of the contour-enhanced image signal S2, that is, the left and right eyes (11L) and (11R) of the face represented by the contour and its constituent parts, for example, It is set at a point that divides the line segment connecting the centers of the pupils into two equal parts.
Then, the conversion device (5) graduates the angle θ from 0 ° to 360 ° in the counterclockwise direction in FIG. 2 with reference to the extension line of this line segment, and the r direction of each part of the contour line with respect to the origin at each angular position. Is calculated and converted into an image signal in a Cartesian coordinate display which is equivalent to the angle θ in the x-axis direction and the length r in the y-axis direction as shown in FIG. The coordinate display image signal is sent as the human phase data signal S3 of the human phase data measuring device (2).

この人相データ測定装置(2)の人相データ信号S3はメ
モリ(11)に格納される。かくしてメモリ(11)に格納され
た人相データ信号S3は直交座標−極座標変換装置(12)
を通じて必要に応じて読出され、プロッタ(13)において
第2図について上述したと同様にして極座標表示された
輪郭強調画像が描き出され、この画像を見ながら人相の
同一性の判断を鑑定人の目で行い得るようになされてい
る。
The human phase data signal S3 of the human phase data measuring device (2) is stored in the memory (11). Thus, the human phase data signal S3 stored in the memory (11) is converted into the rectangular coordinate-polar coordinate converter (12).
Through the plotter (13), a contour-enhanced image displayed in polar coordinates is drawn out in the same manner as described above with reference to FIG. 2 on the plotter (13). It is designed to be done in.

これに対して例えば証明書の写真、人相写真、似顔絵等
のようなIDカードに記載された画像の人相を対象とす
る人物の人相と比較する場合は、IDカード(15)を読取
装置(16)に挿入することによって読取られたIDカード
人相データ信号S4を極座標−直交座標変換装置(5)か
ら得られた人相データ測定装置(2)の人相データ信号S
3と比較装置(17)において比較することにより互いに重
なり合う面積を検出し、その比較結果が鑑定信号S5と
して送出される。ここで人相データ信号S3には、顔の
外観をなす目、口、鼻、眉等の構成部分の形状及び位置
を表す上記輪郭位置データが含まれており、これが比較
装置17において鑑定基準となるIDカード人相データ
信号に含まれている鑑定基準データと比較されることに
より、鑑定結果を表す鑑定信号S5が得られることにな
る。
On the other hand, read the ID card (15) to compare the image of the person described in the ID card, such as a certificate photograph, portrait photograph, portrait, etc. A personal phase data signal S of the human phase data measuring device (2) obtained from the polar coordinate-orthogonal coordinate converting device (5) with the ID card human phase data signal S4 read by inserting it into the device (16).
3 is compared with the comparison device (17) to detect the overlapping areas, and the comparison result is sent out as the appraisal signal S5. Here, the human phase data signal S3 includes the contour position data representing the shape and position of the constituent parts such as eyes, mouth, nose, and eyebrows that make up the appearance of the face, and this is the appraisal standard in the comparison device 17. By being compared with the appraisal reference data included in the ID card personal phase data signal, the appraisal signal S5 representing the appraisal result is obtained.

このようにすれば人相の同一性を鑑定人の判断を要する
ことなく判断できる。
In this way, the identity of the human appearance can be judged without the judgment of the appraiser.

ここで読取装置(16)としてはIDカード(15)から読取っ
た映像信号を輪郭強調処理して読取信号として送出する
構成のものを用いれば良い。これに代え、IDカード(1
5)に輪郭強調した人相像を記載しておき読取装置(16)に
おいては輪郭強調処理を行わないようにしても良い。
Here, as the reading device (16), it is possible to use one having a structure in which the video signal read from the ID card (15) is subjected to contour enhancement processing and sent as a read signal. Instead of this, ID card (1
It is also possible to describe the human phase image with edge enhancement in 5) and not perform the edge enhancement processing in the reading device (16).

