WO2015186236A1 - リード画像認識方法及びリード画像認識装置並びに画像処理用部品データ作成方法及び画像処理用部品データ作成装置 - Google Patents
リード画像認識方法及びリード画像認識装置並びに画像処理用部品データ作成方法及び画像処理用部品データ作成装置 Download PDFInfo
- Publication number
- WO2015186236A1 WO2015186236A1 PCT/JP2014/065043 JP2014065043W WO2015186236A1 WO 2015186236 A1 WO2015186236 A1 WO 2015186236A1 JP 2014065043 W JP2014065043 W JP 2014065043W WO 2015186236 A1 WO2015186236 A1 WO 2015186236A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- lead
- image
- recognition
- image processing
- component data
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 32
- 238000004458 analytical method Methods 0.000 claims abstract description 27
- 239000002184 metal Substances 0.000 abstract description 15
- 239000011295 pitch Substances 0.000 description 13
- 238000005311 autocorrelation function Methods 0.000 description 12
- 238000003384 imaging method Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 11
- 230000000737 periodic effect Effects 0.000 description 6
- 238000007796 conventional method Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000001179 sorption measurement Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0006—Industrial image inspection using a design-rule based approach
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/022—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness by means of tv-camera scanning
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J1/00—Photometry, e.g. photographic exposure meter
- G01J1/42—Photometry, e.g. photographic exposure meter using electric radiation detectors
- G01J1/44—Electric circuits
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
- G06V10/507—Summing image-intensity values; Histogram projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
- G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30148—Semiconductor; IC; Wafer
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/06—Recognition of objects for industrial automation
Definitions
- the present invention relates to a lead image recognition method, a lead image recognition device, an image processing component data creation method, and an image processing component data creation device that recognize a lead by processing an image obtained by imaging a component with leads with a camera. is there.
- Patent Document 1 Japanese Patent Laid-Open No. 2011-2110878
- This image processing part data automatic creation method is a method in which a part having the same specifications as a part with a lead used for production is imaged with a camera in advance and subjected to image processing to obtain shape data of the part (the size of the body part of the part, (Lead position, number of leads, lead interval, lead width, lead length, etc.) are measured, and image processing component data including the shape data is created.
- the part sucked by the suction nozzle of the component mounting machine is imaged with a camera, the shape of the part is image-recognized, and the recognition result is compared with the image processing part data created in advance.
- the product type, suction position, suction posture, etc. are determined.
- a general component with leads has a simple structure in which a plurality of leads are arranged at equal pitches (equal intervals) on two sides or four sides, and there is no metal part confusing with the leads.
- the lead can be recognized from the captured image with relatively high accuracy.
- a part of the coil shown in the captured image may be erroneously recognized as a lead.
- the problem to be solved by the present invention is to prevent misidentification of a metal part having a shape confusing with the lead as a lead even when recognizing a part with a lead having a metal part having a confusing shape with the lead. It is possible to improve the lead recognition accuracy.
- the present invention recognizes the lead by processing an image obtained by capturing images of parts having the same shape of leads arranged in one or more rows at an equal pitch with a camera.
- the lead may be present in a region where the luminance periodically changes by analyzing the waveform of the luminance (pixel value) change pattern along a plurality of lines set in the vertical, horizontal, or diagonal directions. After the target area is specified, the lead is image-recognized in the lead recognition target area.
- leads having the same shape are arranged in one or a plurality of rows at an equal pitch, and therefore, a luminance change pattern along a line overlapping a lead row in an image obtained by imaging the component is as follows.
- a periodic waveform pattern in which the length corresponding to the lead pitch is one wavelength is obtained, but the luminance change pattern along the line not overlapping the lead row is not a periodic waveform pattern.
- an area in which the luminance periodically changes by analyzing the waveform of the luminance change pattern along a plurality of lines of the image is defined as a lead recognition target area where the lead may exist.
- the lead is image-recognized within the lead recognition target area. In this way, even if a metal part having a shape confusing with the lead is present in an area other than the lead recognition target area, it is possible to prevent the metal part from being erroneously recognized as a lead and improve the lead recognition accuracy. be able to.
- the waveform analysis may be performed using one of a normalized square difference function, an average amplitude difference function, and a Fourier transform.
