CN107101598B - An automatic detection method and device for concentricity quality of piezoelectric ceramic silver sheets - Google Patents
An automatic detection method and device for concentricity quality of piezoelectric ceramic silver sheets Download PDFInfo
- Publication number
- CN107101598B CN107101598B CN201710141152.7A CN201710141152A CN107101598B CN 107101598 B CN107101598 B CN 107101598B CN 201710141152 A CN201710141152 A CN 201710141152A CN 107101598 B CN107101598 B CN 107101598B
- Authority
- CN
- China
- Prior art keywords
- piezoelectric ceramic
- silver
- detection
- area
- ceramic silver
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
- 239000000919 ceramic Substances 0.000 title claims abstract description 133
- BQCADISMDOOEFD-UHFFFAOYSA-N Silver Chemical compound [Ag] BQCADISMDOOEFD-UHFFFAOYSA-N 0.000 title claims abstract description 126
- 229910052709 silver Inorganic materials 0.000 title claims abstract description 126
- 239000004332 silver Substances 0.000 title claims abstract description 126
- 238000001514 detection method Methods 0.000 title claims abstract description 98
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000003708 edge detection Methods 0.000 claims description 22
- 239000002699 waste material Substances 0.000 claims description 14
- 238000009499 grossing Methods 0.000 claims description 6
- 230000000877 morphologic effect Effects 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 abstract description 3
- 230000002950 deficient Effects 0.000 abstract description 2
- 238000005245 sintering Methods 0.000 description 6
- 238000007689 inspection Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052573 porcelain Inorganic materials 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000007650 screen-printing Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- 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
- G01B11/26—Measuring arrangements characterised by the use of optical techniques for measuring angles or tapers; for testing the alignment of axes
- G01B11/27—Measuring arrangements characterised by the use of optical techniques for measuring angles or tapers; for testing the alignment of axes for testing the alignment of axes
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
本发明公开了一种压电陶瓷银片同心度质量自动检测方法和装置，方法包括步骤：通过摄像头获取灰度图像，查找图像中各压电陶瓷银片的外圆、内圆轮廓点集，对得到的点集分别进行圆曲线的拟合，计算拟合得到的内圆和外圆的圆心以及半径，计算内外圆的同心度。将各压电陶瓷银片测得的同心度与预先设置的同心度阈值进行比较，逐片判断压电陶瓷银片属于良品还是不合格品。系统根据产品型号设定了质量阈值后，无需调整任何参数，自动测量不同尺寸的压电陶瓷银片的同心度，识别的准确率高，能够大大提高自动化检测的程度，提高生产效率。
The invention discloses a method and device for automatically detecting the concentricity quality of piezoelectric ceramic silver sheets. The method includes the steps of: acquiring a grayscale image through a camera, and searching for the outer circle and inner circle contour point sets of each piezoelectric ceramic silver sheet in the image. Perform circular curve fitting on the obtained point sets respectively, calculate the centers and radii of the fitted inner and outer circles, and calculate the concentricity of the inner and outer circles. The measured concentricity of each piezoelectric ceramic silver sheet is compared with the preset concentricity threshold, and each piece of piezoelectric ceramic silver sheet is judged as a good product or a defective product. After the system sets the quality threshold according to the product model, it can automatically measure the concentricity of piezoelectric ceramic silver sheets of different sizes without adjusting any parameters. The recognition accuracy is high, which can greatly improve the degree of automated detection and improve production efficiency.
Description
技术领域Technical field
本发明涉及计算机视觉以及质量检测研究领域，特别涉及一种压电陶瓷银片同心度质量自动检测方法和装置。The invention relates to the fields of computer vision and quality detection research, and in particular to a method and device for automatic detection of concentricity quality of piezoelectric ceramic silver sheets.
背景技术Background technique
压电陶瓷银片是将压电陶瓷烧结后，采用丝印的方式将银浆印在陶瓷片上，经烘干烧结形成的。压电陶瓷银片的质量好坏主要由下述三个方面来判定：(1)瓷片与银层的同心度：圆形压电陶瓷片内印好的圆形银层的中心须与压电陶瓷片的外圆同心，当二者圆心偏差大于一定值时，即同心度大于一定值时，为同心度不良；(2)烧结不良：银片的表面会因高温烧结而产生气泡、隆起、颜色改变，为烧结不良；(3)瓷片破损、银层划伤等。Piezoelectric ceramic silver sheets are formed by sintering piezoelectric ceramics, printing silver paste on the ceramic sheets using silk screen printing, and drying and sintering. The quality of the piezoelectric ceramic silver sheet is mainly judged by the following three aspects: (1) The concentricity of the ceramic sheet and the silver layer: the center of the circular silver layer printed in the circular piezoelectric ceramic sheet must be consistent with the piezoelectric ceramic sheet. The outer circles of the electric ceramic sheets are concentric. When the deviation between the center centers of the two circles is greater than a certain value, that is, when the concentricity is greater than a certain value, the concentricity is poor; (2) Poor sintering: the surface of the silver sheet will produce bubbles and bulges due to high-temperature sintering. , color changes, indicating poor sintering; (3) damaged porcelain pieces, scratches on the silver layer, etc.
同心度不良的检测不同于烧结不良和瓷片破损的检测，后两者可以通过定性判断是否存在各种缺陷，但同心度则要求进行定量尺寸判断来区分合格品和不合格品，因此在目前大多数还采用裸眼人工检测的生产线上，同心度实际上只做了非常粗糙的判断，因此产品质量的控制是很不精确的。The detection of poor concentricity is different from the detection of poor sintering and damaged ceramic tiles. The latter two can qualitatively determine whether there are various defects, but concentricity requires quantitative size judgment to distinguish qualified products from unqualified products. Therefore, at present, Most production lines that still use naked-eye manual inspection only make very rough judgments on concentricity, so the control of product quality is very imprecise.
