JP2957897B2 - Linear component extraction method - Google Patents
Linear component extraction methodInfo
- Publication number
- JP2957897B2 JP2957897B2 JP20251394A JP20251394A JP2957897B2 JP 2957897 B2 JP2957897 B2 JP 2957897B2 JP 20251394 A JP20251394 A JP 20251394A JP 20251394 A JP20251394 A JP 20251394A JP 2957897 B2 JP2957897 B2 JP 2957897B2
- Authority
- JP
- Japan
- Prior art keywords
- straight line
- extracted
- point
- image information
- circumference
- 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
Links
Landscapes
- Image Analysis (AREA)
Description
【０００１】[0001]
【産業上の利用分野】本発明は、テレビカメラ等の画像
入力手段を利用して画像化された対象中、特に直線の抽
出に用いる直線成分抽出方法に関する。BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method for extracting a straight line component used for extracting a straight line from objects imaged by using an image input means such as a television camera.
【０００２】[0002]
【従来の技術】従来、直線成分の抽出方法としては、特
開昭６２−２０２２９０号に見られるように、直線上の
各点を抽出して最小２乗法により直線を近似し、直線を
求める方法があった。2. Description of the Related Art Conventionally, as a method of extracting a straight line component, a method of extracting each point on a straight line, approximating the straight line by a least square method, and obtaining a straight line as disclosed in Japanese Patent Application Laid-Open No. 62-202290. was there.
【０００３】[0003]
【発明が解決しようとする課題】上記の従来例の方法に
よって直線を求める場合、各特徴点の抽出精度が、抽出
対象である直線の抽出精度に大きく影響を及ぼし、局所
的な特徴点の抽出ミスなどにより正しく直線が抽出され
ない場合が発生するという問題があった。本発明は上述
の問題点に鑑みて為されたもので、その目的とするとこ
ろは円周上の２点を結ぶ直線上の画素の濃度の平均値を
求めるという処理だけで抽出対象である直線を高速に且
つ安定に検出できる直線成分抽出方法を提供するにあ
る。When a straight line is obtained by the above-mentioned conventional method, the extraction accuracy of each feature point greatly affects the extraction accuracy of a straight line to be extracted, and local feature points are extracted. There has been a problem that a straight line may not be correctly extracted due to a mistake or the like. SUMMARY OF THE INVENTION The present invention has been made in view of the above-described problems, and has as its object to extract a straight line to be extracted only by calculating the average value of the density of pixels on a straight line connecting two points on the circumference. It is an object of the present invention to provide a straight-line component extraction method capable of quickly and stably detecting.
【０００４】[0004]
【課題を解決するための手段】上記目的を達成するため
に請求項１の発明では、画像入力手段により撮り込まれ
た画像情報の抽出対象を含む領域に円を設定する段階
と、前記円の円周上の画素の画素濃度のピーク点を求め
る段階と、ピーク点に対向する円周上の点の想定を行な
うとともにピーク点と想定した点とを結ぶ直線上の画素
の画素濃度の総和により得られる直線の画像情報値を、
円の円周上の所定範囲内でピーク点と対向する点を順次
想定しながら、求める段階と、求められた各直線の画像
情報値から抽出対象である直線を選択・抽出する段階と
からなることを特徴とする。In order to achieve the above object, according to the first aspect of the present invention, a step of setting a circle in an area including an extraction target of image information captured by image input means, Calculating the peak point of the pixel density of the pixel on the circumference, assuming a point on the circumference opposite to the peak point, and calculating the sum of the pixel density of the pixel on a straight line connecting the peak point and the assumed point. The image information value of the obtained straight line is
A step of determining a point opposite to the peak point within a predetermined range on the circumference of the circle sequentially, and a step of selecting and extracting a straight line to be extracted from the obtained image information value of each straight line. It is characterized by the following.
【０００５】請求項２の発明では、請求項１の発明にお
いて、設定する円を二つに分割して分割された各々の円
周上について直線抽出を行ない、求められた２つの直線
を平均化することによって抽出対象の直線を選択・抽出
することを特徴とする。請求項３の発明では、請求項
１、２の発明において、画像情報値のピーク値を抽出し
て抽出対象の直線を選択・抽出することを特徴とする。According to a second aspect of the present invention, in the first aspect of the present invention, a line to be set is divided into two, and straight lines are extracted on each of the divided circles, and the obtained two straight lines are averaged. By doing so, a straight line to be extracted is selected and extracted. According to a third aspect of the present invention, in the first and second aspects, a peak value of the image information value is extracted to select and extract a straight line to be extracted.
【０００６】請求項４の発明では、請求項１、２の発明
において、画像情報値の分布の重心を求めて抽出対象の
直線を選択・抽出することを特徴とする。請求項５の発
明では、請求項１、２の発明において、或る値以上を持
つ画像情報値の分布の存在領域の中心を求めて抽出対象
の直線を選択・抽出することを特徴とする。A fourth aspect of the present invention is characterized in that, in the first and second aspects of the present invention, a straight line to be extracted is selected and extracted by obtaining a center of gravity of a distribution of image information values. According to a fifth aspect of the present invention, in the first and second aspects of the present invention, a straight line to be extracted is selected and extracted by finding a center of an existing area of a distribution of image information values having a certain value or more.
【０００７】請求項６の発明では、請求項１の発明にお
いて、抽出対象の直線を選択・抽出した後、前記ピーク
点を中心として円周上の所定範囲内で想定した起点と、
前記ピーク点に対向する抽出された直線と前記円周上の
交点とを結ぶ各直線上の画素の画素濃度の総和により得
られる各直線の画像情報値を求め、求められた各直線の
画像情報値から抽出対象である直線を選択・抽出するこ
とを特徴とする。According to a sixth aspect of the present invention, in the first aspect of the present invention, after selecting and extracting a straight line to be extracted, a starting point assumed within a predetermined range on a circumference around the peak point;
The image information value of each straight line obtained by the sum of the pixel densities of the pixels on each straight line connecting the extracted straight line facing the peak point and the intersection on the circumference is obtained, and the obtained image information of each straight line is obtained. A straight line to be extracted is selected and extracted from the value.
【０００８】請求項７の発明では、請求項１〜６の発明
において、抽出対象の直線の選択・抽出を繰り返して行
なうことを特徴とする。請求項８の発明では、請求項
１、２の発明において、ピーク点を含む小領域を設定し
て該小領域内の空間微分処理を行なって直線成分の方向
を抽出し、この方向に基づいてピーク点に対向する円周
上の想定する点の範囲を設定することを特徴とする。According to a seventh aspect of the present invention, in the first to sixth aspects, selection and extraction of a straight line to be extracted are repeatedly performed. According to an eighth aspect of the present invention, in the first and second aspects of the present invention, a small area including a peak point is set, and a spatial differentiation process in the small area is performed to extract a direction of a linear component. It is characterized in that a range of assumed points on the circumference facing the peak point is set.
【０００９】請求項９の発明では、請求項１〜７の発明
において、設定する円を複数として各円において直線抽
出を行ない、抽出した各直線を平均化して得られた直線
を抽出対象とすることを特徴とする。According to a ninth aspect of the present invention, in the first to seventh aspects, a plurality of circles are set, a straight line is extracted from each circle, and a straight line obtained by averaging the extracted straight lines is set as an extraction target. It is characterized by the following.
【００１０】[0010]
【作用】請求項１の発明によれば、画像入力手段により
撮り込まれた画像情報の抽出対象を含む領域に円を設定
する段階と、前記円の円周上の画素の画素濃度のピーク
点を求める段階と、ピーク点に対向する円周上の点の想
定を行なうとともにピーク点と想定した点とを結ぶ直線
上の画素の画素濃度の総和により得られる直線の画像情
報値を、円の円周上の所定範囲内でピーク点と対向する
点を順次想定しながら求める段階と、求められた各直線
の画像情報値から抽出対象である直線を選択・抽出する
段階とからなるので、コントラストが低い抽出対象であ
っても、空間微分処理や他のフィルタリング手法を用い
ずに、円周上の２点を結ぶ直線上の画素の画素濃度の平
均値を求めるという処理だけで抽出対象である直線を高
速に且つ安定的に抽出でき、また円周上の画素の画素濃
度のピーク点を求めた後、その点に対向する円周上の点
を走査する範囲を指定できるため処理時間の短縮が行な
える。According to the first aspect of the present invention, a step of setting a circle in an area including an extraction target of image information captured by image input means, and a peak point of pixel density of a pixel on the circumference of the circle Is determined, and a point on the circumference opposite to the peak point is assumed, and the image information value of a straight line obtained by summing the pixel densities of pixels on a straight line connecting the peak point and the assumed point is calculated as the circle. The method includes a step of sequentially assuming points facing the peak point within a predetermined range on the circumference, and a step of selecting and extracting a straight line to be extracted from the obtained image information value of each straight line. Is an extraction target even if the average value of pixel densities of pixels on a straight line connecting two points on the circumference is obtained without using spatial differentiation processing or other filtering methods. Fast and stable straight line Out can also After determining the peak point of the pixel density of the pixels on the circumference, allows to shorten the processing time because you can specify a range for scanning a point on the circumference opposite to the point.
【００１１】請求項２の発明によれば、請求項１の発明
において、設定する円を二つに分割して分割された各々
の円周上について直線抽出を行ない、求められた２つの
直線を平均化することによって抽出対象の直線を選択・
抽出するので、直線の抽出の精度を向上することができ
る。請求項３の発明によれば、請求項１、２の発明にお
いて、画像情報値のピーク値を抽出して抽出対象の直線
を選択・抽出するので、抽出のための処理時間を早くす
ることができる。According to a second aspect of the present invention, in the first aspect of the present invention, a circle to be set is divided into two, and a straight line is extracted on each of the divided circles. Select the straight line to be extracted by averaging
Since extraction is performed, the accuracy of straight line extraction can be improved. According to the third aspect of the present invention, in the first and second aspects of the present invention, since the peak value of the image information value is extracted to select and extract the extraction target straight line, the processing time for the extraction can be shortened. it can.
【００１２】請求項４の発明によれば、請求項１、２の
発明において、画像情報値の分布の重心を求めて抽出対
象の直線を選択・抽出するので、略等しいピークが二つ
以上あるときに有効となる。請求項５の発明によれば、
請求項１、２の発明において、或る値以上を持つ画像情
報値の分布の存在領域の中心を求めて抽出対象の直線を
選択・抽出するので、分布の度数が低い情報をカットす
ることになり、直線の抽出の精度を向上することができ
る。According to the fourth aspect of the present invention, in the first and second aspects of the present invention, since the center of gravity of the distribution of image information values is obtained and a straight line to be extracted is selected and extracted, there are two or more substantially equal peaks. It is sometimes effective. According to the invention of claim 5,
According to the first and second aspects of the present invention, since a straight line to be extracted is selected and extracted by finding the center of an existing area of a distribution of image information values having a certain value or more, information having a low frequency of distribution is cut. Thus, the accuracy of straight line extraction can be improved.
【００１３】請求項６の発明によれば、請求項１の発明
において、抽出対象の直線を選択・抽出した後、前記ピ
ーク点を中心として円周上の所定範囲内で想定した起点
と、ピーク点に対向する抽出された直線と円周上の交点
とを結ぶ各直線上の画素の画素濃度の総和により得られ
る各直線の画像情報値を求め、求められた各直線の画像
情報値から抽出対象である直線を選択・抽出するので、
直線抽出の起点としたピーク点の近傍を再度走査するた
め起点の誤検出を補正できて抽出精度を向上させること
ができる。According to a sixth aspect of the present invention, in the first aspect of the present invention, after selecting and extracting a straight line to be extracted, a starting point assumed within a predetermined range on a circle around the peak point, The image information value of each straight line obtained by the sum of the pixel densities of the pixels on each straight line connecting the extracted straight line facing the point and the intersection on the circumference is extracted from the obtained image information value of each straight line. Since the target straight line is selected and extracted,
Since the vicinity of the peak point used as the starting point of the straight line extraction is scanned again, erroneous detection of the starting point can be corrected, and the extraction accuracy can be improved.
【００１４】請求項７の発明によれば、請求項１〜６の
発明において、抽出対象の直線の選択・抽出を繰り返し
て行なうので、直線抽出の信頼性を高めることができ
る。請求項８の発明によれば、請求項１、２の発明にお
いて、ピーク点を含む小領域を設定して該小領域内の空
間微分処理を行なって直線成分の方向を抽出し、この方
向に基づいてピーク点に対向する円周上の想定する点の
範囲を設定するので、直線の抽出走査領域が予め限定さ
れるため走査時間を短縮することができる。According to the invention of claim 7, in the invention of claims 1 to 6, selection and extraction of a straight line to be extracted are repeatedly performed, so that the reliability of the straight line extraction can be improved. According to the eighth aspect of the present invention, in the first and second aspects of the present invention, a small area including a peak point is set, and a spatial differentiation process is performed in the small area to extract a direction of a linear component. Since the range of the assumed point on the circumference facing the peak point is set based on the peak point, the scanning time can be reduced because the straight line extraction scanning area is limited in advance.
【００１５】請求項９の発明では、請求項１〜７の発明
において、設定する円を複数として各円において直線抽
出を行ない、抽出した各直線を平均化して得られた直線
を抽出対象とするので、直線抽出の信頼性を高めること
ができる。According to a ninth aspect of the present invention, in the first to seventh aspects, a plurality of circles are set, a straight line is extracted from each circle, and a straight line obtained by averaging the extracted straight lines is set as an extraction target. Therefore, the reliability of straight line extraction can be improved.