- a function or analysis method suitable for evaluating the periodicity of luminance change is used. It is only necessary to perform waveform analysis to identify the lead recognition target region.
- image processing component data used when recognizing a component with a lead mounted by a component mounter
- the result of recognizing a lead image recognized by the above-described lead image recognition method of the present invention is used.
- image processing component data including at least one data of the lead position, the number of leads, the lead interval, the lead width, and the lead length may be created.
- the lead image recognition method of the present invention it is possible to prevent erroneous recognition of a metal part having a shape confusing with the lead as a lead. Can be created.
- FIG. 1 is a block diagram showing a configuration of an image processing component data creation apparatus according to an embodiment of the present invention.
- FIG. 2 is a diagram illustrating an example of an image obtained by imaging a component in which a row of leads is formed on two sides.
- FIG. 3 is a diagram illustrating an example of an image obtained by imaging a component in which a row of leads is formed on four sides.
- FIG. 4 is a diagram illustrating an example of an image obtained by imaging a component provided with a row of leads and a coil.
- FIG. 5 is a diagram illustrating an example of an image obtained by imaging the connector component with leads.
- FIG. 6 is a diagram for explaining a method of setting a waveform analysis line in an image obtained by imaging a component with leads.
- FIG. 1 is a block diagram showing a configuration of an image processing component data creation apparatus according to an embodiment of the present invention.
- FIG. 2 is a diagram illustrating an example of an image obtained by imaging a component in which a row of leads is formed
- FIG. 7 is a diagram showing a waveform obtained by calculating the luminance change pattern along the lines L1 and L2 using an average amplitude difference function.
- FIG. 8 is a diagram showing a waveform obtained by differentiating the waveform calculated by the average amplitude difference function along each line L1, L2.
- FIG. 9 is a diagram showing waveforms calculated by the normalized square difference function along the lines L1 and L2.
- FIG. 10 is a diagram for explaining processing for extracting a line having periodicity.
- FIG. 11 is a graph showing the average projected luminance and standard deviation of the area (A) shown in FIG.
- FIGS. 12A and 12B are diagrams showing experimental results comparing the lead recognition rate and the erroneous recognition rate between the lead image recognition method of the present embodiment and the conventional lead image recognition method.
- the image processing component data creation apparatus includes a computer 11 such as a personal computer, and an image of a CMOS sensor or the like that captures a component for which image processing component data is to be created and acquires a grayscale image.
- the storage device 15 stores data and the like.
- the image processing component data creation device may be configured using a component mounter control system, or a dedicated image processing component data creation device configured separately from the component mounter control system (for example, a combination of a desktop imaging device and a personal computer may be used.
- a combination of a desktop imaging device and a personal computer may be used.
- the camera 12 captures a component adsorbed by the adsorption nozzle of the component mounter from below (so-called part camera). Should be used.
- the computer 11 analyzes a waveform of a change pattern of luminance (pixel value) along a plurality of lines set in the vertical, horizontal (up, down, left, and right) directions of the image captured by the camera 12, and performs an area in which the luminance changes periodically. It functions as a waveform analysis unit that identifies a lead recognition target area where a lead may exist, and functions as an image recognition unit that recognizes a lead in the lead recognition target area identified by the waveform analysis process.
- Image processing component data creation means for creating image processing component data including at least one data of lead position, number of leads, lead interval, lead width and lead length using the recognition result of the image recognized lead also works. Hereinafter, these functions will be described.
- leads having the same shape are arranged in one or a plurality of rows at an equal pitch, and therefore, as shown in FIG. 6, a line L1 that overlaps a row of leads in an image obtained by imaging the component.
- a line L1 that overlaps a row of leads in an image obtained by imaging the component Is a periodic waveform pattern in which the length corresponding to the lead pitch is one wavelength, but the luminance change pattern along the line L2 that does not overlap the lead row is periodic. Does not become a waveform pattern.
- the computer 11 analyzes the waveform of luminance change patterns along a plurality of lines of an image obtained by imaging a leaded component, and leads the region where the luminance changes periodically. After specifying the lead recognition target area that may exist, the lead is image-recognized in the lead recognition target area.
- An average amplitude difference function (AMDF) is a function representing the strength of periodicity of a signal, and is used as one of pitch detection methods in the field of speech recognition. This average amplitude difference function is defined by the following [Equation 1].