以上の構成において、カメラ(3)によって撮影された対
象となる人物の顔の映像は、輪郭強調処理回路(4)にお
いて輪郭強調処理されて実質的に顔及びその構成部分の
輪郭線でなる画像(第2図)が得られ、続いて極座標−
直交座標変換装置(5)において座標変換されて極座標上
の緯線をx軸線に対応させかつ経線をy軸線に対応させ
てなる直交座標画像(第3図)が実質上得られる。
In the above configuration, the image of the face of the target person photographed by the camera (3) is subjected to contour enhancement processing in the contour enhancement processing circuit (4) and is substantially an image of the contours of the face and its constituent parts. (Fig. 2) is obtained, followed by polar coordinates-
A rectangular coordinate image (FIG. 3) is obtained in which the coordinates are converted in the rectangular coordinate conversion device (5) so that the latitude line on the polar coordinates corresponds to the x axis and the meridian corresponds to the y axis.

かくして得られた直交座標画像は、極座標の原点(r=
0,θ=0)を中心にしてその周囲のθ=0°〜360
°の範囲に亘って散在する顔の構成部分の輪郭をx軸方
向に展開させたと同様の画像になる。しかるにこの画像
は顔の構成部分をx軸方向に分散させてなり、従って各
構成部分の輪郭形状の把握が一段と容易になる。またこ
の画像における構成部分の位置は直接的には極座標画像
の原点から各構成部分の輪郭線までの距離を表わしてお
り、従って各構成部分の相対的位置関係をも表わしてい
る。
The Cartesian coordinate image thus obtained is the origin (r =
0, θ = 0) and θ = 0 ° to 360 around it
An image similar to that obtained by expanding the contours of the facial components scattered over the range of ° in the x-axis direction. However, in this image, the constituent parts of the face are dispersed in the x-axis direction, so that the contour shape of each constituent part can be more easily grasped. Further, the position of the constituent part in this image directly represents the distance from the origin of the polar coordinate image to the contour line of each constituent part, and therefore also the relative positional relationship of each constituent part.

そこで2つの直交座標画像を重ね合せるように比較して
各構成部分の位置及び輪郭形状がほぼ同一か否かを判定
し、ほぼ同一であれば同一人物の人相であると判断でき
る。
Therefore, it is determined whether or not the positions and contour shapes of the respective constituent parts are substantially the same by comparing the two orthogonal coordinate images so as to be superimposed, and if they are substantially the same, it can be determined that the person is the same person.

因みに統計上眼と眼の間隔は人種、性別等を越えて非常
に変動が少ないと言われており、この点について上述の
構成においては極座標の原点を両眼の中央位置に設定し
たことにより、対象となる人物の人種、判別等の人相上
の要素の影響を実質上無視でき、また撮影された顔の向
きの影響もほとんど無視できる。実験によれば、両眼の
瞳孔間の間隔、換言すれば瞳孔の中心間の間隔はほぼ6
3〔mm〕±数〔mm〕であり、また当該原点は顔の中心位
置にあると言って良いので、顔の向きが変っても顔の構
成部分の原点に対する位置はほとんど変化せず、また構
成部分の輪郭形状も極端な変化は見られない。
By the way, it is said that the distance between eyes is statistically small across races, genders, etc. in statistical terms, and regarding this point, by setting the origin of polar coordinates to the center position of both eyes in the above configuration. , The influence of human factors such as race and discrimination of the target person can be virtually ignored, and the influence of the orientation of the face taken can be almost ignored. According to the experiment, the distance between the pupils of both eyes, in other words, the distance between the centers of the pupils is about 6
It is 3 [mm] ± several [mm], and it can be said that the origin is at the center position of the face, so even if the orientation of the face changes, the position of the face component with respect to the origin hardly changes, and The contour shape of the components does not show any extreme change.