现有技术中进行同心度检测，大多采用霍夫变换查找内外圆，计算所查找到的圆的圆心和半径来测算同心度。此种方法对内圆和外圆的最小间距有一定的要求，内外圆距离太近，检测时算法很容易出现内圆和外圆重合到一起的现象。由于印在压电陶瓷片上的银浆形成的内圆一般都和陶瓷片的外圆距离很近，因此很容易出现或检测不到内圆或检测不到外圆的情况，从而无法正确计算内外圆的同心度；另外，当圆的大小发生变化时，该方法需要调整很多参数，如果参数设置不当，很容易出现无法查找到圆的情况，导致无法计算同心度。压电陶瓷银片作为应用广泛的系列产品，有着很多种大大小小不同的尺寸，上述方法将使工人很难在系统中正确地调整参数，致使系统无法正常工作。In the prior art, for concentricity detection, Hough transform is mostly used to find inner and outer circles, and the center and radius of the found circles are calculated to measure concentricity. This method has certain requirements for the minimum distance between the inner circle and the outer circle. If the distance between the inner and outer circles is too close, the algorithm will easily cause the inner circle and the outer circle to overlap during detection. Since the inner circle formed by the silver paste printed on the piezoelectric ceramic sheet is generally very close to the outer circle of the ceramic sheet, it is easy to fail to detect the inner circle or the outer circle, making it impossible to correctly calculate the inner and outer circles. The concentricity of the circle; in addition, when the size of the circle changes, this method requires adjusting many parameters. If the parameters are set improperly, it is easy to fail to find the circle, resulting in the inability to calculate the concentricity. As a widely used series of products, piezoelectric ceramic silver sheets come in many different sizes. The above method will make it difficult for workers to correctly adjust parameters in the system, causing the system to fail to work properly.
发明内容Contents of the invention
本发明的主要目的在于克服现有技术的缺点与不足，提供一种压电陶瓷银片同心度质量自动检测方法，该方法可自动测量不同尺寸的压电陶瓷银片的同心度，识别的准确率高，可靠性好。The main purpose of the present invention is to overcome the shortcomings and deficiencies of the prior art and provide an automatic quality detection method for the concentricity of piezoelectric ceramic silver sheets. This method can automatically measure the concentricity of piezoelectric ceramic silver sheets of different sizes and accurately identify them. High efficiency and good reliability.
本发明的另一目的在于提供实现上述压电陶瓷银片同心度质量自动检测方法的装置，该装置自动化程度高，工作效率高。Another object of the present invention is to provide a device that implements the above-mentioned automatic detection method for the concentricity quality of piezoelectric ceramic silver sheets. The device has a high degree of automation and high work efficiency.
本发明的目的通过以下的技术方案实现：一种压电陶瓷银片同心度质量自动检测方法，包括步骤：The object of the present invention is achieved through the following technical solution: an automatic detection method for the concentricity quality of piezoelectric ceramic silver sheets, including the steps:
(1)初始化：判断当前检测托板的颜色与压电陶瓷银片镀银区域的颜色是否接近，如果接近，则将待检测的压电陶瓷银片镀银面朝上，平放在检测托板上，将检测托板设置在摄像头拍摄视野内，摄像头拍摄得到原始图像；(1) Initialization: Determine whether the color of the current detection support plate is close to the color of the silver-plated area of the piezoelectric ceramic silver sheet. If they are close, place the silver-plated piezoelectric ceramic silver sheet to be detected flatly on the detection support with the silver-plated side facing up. On the board, set the detection pallet within the field of view of the camera, and the camera will capture the original image;
(2)求外圆参数：提取原始图像中待检测压电陶瓷银片的外轮廓点集，进行圆拟合得到拟合外圆，计算拟合外圆的圆心和半径；(2) Find the outer circle parameters: extract the outer contour point set of the piezoelectric ceramic silver sheet to be detected in the original image, perform circle fitting to obtain the fitted outer circle, and calculate the center and radius of the fitted outer circle;
(3)求内圆参数：提取原始图像中待检测压电陶瓷银片的内轮廓点集，进行圆拟合得到拟合内圆，计算拟合内圆的圆心和半径；(3) Find the inner circle parameters: extract the inner contour point set of the piezoelectric ceramic silver sheet to be detected in the original image, perform circle fitting to obtain the fitted inner circle, and calculate the center and radius of the fitted inner circle;
(4)计算内外圆的同心度，如果同心度大于预设的阈值，则判定当前待检测的压电陶瓷银片为良品，否则为废品。(4) Calculate the concentricity of the inner and outer circles. If the concentricity is greater than the preset threshold, the piezoelectric ceramic silver piece currently to be detected is judged to be a good product, otherwise it is a waste product.
优选的，步骤(1)中，判断当前检测托板的颜色与压电陶瓷镀银区域的颜色是否接近，只在更换检测托板时判断一次，具体方法是：在检测托板的中央放置一个压电陶瓷银片，用摄像头采集一幅图像，通过霍夫变换定位压电陶瓷银片的圆心和外圆直径，统计位于外圆内的所有像素点的灰度平均值作为压电陶瓷银片的灰度平均值；由所述外圆开始向外扩大M个像素得到一个环状的背景区域，统计该背景区域内的灰度平均值，并将其和压电陶瓷银片的灰度平均值进行比较，当二者灰度之差在30-50范围内时，认定检测托板的颜色和压电陶瓷镀银区域的颜色接近。Preferably, in step (1), it is judged whether the color of the current detection pallet is close to the color of the silver-plated area of the piezoelectric ceramic, and the judgment is only made once when the detection pallet is replaced. The specific method is: place a in the center of the detection pallet. For the piezoelectric ceramic silver sheet, use a camera to collect an image, locate the circle center and outer circle diameter of the piezoelectric ceramic silver sheet through Hough transform, and calculate the grayscale average of all pixels located within the outer circle as the piezoelectric ceramic silver sheet. The average gray level; expand M pixels outward from the outer circle to obtain a ring-shaped background area, count the average gray level in the background area, and average it with the gray level of the piezoelectric ceramic silver sheet Compare the values, and when the difference in gray scale between the two is within the range of 30-50, it is determined that the color of the detection support plate is close to the color of the silver-plated area of the piezoelectric ceramic.
优选的，步骤(2)中，提取原始图像中待检测压电陶瓷银片的外轮廓点集的步骤是：Preferably, in step (2), the step of extracting the outer contour point set of the piezoelectric ceramic silver sheet to be detected in the original image is:
(2-1)对原始图像进行高斯平滑；(2-1) Perform Gaussian smoothing on the original image;
(2-2)对平滑后的图像进行边缘检测；(2-2) Perform edge detection on the smoothed image;
(2-3)用拓扑原理和边缘跟踪法检测压电陶瓷银片外轮廓点集，具体是：逐行逐列扫描步骤(2-2)边缘检测后的二值图像，搜索到的第一条像素值由0变为1的边界即为外轮廓；(2-3) Use topological principles and edge tracking methods to detect the outer contour point set of the piezoelectric ceramic silver sheet, specifically: scan the binary image after edge detection in step (2-2) row by row and column by row, and search the first The boundary where the pixel value of the strip changes from 0 to 1 is the outer contour;
(2-4)根据外轮廓点集进行基于二次曲线的圆拟合，得到拟合外圆，记录其圆心和半径。(2-4) Perform circle fitting based on the quadratic curve according to the outer contour point set to obtain the fitted outer circle, and record its center and radius.