- D ( ⁇ ) is the average amplitude difference function at the delay ⁇
- W is the size of the window for waveform analysis
- x is the X coordinate of the image (analyzed in the X direction which is the horizontal direction). If you want to).
- n ′ ( ⁇ ) is a normalized square difference function at the delay ⁇
- m ′ ( ⁇ ) is a function defined by the equation [Equation 8] described later
- r ′ ( ⁇ ) is an autocorrelation function (ACF: Autocorrelation Function) defined by the equation [Equation 4] described later.
- r ( ⁇ ) is an autocorrelation function at the delay ⁇
- W is an initial value of the window size for waveform analysis.
- the type 2 autocorrelation function is defined by the following equation (4).
- the type 2 autocorrelation function r ′ ( ⁇ ) defined by the above equation (4) has a feature that the integration range decreases as ⁇ increases.
- M ′ ( ⁇ ) included in the right side of the equation [Equation 2] is obtained by a square difference function (SDF). Similar to the autocorrelation function, there are two types of this square difference function, and when they are classified into type 1 and type 2, the square difference function of type 1 is defined by the following equation (5).
- d ( ⁇ ) is a type 1 square difference function at the delay ⁇
- W is an initial value of the window size.
- the square difference function of type 2 is defined by the following [Equation 6].
- d ′ ( ⁇ ) is a type 2 squared difference function at the delay ⁇ , and as the type 2 autocorrelation function r ′ ( ⁇ ) described above, the integral is increased as ⁇ increases. It shows that the range decreases.
- the formula of the autocorrelation function is included in the formula of the square difference function as shown in the following formula of [Formula 7].
- Equation 8 the equation of m ′ ( ⁇ ) is defined by the following equation [Equation 8].
- the line L1 is a line that overlaps the row of leads shown in the image
- the line L2 is a line that does not overlap the row of leads in the image.
- FIG. 7 shows a waveform obtained by calculating the luminance change pattern along the lines L1 and L2 using the average amplitude difference function.
- FIG. 8 shows a waveform obtained by differentiating the waveform calculated by the average amplitude difference function along the lines L1 and L2.
- FIG. 9 shows waveforms calculated by the normalized square difference function along the lines L1 and L2.
- the average amplitude difference function takes the absolute value of the difference when the waveform is shifted, the value is always positive (see FIG. 7).
- the normalized square difference function is inconvenient because the negative correlation does not become a negative value. Therefore, in this embodiment, the waveform calculated with the average amplitude difference function (see FIG. 7) is differentiated along the lines L1 and L2 (see FIG. 8), and the normalized square difference function is obtained with respect thereto. A location having a high positive correlation was determined (see FIG. 9).
- the average amplitude difference function in the line L1 that overlaps the lead row has some periodicity, but that there is no periodicity in the line L2 that does not overlap the lead row.
- a waveform obtained by differentiating the waveform of this average amplitude difference function is shown in FIG. Even with this differential waveform, the periodicity of the waveform of the line L1 that overlaps the row of leads can naturally be confirmed.
- FIG. 9 shows a result obtained by obtaining a normalized square difference function for this differential waveform. In the line L1 overlapping the lead row, it can be seen that a peak value having a very high correlation is obtained at the first pitch.
- the luminance is projected in the X direction (horizontal direction) on the region determined to have periodicity by the waveform analysis.
- the average projected luminance T (x) is expressed by the following [Equation 9].
- I (x, y) is the luminance of the image at the coordinates (x, y), and y 1 and y 2 are the start of the region determined to be continuously periodic and This is the end Y coordinate. Since this area has already been determined to have periodicity and the pitch can also be detected, if a standard deviation S (x) of the waveform data projected at the detected pitch is taken, a lead row exists.
- the standard deviation S (x) is high in a region where the standard deviation is performed, and the standard deviation S (x) is low in a region where the standard deviation is not.
- This standard deviation S (x) is defined by the following [Equation 10].
- Tav (x) is the section average projected luminance of the pitch p.
- Tav (x) is defined by the following equation [11].
- FIG. 11 is a graph showing the average projected luminance and standard deviation of the area (A) shown in FIG. By extracting only the region having a high standard deviation, the start and end coordinates x 1 and x 2 of the lead row can be obtained.