実験によれば、第1図の構成において人相データ測定装
置(2)から得られる正面から撮影して得た人相データ信
号S3(第3図)をIDカード(15)の画像として第4図
に示す如く僅かに横向きの似顔絵を用いた場合の読取装
置(16)の出力(第5図)と比較した場合、両者間には実
質上同一と判断できる程度の類似性が得られた。因みに
2つの直交座標画像(第3図及び第5図)の各構成部分
の輪郭図形の大きさ及び曲率の正、負や、各構成部分の
輪郭図形の相互位置関係などはたとえ顔の向きや、大小
関係に差があっても個人的特徴を良く表わしており、従
ってこの特徴を数値データとして評定することができ
る。
According to the experiment, the human phase data signal S3 (FIG. 3) obtained by photographing from the front of the human phase data measuring device (2) in the configuration of FIG. As shown in the figure, when compared with the output (FIG. 5) of the reading device (16) in the case where a slightly lateral portrait was used, similarities were obtained between the two so that they could be judged to be substantially the same. By the way, the size and curvature of the contour figure of each constituent part of the two orthogonal coordinate images (Figs. 3 and 5) are positive and negative, and the mutual positional relationship of the contour figures of each constituent part is different even if the face orientation and , The personal characteristics are well represented even if there is a difference in magnitude relationship, and therefore, this characteristic can be evaluated as numerical data.

この点について第5図を観ると、左眼及び左眉に相当す
る部分の輪郭図形(21)及び(22)は第3図の人相データ信
号S3の対応する輪郭図形(24)及び(25)と重なり合う面
積が大きいので、酷似していると言い得、また右眼及び
右眉に相当する部分の輪郭図形(28)及び(29)は第3図の
人相データ信号S3の対応する輪郭図形(26)及び(27)と
重なり合う面積が大きいので、酷似していると言い得、
さらに口、鼻及び口から鼻にかけてしわの輪郭図形(3
0),(31)及び(32)は第3図の人相データ信号S3の対応
する図形(33),(34)及び(35)と重なり合う面積が大きい
ので、酷似していると言い得る。従って比較的良く似て
いると認められる似顔絵に描かれた顔は対象となる人物
の素顔の個人的特徴をうまくとらえており、換言すれば
冒頭において述べたように素顔に対して外部から加えら
れた外観的要因が相違していたり、内面から生じた内面
的要因に基づいて外観に差異が生じたり、素顔に永久的
変形が加えられたために外観に差異が生じたりしたとし
ても、似顔絵のように似ていると認められている程度に
素顔の個人的特徴が共通していれば、これが直交座標画
像上に各構成部分の輪郭形状及びその位置が酷似した分
散形態として生ずることにより、互いに重なり合う面積
が大きくなる。従って互いに重なり合う面積が大きいか
否かを判定することにより同一性を容易に把握できるこ
とになる。
In view of this point in FIG. 5, the contour figures (21) and (22) of the portions corresponding to the left eye and the left eyebrow are the corresponding contour figures (24) and (25) of the human phase data signal S3 in FIG. It can be said that they are very similar to each other because the overlapping area with) is large, and the contour figures (28) and (29) of the portions corresponding to the right eye and the right eyebrow are the corresponding contours of the human phase data signal S3 of FIG. It can be said that they are very similar because the area that overlaps with the figures (26) and (27) is large,
In addition, the outline figure of wrinkles from the mouth, nose and mouth to nose (3
It can be said that 0), (31) and (32) are very similar to each other because they have a large overlapping area with the corresponding figures (33), (34) and (35) of the human phase data signal S3 in FIG. Therefore, a face drawn in a caricature that is recognized as relatively similar captures well the personal characteristics of the target person's real face, in other words, it is added from the outside to the real face as described at the beginning. Even if the appearance factor is different, the appearance is different based on the inner factor generated from the inner surface, or the appearance is different due to permanent deformation of the bare face, it looks like a caricature. If the personal features of the bare face are common to the extent that they are recognized as being similar to, the contour shapes and the positions of the constituent parts on the Cartesian coordinate image occur as a distributed form that closely resembles each other, so that they overlap each other. The area becomes large. Therefore, the identity can be easily grasped by determining whether or not the overlapping areas are large.

なお上述においては、顔をカメラ(3)によって正面から
撮影した場合について述べたがこれに代え、少し横向き
にした顔を撮影すれば極座標−直交座標変換装置(5)の
人相データ信号S3として立体的凹凸情報を含んだ情報
を得ることができ、かくすることにより顔の構成部分の
立体的特徴をも同一性の判断情報として用い得、これに
よりさらに正確に人相の同一性を判断することができ
る。
In the above description, the case where the face is photographed from the front by the camera (3) has been described, but instead of this, if the face is made slightly sideways, the human-phase data signal S3 of the polar coordinate-orthogonal coordinate converter (5) is obtained. Information including three-dimensional concavo-convex information can be obtained, and by doing so, the three-dimensional characteristics of the facial components can also be used as the determination information of identity, thereby more accurately determining the identity of human appearance. be able to.

以上のように本発明に依れば、両眼を結ぶ線分のほぼ1/
2の位置を極座標の原点に設定して極座標データ信号を
得、これを直交座標データ信号に変換して人相データ信
号S3を得るようにしたことにより、対象とする人物の
素顔の個人的特徴を数値データ処理ができる形式の電気
的信号として得ることができる。従って人相の同一性の
判断を人手を介さずに容易になし得る。
As described above, according to the present invention, the line segment connecting both eyes is approximately 1 /
By setting the position of 2 as the origin of polar coordinates and obtaining polar coordinate data signals, and converting these into orthogonal coordinate data signals to obtain the human phase data signal S3, the personal characteristics of the bare face of the target person are obtained. Can be obtained as an electrical signal in a format that can be processed by numerical data. Therefore, it is possible to easily judge the identity of human appearance without human intervention.

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

第1図は本発明に依る人相データ測定装置を用いた人相
認識装置を示すブロック図、第2図は輪郭強調画像信号
の説明に供する略線図、第3図はその直交座標表示画像
信号の説明に供する略線図、第4図はIDカードから入
力された人相データ信号の説明に供する略線図、第5図
はその直交座標表示画像信号の説明に供する略線図であ
る。 (1)…人相認識装置、(2)…人相データ測定装置、 (3)…テレビジョンカメラ、(4)…輪郭強調処理回路、 (5)…極座標−直交座標変換装置、(11)…メモリ、 (12)…直交座標−極座標変換装置、(13)…プロッ タ、(15)…IDカード、(16)…読取装置、(17)…比較装
置。
FIG. 1 is a block diagram showing a human phase recognition device using a human phase data measuring device according to the present invention, FIG. 2 is a schematic diagram used for explaining an edge-enhanced image signal, and FIG. 3 is its orthogonal coordinate display image. FIG. 4 is a schematic diagram for explaining a signal, FIG. 4 is a schematic diagram for explaining a human phase data signal input from an ID card, and FIG. 5 is a schematic diagram for explaining a Cartesian coordinate display image signal. . (1) ... Human phase recognition device, (2) ... Human phase data measuring device, (3) ... Television camera, (4) ... Edge enhancement processing circuit, (5) ... Polar coordinate-orthogonal coordinate converter, (11) ... memory, (12) ... Cartesian-polar coordinate converter, (13) ... plotter, (15) ... ID card, (16) ... reader, (17) ... comparison device.

Claims (1)

【特許請求の範囲】[Claims] 【請求項1】対象とする人物の顔を撮影して画像信号を
得るテレビジョンカメラと、 この画像信号を輪郭強調処理して輪郭強調画像信号に得
る輪郭強調処理回路と、 上記輪郭強調画像信号を両眼を結ぶ線分のほぼ1/2の
位置を極座標系の原点に設定する手段と、 極座標系で入力された画像を該極座標上の緯線と経緯と
が直交座標系のX軸とY軸とに対応する座標系に形式変
換された輪郭位置データ信号を出力する座標形式変換手
段と、 顔の外観をなす目、口、鼻、眉等の構成部分の形状及び
位置を表す上記輪郭位置データ信号を鑑定基準となる鑑
定基準データ信号と比較して鑑定結果信号を得る比較手
段と を具えることを特徴とする人相データ測定装置。
1. A television camera for photographing a face of a target person to obtain an image signal, a contour enhancement processing circuit for subjecting the image signal to a contour enhancement image signal to obtain a contour enhancement image signal, and the contour enhancement image signal. And a means for setting approximately half the position of the line segment connecting the two eyes to the origin of the polar coordinate system, and the image input in the polar coordinate system, in which the latitude and longitude on the polar coordinate system are the X-axis and the Y-axis of the orthogonal coordinate system. Coordinate format conversion means for outputting a contour position data signal whose format is converted into a coordinate system corresponding to the axis, and the contour position representing the shape and position of the eye, mouth, nose, eyebrow and other components forming the appearance of the face A human phase data measuring device, comprising: a comparing unit that obtains an appraisal result signal by comparing a data signal with an appraisal standard data signal serving as an appraisal standard.
JP57121749A 1982-07-13 1982-07-13 Human phase data measuring device Expired - Lifetime JPH067388B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP57121749A JPH067388B2 (en) 1982-07-13 1982-07-13 Human phase data measuring device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP57121749A JPH067388B2 (en) 1982-07-13 1982-07-13 Human phase data measuring device

Publications (2)

Publication Number Publication Date
JPS5911471A JPS5911471A (en) 1984-01-21
JPH067388B2 true JPH067388B2 (en) 1994-01-26

Family

ID=14818928

Family Applications (1)

Application Number Title Priority Date Filing Date
JP57121749A Expired - Lifetime JPH067388B2 (en) 1982-07-13 1982-07-13 Human phase data measuring device

Country Status (1)

Country Link
JP (1) JPH067388B2 (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS6290779A (en) * 1985-10-16 1987-04-25 Nippon Denshi Kiki Kk Individual identifying system
JPS63126076A (en) * 1986-11-14 1988-05-30 Nippon Denshi Kiki Kk Setting system for profile reading range of face collating device
GB9201006D0 (en) * 1992-01-17 1992-03-11 Philip Electronic And Associat Classifying faces
JP3264460B2 (en) * 1993-04-26 2002-03-11 富士写真フイルム株式会社 Image identification method

Also Published As

Publication number Publication date
JPS5911471A (en) 1984-01-21

Similar Documents

Publication Publication Date Title
CN105574518B (en) Method and device for detecting living human face
Kale et al. Towards a view invariant gait recognition algorithm
US9881204B2 (en) Method for determining authenticity of a three-dimensional object
US8406479B2 (en) Visual axis direction detection device and visual line direction detection method
EP1260935B1 (en) Face detection device, face pose detection device, partial image extraction device, and methods for said devices
CN110675487B (en) Three-dimensional face modeling and recognition method and device based on multi-angle two-dimensional face
TWI383325B (en) Face expressions identification
CN105740781B (en) Three-dimensional human face living body detection method and device
CN105740778B (en) Improved three-dimensional human face in-vivo detection method and device
Sohail et al. Detection of facial feature points using anthropometric face model
WO2012101962A1 (en) State-of-posture estimation device and state-of-posture estimation method
WO1999006940A9 (en) A method and apparatus for personnel detection and tracking
JP6191943B2 (en) Gaze direction estimation device, gaze direction estimation device, and gaze direction estimation program
CN108416291A (en) Face datection recognition methods, device and system
Jana et al. Age group estimation using face features
CN111854620A (en) Monocular camera-based actual pupil distance measuring method, device and equipment
CN112633217A (en) Human face recognition living body detection method for calculating sight direction based on three-dimensional eyeball model
JP3970573B2 (en) Facial image recognition apparatus and method
JP3577908B2 (en) Face image recognition system
KR101775874B1 (en) Integrated Control method for Vehicle Drive using Depth Information based Face Recognition
JPH067388B2 (en) Human phase data measuring device
JP2000268161A (en) Real time expression detector
Taertulakarn et al. The preliminary investigation of ear recognition using hybrid technique
Lin et al. A novel framework for automatic 3D face recognition using quality assessment
KR20050039765A (en) Method for extracting face outline and face feature points