更进一步的，步骤(2-2)中采用canny边缘检测算法。Furthermore, the canny edge detection algorithm is used in step (2-2).
更进一步的，考虑到步骤(2-2)进行边缘检测后可能包含一些噪声，为了更准确找到外轮廓，对方法进行了如下改进：所述步骤(2-3)，提取边缘检测后所得图像中的所有边缘，计算每一条边缘所包围区域的面积，取面积最大值对应的边缘作为压电陶瓷银片外轮廓。Furthermore, considering that the edge detection in step (2-2) may contain some noise, in order to find the outer contour more accurately, the method is improved as follows: in step (2-3), extract the image obtained after edge detection For all edges in , calculate the area of the area surrounded by each edge, and take the edge corresponding to the maximum area as the outer contour of the piezoelectric ceramic silver sheet.
优选的，步骤(3)中，提取原始图像中待检测压电陶瓷银片的内轮廓点集的步骤是：Preferably, in step (3), the step of extracting the inner contour point set of the piezoelectric ceramic silver sheet to be detected in the original image is:
(3-1)对原始图像进行高斯平滑；(3-1) Perform Gaussian smoothing on the original image;
(3-2)利用检测托板的颜色与压电陶瓷银片镀银区域的颜色接近的特点，采用一矩形内核对平滑后的图像进行形态学闭运算，使得图像中仅保留压电陶瓷银片镀银区域；(3-2) Taking advantage of the fact that the color of the detection support plate is close to the color of the silver-plated area of the piezoelectric ceramic silver sheet, a rectangular kernel is used to perform morphological closing operation on the smoothed image, so that only the piezoelectric ceramic silver remains in the image. Silver plated area;
(3-3)对步骤(3-2)所得图像进行边缘检测；(3-3) Perform edge detection on the image obtained in step (3-2);
(3-4)提取压电陶瓷银片镀银区域的边缘，即内轮廓点集；(3-4) Extract the edge of the silver-plated area of the piezoelectric ceramic silver sheet, that is, the inner contour point set;
(3-5)根据内轮廓点集进行基于二次曲线的圆拟合，得到拟合内圆，记录其圆心和半径。(3-5) Perform circle fitting based on the quadratic curve according to the inner contour point set to obtain the fitted inner circle, and record its center and radius.
更进一步的，步骤(3-3)中采用canny边缘检测算法。Furthermore, the canny edge detection algorithm is used in step (3-3).
更进一步的，考虑到步骤(3-3)进行边缘检测后可能包含一些噪声，为了更准确找到外轮廓，对方法进行了如下改进：所述步骤(3-4)，提取边缘检测后所得图像中的所有边缘，计算每一条边缘所包围区域的面积，取面积最大值对应的边缘作为压电陶瓷银片镀银区域的边缘。Furthermore, considering that the edge detection in step (3-3) may contain some noise, in order to find the outer contour more accurately, the method is improved as follows: In step (3-4), the image obtained after edge detection is extracted For all edges in , calculate the area of the area surrounded by each edge, and take the edge corresponding to the maximum area as the edge of the silver-plated area of the piezoelectric ceramic silver sheet.
优选的，步骤(4)中，计算内外圆的同心度c的公式是：Preferably, in step (4), the formula for calculating the concentricity c of the inner and outer circles is:
c＝1-((x1-x2)2+(y1-y2)2)/(R-r)2 c＝1-((x1-x2) 2 +(y1-y2) 2 )/(Rr) 2
其中，(x1,y1)是外圆圆心，R是外圆半径，(x2,y2)是内圆圆心，r是内圆半径，同心度c的值域为[0,1]。Among them, (x1, y1) is the center of the outer circle, R is the radius of the outer circle, (x2, y2) is the center of the inner circle, r is the radius of the inner circle, and the value range of concentricity c is [0,1].
为了提高检测效率，检测托板上按照设定的排布方式一次放置N个待检测的压电陶瓷银片，根据各压电陶瓷银片中心坐标的排列规律确定每个待检测的压电陶瓷银片在图像中的位置，提取内外轮廓的步骤是：In order to improve the detection efficiency, N pieces of piezoelectric ceramic silver pieces to be detected are placed on the detection pallet at a time according to the set arrangement, and each piezoelectric ceramic to be detected is determined according to the arrangement pattern of the center coordinates of each piezoelectric ceramic silver piece. The position of the silver piece in the image and the steps to extract the inner and outer contours are:
步骤(2-2)提取图像中的所有边缘后，计算每一条边缘所包围区域的面积，按照面积由大至小进行排序，将面积最大的N条边缘对应的点集选定为待测的N个压电陶瓷银片的外轮廓点集；Step (2-2) After extracting all edges in the image, calculate the area of the area surrounded by each edge, sort the areas from large to small, and select the point set corresponding to the N edges with the largest area as the point set to be measured. The outer contour point set of N piezoelectric ceramic silver sheets;
步骤(3-3)提取图像中的所有边缘后，计算每一条边缘所包围区域的面积，按照面积由大至小进行排序，将面积最大的N条边缘对应的点集选定为待测的N个压电陶瓷银片的内轮廓点集。Step (3-3) After extracting all edges in the image, calculate the area of the area surrounded by each edge, sort the areas from large to small, and select the point set corresponding to the N edges with the largest area as the point set to be measured. The inner contour point set of N piezoelectric ceramic silver sheets.