- the above-described waveform analysis processing may be performed only in the left and right direction (X direction).
- the lead since the lead extends in the vertical and horizontal directions (X direction and Y direction) of the component, the same processing is performed in both the vertical and horizontal directions (X direction and Y direction) of the image, and the vertical direction (Y direction). ) And a region where a horizontal (X direction) lead column exists, respectively.
- the lead is read within the lead recognition target area. Recognize the image.
- the image recognition of the lead uses a detector using AdaBoost and Haar-Like features often used in face detection.
- image recognition using the HOG feature may be used, but since the lead tip has a characteristic due to the brightness difference of the region rather than the feature of the brightness gradient, in the image recognition using the HOG feature, the Haar-Like feature is used. Compared to the method used, the lead recognition rate tends to be low.
- Lead image recognition is not limited to these methods, and for example, the methods described in Japanese Patent Application Laid-Open Nos. 2007-142039 and 2941617 may be used.
- the inventors of the present invention identified the lead recognition target region from the image of the part with the lead and recognized the lead, and the conventional method for recognizing the lead from the entire image.
- An experiment for comparing the recognition rate and the misrecognition rate is shown in FIG.
- the lead recognition rate is the ratio of the number of leads that can be recognized correctly to the total number of leads for the entire component
- the lead misrecognition rate is the ratio of non-leads mistakenly recognized as leads. It is.
- the image sample used for the experiment was an image sample of a leaded part in which a metal part having a shape confusing with the lead shown in FIGS. 4 and 5 exists.
- the lead recognition rate of this example was not much different from the conventional lead recognition rate, but it was confirmed that the misrecognition rate was greatly reduced from 24.5% to 2.4%. On the other hand, the recognition rate decreased slightly from 96.8% to 95.7%. This is due to the fact that there are leads with no periodicity such as one or two in one component. It is thought that it was excluded by specifying the area by sex. As a whole, only one or two parts with leads are often shaped parts having a simple shape, and it is only necessary to recognize images of the leads using a conventional method.
- the lead position, the number of leads, the lead interval, the lead width, and the lead length are measured, and image processing component data including at least one of these data is created. .
- the lead is image-recognized in the lead recognition target area, even if a metal part having a shape confusing with the lead exists in an area other than the lead recognition target area, the metal part is erroneously recognized as a lead. This can be prevented and lead recognition accuracy can be improved.
- the image processing component data is created using the lead recognition result of the present embodiment, the image processing component data is automatically created by misrecognizing a metal part having a shape confusing with the lead as a lead. Therefore, it is possible to automatically create image processing component data with higher reliability than in the past.
- a line for performing periodic waveform analysis is arranged in an oblique direction of the image (for example, a diagonal direction of the image or a direction inclined 45 ° from the horizontal direction). ) May be set.
- the waveform analysis of periodicity along the line is not limited to the one using the normalized square difference function or the average amplitude difference function, and may use Fourier transform or the like.
- the periodicity of luminance change is evaluated.
- the lead recognition target area may be specified by using a function or analysis method suitable for this.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Image Analysis (AREA)
- Supply And Installment Of Electrical Components (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
Description
図1に示すように、画像処理用部品データ作成装置は、パーソナルコンピュータ等のコンピュータ11と、画像処理用部品データの作成対象となる部品を撮像してグレースケール画像を取得するCMOSセンサ等のイメージセンサを内蔵するカメラ12と、キーボード、マウス、タッチパネル等の入力装置13と、液晶ディスプレイ、CRT等の表示装置14と、後述するリード画像認識と画像処理用部品データ作成のためのプログラムや各種のデータ等を記憶する記憶装置15とを備えた構成となっている。
[平均振幅差関数を用いる波形解析処理]
平均振幅差関数(AMDF:Average Magnitude Difference Function )は、信号の周期性の強さを現す関数であり、音声認識の分野ではピッチの検出のための手法の一つとして用いられている。この平均振幅差関数は、下記の[数1]の式によって定義される。
正規化二乗差関数(NSDF:Normalized Square Difference Function )は、下記の[数2]の式によって定義される。
自己相関関数は主に2種類あり、それらをタイプ1とタイプ2に分類すると、タイプ1の自己相関関数は、下記の[数3]の式によって定義される。
タイプ2の自己相関関数は、下記の[数4]の式によって定義される。
前記[数2]の式の右辺に含まれるm'(τ) は二乗差関数(SDF :Square Difference Function )によって求められる。この二乗差関数も、自己相関関数と同様に、2種類あり、それらをタイプ1とタイプ2に分類すると、タイプ1の二乗差関数は、下記の[数5]の式によって定義される。
同様に、タイプ2の二乗差関数は、下記の[数6]の式によって定義される。
前記[数5]の式を展開すると、下記の[数7]の式に示すように、二乗差関数の式の中に、自己相関関数の式が含まれていることが分かる。
まず、上記波形解析により周期性があると判定した領域に対して、X方向(水平方向)への輝度の投影を行う。平均投影輝度T(x)は、下記の[数9]の式で表される。
Claims (6)
- 同一形状のリードが等ピッチで1列又は複数列に配列された部品をカメラで撮像した画像を処理して前記リードを認識するリード画像認識方法において、
前記画像の縦、横、又は斜め方向に設定した複数のラインに沿って輝度の変化パターンを波形解析して輝度が周期的に変化する領域を前記リードが存在する可能性のあるリード認識対象領域として特定する波形解析処理と、
前記波形解析処理で特定した前記リード認識対象領域内で前記リードを画像認識する画像認識処理と
を含むことを特徴とするリード画像認識方法。 - 前記波形解析処理では、正規化二乗差関数、平均振幅差関数、フーリエ変換のいずれかを用いて前記リード認識対象領域を特定することを特徴とする請求項1に記載のリード画像認識方法。
- 同一形状のリードが等ピッチで1列又は複数列に配列された部品をカメラで撮像した画像を処理して前記リードを認識するリード画像認識装置において、
前記画像の縦、横、又は斜め方向に設定した複数のラインに沿って輝度の変化パターンを波形解析して輝度が周期的に変化する領域を前記リードが存在する可能性のあるリード認識対象領域として特定する波形解析手段と、
前記波形解析処理で特定した前記リード認識対象領域内で前記リードを画像認識する画像認識手段と
を含むことを特徴とするリード画像認識装置。 - 前記波形解析手段は、正規化二乗差関数、平均振幅差関数、フーリエ変換のいずれかを用いて前記リード認識対象領域を特定することを特徴とする請求項3に記載のリード画像認識装置。
- 部品実装機で実装するリード付きの部品を画像認識する際に使用する画像処理用部品データを作成する画像処理用部品データ作成方法において、
請求項1又は2に記載のリード画像認識方法で画像認識したリードの認識結果を用いて、リード位置、リード本数、リード間隔、リード幅、リード長さのうちの少なくとも1つのデータを含む画像処理用部品データを作成することを特徴とする画像処理用部品データ作成方法。 - 部品実装機で実装するリード付きの部品を画像認識する際に使用する画像処理用部品データを作成する画像処理用部品データ作成装置において、
請求項3又は4に記載のリード画像認識装置で画像認識したリードの認識結果を用いて、リード位置、リード本数、リード間隔、リード幅、リード長さのうちの少なくとも1つのデータを含む画像処理用部品データを作成することを特徴とする画像処理用部品データ作成装置。
Priority Applications (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2014/065043 WO2015186236A1 (ja) | 2014-06-06 | 2014-06-06 | リード画像認識方法及びリード画像認識装置並びに画像処理用部品データ作成方法及び画像処理用部品データ作成装置 |
CN201480079514.9A CN106415192B (zh) | 2014-06-06 | 2014-06-06 | 引线图像识别方法及识别装置以及图像处理用元件数据生成方法及生成装置 |
US15/314,691 US10102426B2 (en) | 2014-06-06 | 2014-06-06 | Lead image recognition method and lead image recognition device, and image processing-use component data creation method and image-processing-use component data creation device |
EP14893844.2A EP3153814B1 (en) | 2014-06-06 | 2014-06-06 | Lead image recognition method, lead image recognition device, method for creating component data for image processing, and device for creating component data for image processing |