【００１６】[0016]
【実施例】以下、本発明の実施例を図面を参照して説明
する。 （実施例１）本実施例は図２に示す画像処理システムを
利用して実現したもので、図１に示すフローチャートに
沿って抽出対象の直線を抽出処理を行なうようになって
いる。まず画像入力、画像メモリへの格納の段階ではＴ
Ｖカメラ１により抽出対象を撮像し、撮像して得られた
画像信号はＡ／Ｄ変換器２によりＡ／Ｄ変換された後、
画像処理プロセッサ３の制御の下で、画像メモリ４に原
画像、微分画像、微分方向画像、エッジ画像等として格
納される。Embodiments of the present invention will be described below with reference to the drawings. (Embodiment 1) This embodiment is realized by using the image processing system shown in FIG. 2, and extracts a straight line to be extracted in accordance with the flowchart shown in FIG. First, at the stage of image input and storage in the image memory, T
An image of the extraction target is imaged by the V camera 1, and the image signal obtained by the imaging is A / D converted by the A / D converter 2.
Under the control of the image processor 3, the image data is stored in the image memory 4 as an original image, a differential image, a differential direction image, an edge image, and the like.
【００１７】この画像メモリ４に格納された画像データ
からコンピュータ５により、次の各処理段階を経て直線
抽出を行なうのである。まず抽出対象である図３に示す
直線Ｌを含む領域へ円Ｃを設定し、その後この円周上の
画素について画素濃度のピーク点Ｐを求める。そして円
周上のピーク点Ｐに対向するＡ点の走査範囲（ａ点−
ａ’点）を決定する。A straight line is extracted from the image data stored in the image memory 4 by the computer 5 through the following processing steps. First, a circle C is set in an area including a straight line L shown in FIG. 3 to be extracted, and then a pixel density peak point P is obtained for pixels on the circumference. Then, the scanning range of point A opposite to the peak point P on the circumference (point a-
a ′) is determined.
【００１８】この決定方法を図４に示すフローチャート
及び図５によって更に詳説すると、まず円Ｃの円周上の
画素を走査し、その画素濃度のピーク値Ａｍａｘをとる
点を上記のピーク点Ｐとする。次にピーク点Ｐより円周
上にｋ画素だけ時計回りと、反時計回りとで離れた点を
夫々ａ，ａ’とする。そして点ａから図５において時計
回りの方向でａ’点までの領域を走査範囲（ＳＲ）とす
る。This determination method will be described in further detail with reference to the flowchart shown in FIG. 4 and FIG. 5. First, a pixel on the circumference of the circle C is scanned, and the point at which the peak value Amax of the pixel density is obtained is defined as the above-mentioned peak point P. I do. Next, points separated by k pixels clockwise and counterclockwise on the circumference from the peak point P are defined as a and a ', respectively. An area from the point a to the point a ′ in the clockwise direction in FIG. 5 is defined as a scanning range (SR).
【００１９】さて走査範囲（ＳＲ）が決定されると、対
向点Ａをａ点からａ’点方向に１画素ずつシフトさせな
がらピーク点Ｐと各対向点Ａとを結ぶ直線上の画素の画
素濃度の平均値（Ａａｖｅ）を求める。この平均値（Ａ
ａｖｅ）が画像情報値となる。そして対向点Ａの走査範
囲（ａ点−ａ’点）が終了すると、各直線の画像情報値
（Ａａｖｅ）から求める直線Ｌを抽出するのである。When the scanning range (SR) is determined, the pixel of the pixel on the straight line connecting the peak point P and each of the opposing points A while shifting the opposing point A one pixel at a time from the point a to the point a '. An average value (Aave) of the density is obtained. This average value (A
ave) is the image information value. When the scanning range of the opposing point A (point a-a ') ends, a straight line L obtained from the image information value (Aave) of each straight line is extracted.
【００２０】（実施例２）上記実施例１おいては、円Ｃ
の円周上の画素を走査してその画素濃度のピーク点Ｐを
求め、このピーク点Ｐに対する対向点Ａの走査を行なう
方法であったが、本実施例は図６に示すように円Ｃを二
つに分割して、夫々の半円の円周Ｃｕ、Ｃｄ上の画素を
走査してその画素濃度のピーク点Ｐｄ、Ｐｕを求めて、
夫々のピーク点Ｐｄ、Ｐｕについて図６（ａ）（ｂ）に
示すように対向点Ａの走査を行なって夫々直線抽出を行
ない、抽出した二つの直線Ｌｄ，Ｌｕを平均化して求め
る直線Ｌとする方法である。(Embodiment 2) In Embodiment 1 described above, the circle C
Is a method of scanning the pixels on the circumference of the circle to find the peak point P of the pixel density and scanning the point A opposite to the peak point P. In this embodiment, as shown in FIG. Is divided into two, and pixels on the circumferences Cu and Cd of the respective semicircles are scanned to obtain peak points Pd and Pu of the pixel density,
As shown in FIGS. 6 (a) and 6 (b), each of the peak points Pd and Pu is scanned at the opposing point A, and straight lines are extracted. The straight line L obtained by averaging the two extracted straight lines Ld and Lu is shown in FIG. How to
【００２１】図７は本実施例の処理過程を示すフローチ
ャートであり、図示するように抽出対象を含む画像デー
タの画像メモリ４への格納後、円Ｃを実施例１と同様に
設定した後、更に円Ｃの中心Ｏを通る水平な線ＬＨによ
り、円Ｃを二つに分割する。次に分割された半円の円周
Ｃｄ，Ｃｕ上の画素について画素濃度のピーク点Ｐｄ，
Ｐｕを求める。FIG. 7 is a flowchart showing the processing steps of the present embodiment. As shown in the figure, after storing the image data including the extraction target in the image memory 4, the circle C is set in the same manner as in the first embodiment. Further, the circle C is divided into two by a horizontal line LH passing through the center O of the circle C. Next, regarding the pixels on the circumferences Cd and Cu of the divided semicircles, the pixel density peak points Pd and
Find Pu.
【００２２】そして下側の円周Ｃｄ上のピーク点Ｐｄに
対向する対向点Ａの走査範囲（ａ点−ａ’点）を反対側
の円周Ｃｕ上に設定し、実施例１と同様に対向点Ａをａ
点からａ’点方向に１画素ずつシフトさせながらピーク
点Ｐｄと各対向点Ａとを結ぶ直線上の画素の画素濃度の
平均値（Ａａｖｅ）を求める。そして対向点Ａの走査範
囲（ａ点−ａ’点）が終了すると、各直線の画像情報値
（Ａａｖｅ）から直線Ｌｄを抽出する。Then, the scanning range (point a-a ') of the facing point A facing the peak point Pd on the lower circumference Cd is set on the opposite circumference Cu, as in the first embodiment. Let opposing point A be
The average value (Aave) of pixel densities of pixels on a straight line connecting the peak point Pd and each of the opposing points A is obtained while shifting one pixel at a time from the point to the point a ′. When the scanning range (point a-a ') of the opposing point A ends, a straight line Ld is extracted from the image information value (Aave) of each straight line.
【００２３】次に上側の円周Ｃｕ上のピーク点Ｐｕに対
向する対向点Ａの走査範囲（ａ点−ａ’点）を反対側の
円周Ｃｄ上に設定し、上述と同様に対向点Ａをａ点から
ａ’点方向に１画素ずつシフトさせながらピーク点Ｐｕ
と各対向点Ａとを結ぶ直線上の画素の画素濃度の平均値
（Ａａｖｅ）を求める。そして対向点Ａの走査範囲（ａ
点−ａ’点）が終了すると、各直線の画像情報値（Ａａ
ｖｅ）から直線Ｌｕを抽出する。Next, the scanning range (point a-a ') of the opposing point A facing the peak point Pu on the upper circumference Cu is set on the opposite circumference Cd, and the opposing point is set in the same manner as described above. A is shifted from the point a to the point a ′ by one pixel at a time while the peak point Pu is shifted.
The average value (Aave) of the pixel densities of the pixels on the straight line connecting the point A and each of the opposing points A is obtained. Then, the scanning range (a
When the point -a 'point is completed, the image information value (Aa
ve), a straight line Lu is extracted.
【００２４】このようにして抽出した二つの直線Ｌｄ，
Ｌｕを更に平均化して求める直線Ｌとするのである。こ
のように本実施例では抽出対象の直線Ｌを含む領域に設
定する円Ｃを二つに分割することにより、直線抽出の精
度を向上させている。 （実施例３）本実施例は、ピーク点Ｐと対向点Ａとを結
ぶ直線上の画素の画素濃度を総和した画像情報値から、
画像情報値のピーク値を抽出して、直線Ｌを選択する方
法を採用したものである。The two straight lines Ld, extracted in this way,
Lu is further averaged to obtain a straight line L to be obtained. As described above, in the present embodiment, the accuracy of the straight line extraction is improved by dividing the circle C set in the area including the straight line L to be extracted into two. (Embodiment 3) In this embodiment, the image information value obtained by summing the pixel densities of the pixels on the straight line connecting the peak point P and the opposing point A is calculated as follows.
This method employs a method of extracting a peak value of image information values and selecting a straight line L.
【００２５】つまり本実施例では図８のフローチャート
で示すように走査終了後、走査範囲（ａ点−ａ’点）内
での直線上の画像情報値（Ａａｖｅ）の分布を図９の如
く求め、更にこの分布のピーク値（Ｐｍａｘ）を求め
る。そしてこのピーク値（Ｐｍａｘ）をとる対向点Ａの
アドレスｐより求める直線Ｌを選択するのである。尚図
８の走査終了までの処理は実施例１（或いは実施例２）
と同じであるためその処理についての説明は省略する。That is, in this embodiment, as shown in the flowchart of FIG. 8, after the scanning is completed, the distribution of image information values (Aave) on a straight line within the scanning range (point a-a ') is obtained as shown in FIG. , And the peak value (Pmax) of this distribution is obtained. Then, a straight line L obtained from the address p of the opposing point A having the peak value (Pmax) is selected. The processing up to the end of scanning in FIG. 8 is performed in the first embodiment (or the second embodiment).
Since it is the same as that described above, the description of the processing is omitted.
【００２６】而して本実施例ではピーク値を抽出して直
線Ｌを選択する方法であるため処理時間が短くて済む。 （実施例４）本実施例は、画像情報値（Ａａｖｅ）の分
布の重心を求めて直線を選択する方法を採用したもので
ある。In this embodiment, since the method is a method of extracting the peak value and selecting the straight line L, the processing time is short. (Embodiment 4) This embodiment employs a method of obtaining a center of gravity of a distribution of image information values (Aave) and selecting a straight line.
【００２７】つまり本実施例では図１０のフローチャー
トで示すように走査終了後、走査範囲（ａ点−ａ’点）
での直線上の画像情報値（Ａａｖｅ）の分布を図１１の
如く求め、その重心のアドレスを次式により求める。 Gr＝(p1 ×Aave(p1)＋p2×Aave(p2)＋…＋pn×Aave(p
n)) ／ΣAave(p) この求めた重心Ｇｒとピーク点Ｐを、結ぶ直線が求める
直線Ｌとなる。That is, in this embodiment, as shown in the flowchart of FIG. 10, after the scanning is completed, the scanning range (point a-a ')
The distribution of the image information value (Aave) on the straight line at is obtained as shown in FIG. 11, and the address of the center of gravity is obtained by the following equation. Gr = (p 1 × Aave (p 1 ) + p 2 × Aave (p 2 ) + ... + pn × Aave (p
n)) / ΣAave (p) A straight line connecting the obtained center of gravity Gr and the peak point P is a straight line L to be obtained.
【００２８】尚図１０の走査終了までの処理は実施例１
（或いは実施例２）と同じであるためその処理について
の説明は省略する。以上のような処理を行なう本実施例
は略等しいピークが二つ以上あるときに有効な方法と言
える。 （実施例５）本実施例は、或る値以上を持つ画像情報分
布の存在領域の中心を求めて直線を選択する方法を採用
したものである。The processing up to the end of scanning in FIG.
Since this is the same as (or the second embodiment), a description of that processing will be omitted. This embodiment that performs the above-described processing can be said to be an effective method when there are two or more substantially equal peaks. (Embodiment 5) In this embodiment, a method is adopted in which the center of the existence area of the image information distribution having a certain value or more is obtained and a straight line is selected.
【００２９】つまり本実施例では図１２のフローチャー
トで示すように走査終了後、走査範囲（ａ点−ａ’点）
での直線上の画像情報値（Ａａｖｅ）の平均値（Ａｍｅ
ａｎ）を求め、しきい値とする。そして図１３に示す画
像情報値分布において、求めたしきい値（Ｅmean）以上
の値をとる画像情報値分布の存在領域ａ1 −ａ2 を求
め、この存在領域ａ1 −ａ2 の中心のアドレスより求め
る直線Ｌを選択する。That is, in this embodiment, as shown in the flow chart of FIG. 12, after the scanning is completed, the scanning range (point a-a ')
(Ame) of image information values (Aave) on a straight line at
an) is obtained and set as a threshold value. Then, in the image information value distribution shown in FIG. 13, the determined threshold value (Emean) or more for the presence area a 1 -a 2 of the image information value distribution takes the value of the existing areas a 1 -a 2 center Select the straight line L obtained from the address.
【００３０】尚図１２の走査終了までの処理は実施例１
（或いは実施例２）と同じであるためその処理について
の説明は省略する。而して本実施例によれば、分布の度
数の低い情報をカットすることができるため、抽出精度
を向上させることができる。尚実施例３乃至実施例５の
直線Ｌの抽出選択に画像情報値の分布を用いる方法を実
施例１以外に実施例２においても採用しても勿論よい。The processing up to the end of scanning in FIG.
Since this is the same as (or the second embodiment), a description of that processing will be omitted. Thus, according to the present embodiment, information having a low frequency of distribution can be cut, and thus the extraction accuracy can be improved. The method of using the distribution of image information values for extracting and selecting the straight line L according to the third to fifth embodiments may be applied to the second embodiment other than the first embodiment.
【００３１】（実施例６）上記各実施例ではピーク点Ｐ
を起点として対向する点Ａの走査範囲を決定し、対向点
Ａを１画素ずつシフトする走査を行なっているが、本実
施例は、この走査による直線抽出後、ピーク点Ｐに対向
するＡ点を起点として走査範囲を決定して走査範囲の円
周上の点とＡ点とを結ぶ各直線上の画像の画素濃度の平
均値（Ｂａｖｅ）を求めてこの平均値を画像情報値と
し、各直線の画像情報値（Ｂａｖｅ）から求める直線Ｌ
を抽出する過程を加えて、直線抽出の信頼性を高めるよ
うにしたものである。(Embodiment 6) In each of the above embodiments, the peak point P
The scanning range of the point A opposed to the starting point is determined, and the scanning of shifting the opposed point A by one pixel is performed. In this embodiment, after the straight line is extracted by this scanning, the point A opposed to the peak point P is obtained. Is determined as a starting point, an average value (Bave) of pixel densities of images on each straight line connecting a point on the circumference of the scanning range and point A is determined, and the average value is used as an image information value. Straight line L obtained from the straight line image information value (Bave)
Is added to increase the reliability of line extraction.
【００３２】つまり本実施例では図１４のフローチャー
トで示すように実施例１と同様にしてピーク点Ｐと対向
点Ａとを結ぶ直線の画像情報値（Ａａｖｅ）を求める走
査を行なって各直線の画像情報値（Ａａｖｅ）から求め
る直線Ｌを抽出し、図１５（ａ）に示す如くピーク点Ｐ
と対向点Ａを結ぶ直線Ｌの抽出完了した後、求められた
Ａ点を起点として、円周上にｂ画素だけ時計回りと、反
時計回りとで離れた点ｂ、ｂ’を求め、この求めたｂ点
と、ｂ’点との間の領域を図５（ｂ）に示すようにＡ点
に対向する点Ｂの走査領域とする。That is, in the present embodiment, as shown in the flow chart of FIG. 14, scanning for obtaining the image information value (Aave) of the straight line connecting the peak point P and the opposite point A is performed in the same manner as in the first embodiment, and each straight line is scanned. A straight line L obtained from the image information value (Aave) is extracted, and as shown in FIG.
After completing the extraction of the straight line L connecting the point A and the opposite point A, starting from the obtained point A, the points b and b ′ separated clockwise and counterclockwise by b pixels on the circumference are obtained. The area between the obtained point b and point b ′ is defined as a scanning area of point B opposite to point A as shown in FIG.
【００３３】次に対向点Ｂをｂ点からｂ’点方向に１画
素ずつシフトさせながらＡ点と各対向点Ｂとを結ぶ直線
上の画素の画素濃度の平均値（Ｂａｖｅ）を求める。こ
の平均値（Ｂａｖｅ）が画像情報値となる。そして対向
点Ｂの走査範囲（ｂ点−ｂ’点）が終了すると、各直線
の画像情報値（Ｂａｖｅ）から求める直線Ｌを抽出する
のである。Next, an average value (Bave) of pixel densities of pixels on a straight line connecting the point A and each of the opposing points B is obtained while shifting the opposing point B one pixel at a time from the point b to the point b ′. This average value (Bave) becomes the image information value. Then, when the scanning range of the opposing point B (point b−b ′) ends, a straight line L obtained from the image information value (Bave) of each straight line is extracted.
【００３４】而して本実施例によれば、直線抽出の起点
としてピーク点Ｐの近傍を再び走査するため起点の誤検
出を補正することができて、抽出精度を向上させること
ができる。 （実施例７）上記実施例６では１回だけ起点と対向点と
を交換して走査を行ない各直線の画像情報値（Ｂａｖ
ｅ）から求める直線Ｌを抽出すると処理を終了している
が、本実施例では実施例５の処理に加えて図１６のフロ
ーチャートに示すように規定回数（複数回）だけ起点と
対向点を交換する操作を繰り返し行なって規定回数だけ
直線抽出を繰り返して行なうようにしたものであり、こ
の複数回の直線抽出を行なうことにより直線抽出の信頼
性を高めることができる。According to the present embodiment, since the vicinity of the peak point P is re-scanned as the starting point of the straight line extraction, erroneous detection of the starting point can be corrected, and the extraction accuracy can be improved. (Embodiment 7) In the above-described embodiment 6, scanning is performed by exchanging the starting point and the opposing point only once, and the image information value (Bav
The processing is terminated when the straight line L obtained from e) is extracted. In the present embodiment, in addition to the processing of the fifth embodiment, the starting point and the opposing point are exchanged by a specified number (a plurality of times) as shown in the flowchart of FIG. The line extraction is repeatedly performed a specified number of times by repeatedly performing the above operation. By performing the line extraction a plurality of times, the reliability of the line extraction can be improved.
【００３５】尚上記直線抽出を繰り返す操作は、実施例
１乃至５においても採用することができ、夫々の実施例
において直線抽出の信頼性を高めることができるのは勿
論である。 （実施例８）本実施例はピーク点Ｐを求めると、ピーク
点Ｐを含む小さいな領域Ｇを図１７に示すように設定し
て、その領域Ｇ内を空間微分処理して直線成分の方向を
抽出、ピーク点Ｐに対向する円周上のＡ点の走査範囲を
限定するようにしたものである。The operation of repeating the above-described straight line extraction can be adopted also in the first to fifth embodiments, and it is needless to say that the reliability of the straight line extraction can be improved in each embodiment. (Embodiment 8) In this embodiment, when a peak point P is obtained, a small area G including the peak point P is set as shown in FIG. Is extracted to limit the scanning range of the point A on the circumference facing the peak point P.
【００３６】つまり本実施例では図１８のフローチャー
トで示すように、ピーク点Ｐを求めた後、ピーク点Ｐを
中心としてｆ×ｆ画素の領域Ｇを設定し、その領域Ｇ内
の空間微分処理を行なって直線成分の方向抽出を行な
う。そして抽出された方向へ直線を延長し、円周との交
点Ｑを中心とし、円周上の両側へｒ画素だけ離れた点ｒ
と点ｒ’との間の領域を対向点Ａの走査範囲とする。走
査範囲が決定されると、対向点Ａをｒ点からｒ’点方向
に１画素ずつシフトさせながらピーク点Ｐと各対向点Ａ
とを結ぶ直線上の画素の画素濃度の平均値（Ａａｖｅ）
を求める。この平均値（Ａａｖｅ）が画像情報値とな
る。そして対向点Ａの走査範囲（ｒ点−ｒ’点）が終了
すると、各直線の画像情報値（Ａａｖｅ）から求める直
線Ｌを抽出するのである。That is, in the present embodiment, as shown in the flowchart of FIG. 18, after the peak point P is obtained, an area G of f × f pixels is set around the peak point P, and the spatial differentiation processing in the area G is performed. To extract the direction of the linear component. Then, a straight line is extended in the extracted direction, and a point r, which is separated by r pixels on both sides on the circumference, around the intersection Q with the circumference.
The area between the point r ′ and the point r ′ is defined as the scanning range of the opposing point A. When the scanning range is determined, the peak point P and each of the opposing points A are shifted while the opposing point A is shifted one pixel at a time from the point r to the point r ′.
(Aave) of the pixel density of the pixel on the straight line connecting
Ask for. This average value (Aave) becomes the image information value. When the scanning range of the opposing point A (point r-r ') ends, a straight line L to be obtained from the image information value (Aave) of each straight line is extracted.
【００３７】尚この走査範囲の決定方法は実施例１以外
の他の実施例において採用しても勿論よい。而して本実
施例によれば走査範囲が予め限定されるため、走査に要
する時間を短縮することができる。 （実施例９）上記各実施例では抽出対象の直線Ｌに対し
て一つの円Ｃを設定しているが、本実施例では複数の円
Ｃ1 〜Ｃ4 を設定し、各々の円Ｃ1 〜Ｃ4 について直線
抽出を実施例１乃至実施例８の方法の何れかにより行な
い、抽出された直線Ｌ1 〜Ｌ 4 （但しＬ1 ：ｙ＝α1 ｘ
＋ｂ1 ，Ｌ2 ：ｙ＝α2 ｘ＋ｂ2 ，Ｌ3 ：ｙ＝α3 ｘ＋
ｂ3 ，Ｌ4 ：ｙ＝α4 ｘ＋ｂ4 ）の傾きαの平均とｂの
平均を求め、求める直線Ｌとするのである。The method of determining the scanning range is different from that of the first embodiment.
Of course, it may be adopted in other embodiments. And the truth
According to the embodiment, the scanning range is limited in advance.
The time required to do so can be reduced. (Embodiment 9) In each of the above embodiments, the straight line L to be extracted is
In this embodiment, a plurality of circles C are set.
C1~ CFourAnd set each circle C1~ CFourAbout straight line
The extraction is performed by any of the methods of the first to eighth embodiments.
The extracted straight line L1~ L Four(However, L1: Y = α1x
+ B1, LTwo: Y = αTwox + bTwo, LThree: Y = αThreex +
bThree, LFour: Y = αFourx + bFour) The average of the slope α and b
The average is determined, and a straight line L is determined.
【００３８】このようにすることにより本実施例では直
線抽出の信頼性を高めることができる。By doing so, in the present embodiment, the reliability of straight line extraction can be improved.
【００３９】[0039]
【発明の効果】請求項１の発明は、画像入力手段により
撮り込まれた画像情報の抽出対象を含む領域に円を設定
する段階と、前記円の円周上の画素の画素濃度のピーク
点を求める段階と、ピーク点に円の中心を介して対向す
る円周上の点の想定を行なうとともにピーク点と想定し
た点とを結ぶ直線上の画素の画素濃度の総和により得ら
れる直線の画像情報値を求める段階と、前記想定した点
を中心として円の円周上の所定範囲内でピーク点と対向
する点を順次想定しながら、ピーク点と想定した各点と
を結ぶ各直線上の画素の画素濃度の総和により得られる
各直線の画像情報値を求める段階と、求められた各直線
の画像情報値から抽出対象である直線を選択・抽出する
段階とからなるので、コントラストが低い抽出対象であ
っても、空間微分処理や他のフィルタリング手法を用い
ずに、円周上の２点を結ぶ直線上の画素の画素濃度の平
均値を求めるという処理だけで抽出対象である直線を高
速に且つ安定的に抽出でき、また円周上の画素の画素濃
度のピーク点を求めた後、その点に対向する円周上の点
を走査する範囲を指定できるため処理時間の短縮が行な
えるという効果がある。According to the first aspect of the present invention, a step of setting a circle in an area including an object to be extracted of image information captured by an image input means, and a peak point of pixel density of a pixel on the circumference of the circle And calculating a point on the circumference opposite to the peak point via the center of the circle, and a straight line image obtained by summing the pixel densities of pixels on a straight line connecting the peak point and the assumed point. Obtaining the information value, and sequentially assuming points facing the peak point within a predetermined range on the circumference of the circle with the assumed point as the center, on each straight line connecting the peak point and each assumed point It consists of the steps of obtaining the image information value of each straight line obtained by the sum of the pixel densities of the pixels, and the step of selecting and extracting the straight line to be extracted from the obtained image information value of each straight line. Spatial differentiation A straight line to be extracted can be quickly and stably extracted only by calculating the average value of the pixel densities of pixels on a straight line connecting two points on the circumference without using logic or other filtering methods. Further, after the peak point of the pixel density of the pixel on the circumference is obtained, a range for scanning a point on the circumference opposite to the point can be designated, so that the processing time can be shortened.
【００４０】請求項２の発明は、請求項１の発明におい
て、設定する円を二つに分割して分割された各々の円周
上について直線抽出を行ない、求められた２つの直線を
平均化することによって抽出対象の直線を選択・抽出す
るので、直線の抽出の精度を向上することができるとい
う効果がある。請求項３の発明は、請求項１、２の発明
において、画像情報値のピーク値を抽出して抽出対象の
直線を選択・抽出するので、抽出のための処理時間を早
くすることができるという効果がある。According to a second aspect of the present invention, in the first aspect of the present invention, a line to be set is divided into two, and a straight line is extracted on each of the divided circles, and the two obtained straight lines are averaged. By doing so, a straight line to be extracted is selected and extracted, so that there is an effect that the accuracy of straight line extraction can be improved. According to a third aspect of the present invention, in the first and second aspects of the present invention, since a peak value of an image information value is extracted to select and extract a straight line to be extracted, the processing time for the extraction can be shortened. effective.
【００４１】請求項４の発明は、請求項１、２の発明に
おいて、画像情報値の分布の重心を求めて抽出対象の直
線を選択・抽出するので、略等しいピークが二つ以上あ
るときに有効となるという効果がある。請求項５の発明
は、請求項１、２の発明において、或る値以上を持つ画
像情報値の分布の存在領域の中心を求めて抽出対象の直
線を選択・抽出するので、分布の度数が低い情報をカッ
トすることになり、直線の抽出の精度を向上することが
できるという効果がある。According to a fourth aspect of the present invention, in the first and second aspects of the present invention, a straight line to be extracted is selected and extracted by calculating the center of gravity of the distribution of image information values. This has the effect of being effective. According to a fifth aspect of the present invention, in the first and second aspects of the present invention, a straight line to be extracted is selected and extracted by obtaining a center of an existing area of a distribution of image information values having a certain value or more. Since low information is cut, there is an effect that the accuracy of straight line extraction can be improved.
【００４２】請求項６の発明は、請求項１の発明におい
て、抽出対象の直線を選択・抽出した後、前記ピーク点
を中心として円周上の所定範囲内で想定した起点と、ピ
ーク点に対向する抽出された直線と円周上の交点とを結
ぶ各直線上の画素の画素濃度の総和により得られる各直
線の画像情報値を求め、求められた各直線の画像情報値
から抽出対象である直線を選択・抽出するので、直線抽
出の起点としたピーク点の近傍を再度走査するため起点
の誤検出を補正できて抽出精度を向上させることができ
るという効果がある。According to a sixth aspect of the present invention, in the first aspect of the present invention, after selecting and extracting a straight line to be extracted, a starting point assumed within a predetermined range on a circumference around the peak point and a peak point The image information value of each straight line obtained by the sum of the pixel densities of the pixels on each straight line connecting the opposing extracted straight line and the intersection on the circumference is obtained. Since a certain straight line is selected and extracted, the vicinity of the peak point used as the starting point of the straight line extraction is scanned again, so that there is an effect that erroneous detection of the starting point can be corrected and the extraction accuracy can be improved.
【００４３】請求項７の発明は、請求項１〜６の発明に
おいて、抽出対象の直線の選択・抽出を繰り返して行な
うので、直線抽出の信頼性を高めることができるという
効果がある。請求項８の発明は、請求項１、２の発明に
おいて、ピーク点を含む小領域を設定して該小領域内の
空間微分処理を行なって直線成分の方向を抽出し、この
方向に基づいてピーク点に対向する円周上の想定する点
の範囲を設定するので、直線の抽出走査領域が予め限定
されるため走査時間を短縮することができるという効果
がある。According to the seventh aspect of the present invention, since the selection and extraction of the straight line to be extracted is repeatedly performed in the first to sixth aspects, there is an effect that the reliability of the straight line extraction can be improved. According to an eighth aspect of the present invention, in the first and second aspects of the present invention, a small area including a peak point is set, and a spatial differentiation process is performed in the small area to extract a direction of a linear component. Since the range of assumed points on the circumference opposite to the peak point is set, the effect is that the scanning time can be reduced because the straight line extraction scanning area is limited in advance.
【００４４】請求項９の発明では、請求項１〜７の発明
において、設定する円を複数として各円において直線抽
出を行ない、抽出した各直線を平均化して得られた直線
を抽出対象とするので、直線抽出の信頼性を高めること
ができるという効果がある。According to a ninth aspect of the present invention, in the first to seventh aspects of the present invention, a plurality of circles are set, a straight line is extracted from each circle, and a straight line obtained by averaging the extracted straight lines is set as an extraction target. Therefore, there is an effect that the reliability of straight line extraction can be improved.
【図１】本発明方法の実施例１のフローチャートであ
る。FIG. 1 is a flowchart of Embodiment 1 of the method of the present invention.
【図２】同上に用いる画像処理システムのブロック図で
ある。FIG. 2 is a block diagram of an image processing system used in the embodiment.
【図３】同上の抽出対象の直線と抽出するために設定す
る円との関係を示す説明図である。FIG. 3 is an explanatory diagram showing a relationship between a straight line to be extracted and a circle set for extraction.
【図４】同上に用いる対向点の走査範囲の決定方法のフ
ローチャートである。FIG. 4 is a flowchart of a method for determining a scanning range of an opposing point used in the embodiment.
【図５】同上に用いる対向点の走査範囲の説明図であ
る。FIG. 5 is an explanatory diagram of a scanning range of an opposing point used in the embodiment.
【図６】本発明方法の実施例２の抽出対象の直線と抽出
するために設定する円との関係を示す説明図である。FIG. 6 is an explanatory diagram showing a relationship between a straight line to be extracted and a circle set for extraction according to the second embodiment of the present invention.
【図７】同上のフローチャートである。FIG. 7 is a flowchart of the above.
【図８】本発明方法の実施例３のフローチャートであ
る。FIG. 8 is a flowchart of Embodiment 3 of the method of the present invention.
【図９】同上の直線抽出の説明図である。FIG. 9 is an explanatory diagram of straight line extraction according to the embodiment;
【図１０】本発明方法の実施例４のフローチャートであ
る。FIG. 10 is a flowchart of Embodiment 4 of the method of the present invention.
【図１１】同上の直線抽出の説明図である。FIG. 11 is an explanatory diagram of straight line extraction according to the embodiment;
【図１２】本発明方法の実施例５のフローチャートであ
る。FIG. 12 is a flowchart of Embodiment 5 of the method of the present invention.
【図１３】同上の直線抽出の説明図である。FIG. 13 is an explanatory diagram of straight line extraction according to the embodiment;
【図１４】本発明方法の実施例６のフローチャートであ
る。FIG. 14 is a flowchart of Embodiment 6 of the method of the present invention.
【図１５】本発明方法の実施例６の説明図である。FIG. 15 is an explanatory view of Embodiment 6 of the method of the present invention.
【図１６】本発明方法の実施例７のフローチャートであ
る。FIG. 16 is a flowchart of Embodiment 7 of the method of the present invention.
【図１７】本発明方法の実施例８に用いる対向点の走査
範囲の決定方法の説明図である。FIG. 17 is an explanatory diagram of a method of determining a scanning range of an opposing point used in Embodiment 8 of the present invention.
【図１８】同上のフローチャートである。FIG. 18 is a flowchart of the above.
【図１９】本発明方法の実施例９の説明図である。FIG. 19 is an explanatory view of Embodiment 9 of the method of the present invention.
Claims (9)
の抽出対象を含む領域に円を設定する段階と、前記円の
円周上の画素の画素濃度のピーク点を求める段階と、ピ
ーク点に対向する円周上の点の想定を行なうとともにピ
ーク点と想定した点とを結ぶ直線上の画素の画素濃度の
総和により得られる直線の画像情報値を、円の円周上の
所定範囲内でピーク点と対向する点を順次想定しなが
ら、求める段階と、求められた各直線の画像情報値から
抽出対象である直線を選択・抽出する段階とからなるこ
とを特徴とする直線成分抽出方法。1. A step of setting a circle in an area including an object to be extracted of image information captured by image input means, a step of obtaining a peak point of a pixel density of a pixel on a circumference of the circle, The image information value of a straight line obtained by the sum of the pixel densities of the pixels on the straight line connecting the peak point and the assumed point is assumed within a predetermined range on the circumference of the circle. A line component extraction method characterized by comprising a step of sequentially determining a point opposite to a peak point, and a step of selecting and extracting a line to be extracted from the obtained image information value of each line. .
々の円周上について直線抽出を行ない、求められた２つ
の直線を平均化することによって抽出対象の直線を選択
・抽出することを特徴とする請求項１記載の直線成分抽
出方法。2. A straight line is extracted on each of the divided circles by dividing a set circle into two, and the obtained straight lines are averaged to select and extract a straight line to be extracted. 2. The method for extracting a straight line component according to claim 1, wherein:
の直線を選択・抽出することを特徴とする請求項１、２
記載の直線成分抽出方法。3. The method according to claim 1, wherein a peak value of the image information value is extracted and a straight line to be extracted is selected and extracted.
The linear component extraction method described in the above.
の直線を選択・抽出することを特徴とする請求項１、２
記載の直線成分抽出方法。4. The method according to claim 1, wherein a straight line to be extracted is selected and extracted by obtaining a center of gravity of the distribution of image information values.
The linear component extraction method described in the above.
領域の中心を求めて抽出対象の直線を選択・抽出するこ
とを特徴とする請求項１、２記載の直線成分抽出方法。5. The straight line component extracting method according to claim 1, wherein a straight line to be extracted is selected and extracted by obtaining a center of an existing area of a distribution of image information values having a certain value or more.
ピーク点を中心として円周上の所定範囲内で想定した起
点と、ピーク点に対向する抽出された直線と円周上の交
点とを結ぶ各直線上の画素の画素濃度の総和により得ら
れる各直線の画像情報値を求め、求められた各直線の画
像情報値から抽出対象である直線を選択・抽出すること
を特徴とする請求項１記載の直線成分抽出方法。6. After selecting and extracting a straight line to be extracted, a starting point assumed within a predetermined range on the circumference centering on the peak point, and an intersection between the extracted straight line facing the peak point and the circumference. The image information value of each straight line obtained by the sum of the pixel densities of the pixels on each straight line connecting the line is selected, and a straight line to be extracted is selected and extracted from the obtained image information value of each straight line. The method for extracting a straight line component according to claim 1.
行なうことを特徴とする請求項１〜６の直線成分抽出方
法。7. A straight line component extracting method according to claim 1, wherein selection and extraction of a straight line to be extracted are repeatedly performed.
内の空間微分処理を行なって直線成分の方向を抽出し、
この方向に基づいてピーク点に対向する円周上の想定す
る点の範囲を設定することを特徴とする請求項１、２記
載の直線成分抽出方法。8. A small area including a peak point is set, and a spatial differentiation process is performed in the small area to extract a direction of a linear component.
3. The method according to claim 1, wherein a range of assumed points on the circumference facing the peak point is set based on the direction.
抽出を行ない、抽出した各直線を平均化して得られた直
線を抽出対象とすることを特徴とする請求項１〜７記載
の直線成分抽出方法。9. A straight line component according to claim 1, wherein a plurality of circles are set, a straight line is extracted from each circle, and a straight line obtained by averaging the extracted straight lines is used as an extraction target. Extraction method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP20251394A JP2957897B2 (en) | 1994-08-26 | 1994-08-26 | Linear component extraction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP20251394A JP2957897B2 (en) | 1994-08-26 | 1994-08-26 | Linear component extraction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JPH0869527A JPH0869527A (en) | 1996-03-12 |
| JP2957897B2 true JP2957897B2 (en) | 1999-10-06 |
Family
ID=16458738
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP20251394A Expired - Lifetime JP2957897B2 (en) | 1994-08-26 | 1994-08-26 | Linear component extraction method |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JP2957897B2 (en) |
-
1994
- 1994-08-26 JP JP20251394A patent/JP2957897B2/en not_active Expired - Lifetime
Also Published As
| Publication number | Publication date |
|---|---|
| JPH0869527A (en) | 1996-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8160366B2 (en) | Object recognition device, object recognition method, program for object recognition method, and recording medium having recorded thereon program for object recognition method | |
| US6865288B1 (en) | Pattern inspection method and apparatus | |
| US8175335B2 (en) | Content adaptive detection of images with stand-out object | |
| CN109409163A (en) | A kind of QR code method for rapidly positioning based on texture features | |
| CN114463184B (en) | Image splicing method and device, storage medium and electronic equipment | |
| JP3193240B2 (en) | Image processing device | |
| US8731326B2 (en) | Object recognition system and method | |
| JPH08292014A (en) | Measuring method of pattern position and device thereof | |
| JP2957897B2 (en) | Linear component extraction method | |
| US6584236B1 (en) | Image processing apparatus and method for image processing | |
| US20020025080A1 (en) | Image processing apparatus, image processing method, and computer readable recording medium recording image processing program for processing image obtained by picking up or reading original | |
| CN114820748B (en) | Full-view-angle characteristic intelligent evidence obtaining method based on panoramic data | |
| US6804413B1 (en) | Image processing device and method for combining images obtained from separate-pickup | |
| WO2002056252A2 (en) | Apparatus and method for boundary detection in vector sequences and edge detection in color image signals | |
| JP2000022943A (en) | Device and method for discriminating image area, and recording medium recorded with image area discriminating program | |
| JP3140954B2 (en) | Linear component extraction method | |
| JP2516844B2 (en) | Parts detection method and device | |
| JP3116438B2 (en) | Inspection apparatus and inspection method for printed wiring board | |
| JP2897439B2 (en) | Corner position detection method | |
| US20230290106A1 (en) | Image processing apparatus, image processing method, image processing system, and storage medium | |
| JP3005163B2 (en) | Circle component extraction method | |
| JP7066580B2 (en) | Image processing equipment | |
| JP4004217B2 (en) | Image processing device | |
| JP3111563B2 (en) | Inspection equipment for printed wiring boards | |
| JPH07141465A (en) | Method for detecting inclination of document image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| A01 | Written decision to grant a patent or to grant a registration (utility model) |
Free format text: JAPANESE INTERMEDIATE CODE: A01 Effective date: 19990713 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20070723 Year of fee payment: 8 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20080723 Year of fee payment: 9 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20090723 Year of fee payment: 10 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20090723 Year of fee payment: 10 |
|
| S533 | Written request for registration of change of name |
Free format text: JAPANESE INTERMEDIATE CODE: R313533 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20090723 Year of fee payment: 10 |
|
| R350 | Written notification of registration of transfer |
Free format text: JAPANESE INTERMEDIATE CODE: R350 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20090723 Year of fee payment: 10 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20100723 Year of fee payment: 11 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20100723 Year of fee payment: 11 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20110723 Year of fee payment: 12 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20120723 Year of fee payment: 13 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20120723 Year of fee payment: 13 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20130723 Year of fee payment: 14 |
|
| EXPY | Cancellation because of completion of term |