一种用于实现上述压电陶瓷银片同心度质量自动检测方法的装置，包括控制器、工作台、摄像装置、检测托板和机械手，控制器分别与摄像装置、机械手相连，工作台上设有检测区，检测托板设置在该检测区处，摄像装置固定在检测托板的上方；在检测时，待检测的压电陶瓷银片镀银面朝上，按照一定排布方式放置在检测托板上，检测托板的颜色与压电陶瓷银片镀银区域的颜色接近；机械手的末端为一吸盘，根据检测托板上待检测的压电陶瓷银片的排布，吸盘上按同样排布方式设置若干个吸嘴；在检测区的一侧设有良品区，检测托板在控制器控制下可旋转，在检测托板旋转方向的下侧设有废品框；控制器根据上述压电陶瓷银片同心度质量自动检测方法对各个压电陶瓷银片进行检测，根据检测结果判定良品的位置，然后发送信号到机械手，机械手开启对应的吸嘴吸取良品并输送到良品区，然后控制器控制检测托板旋转使剩下的废品落入废品框。A device for realizing the above-mentioned automatic detection method for the concentricity quality of piezoelectric ceramic silver sheets, including a controller, a workbench, a camera device, a detection support plate and a manipulator. The controller is connected to the camera device and the manipulator respectively. There is a device on the workbench. There is a detection area, the detection pallet is set in the detection area, and the camera device is fixed above the detection pallet; during detection, the silver-plated side of the piezoelectric ceramic silver sheet to be detected faces upward and is placed on the detection surface in a certain arrangement. On the pallet, the color of the detection pallet is close to the color of the silver-plated area of the piezoelectric ceramic silver sheet; the end of the manipulator is a suction cup. According to the arrangement of the piezoelectric ceramic silver pieces to be detected on the detection pallet, press the same button on the suction cup. Several suction nozzles are arranged in an arrangement; a good product area is provided on one side of the detection area, the detection pallet can rotate under the control of the controller, and a waste frame is provided on the lower side of the rotation direction of the detection pallet; the controller operates according to the above pressure The automatic detection method for the concentricity quality of electric ceramic silver sheets detects each piezoelectric ceramic silver sheet, determines the location of the good product based on the detection results, and then sends a signal to the manipulator. The manipulator opens the corresponding nozzle to suck the good product and transport it to the good product area, and then controls The controller controls the rotation of the detection pallet so that the remaining scrap falls into the scrap frame.
本发明与现有技术相比，具有如下优点和有益效果：Compared with the existing technology, the present invention has the following advantages and beneficial effects:
(1)本发明仅需一个CCD摄像头便可完成同心度的测量，无需其他传感器。(1) The present invention only needs one CCD camera to complete the concentricity measurement without the need for other sensors.
(2)本发明能够自动将压电陶瓷银片的内圆和外圆轮廓分开，能够很好的解决当压电陶瓷银片比较小时，用传统算法中会使内圆、外圆混合在一起，无法正确区分的难题。(2) The present invention can automatically separate the inner circle and outer circle contours of the piezoelectric ceramic silver sheet, and can well solve the problem that when the piezoelectric ceramic silver sheet is relatively small, the inner circle and the outer circle will be mixed together using the traditional algorithm. , a difficult problem that cannot be distinguished correctly.
(3)本发明通过对已经分开的内外圆轮廓进行圆拟合来确定圆心和半径，无需调整参数便可自动测量不同尺寸的压电陶瓷银片的同心度，适用范围广，操作简单。(3) The present invention determines the center and radius of the circle by performing circle fitting on the separated inner and outer circle contours, and can automatically measure the concentricity of piezoelectric ceramic silver sheets of different sizes without adjusting parameters. It has a wide range of applications and is simple to operate.
(4)本发明识别准确率高，能够大大提高自动化检测的程度，提高生产效率。(4) The present invention has high recognition accuracy, can greatly improve the degree of automated detection and improve production efficiency.
(5)本发明通过采用一具有吸盘的机械手，可以实现检测后对良品的抓取，同时检测托板在控制器控制下可旋转，从而实现良品和废品的自动筛选，具有效率高的优点。(5) The present invention uses a manipulator with a suction cup to capture good products after detection. At the same time, the detection pallet can rotate under the control of the controller, thereby realizing automatic screening of good products and waste products, and has the advantage of high efficiency.
附图说明Description of drawings
图1为本实施例压电陶瓷银片同心度质量自动检测装置的系统组成示意图。Figure 1 is a schematic diagram of the system composition of the automatic concentricity quality detection device for piezoelectric ceramic silver sheets in this embodiment.
图2为本实施例自动测量同心度的工作流程图。Figure 2 is a workflow diagram for automatically measuring concentricity in this embodiment.
图3是本实施例同心度检测的算法流程图。Figure 3 is a flow chart of the algorithm for concentricity detection in this embodiment.
图4是本实施例同心度检测算法中检测外轮廓的流程图。Figure 4 is a flow chart for detecting the outer contour in the concentricity detection algorithm of this embodiment.
图5是本实施例同心度检测算法中检测内轮廓的流程图。Figure 5 is a flow chart for detecting inner contours in the concentricity detection algorithm of this embodiment.
图6是本实施例方法中压电陶瓷银片的原图、高斯滤波结果图和形态学滤波结果图。Figure 6 is the original image, Gaussian filtering result image and morphological filtering result image of the piezoelectric ceramic silver sheet in the method of this embodiment.
具体实施方式Detailed ways
下面结合实施例及附图对本发明作进一步详细的描述，但本发明的实施方式不限于此。The present invention will be described in further detail below with reference to the examples and drawings, but the implementation of the present invention is not limited thereto.
实施例1Example 1
如图1所示，本实施例一种压电陶瓷银片同心度质量自动检测装置，包括PC机1、摄像头2、工作台3、检测托板4、良品区5、废品框6、机械手7。摄像头2设置在检测托板4的上方，具体高度可根据摄像头的参数、待检测压电陶瓷银片的大小等因素综合考虑设定，例如可设置为30-50cm。PC机1通过有线或无线的方式分别与摄像头2和机械手7信号连接，用于接收摄像头2拍摄的图像，基于图像处理的方式对当前图像中的压电陶瓷银片同心度进行质量检测，根据质量检测结果判定良品的位置，然后发送信号到机械手2，机械手2开启对应的吸嘴将良品吸取输送的良品区5，剩下的废品则落入废品框6。As shown in Figure 1, this embodiment is an automatic detection device for the concentricity quality of piezoelectric ceramic silver sheets, including a PC 1, a camera 2, a workbench 3, a detection pallet 4, a good product area 5, a waste frame 6, and a manipulator 7 . The camera 2 is arranged above the detection support plate 4. The specific height can be set according to the parameters of the camera, the size of the piezoelectric ceramic silver piece to be detected and other factors. For example, it can be set to 30-50cm. The PC 1 is connected to the camera 2 and the manipulator 7 via wired or wireless signals respectively, and is used to receive the image captured by the camera 2, and perform quality inspection on the concentricity of the piezoelectric ceramic silver sheet in the current image based on image processing. The quality inspection results determine the location of the good products, and then send a signal to the robot 2. The robot 2 opens the corresponding suction nozzle to suck and transport the good products to the good product area 5, and the remaining waste products fall into the waste box 6.