JP2016525642A JP6476397B2 (ja) | 2014-06-06 | 2014-06-06 | リード画像認識方法及びリード画像認識装置並びに画像処理用部品データ作成方法及び画像処理用部品データ作成装置 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2014/065043 WO2015186236A1 (ja) | 2014-06-06 | 2014-06-06 | リード画像認識方法及びリード画像認識装置並びに画像処理用部品データ作成方法及び画像処理用部品データ作成装置 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2015186236A1 true WO2015186236A1 (ja) | 2015-12-10 |
Family
ID=54766331
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2014/065043 WO2015186236A1 (ja) | 2014-06-06 | 2014-06-06 | リード画像認識方法及びリード画像認識装置並びに画像処理用部品データ作成方法及び画像処理用部品データ作成装置 |
Country Status (5)
Country | Link |
---|---|
US (1) | US10102426B2 (ja) |
EP (1) | EP3153814B1 (ja) |
JP (1) | JP6476397B2 (ja) |
CN (1) | CN106415192B (ja) |
WO (1) | WO2015186236A1 (ja) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017155470A1 (en) * | 2016-03-09 | 2017-09-14 | Agency For Science, Technology And Research | Self-determining inspection method for automated optical wire bond inspection |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3270351B1 (en) * | 2015-03-11 | 2023-03-01 | FUJI Corporation | Component type automatic distinguishing method and component type automatic distinguishing system |
JP7098365B2 (ja) * | 2018-03-15 | 2022-07-11 | キヤノン株式会社 | 画像処理装置、画像処理方法およびプログラム |
JP7120835B2 (ja) * | 2018-07-18 | 2022-08-17 | トヨタ自動車株式会社 | 画像処理装置 |
US11063000B2 (en) * | 2019-01-29 | 2021-07-13 | Infineon Technologies Ag | Semiconductor package authentication feature |
US20230108672A1 (en) * | 2020-02-21 | 2023-04-06 | Fuji Corporation | Image processing device, mounting device, and image processing method |
CN111931658A (zh) * | 2020-08-11 | 2020-11-13 | 合肥瑞纳通软件技术开发有限公司 | 一种烹饪油烟识别方法 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH10283479A (ja) * | 1997-03-31 | 1998-10-23 | Omron Corp | リード認識装置およびそのリード認識用の記憶媒体、ならびにその認識装置を用いた電子部品の外観計測装置 |
JP2011211088A (ja) * | 2010-03-30 | 2011-10-20 | Fuji Mach Mfg Co Ltd | 画像処理用部品データ作成方法及び画像処理用部品データ作成装置 |
JP2013114652A (ja) * | 2011-12-01 | 2013-06-10 | Yazaki Energy System Corp | 横断歩道検出装置 |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4589140A (en) * | 1983-03-21 | 1986-05-13 | Beltronics, Inc. | Method of and apparatus for real-time high-speed inspection of objects for identifying or recognizing known and unknown portions thereof, including defects and the like |
JP2934455B2 (ja) * | 1988-08-26 | 1999-08-16 | 株式会社日立製作所 | X線透過画像によるはんだ付部の検査方法及びその装置 |
JP3182936B2 (ja) * | 1992-11-25 | 2001-07-03 | 松下電器産業株式会社 | リード端部検出方法 |
US6647132B1 (en) | 1999-08-06 | 2003-11-11 | Cognex Technology And Investment Corporation | Methods and apparatuses for identifying regions of similar texture in an image |
JP4830501B2 (ja) * | 2005-02-21 | 2011-12-07 | オムロン株式会社 | 基板検査方法および装置、並びに、その検査ロジック設定方法および装置 |
JP4595705B2 (ja) * | 2005-06-22 | 2010-12-08 | オムロン株式会社 | 基板検査装置並びにそのパラメータ設定方法およびパラメータ設定装置 |
JP5730114B2 (ja) * | 2011-04-25 | 2015-06-03 | 富士機械製造株式会社 | 部品回転角度検出装置及び画像処理用部品データ作成装置並びに部品回転角度検出方法及び画像処理用部品データ作成方法 |
US9646373B2 (en) * | 2013-09-17 | 2017-05-09 | IEC Electronics Corp. | System and method for counterfeit IC detection |
JP6254929B2 (ja) * | 2014-11-26 | 2017-12-27 | 東京エレクトロン株式会社 | 測定処理装置、基板処理システム、測定用治具、測定処理方法、及びその記憶媒体 |
-
2014
- 2014-06-06 EP EP14893844.2A patent/EP3153814B1/en active Active
- 2014-06-06 JP JP2016525642A patent/JP6476397B2/ja active Active
- 2014-06-06 US US15/314,691 patent/US10102426B2/en active Active
- 2014-06-06 CN CN201480079514.9A patent/CN106415192B/zh active Active
- 2014-06-06 WO PCT/JP2014/065043 patent/WO2015186236A1/ja active Application Filing
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH10283479A (ja) * | 1997-03-31 | 1998-10-23 | Omron Corp | リード認識装置およびそのリード認識用の記憶媒体、ならびにその認識装置を用いた電子部品の外観計測装置 |
JP2011211088A (ja) * | 2010-03-30 | 2011-10-20 | Fuji Mach Mfg Co Ltd | 画像処理用部品データ作成方法及び画像処理用部品データ作成装置 |
JP2013114652A (ja) * | 2011-12-01 | 2013-06-10 | Yazaki Energy System Corp | 横断歩道検出装置 |
Non-Patent Citations (1)
Title |
---|
See also references of EP3153814A4 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017155470A1 (en) * | 2016-03-09 | 2017-09-14 | Agency For Science, Technology And Research | Self-determining inspection method for automated optical wire bond inspection |
US10776912B2 (en) | 2016-03-09 | 2020-09-15 | Agency For Science, Technology And Research | Self-determining inspection method for automated optical wire bond inspection |
Also Published As
Publication number | Publication date |
---|---|
US20170147856A1 (en) | 2017-05-25 |
US10102426B2 (en) | 2018-10-16 |
CN106415192A (zh) | 2017-02-15 |
EP3153814A4 (en) | 2017-05-10 |
EP3153814A1 (en) | 2017-04-12 |
JP6476397B2 (ja) | 2019-03-06 |
CN106415192B (zh) | 2019-05-03 |
EP3153814B1 (en) | 2021-05-26 |
JPWO2015186236A1 (ja) | 2017-04-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6476397B2 (ja) | リード画像認識方法及びリード画像認識装置並びに画像処理用部品データ作成方法及び画像処理用部品データ作成装置 | |
US9892312B1 (en) | Face detecting and tracking method and device and method and system for controlling rotation of robot head | |
US10747988B2 (en) | Method and device for face tracking and smart terminal | |
US10212324B2 (en) | Position detection device, position detection method, and storage medium | |
US10445887B2 (en) | Tracking processing device and tracking processing system provided with same, and tracking processing method | |
EP2908220A1 (en) | Gesture recognition device and method of controlling gesture recognition device | |
US20110158476A1 (en) | Robot and method for recognizing human faces and gestures thereof | |
US9836130B2 (en) | Operation input device, operation input method, and program | |
US9218060B2 (en) | Virtual mouse driving apparatus and virtual mouse simulation method | |
JP2009026223A (ja) | 物体検出装置及びプログラム | |
JP5048609B2 (ja) | 対象物追跡装置及びプログラム | |
JP2014238727A5 (ja) | ||
EP3200126A3 (en) | Biometric information process device, biometric information process method, biometric information process program and distance detection device | |
EP3223193A1 (en) | Image processing device, image processing method and image processing program | |
JP6548920B2 (ja) | 情報処理装置、情報処理方法及びプログラム | |
EP3270351B1 (en) | Component type automatic distinguishing method and component type automatic distinguishing system | |
JP6229554B2 (ja) | 検出装置および検出方法 | |
JP5120627B2 (ja) | 画像処理装置および画像処理プログラム | |
JP2010113562A (ja) | 物体検知追跡装置,物体検知追跡方法および物体検知追跡プログラム | |
WO2021140844A1 (ja) | 人体検出装置および人体検出方法 | |
US11373451B2 (en) | Device and method for recognizing gesture | |
CN102759333A (zh) | 零件旋转角度检测装置及图像处理用零件数据生成装置 | |
CN110858404B (zh) | 一种基于区域偏移的识别方法及终端 | |
WO2020175085A1 (ja) | 画像処理装置、及び画像処理方法 | |
KR101802918B1 (ko) | 3차원 영상 획득 장치 및 그 동작방법 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 14893844 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2016525642 Country of ref document: JP Kind code of ref document: A |
|
REEP | Request for entry into the european phase |
Ref document number: 2014893844 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2014893844 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 15314691 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |