JPS61276077A - Positioning system for picture - Google Patents
Positioning system for pictureInfo
- Publication number
- JPS61276077A JPS61276077A JP60118040A JP11804085A JPS61276077A JP S61276077 A JPS61276077 A JP S61276077A JP 60118040 A JP60118040 A JP 60118040A JP 11804085 A JP11804085 A JP 11804085A JP S61276077 A JPS61276077 A JP S61276077A
- Authority
- JP
- Japan
- Prior art keywords
- gravity
- center
- picture
- image
- data
- 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.)
- Pending
Links
- 230000005484 gravity Effects 0.000 claims abstract description 31
- 238000000034 method Methods 0.000 claims abstract description 9
- 238000013519 translation Methods 0.000 claims description 3
- 230000002093 peripheral effect Effects 0.000 claims 1
- 238000012545 processing Methods 0.000 abstract description 5
- 230000000052 comparative effect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 11
- 238000012795 verification Methods 0.000 description 7
- 238000000605 extraction Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 239000000470 constituent Substances 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 1
Landscapes
- Image Input (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
Description
【発明の詳細な説明】
〔概要〕
画像の位置合わせ方式であって登録画像と入力画像との
重心位置の比較を入力画像の重心を回転を生じさせつつ
行なって回転角度差と平行移動量を求めて位置合わせを
行なう。[Detailed Description of the Invention] [Summary] This is an image alignment method in which the center of gravity of the registered image and the input image are compared while rotating the center of gravity of the input image, and the rotation angle difference and the amount of parallel movement are calculated. Find and align.
本発明は画像処理に際して、画像の位置合わせを行なう
ための画像の位置合わせ方式に関する。The present invention relates to an image alignment method for aligning images during image processing.
印鑑照合装置等のように予め登録された画像と入力画像
との照合を行なう装置にあっては、一方の画像を回転さ
せると共に、回転後の画像における所定の位置関係にあ
る点の濃度を調べることで照合が行なわれる。このよう
な装置にあっては、高速な処理と簡易な照合方式の提供
が要望されている。In a device such as a seal matching device that matches a pre-registered image with an input image, one of the images is rotated and the density of points in a predetermined positional relationship in the rotated image is checked. This is how verification is performed. There is a demand for such devices to provide high-speed processing and a simple verification method.
登録画像と入力画像との照合のために一方の画像を実際
に回転することが行なわれている。回転に際しては各画
素の濃度勾配の角度ヒストグラムより２つの画像間の回
転角度差が求められる。また、回転した画像を夫々直交
する方向に投影することで２つの画像間の平行移動量を
求めている。In order to match a registered image and an input image, one of the images is actually rotated. During rotation, the rotation angle difference between the two images is determined from the angle histogram of the density gradient of each pixel. Furthermore, the amount of parallel movement between the two images is determined by projecting the rotated images in directions perpendicular to each other.
しかし、画像に濃淡のむらが存在する場合、角度ヒスト
グラムで回転角度差を決定するのは困難が多い。そこで
角度ヒストグラムでは回−角度差の候補を数個選出する
にとどめ、候補角に従って画像を回転し、より精度の良
い投影を用いて候補を検証し、回転角度差を決定してい
る。However, when there is unevenness in shading in an image, it is often difficult to determine the rotation angle difference using an angle histogram. Therefore, in the angle histogram, only a few candidates for the angle-angle difference are selected, the image is rotated according to the candidate angle, the candidates are verified using a more accurate projection, and the rotation angle difference is determined.
この従来方式では回転角度差候補の検証及び平行移動量
の算出には、候補の数だけ画像の回転と投影の比較を必
要とし、処理時間が長くなると共にソフトウェア及びハ
ードウェアの両方について規模が大きくなるという欠点
を有する。In this conventional method, in order to verify the rotation angle difference candidates and calculate the translation amount, it is necessary to compare the rotation and projection of images for the number of candidates, which increases the processing time and increases the scale of both software and hardware. It has the disadvantage of becoming.
本発明はこのような点に鑑みて創作されたもので、装置
の規模を拡大することなく高速処理が可能な画像の位置
合わせ方式を提供することを目的とする。The present invention was created in view of these points, and it is an object of the present invention to provide an image alignment method that enables high-speed processing without increasing the scale of the apparatus.
第１図は本発明の画像の位置合わせ方式の原理ブロック
図である。FIG. 1 is a block diagram of the principle of the image alignment method of the present invention.
第１図において、１０は重心算出手段で、これは濃度勾
配方向毎にその構成画素の重心を求めるものである。１
１は求められた入力画像の重心を回転させる回転手段で
ある。１２は回転された入力画像の重心と登録画像の重
心との比較からこれら画像間の回転角度差及び平行移動
量を求める位置合わせ量算出手段である。１３は求めら
れた回転角度差及び平行移動量を基にして入力画像の位
置合わせを行なう位置合わせ手段である。In FIG. 1, reference numeral 10 denotes a center of gravity calculating means, which calculates the center of gravity of the constituent pixels for each density gradient direction. 1
Reference numeral 1 denotes a rotation means for rotating the center of gravity of the obtained input image. Reference numeral 12 denotes a positioning amount calculation means for calculating the rotation angle difference and parallel movement amount between the images by comparing the center of gravity of the rotated input image and the center of gravity of the registered image. Reference numeral 13 denotes a positioning means for positioning the input image based on the determined rotational angle difference and the amount of parallel movement.
入力画像が重心算出手段１０へ入力され、そこにおいて
空間微分法により画像周辺画素の濃度勾配が求められ、
その濃度勾配方向毎にその構成画素の重心が求められる
。その重心データが回転手段１１に入力され、入力画像
の重心が回転されて位置合わせ量算出手段１２へ供給さ
れ、そこにおいて登録画像重心格納手段１４からの登録
画像の重心との比較が行なわれる。最適な比較が得られ
るまで回転手段に制御を戻して比較を続ける。その比較
から求められた回転角度差及び平行移動量が位置合わせ
手段１３へ与えられて位置合わせされた画像が出力され
る。The input image is input to the center of gravity calculation means 10, where the density gradient of pixels around the image is determined by the spatial differential method,
The center of gravity of the constituent pixels is determined for each concentration gradient direction. The center of gravity data is input to the rotation means 11, the center of gravity of the input image is rotated and supplied to the alignment amount calculation means 12, where it is compared with the center of gravity of the registered image from the registered image center of gravity storage means 14. Control is returned to the rotating means and comparisons are continued until an optimal comparison is obtained. The rotational angle difference and the amount of parallel movement determined from the comparison are applied to the alignment means 13, and a aligned image is output.
第４図は本発明の実施例であって、入力画像メモリ１に
格納された画像データ（第３図（ｂ））が空間微分回路
２により微分されて各画素における濃度勾配及び方向が
求められる。次に第３図（ｄ）に示すように方向別に分
類して各々重心座標が求められる。この重心の抽出は重
心抽出回路３にて行なわれる。このようにして求められ
た重心の座標データは入力画像重心格納レジスタ４に格
納される。FIG. 4 shows an embodiment of the present invention, in which the image data (FIG. 3(b)) stored in the input image memory 1 is differentiated by the spatial differentiation circuit 2 to determine the density gradient and direction at each pixel. . Next, as shown in FIG. 3(d), the barycenter coordinates are determined for each direction. This extraction of the center of gravity is performed by the center of gravity extraction circuit 3. The coordinate data of the center of gravity thus obtained is stored in the input image center of gravity storage register 4.
次いで重心回転回路６で第３図（ｅ）に示すように格納
された画像が回転される。この回転と共に格納された座
標データと登録画像重心格納レジスタ５の内容とが重心
位置比較回路７にて比較される。Next, the stored image is rotated by the centroid rotation circuit 6 as shown in FIG. 3(e). The coordinate data stored along with this rotation and the contents of the registered image gravity center storage register 5 are compared in the gravity center position comparison circuit 7.
この結果、第３図（ｆ）で示すようにＸ及びｙ方向にｄ
ｘ、ｄｙで示す一定の距離を隔てた位置において、登録
画像と入力画像の各画素の値が一致する回転角度が求め
られる。即ち、登録画像と入力画像との角度差及び平行
移動量が重心点及びこの近傍の点を幾つか参照すること
で求められる。このようにして求めた回転角と平行移動
量のデータｇ。As a result, d in the X and y directions as shown in Figure 3(f).
A rotation angle at which the values of each pixel of the registered image and the input image match at a position separated by a certain distance indicated by x and dy is determined. That is, the angular difference and the amount of parallel movement between the registered image and the input image are determined by referring to the center of gravity and several points in the vicinity thereof. Data g of the rotation angle and the amount of parallel movement obtained in this way.
ｈを座標変換回路８に供給することで出力画像メモリ９
に例えば印鑑照合のための正しい角度及び位置情報を持
つ画像データが格納される。By supplying h to the coordinate conversion circuit 8, the output image memory 9
For example, image data having correct angle and position information for seal stamp verification is stored.
ここで第２図を参照すると、登録画像が（ａ）で示され
、また、登録画像（ａ）と角度θ及び（ｄｘ、ｄｙ）の
平行移動量を持つ照合のための入力画像（ｂ）が示され
る。これ等の画像において、照合側の任意の点Ｐ （ｘ
、ｙ）と、この点に対応する登録側の点Ｐ’（ｘ’、ｙ
”）との関係は、
で表される。従って、第３図（Ｃ）及び（ｄ）を参照す
ると、例えば−２０”の角度差θにおける登録側の重心
Ｇ” ９０と、照合側の重心Ｃｌｌ０とが対応するので
照合側の重心Ｇｉ （ｘ、ｙ） ・・・ （ｉ−１
，２，・・・、３６０）をα度回転させて登録側の重心
Ｇ′丙 （Ｘ’ 、 ｙ’ ）との差５ｉ（Ｓｘ、Ｓ
ｙ）を求めるとα＝θのときにＳ’１（Ｓｘ。Now, referring to FIG. 2, the registered image is shown as (a), and the input image (b) for matching has a parallel movement amount of angle θ and (dx, dy) with respect to the registered image (a). is shown. In these images, any point P (x
, y) and the registration side point P'(x', y
Therefore, referring to FIGS. 3(C) and (d), for example, at an angle difference θ of -20", the center of gravity on the registration side G"90 and the center of gravity on the verification side Since it corresponds to Cll0, the center of gravity on the verification side Gi (x, y) ... (i-1
, 2, ..., 360) by α degrees and the difference 5i (Sx, S
y), when α=θ, S'1(Sx.
Ｓｙ）はｉの値に関係なく一定な平行移動量（ｄｘ、ｄ
ｙ）を示す。この差Ｓｔ （Ｓｘ、Ｓｙ）の一般式は
以下のようになる。Sy) is a constant translation amount (dx, d
y). The general formula for this difference St (Sx, Sy) is as follows.
・・・ （ｉ−１，２，・・・、３６０）従って、α≠
θのときはα＝θ＋１８０°も含めて登録側画像の任意
の点と、これに対応する照合側画像の点の値とが一定の
関係にはならない。... (i-1, 2, ..., 360) Therefore, α≠
When θ, any point on the registration side image including α=θ+180° and the value of the corresponding point on the verification side image do not have a constant relationship.
このため、照合側画像を回転させ乍ら、幾つかの点の差
Ｓｉ （Ｓｘ、Ｓｙ）を調べることで回転角度差と平
行移動量とが求められる。For this reason, the rotation angle difference and the amount of parallel movement can be determined by examining the difference Si (Sx, Sy) between several points while rotating the comparison side image.
以上述べてきたように本発明によれば、照合のための位
置及び角度データが簡易な構成で高速に得られる。As described above, according to the present invention, position and angle data for verification can be obtained quickly with a simple configuration.
第１図は本発明の原理ブロック図、
第２図は登録画像と入力画像との角度位置を説明するた
めの説明図、
第３図（ａ）は登録画像の例を示す説明図、第３図山）
は入力画像の例を示す説明図、第３図（ｃ） 、 （ｄ
）は重心の例を示す説明図、第３図（ｅ）は重心を回転
させた状態を示す図、第３図（ｆ）は正しく回転された
入力画像と登録画像との関係を示す説明図、
第３図（ｇ）は回転の途中における入力画像と登録画像
との関係を示す説明図、
第４図は本発明の実施例のブロック図である。
第４図において、
１は入力画像メモリ、
２は空間微分回路、
３は重心抽出回路、
４は入力画像重心格納レジスタ、
５は登録画像重心格納レジスタ、
６は重心回転回路、
７は重心位置比較回路、
８は座標変換回路、
９は出力画像メモリである。
不肩知月の原王！フ゛ロツタ図
第１図
第２図
（ａ） （ｂ）（ｆ）
（９）
ｌ！５Ｊ１象位」合わせど絖明するための置市３図
本発明の大加イダ１１を示す図
第４図FIG. 1 is a principle block diagram of the present invention. FIG. 2 is an explanatory diagram for explaining the angular position of a registered image and an input image. FIG. 3(a) is an explanatory diagram showing an example of a registered image. (Figure mountain)
are explanatory diagrams showing examples of input images, FIGS. 3(c) and (d)
) is an explanatory diagram showing an example of the center of gravity, FIG. 3(e) is an explanatory diagram showing a state in which the center of gravity has been rotated, and FIG. 3(f) is an explanatory diagram showing the relationship between a correctly rotated input image and a registered image. , FIG. 3(g) is an explanatory diagram showing the relationship between the input image and the registered image during rotation, and FIG. 4 is a block diagram of an embodiment of the present invention. In Fig. 4, 1 is an input image memory, 2 is a spatial differentiation circuit, 3 is a centroid extraction circuit, 4 is an input image centroid storage register, 5 is a registered image centroid storage register, 6 is a centroid rotation circuit, and 7 is a centroid position comparison 8 is a coordinate conversion circuit, and 9 is an output image memory. The original king of Fushizuki! Figure 1 Figure 2 (a) (b) (f)
(9) l! 5J1 zodiac position" 3 diagrams of Okiichi for illuminating the alignment Figure 4 Figure 4 showing the Okaida 11 of the present invention
Claims (1)
の位置合わせを行なう画像の位置合わせ方式において、 濃度勾配方向毎にその構成画素群の重心を求める重心算
出手段（１０）と、 求めた入力画像の重心を回転させる回転手段（１１）と
、 回転された入力画像の重心と登録画像の重心との比較か
らこれら画像間の回転角度差及び平行移動量を求める位
置合わせ量算出手段（１２、１４）と、 前記回転角度差及び平行移動量を基にして入力画像の位
置合わせを行なう位置合わせ手段（１３）とを備えて構
成したことを特徴とする画像の位置合わせ方式。[Claims] In an image alignment method that aligns an input image and a registered image by determining the density gradient of peripheral pixels of the image, the center of gravity calculation means ( 10), a rotation means (11) for rotating the center of gravity of the input image obtained, and a position for determining the rotation angle difference and the amount of parallel movement between these images by comparing the center of gravity of the rotated input image and the center of gravity of the registered image. An image position system characterized by comprising: alignment amount calculation means (12, 14); and alignment means (13) for aligning input images based on the rotation angle difference and the translation amount. Matching method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP60118040A JPS61276077A (en) | 1985-05-31 | 1985-05-31 | Positioning system for picture |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP60118040A JPS61276077A (en) | 1985-05-31 | 1985-05-31 | Positioning system for picture |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| JPS61276077A true JPS61276077A (en) | 1986-12-06 |
Family
ID=14726553
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP60118040A Pending JPS61276077A (en) | 1985-05-31 | 1985-05-31 | Positioning system for picture |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JPS61276077A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1999067943A1 (en) * | 1998-06-23 | 1999-12-29 | Sharp Kabushiki Kaisha | Image processor, image processing method, and medium on which image processing program is recorded |
-
1985
- 1985-05-31 JP JP60118040A patent/JPS61276077A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1999067943A1 (en) * | 1998-06-23 | 1999-12-29 | Sharp Kabushiki Kaisha | Image processor, image processing method, and medium on which image processing program is recorded |
| US7006708B1 (en) | 1998-06-23 | 2006-02-28 | Sharp Kabushiki Kaisha | Image processor, image processing method, and medium on which image processing program is recorded |
| US7158688B2 (en) | 1998-06-23 | 2007-01-02 | Sharp Kabushiki Kaisha | Image processing apparatus, image processing method, and medium on which image processing program is recorded |
| US7298927B2 (en) | 1998-06-23 | 2007-11-20 | Sharp Kabushiki Kaisha | Image processing apparatus, image processing method, and medium on which image processing program is recorded |
| US7327879B2 (en) | 1998-06-23 | 2008-02-05 | Sharp Kabushiki Kaisha | Image processing apparatus, image processing method, and medium on which image processing program is recorded |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Baboud et al. | Automatic photo-to-terrain alignment for the annotation of mountain pictures | |
| JP2810320B2 (en) | Sphere rotation measuring device and measuring method | |
| CN108717709A (en) | Image processing system and image processing method | |
| CN110388919A (en) | Threedimensional model localization method in augmented reality based on characteristic pattern and inertia measurement | |
| JP2009216503A (en) | Three-dimensional position and attitude measuring method and system | |
| Xu et al. | Cammap: Extrinsic calibration of non-overlapping cameras based on slam map alignment | |
| JP2559939B2 (en) | Three-dimensional information input device | |
| JPH07103715A (en) | Method and apparatus for recognizing three-dimensional position and attitude based on visual sense | |
| JPS61276077A (en) | Positioning system for picture | |
| JP3452188B2 (en) | Tracking method of feature points in 2D video | |
| Lima et al. | Texture-less planar object detection and pose estimation using depth-assisted rectification of contours | |
| JPH1030917A (en) | Object recognition method and device therefor, and recording medium | |
| CN110544203A (en) | Motion least square method and line constraint combined parallax image splicing method | |
| JPS6228882A (en) | Method for correcting angular deviation of image | |
| JPH10332333A (en) | Method for detecting angle of rotation and position of object | |
| CN113096163B (en) | Satellite-borne SAR image high-precision matching method without priori lifting rail information | |
| JPH087102A (en) | Correspondent point extracting device | |
| JP2600027B2 (en) | Image alignment method and apparatus | |
| JPS62172482A (en) | Positioning system for picture | |
| JPS61134886A (en) | Detector of rotary angle difference between pictures | |
| CN117253022A (en) | Object identification method, device and inspection equipment | |
| JPS59200379A (en) | Picture collating device | |
| JPS62127984A (en) | Rotation-deviated character recognizing device | |
| Lv et al. | Stitching High Resolution Notebook Keyboard Surface Based on Halcon Calibration | |
| CN111968035A (en) | Image relative rotation angle calculation method based on loss function |