本实施例中，在工作台3一侧设有一滑轨，良品区5、废品框6分别设置在工作台3的两端，机械手7沿着滑轨在检测托板4和良品区5之间滑动，在摄像头2进行拍摄时，机械手2停在良品区5上方。检测托板4的一侧固定在一旋转轴上，该旋转轴由一驱动电机控制，驱动电机与PC机1相连。在需要将检测托板上的废品去掉时，通过PC机1发送信号到驱动电机，驱动电机驱动旋转轴旋转，进而带动检测托板4旋转，废品框6设置在检测托板4旋转方向的下侧，因此废品自动落入废品框6。In this embodiment, a slide rail is provided on one side of the workbench 3. The good product area 5 and the waste product frame 6 are respectively arranged at both ends of the workbench 3. The manipulator 7 is along the slide rail between the detection pallet 4 and the good product area 5. Sliding, when the camera 2 is shooting, the manipulator 2 stops above the good product area 5. One side of the detection support plate 4 is fixed on a rotating shaft, which is controlled by a driving motor, and the driving motor is connected to the PC 1 . When it is necessary to remove the waste products on the detection pallet, a signal is sent to the drive motor through the PC 1, and the drive motor drives the rotating shaft to rotate, which in turn drives the detection pallet 4 to rotate. The waste frame 6 is arranged under the rotation direction of the detection pallet 4. side, so the scrap automatically falls into scrap box 6.
为了便于吸取良品，检测托板4上待检测的压电陶瓷银片镀银面朝上，等间距地平放在检测托板4上，间距在5-8mm之间，具体也可根据待检测的压电陶瓷银片的尺寸、检测区以及检测托板的大小进行适应性调整。机械手7吸盘上吸嘴的排布方式与之相同。且检测托板4采用银色平板，颜色与压电陶瓷银片镀银区域的颜色接近。从而便于后续的图像检测。In order to facilitate the collection of good products, the silver-plated piezoelectric ceramic silver sheets to be tested on the detection pallet 4 are placed flatly on the detection pallet 4 at equal intervals, with the spacing between 5-8mm. The size of the piezoelectric ceramic silver piece, the detection area and the size of the detection support plate are adaptively adjusted. The arrangement of the suction nozzles on the suction cup of manipulator 7 is the same. And the detection support plate 4 is made of a silver flat plate, and its color is close to the color of the silver-plated area of the piezoelectric ceramic silver sheet. This facilitates subsequent image detection.
另外，为了更进一步提高效率，将待检测的压电陶瓷银片放置到检测托板上这一过程，同样可采用机械手辅助上料装置实现，这一装置可直接采用现有的机械手装置，这里不再赘述。In addition, in order to further improve efficiency, the process of placing the piezoelectric ceramic silver sheets to be tested on the testing pallet can also be implemented using a robot-assisted loading device. This device can directly use the existing robot device. Here No longer.
同样的，为了提高装置的使用便捷性，本实施例在PC机1处还设有人机交互设备，该人机交互设备包括用户输入设备和显示设备，可以直接采用现有的键盘、触摸屏、显示屏等设备，从而可实现信息的输入和对外输出，这里输入的信息包括但不限于当前待检测压电陶瓷银片的型号、各种缺陷检测必须的预设值等，输出的信息包括但不限于当前采集的检测托板的图像、检测识别的过程图以及结果图，以及良品率、缺陷类型等信息。具体可根据实际应用，由操作者自主设定，这里不再赘述。Similarly, in order to improve the convenience of use of the device, this embodiment is also provided with a human-computer interaction device at the PC 1. The human-computer interaction device includes a user input device and a display device. The existing keyboard, touch screen, and display device can be directly used. Screens and other equipment can realize the input and external output of information. The information input here includes but is not limited to the model of the piezoelectric ceramic silver sheet currently to be detected, the preset values necessary for various defect detection, etc. The output information includes but is not limited to It is limited to the currently collected images of the inspection pallet, inspection and identification process diagrams and result diagrams, as well as information such as yield rate and defect type. The details can be set independently by the operator according to the actual application, and will not be described again here.
如图2所示，上述装置实现的压电陶瓷银片同心度质量自动检测方法，包括如下步骤：As shown in Figure 2, the automatic detection method for the concentricity quality of piezoelectric ceramic silver sheets implemented by the above device includes the following steps:
(1)系统初始化，检查摄像头与PC机的连接、摄像头驱动软件的安装；检查机械手是否置于良品区；(1) System initialization, check the connection between the camera and the PC, and the installation of the camera driver software; check whether the manipulator is placed in the good product area;
(2)将压电陶瓷银片镀银面朝上，等间距地平放在检测托板上，间距可为5-8mm；(2) Place the piezoelectric ceramic silver sheet with the silver-plated side facing up and place it flatly on the detection pallet at equal intervals. The spacing can be 5-8mm;
(3)根据产品型号设置良品和不合格品的同心度检测阈值；(3) Set the concentricity detection threshold for good and defective products according to the product model;
(4)摄像头将检测托板上的全部压电陶瓷银片拍摄为一张图像，记为原始图像，传送至PC机内存中；(4) The camera captures all the piezoelectric ceramic silver pieces on the detection pallet as one image, records it as the original image, and transmits it to the PC memory;
(5)测所述图像中各压电陶瓷银片的同心度值；(5) Measure the concentricity value of each piezoelectric ceramic silver piece in the image;
(6)将所述步骤(5)中测得的各压电陶瓷银片的同心度值逐一与所述步骤(3)中设定的阈值比较，判断各压电陶瓷银片属于良品还是不合格品，存储判断结果；(6) Compare the concentricity values of each piezoelectric ceramic silver sheet measured in step (5) one by one with the threshold set in step (3) to determine whether each piezoelectric ceramic silver sheet is a good product or not. Qualified products, store the judgment results;
(7)PC机控制机械手吸取所有良品压电陶瓷银片，送至良品区；(7) The PC controls the manipulator to pick up all the good-quality piezoelectric ceramic silver pieces and send them to the good-quality area;
(8)侧倾检测托板，使不合格品滑落至废品框。(8) Tilt the detection pallet to make the unqualified products slide to the waste frame.
在实际应用中，为了便于进行后续的图像处理，在更换检测托板时需要先判断当前检测托板的颜色与压电陶瓷镀银区域的颜色是否接近，具体方法是：在检测托板的中央放置一个压电陶瓷银片，用摄像头采集一幅图像，通过霍夫变换定位压电陶瓷银片的圆心和外圆直径，统计位于外圆内的所有像素点的灰度平均值作为压电陶瓷银片的灰度平均值；由所述外圆开始向外扩大50个像素得到一个环状的背景区域，统计该背景区域内的灰度平均值，并将其和压电陶瓷银片的灰度平均值进行比较，当二者灰度之差在30-50范围内时，认定检测托板的颜色和压电陶瓷镀银区域的颜色接近。In practical applications, in order to facilitate subsequent image processing, when replacing the detection pallet, it is necessary to first determine whether the color of the current detection pallet is close to the color of the piezoelectric ceramic silver-plated area. The specific method is: in the center of the detection pallet Place a piezoelectric ceramic silver piece, collect an image with a camera, locate the circle center and outer circle diameter of the piezoelectric ceramic silver piece through Hough transform, and count the grayscale average of all pixels located within the outer circle as the piezoelectric ceramic The average gray level of the silver sheet; expand 50 pixels outward from the outer circle to obtain a ring-shaped background area, count the average gray level in the background area, and compare it with the gray level of the piezoelectric ceramic silver sheet. Compare the average values of the two. When the difference in gray scale between the two is within the range of 30-50, it is determined that the color of the detection support plate is close to the color of the silver-plated area of the piezoelectric ceramic.
所述步骤(5)还包括如下步骤，见图3：The step (5) also includes the following steps, see Figure 3:
(5-1)提取原始图像中待检测压电陶瓷银片的外轮廓点集，进行圆拟合得到拟合外圆，计算拟合外圆的圆心和半径；(5-1) Extract the outer contour point set of the piezoelectric ceramic silver sheet to be detected in the original image, perform circle fitting to obtain the fitted outer circle, and calculate the center and radius of the fitted outer circle;
(5-2)提取原始图像中待检测压电陶瓷银片的内轮廓点集，进行圆拟合得到拟合内圆，计算拟合内圆的圆心和半径；(5-2) Extract the inner contour point set of the piezoelectric ceramic silver sheet to be detected in the original image, perform circle fitting to obtain the fitted inner circle, and calculate the center and radius of the fitted inner circle;
(5-3)计算内外圆的同心度，如果同心度大于预设的阈值，则判定当前待检测的压电陶瓷银片为良品，否则为废品，计算内外圆的同心度c的公式为：(5-3) Calculate the concentricity of the inner and outer circles. If the concentricity is greater than the preset threshold, the piezoelectric ceramic silver sheet currently to be detected is judged to be a good product, otherwise it is a waste product. The formula for calculating the concentricity c of the inner and outer circles is:
c＝1-((x1-x2)2+(y1-y2)2)/(R-r)2 c＝1-((x1-x2) 2 +(y1-y2) 2 )/(Rr) 2
其中(x1,y1)是外圆圆心，R是外圆半径，(x2,y2)是内圆圆心，r是内圆半径，同心度c的值域为[0,1]。Among them (x1, y1) is the center of the outer circle, R is the radius of the outer circle, (x2, y2) is the center of the inner circle, r is the radius of the inner circle, and the value range of concentricity c is [0,1].
参见图4，步骤(5-1)求外圆参数的具体步骤如下：Referring to Figure 4, the specific steps for finding the outer circle parameters in step (5-1) are as follows:
(5-1-1)对原始图像进行高斯平滑。(5-1-1) Perform Gaussian smoothing on the original image.
(5-1-2)用canny边缘检测算法检测平滑后图像的边缘。(5-1-2) Use canny edge detection algorithm to detect the edges of the smoothed image.
(5-1-3)用拓扑原理和边缘跟踪法检测各压电陶瓷银片外轮廓点集。(5-1-3) Use topological principles and edge tracking methods to detect the outer contour point set of each piezoelectric ceramic silver sheet.
本实施例设定检测托板上按照5×5的排布方式一次放置25个待检测的压电陶瓷银片，在进行检测时，先根据压电陶瓷银片中心坐标从左到右和从上到下的排列规律，确定每个待检测的压电陶瓷银片位置。In this embodiment, 25 piezoelectric ceramic silver pieces to be tested are placed on the detection pallet in a 5×5 arrangement at a time. During detection, first from left to right and from left to right according to the center coordinates of the piezoelectric ceramic silver pieces. The arrangement pattern from top to bottom determines the position of each piezoelectric ceramic silver piece to be detected.
作为一种方案，在工作条件理想情况下，在每个待检测的压电陶瓷银片区域，采用逐行逐列扫描步骤(5-1-2)边缘检测后的二值图像，搜索到的第一条像素值由0变为1的边界即为外轮廓。这种方法实现简单，计算复杂度低，但对实验环境要求较高。As a solution, under ideal working conditions, in each piezoelectric ceramic silver sheet area to be detected, use the binary image after edge detection in the row-by-row and column-by-column scanning steps (5-1-2), and the searched The first boundary where the pixel value changes from 0 to 1 is the outer contour. This method is simple to implement and has low computational complexity, but has high requirements on the experimental environment.
作为另一种方案，在考虑噪声点的情况下，利用压电陶瓷银片的外轮廓点集所包围区域的面积大于噪声的外轮廓点集所包围区域的面积特点，可以提取边缘检测后所得图像中的所有边缘，计算每一条边缘所包围区域的面积，按照面积由大至小进行排序，将面积最大的25条边缘对应的点集选定为待测的25个压电陶瓷银片的外轮廓点集。这种方法对实验环境要求低。As another solution, when considering noise points, the area surrounded by the outer contour point set of the piezoelectric ceramic silver sheet is larger than the area surrounded by the noise outer contour point set, and the obtained results after edge detection can be extracted. For all edges in the image, calculate the area of the area surrounded by each edge, sort them from large to small, and select the point sets corresponding to the 25 edges with the largest areas as the 25 piezoelectric ceramic silver sheets to be tested. Outline point set. This method has low requirements on the experimental environment.
(5-1-4)将所述步骤(5-1-3)得到的各外轮廓点集进行基于二次曲线的圆拟合，得到各压电陶瓷银片的拟合外圆。(5-1-4) Perform circle fitting based on quadratic curves on each outer contour point set obtained in step (5-1-3) to obtain the fitted outer circle of each piezoelectric ceramic silver sheet.
(5-1-5)计算所述步骤(5-1-4)得到的各拟合外圆的圆心和半径，定为各压电陶瓷银片外圆的圆心和半径。(5-1-5) Calculate the center and radius of each fitted outer circle obtained in the step (5-1-4), and set them as the center and radius of the outer circle of each piezoelectric ceramic silver sheet.
参见图5，步骤(5-2)求内圆参数的具体步骤如下：Referring to Figure 5, the specific steps for finding the inner circle parameters in step (5-2) are as follows:
(5-2-1)对原始图像进行高斯平滑。(5-2-1) Perform Gaussian smoothing on the original image.
(5-2-2)利用检测托板的颜色与压电陶瓷银片镀银区域的颜色接近的特点，采用一矩形内核对平滑后图像进行形态学闭运算，使得图像中仅保留压电陶瓷银片镀银区域。见图6，其中第一行为原图，第二行为高斯滤波结果图，第三行为形态学闭运算后结果图。(5-2-2) Taking advantage of the fact that the color of the detection support plate is close to the color of the silver-plated area of the piezoelectric ceramic silver sheet, a rectangular kernel is used to perform morphological closing operation on the smoothed image, so that only the piezoelectric ceramic remains in the image. Silver plated areas. See Figure 6, where the first line is the original image, the second line is the Gaussian filtering result image, and the third line is the result image after morphological closing operation.
(5-2-3)用canny边缘检测算法对形态学闭运算后的图像进行边缘检测。(5-2-3) Use canny edge detection algorithm to perform edge detection on the image after morphological closure operation.
(5-2-4)用拓扑原理和边缘跟踪法检测各压电陶瓷银片镀银区域的轮廓点集。(5-2-4) Use topological principles and edge tracking methods to detect the contour point set of the silver-plated area of each piezoelectric ceramic silver sheet.
同样的，为了避免噪声影响，利用压电陶瓷银片的内轮廓点集所包围区域的面积大于噪声的内轮廓点集所包围区域的面积特点，可以提取边缘检测后所得图像中的所有边缘，计算每一条边缘所包围区域的面积，按照面积由大至小进行排序，将面积最大的25条边缘对应的点集选定为待测的25个压电陶瓷银片的内轮廓点集。这种方法对实验环境要求低。Similarly, in order to avoid the influence of noise, all edges in the image obtained after edge detection can be extracted by taking advantage of the feature that the area surrounded by the inner contour point set of the piezoelectric ceramic silver sheet is larger than the area surrounded by the noise inner contour point set. Calculate the area of the area surrounded by each edge, sort them from large to small, and select the point sets corresponding to the 25 edges with the largest areas as the inner contour point sets of the 25 piezoelectric ceramic silver sheets to be measured. This method has low requirements on the experimental environment.
(5-2-5)将所述步骤(5-2-4)得到的各内轮廓点集进行基于二次曲线的圆拟合，得到各压电陶瓷银片镀银区域的拟合圆；(5-2-5) Perform circle fitting based on quadratic curves on each inner contour point set obtained in step (5-2-4) to obtain a fitting circle for the silver-plated area of each piezoelectric ceramic silver sheet;
(5-2-6)计算所述各镀银区域的拟合圆的圆心和半径定为各压电陶瓷银片内圆的圆心和半径。(5-2-6) Calculate the center and radius of the fitting circle of each silver-plated area and set it as the center and radius of the inner circle of each piezoelectric ceramic silver sheet.
上述实施例为本发明较佳的实施方式，但本发明的实施方式并不受上述实施例的限制，其他的任何未背离本发明的精神实质与原理下所作的改变、修饰、替代、组合、简化，均应为等效的置换方式，都包含在本发明的保护范围之内。The above embodiments are preferred embodiments of the present invention, but the embodiments of the present invention are not limited to the above embodiments. Any other changes, modifications, substitutions, combinations, etc. may be made without departing from the spirit and principles of the present invention. All simplifications should be equivalent substitutions, and are all included in the protection scope of the present invention.
Claims (5)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710141152.7A CN107101598B (en) | 2017-03-10 | 2017-03-10 | An automatic detection method and device for concentricity quality of piezoelectric ceramic silver sheets |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710141152.7A CN107101598B (en) | 2017-03-10 | 2017-03-10 | An automatic detection method and device for concentricity quality of piezoelectric ceramic silver sheets |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107101598A CN107101598A (en) | 2017-08-29 |
| CN107101598B true CN107101598B (en) | 2023-11-03 |
Family
ID=59675766
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710141152.7A Expired - Fee Related CN107101598B (en) | 2017-03-10 | 2017-03-10 | An automatic detection method and device for concentricity quality of piezoelectric ceramic silver sheets |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107101598B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108594104B (en) * | 2018-04-17 | 2020-08-11 | 中广核工程有限公司 | Fault detection method and system for rotating diode of brushless exciter |
| CN110017802B (en) * | 2019-04-29 | 2021-03-30 | 合肥旺和电子科技有限公司 | Instrument for detecting assembly precision of coaxial parts |
| CN111174734A (en) * | 2019-12-11 | 2020-05-19 | 武汉一本光电有限公司 | High-precision ccd coaxial recognition system |
| CN111521144B (en) * | 2020-05-13 | 2024-06-25 | 山西汾西重工有限责任公司 | Concentricity processing method and system |
| CN111707220A (en) * | 2020-06-09 | 2020-09-25 | 南京鲲途机电科技有限公司 | Concentricity alignment recognition vision system |
| CN113819859B (en) * | 2020-06-18 | 2024-03-26 | 上海泰胜(东台)电力工程机械有限公司 | Concentricity detection method for tower folding structure |
| CN111860484B (en) * | 2020-07-22 | 2023-11-03 | 腾讯科技（深圳）有限公司 | Region labeling method, device, equipment and storage medium |
| CN113870216B (en) * | 2021-09-27 | 2025-06-13 | 中国电子科技集团公司第四十一研究所 | A method for detecting foreign matter at the bottom of a packaging hose |
| CN117970055B (en) * | 2024-02-08 | 2024-11-05 | 北京新雨华祺科技有限公司 | High-voltage testing system for environment-friendly ceramic silver-plated pore plate |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0000259A1 (en) * | 1977-06-23 | 1979-01-10 | Europäische Atomgemeinschaft (Euratom) | Process and apparatus for the alignment of a transducer forming part of a radiation generator |
| US5335298A (en) * | 1991-08-19 | 1994-08-02 | The United States Of America As Represented By The Secretary Of The Army | Automated extraction of airport runway patterns from radar imagery |
| JP2002318195A (en) * | 2001-04-19 | 2002-10-31 | Murata Mfg Co Ltd | External appearance inspection method and external appearance inspection device |
| US6489705B1 (en) * | 2001-06-26 | 2002-12-03 | National Science Council Of Republic Of China | Thin-disc piezoelectric actuating ultrasonic motor |
| JP2003303342A (en) * | 2002-04-10 | 2003-10-24 | Tateyama Machine Kk | Method and apparatus for detecting reference position of annular image by omnidirectional imaging |
| CN101699217A (en) * | 2009-11-03 | 2010-04-28 | 武汉大学 | Method used for detecting concentric circle of industrial part |
| CN102353349A (en) * | 2011-09-30 | 2012-02-15 | 广东工业大学 | Machine vision based micro-sound film concentricity online testing system and testing method |
| CN103439337A (en) * | 2013-08-29 | 2013-12-11 | 华南理工大学 | Automatic detection device and method for apparent defects of piezoelectric ceramic buzzers |
| CN105335976A (en) * | 2015-10-23 | 2016-02-17 | 广州视睿电子科技有限公司 | Image processing method and device |
| CN105469046A (en) * | 2015-11-23 | 2016-04-06 | 电子科技大学 | Vehicle model identification method based on PCA and SURF characteristic cascade |
| CN105930791A (en) * | 2016-04-19 | 2016-09-07 | 重庆邮电大学 | Road traffic sign identification method with multiple-camera integration based on DS evidence theory |
-
2017
- 2017-03-10 CN CN201710141152.7A patent/CN107101598B/en not_active Expired - Fee Related
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0000259A1 (en) * | 1977-06-23 | 1979-01-10 | Europäische Atomgemeinschaft (Euratom) | Process and apparatus for the alignment of a transducer forming part of a radiation generator |
| US5335298A (en) * | 1991-08-19 | 1994-08-02 | The United States Of America As Represented By The Secretary Of The Army | Automated extraction of airport runway patterns from radar imagery |
| JP2002318195A (en) * | 2001-04-19 | 2002-10-31 | Murata Mfg Co Ltd | External appearance inspection method and external appearance inspection device |
| US6489705B1 (en) * | 2001-06-26 | 2002-12-03 | National Science Council Of Republic Of China | Thin-disc piezoelectric actuating ultrasonic motor |
| JP2003303342A (en) * | 2002-04-10 | 2003-10-24 | Tateyama Machine Kk | Method and apparatus for detecting reference position of annular image by omnidirectional imaging |
| CN101699217A (en) * | 2009-11-03 | 2010-04-28 | 武汉大学 | Method used for detecting concentric circle of industrial part |
| CN102353349A (en) * | 2011-09-30 | 2012-02-15 | 广东工业大学 | Machine vision based micro-sound film concentricity online testing system and testing method |
| CN103439337A (en) * | 2013-08-29 | 2013-12-11 | 华南理工大学 | Automatic detection device and method for apparent defects of piezoelectric ceramic buzzers |
| CN105335976A (en) * | 2015-10-23 | 2016-02-17 | 广州视睿电子科技有限公司 | Image processing method and device |
| CN105469046A (en) * | 2015-11-23 | 2016-04-06 | 电子科技大学 | Vehicle model identification method based on PCA and SURF characteristic cascade |
| CN105930791A (en) * | 2016-04-19 | 2016-09-07 | 重庆邮电大学 | Road traffic sign identification method with multiple-camera integration based on DS evidence theory |
Non-Patent Citations (3)
| Title |
|---|
| 基于机器视觉的小型元器件同心度测量仪的设计;林奇鸿等;《传感器与仪器仪表》;20091231;第25卷(第11-1期);第117-118、142页 * |
| 杨帆等.《数字图像处理与分析》.北京航空航天大学出版社,2007,第45-46页. * |
| 林奇鸿等.基于机器视觉的小型元器件同心度测量仪的设计.《传感器与仪器仪表》.2009,第25卷(第11-1期),第117-118、142页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107101598A (en) | 2017-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107101598B (en) | An automatic detection method and device for concentricity quality of piezoelectric ceramic silver sheets | |
| CN109772733B (en) | A vision-based defective bamboo block detection and sorting device and method | |
| CN109884070B (en) | A machine vision-based defect detection method for aluminum-aluminum blister packaging tablets | |
| CN109115785B (en) | Casting polishing quality detection method and device and use method thereof | |
| CN109785317B (en) | Automatic pile up neatly truss robot's vision system | |
| CN103499585B (en) | Based on noncontinuity lithium battery film defect inspection method and the device thereof of machine vision | |
| CN108896547A (en) | Refractory brick measuring system based on machine vision | |
| CN105044114B (en) | A kind of electrolytic capacitor appearance packaging defect image detecting system and method | |
| CN108416809B (en) | Steel drum threaded cap pose recognition method based on machine vision | |
| CN107876425A (en) | A kind of bearing defect detecting system device of view-based access control model | |
| CN107203990A (en) | A kind of labeling damage testing method based on template matches and image quality measure | |
| CN107402221A (en) | A kind of defects of display panel recognition methods and system based on machine vision | |
| CN108662977A (en) | A kind of refractory brick geometric dimension measurement method | |
| CN105865329B (en) | The acquisition system and method for the bundled round steel end face center coordinate of view-based access control model | |
| CN106370671A (en) | PCB (printed circuit board) component detection system and method based on machine vision | |
| CN110108712A (en) | Multifunctional visual defect detection system | |
| CN108355987A (en) | A kind of screen printing of battery quality determining method based on piecemeal template matches | |
| CN102680494B (en) | Based on arcuation face, the polishing metal flaw real-time detection method of machine vision | |
| CN108596873A (en) | The recognition methods of refractory brick deep defects based on height histogram divion | |
| CN117132655B (en) | Filling barrel opening position measuring method based on machine vision | |
| CN102496161A (en) | Method for extracting contour of image of printed circuit board (PCB) | |
| CN110108724A (en) | Strip-shaped workpiece visual detection system | |
| CN108550138A (en) | Refractory brick surface scratch recognition methods based on frequency filtering enhancing | |
| CN104952754B (en) | Sorting method of coated silicon wafers based on machine vision | |
| CN114943704A (en) | Method, device and equipment for detecting defects of battery electrode die-cut piece |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20231103 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |