CN109741303B - Filter stick counting method and device based on image acquisition and recognition - Google Patents
Filter stick counting method and device based on image acquisition and recognition Download PDFInfo
- Publication number
- CN109741303B CN109741303B CN201811592070.5A CN201811592070A CN109741303B CN 109741303 B CN109741303 B CN 109741303B CN 201811592070 A CN201811592070 A CN 201811592070A CN 109741303 B CN109741303 B CN 109741303B
- Authority
- CN
- China
- Prior art keywords
- filter stick
- filter
- drawing structure
- image
- camera
- 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.)
- Active
Links
Images
Landscapes
- Image Input (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a filter stick counting method and device based on image acquisition and recognition, which comprises the following steps: the device comprises a movable box body, wherein a UPS for supplying power to an imaging light supplement lamp and a camera is arranged at the bottom of the box body; the box body comprises a drawer type first drawing structure for fixing the camera and a drawer type second drawing structure for bearing the filter stick plastic lattices, wherein the drawing directions of the first drawing structure and the second drawing structure are parallel; the drawer also comprises a storage drawer with the drawing direction orthogonal to that of the first drawing structure; an imaging light supplement lamp and a camera are also arranged in the box body; and the notebook computer is in communication connection with the camera, receives the filter stick image, sequentially performs filtering and denoising, image binarization, morphological processing and counting analysis on the filter stick image, and obtains and outputs the number of the filter sticks. The filter stick counting device improves the definition and the regularity of collected images, so that the accuracy of filter stick counting is improved.
Description
Technical Field
The invention relates to the field of counting, in particular to a filter stick counting method and device based on image acquisition and recognition.
Background
The cigarette filter stick is a filter layer for preventing harmful components such as coal tar, nicotine and the like generated in the burning process of cigarettes from entering a human body, and can effectively reduce the harmful components generated in smoking from entering the human body. The filter stick is used as an important component of a cigarette material 'three paper one stick', and has important influence on the quality of cigarettes. And the filter stick is transported by adopting plastic grids as storage carriers in the logistics process. And for the filter stick, the produced filter stick is separately packaged in a plastic grid at the HCF part of the forming machine, the on-duty production capacity is counted according to the number of plastic grid discs when the workshop carries out production statistics, and each disc is converted according to 4550 filter sticks.
In the actual production process, the difference between the number of filter sticks in each tray of plastic lattices and the number of standard trays is often existed. Workshop production management wants to master the filter rod count that every board produced more difficultly accurately, can only carry out the manual sampling to the full dish filter rod of board production at present, then carry out the difference of manual count mode statistics production filter rod dish and standard dish to guarantee that the full dish filter rod of board production is unanimous as far as possible with the quantity of standard dish. However, the manual counting mode has the problems of long manual counting time, low efficiency, high possibility of error, repeated return to and from the field production machine and the forming inspection room, and specification error caused by returning the sampled filter stick to other machines.
With the development of the computer vision field, in order to better count the filter rods, an image recognition method is adopted, such as a cigarette filter rod on-line counting and quality detection method based on machine vision disclosed in the patent application with the application publication number of CN 104537671a, and a cigarette filter rod counting system for boxing based on a line scanning camera disclosed in the patent application with the application publication number of CN 104574398A. However, the blurring and distortion of the images acquired by the two modes affect the characteristic extraction of the filter stick, so that the problem of inaccurate counting of the filter stick is caused.
Disclosure of Invention
The invention aims to provide a filter stick counting method and device based on image acquisition and identification, which improve the definition and regularity of acquired images, provide guarantee for identifying filter sticks by subsequent images and improve the accuracy of filter stick counting.
In order to achieve the purpose, the invention provides the following technical scheme:
a filter stick counting method based on image acquisition and recognition comprises the following steps:
the device comprises a movable box body, wherein a UPS for supplying power to an imaging light supplement lamp and a camera is arranged at the bottom of the box body; the box body comprises a drawer type first drawing structure for fixing the camera and a drawer type second drawing structure for bearing the filter stick plastic lattices, wherein the drawing directions of the first drawing structure and the second drawing structure are parallel; the drawer also comprises a storage drawer with the drawing direction orthogonal to that of the first drawing structure; an imaging light supplement lamp and a camera are also arranged in the box body;
the notebook computer is placed on the top surface of the box body and is in communication connection with the camera;
the filter stick counting method comprises the following steps:
the second drawing structure is drawn out to bear the filter stick plastic lattices to be counted and filled with filter sticks;
according to the size of the filter stick plastic lattice, the first drawing structure is drawn out to the optimal imaging focal distance position of the filter stick plastic lattice;
the notebook computer controls the camera to shoot the filter stick and receives the filter stick image shot by the camera;
and the notebook computer carries out filtering and denoising, image binarization, morphological processing and counting analysis on the received filter stick image in sequence to obtain the number of the filter sticks and output the number.
A filter stick counting device based on image acquisition and recognition comprises:
the device comprises a movable box body, wherein a UPS for supplying power to an imaging light supplement lamp and a camera is arranged at the bottom of the box body; the box body comprises a drawer type first drawing structure for fixing the camera and a drawer type second drawing structure for bearing the filter stick plastic lattices, wherein the drawing directions of the first drawing structure and the second drawing structure are parallel; the drawer also comprises a storage drawer with the drawing direction orthogonal to that of the first drawing structure; an imaging light supplement lamp and a camera are also arranged in the box body;
the notebook computer is placed on the top surface of the box body and is in communication connection with the camera, the camera is controlled to shoot the filter rods, the filter rod images shot by the camera are received, then the filter rods are counted, and specifically, the filter rod images are sequentially subjected to filtering denoising, image binarization, morphological processing and counting analysis to obtain the number of the filter rods and output.
Compared with the prior art, the invention has the beneficial effects that:
the filter stick counting device can provide an even and high-intensity illumination environment for shooting filter stick images, the camera and the filter stick plastic lattices are arranged oppositely, the distance between the filter stick plastic lattices and the camera is adjusted according to the size of the filter stick plastic lattices to obtain the focal length of perfect imaging of the filter stick plastic lattices, and then the filter stick images with high definition and regularity are obtained, and the notebook computer identifies and counts the obtained filter stick images to obtain the number of accurate filter sticks.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 and 2 are schematic structural diagrams of a filter stick counting device based on image acquisition and recognition provided by embodiment 1;
figure 3 is a side view of the filter rod counting device provided in example 2 based on image acquisition and identification.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the detailed description and specific examples, while indicating the scope of the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention.
Example 1
As shown in fig. 1 and 2, the filter rod counting device based on image acquisition and recognition provided by embodiment 1 comprises a movable box 100 and a notebook computer placed on the top surface of the box 100.
The lower half of box 100 is one and deposits the cavity, has placed UPS (Uninterruptable Power System) on the bottom, and this UPS provides external power source interface as the power outward, and is internal for formation of image light filling lamp and camera power supply, and sustainable power supply is about 2 hours, satisfies the operation personnel and uses at the arbitrary board in workshop. The UPS increases the weight of the bottom of the vehicle body and enhances the stability of the whole vehicle. A drawing storage drawer 103 is also installed in the storage cavity and is mainly used for storing external power lines, notebook computers and other articles.
The upper half of the box 100 is an imaging cavity, and mainly includes a first drawer 101 for fixing the camera and a second drawer 102 for carrying the filter candle, wherein the drawing directions of the first drawer 101 and the second drawer 102 are parallel and orthogonal to the drawing direction of the storage drawer 103.
The first drawing structure 101 is a frame structure, and includes a front panel 1011, two triangular side frames 1012, and a first cross bar 1013 connecting the two side frames 1012, and a camera 107 for capturing a filter rod image is installed on an inner wall of the front panel 1011.
The second drawing structure 102 is a frame structure, and includes a front panel 1021, two side frames 1022 of a right trapezoid, and a second cross bar 1023 connecting the two side frames 1022, two side panels 1024 are fixed on the two side frames 1022 near the front panel, and the two side panels 1024 and the front panel 1021 form a containing cavity for bearing the filter candle plastic lattice. The accommodating cavity is suitable for accommodating filter sticks of various specifications in length. The two side panels 1024 are provided with clearance holes, which is beneficial to the ventilation of the filter stick.
The first drawer 101 is disposed opposite the second drawer 102 such that when closed, the angled surface of the triangular side frame 1012 abuts against the angled surface of the right angle trapezoidal side frame 1022. Such a structure is provided to facilitate the first drawing structure 101 and the second drawing structure 102 to be drawn out of the box body or to be closed respectively.
The first drawing structure 101, the second drawing structure 102 and the storage drawer 103 are drawn by linear guide rails. Specifically, the first drawing structure 101 slides back and forth by means of a linear guide 106 provided on the top of the cabinet 100. The second drawer 102 slides back and forth by means of linear guides 105 provided on the side walls of the cabinet 100. The storage drawer 103 slides back and forth by a linear guide provided on the bottom of the cabinet 100.
During operation, the first drawing structure 101 and the second drawing structure 102 slide outwards along the linear guide rail 106 and the linear guide rail 105 respectively, and the distance between the camera 107 and the filter stick plastic lattice accommodating cavity plastic lattice is increased, so that the focal length of perfect imaging of the filter stick plastic lattice is obtained, and a filter stick image with high definition and regularity is obtained.
In order to avoid the influence of an external light source on the image quality of the filter stick, an imaging light supplement lamp is further arranged in the imaging cavity of the box body 100. Specifically, a pair of parallel LED fill lights 108 and a pair of vertical LED fill lights 109 are provided through a bracket in a space near the front panel 1011 of the first pull structure 101. The two pairs are skillfully arranged on the bracket, so that the uniform illumination intensity of the shooting environment is improved, and the exposure time of the camera is also reduced.
A hand-push handle 104 forming an angle of 30 degrees with the side of the box 100 is fixed on the side of the box 100. The hand push handrail 104 adopts a seamless steel pipe of SPCC, the automatic cutting technology and the surface electroplating and brightening treatment are adopted, the appearance is attractive and elegant, the hand push handrail 104 and the car body are in an arc-shaped design of 30 degrees, the design of human engineering is met, and the use is light and labor-saving.
A pair of universal wheels 110 are mounted on one side, close to the hand-push handrail 104, of the bottom of the box 100, a pair of directional wheels 111 are mounted on one side, far away from the hand-push handrail, of the bottom of the box, wherein a fixing support is adopted as a support of the directional wheels 111, and a double-wave-disc double-track arc-shaped design is adopted as a support of the universal wheels 110, so that the flexibility of the box is guaranteed, the box is convenient to use on any machine table in a workshop, and the workshop production can be.
Specifically, the top surface of the box 100 is adhered with a non-slip mat to increase the friction between the notebook computer and the top surface of the box 100, so that the notebook computer is prevented from sliding off during the movement of the filter stick counting device.
The method for realizing the counting of the filter sticks by utilizing the filter stick counting device comprises the following steps:
the second drawing structure 102 is drawn out to bear the filter stick plastic lattices to be counted and filled with filter sticks;
according to the size of the filter stick plastic lattice, the first drawing structure 101 is drawn out to the optimal imaging focal distance position of the filter stick plastic lattice;
the notebook computer controls the camera 107 to shoot the filter stick and receives the filter stick image shot by the camera;
and the notebook computer carries out filtering and denoising, image binarization, morphological processing and counting analysis on the received filter stick image in sequence to obtain the number of the filter sticks and output the number.
The image collected by the camera contains noise due to the characteristics of the camera and the interference of light, random noise is eliminated by utilizing smooth filtering, and meanwhile, the effective edge contour is kept to the greatest extent.
Specifically, filtering denoising includes:
and filtering and denoising by adopting bilateral filtering, wherein during denoising, the diameter parameter is set to be the width occupied by a filter stick in an imaging picture, the SigmaColor is set to be 10, and the SigmaSpace is set to be 0.
The bilateral filtering can not only remove noise, but also play a role in edge protection. The imaging noise is represented by the gray difference of adjacent pixels being about 10, therefore, the SigmaColor is set to be 10, and the pixels meeting the distribution are fused into one pixel as much as possible. SigmaSpace is set to 0 in order to preserve the fine edges between the filter rods away from the center. Therefore, the influence of mutual adhesion of adjacent filter rods can be reduced in the subsequent treatment.
The filtering and denoising step can overcome the image blurring phenomenon caused by filtering by a domain averaging method, and can well protect the edge of the image, so that the aims of eliminating noise and keeping the edge can be fulfilled.
The cross section of the filter stick is distinguished from the background through image binarization operation, and on the premise of uniform illumination, the gray value of the cross section of the filter stick is similar and is greatly different from the background. Specifically, the image binarization comprises: and (3) adopting a histogram to count the pixel value of the denoised filter stick image, adopting a histogram double-peak method to select a middle pixel value as a segmentation threshold value, and carrying out binarization processing on the denoised filter stick image to segment the background and the filter stick.
And (3) adopting a histogram to count the pixel value of the denoised filter stick image, adopting a histogram double-peak method to select a middle pixel value as a segmentation threshold value, and carrying out binarization processing on the denoised filter stick image to segment the background and the filter stick.
The morphological method is to use structural elements of a certain shape to extract a corresponding shape in an image so as to achieve the purpose of image analysis and identification. As the adhesion condition among the filter sticks is complex and the adhesion is not completely the same, the circular elements, the square elements and the elliptical elements are repeatedly compared, and according to the shape characteristics of the filter sticks, the circular elements are found to be more beneficial to obtaining information such as the size, the shape, the connectivity, the direction and the like of a target. And finally, processing the adhesion problem among the filter sticks through opening operation.
Specifically, the morphological treatment comprises:
extracting a filter stick foreground interested region corresponding to the original image by using the filter stick mask obtained by binarization processing, setting a first morphological gradient size template to take 3, and performing first morphological gradient calculation on a filter stick foreground interested region picture to obtain a first gradient picture; setting a second morphological gradient size taking 5, and performing second morphological gradient calculation on the filter stick foreground region-of-interest picture to obtain a second gradient picture; carrying out weighted summation on the first gradient picture and the second gradient picture according to the weights of 0.5 and 0.5 to obtain a gradient image;
setting the size of the template to be 5, and performing morphological closed operation on the gradient image to obtain the final gradient image.
Through careful study and observation, the size of the gaps between the normal adjacent filter rods is 1-3, so that 3 templates with the morphological gradient are taken for the first time; to try to preserve the sticky edges, the second morphological gradient size was taken as 5. In order to allow the gradient edges to be closed, the template size is set to 5 when performing a morphological closing operation on the gradient image.
The counting analysis comprises the following steps:
processing the gradient picture after morphological processing by using a maximum between-class variance threshold (OTSU) method to obtain a reverse binary picture; then, performing distance transformation on the reverse binary image to obtain a centroid skeleton image; finally, carrying out extreme point detection on the centroid skeleton diagram to obtain an independent connected region;
aiming at the communicated areas, calculating the number of the single communicated areas to obtain the total number of the filter sticks, wherein each single communicated area is a filter stick;
aiming at the adhesion area, the number of the filter sticks can be obtained by dividing the area of the adhesion area by the area of a single communication area.
Specifically, the MaskSize size of the distance conversion is set to be the width size of one filter stick on the picture. The extreme point detection is also an extreme point around the size of the filter stick, and the size of the template is also set to be the width of the filter stick on the picture. This allows the gradient image to shrink inward from the edge into a region.
In this embodiment, this filter rod counting assembly can provide even, the higher illumination environment of intensity for shooting the filter rod image, and camera and filter rod mould check relative setting, moulds the size of check according to the filter rod, and the distance between check and the camera is moulded to the adjustment filter rod to obtain the filter rod and mould the focus that the check was perfectly imaged, and then obtain the higher filter rod image of definition and regularity, notebook computer carries out filtering and denoising, image binarization, morphological processing and count analysis according to the filter rod image to obtaining, obtains the filter rod number of accuracy.
Example 2
The filter stick counting device based on image acquisition and recognition provided by embodiment 2 is basically the same as that of embodiment 1, except that the box body is further provided with a sleeve rod type hand push handrail 301, one end of the hand push handrail 301 is fixedly connected with a front panel 1021 of the second drawing structure, as shown in fig. 3, when the second drawing structure 102 is drawn away, the hand push handrail 301 is driven to be drawn away, a contact point for originally supporting the hand push handrail is a supporting point of the hand push handrail 301, so that the whole hand push handrail 301 forms a lever structure, and the second drawing structure 102 is well supported and fixed, when the accommodating cavity bears a heavy plastic filter stick grid, the weight of the filter stick plastic is shared on the hand push handrail 301, the bearing weight of the slider of the linear slide rail 105 is reduced, the slider is prevented from being damaged, and the service life of the slider is prolonged.
The above-mentioned embodiments are intended to illustrate the technical solutions and advantages of the present invention, and it should be understood that the above-mentioned embodiments are only the most preferred embodiments of the present invention, and are not intended to limit the present invention, and any modifications, additions, equivalents, etc. made within the scope of the principles of the present invention should be included in the scope of the present invention.
Claims (9)
1. A filter stick counting method based on image acquisition and recognition is characterized in that a device for realizing the filter stick counting method comprises the following steps:
the device comprises a movable box body, wherein a UPS for supplying power to an imaging light supplement lamp and a camera is arranged at the bottom of the box body; the box body comprises a drawer type first drawing structure for fixing the camera and a drawer type second drawing structure for bearing the filter stick plastic lattices, wherein the drawing directions of the first drawing structure and the second drawing structure are parallel; the drawer also comprises a storage drawer with the drawing direction orthogonal to that of the first drawing structure; an imaging light supplement lamp and a camera are also arranged in the box body;
the notebook computer is placed on the top surface of the box body and is in communication connection with the camera;
the filter stick counting method comprises the following steps:
the second drawing structure is drawn out to bear the filter stick plastic lattices to be counted and filled with filter sticks;
according to the size of the filter stick plastic lattice, the first drawing structure is drawn out to the optimal imaging focal distance position of the filter stick plastic lattice;
the notebook computer controls the camera to shoot the filter stick and receives the filter stick image shot by the camera;
the notebook computer carries out filtering denoising, image binarization, morphological processing and counting analysis on the received filter stick image in sequence to obtain the number of filter sticks and output the filter stick number;
the first drawing structure is of a frame structure and comprises a front panel, two triangular side frames and a first cross rod for connecting the two side frames, and a camera is mounted on the inner wall of the front panel;
the second drawing structure is of a frame structure and comprises a front panel, two right trapezoid side frames and a second cross rod for connecting the two side frames, two side panels are fixed on the two side frames close to the front panel, and the two side panels and the front panel form an accommodating cavity for bearing the filter stick plastic lattices;
the first drawing structure and the second drawing structure are oppositely arranged, and when the first drawing structure and the second drawing structure are closed, the inclined surface of the triangular side frame is abutted to and contacted with the inclined surface of the right-angled trapezoid side frame.
2. The image acquisition and recognition-based filter rod counting method according to claim 1, wherein the first draw, the second draw and the storage drawer are drawn by linear guides.
3. The filter stick counting method based on image acquisition and recognition according to claim 1, wherein a pair of parallel LED fill lights and a pair of vertical LED fill lights are arranged through a bracket in a space near the front panel of the first drawing structure.
4. The method for counting filter rods based on image acquisition and recognition according to claim 1, wherein a hand-push handrail which forms an angle of 30 degrees with the side of the box is further fixed on the side of the box.
5. The method for counting filter rods based on image acquisition and recognition according to claim 1, wherein the box body is further provided with a sleeve-rod type hand-push handrail, and one end of the hand-push handrail is fixedly connected with the front panel of the second drawing structure.
6. The filter stick counting method based on image acquisition and recognition according to claim 1, wherein a pair of universal wheels are installed on one side of the bottom of the box body close to the hand push handrail, and a pair of orientation wheels are installed on one side of the bottom of the box body far away from the hand push handrail, wherein a fixed support is adopted as a support of the orientation wheels, and a double-wave-disc double-track circular arc design is adopted as a support of the universal wheels.
7. A method for filter rod counting based on image acquisition and recognition according to claim 1, wherein filtering and de-noising comprises: carrying out filtering and denoising by adopting bilateral filtering, wherein during denoising, the diameter parameter is set to be the width occupied by a filter stick in an imaging picture, the SigmaColor is set to be 10, and the SigmaSpace is set to be 0;
the image binarization comprises the following steps: and (3) adopting a histogram to count the pixel value of the denoised filter stick image, adopting a histogram double-peak method to select a middle pixel value as a segmentation threshold value, and carrying out binarization processing on the denoised filter stick image to segment the background and the filter stick.
8. An image acquisition and recognition based filter rod counting method according to claim 1, wherein the morphological processing comprises:
extracting a filter stick foreground interested region corresponding to the original image by using the filter stick mask obtained by binarization processing, setting a first morphological gradient size template to take 3, and performing first morphological gradient calculation on a filter stick foreground interested region picture to obtain a first gradient picture; setting a second morphological gradient size taking 5, and performing second morphological gradient calculation on the filter stick foreground region-of-interest picture to obtain a second gradient picture; carrying out weighted summation on the first gradient picture and the second gradient picture according to the weights of 0.5 and 0.5 to obtain a gradient image;
setting the size of the template to be 5, and performing morphological closed operation on the gradient image to obtain a final gradient image;
the counting analysis comprises the following steps:
processing the gradient picture after morphological processing by using a maximum between-class variance threshold method to obtain a reverse binary picture; then, performing distance transformation on the reverse binary image to obtain a centroid skeleton image; finally, carrying out extreme point detection on the centroid skeleton diagram to obtain an independent connected region;
aiming at the communicated areas, calculating the number of the single communicated areas to obtain the total number of the filter sticks, wherein each single communicated area is a filter stick;
aiming at the adhesion area, the number of the filter sticks can be obtained by dividing the area of the adhesion area by the area of a single communication area.
9. A filter stick counting device based on image acquisition and recognition is characterized by comprising:
the device comprises a movable box body, wherein a UPS for supplying power to an imaging light supplement lamp and a camera is arranged at the bottom of the box body; the box body comprises a drawer type first drawing structure for fixing the camera and a drawer type second drawing structure for bearing the filter stick plastic lattices, wherein the drawing directions of the first drawing structure and the second drawing structure are parallel; the drawer also comprises a storage drawer with the drawing direction orthogonal to that of the first drawing structure; an imaging light supplement lamp and a camera are also arranged in the box body;
the notebook computer is placed on the top surface of the box body and is in communication connection with the camera, controls the camera to shoot the filter rods, receives the filter rod images shot by the camera, counts the filter rods, and specifically performs filtering denoising, image binarization, morphological processing and counting analysis on the filter rod images in sequence to obtain the number of the filter rods and output the filter rod images;
the first drawing structure is of a frame structure and comprises a front panel, two triangular side frames and a first cross rod for connecting the two side frames, and a camera is mounted on the inner wall of the front panel;
the second drawing structure is of a frame structure and comprises a front panel, two right trapezoid side frames and a second cross rod for connecting the two side frames, two side panels are fixed on the two side frames close to the front panel, and the two side panels and the front panel form an accommodating cavity for bearing the filter stick plastic lattices;
the first drawing structure and the second drawing structure are oppositely arranged, and when the first drawing structure and the second drawing structure are closed, the inclined surface of the triangular side frame is abutted to and contacted with the inclined surface of the right-angled trapezoid side frame.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811592070.5A CN109741303B (en) | 2018-12-25 | 2018-12-25 | Filter stick counting method and device based on image acquisition and recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811592070.5A CN109741303B (en) | 2018-12-25 | 2018-12-25 | Filter stick counting method and device based on image acquisition and recognition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109741303A CN109741303A (en) | 2019-05-10 |
CN109741303B true CN109741303B (en) | 2020-09-01 |
Family
ID=66359845
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811592070.5A Active CN109741303B (en) | 2018-12-25 | 2018-12-25 | Filter stick counting method and device based on image acquisition and recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109741303B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112691926A (en) * | 2020-12-10 | 2021-04-23 | 苏州阿甘机器人有限公司 | Automatic quality detection device based on machine vision and working method thereof |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105718989A (en) * | 2014-11-30 | 2016-06-29 | 中国科学院沈阳自动化研究所 | Bar counting method based on machine vision |
CN108507484A (en) * | 2018-04-08 | 2018-09-07 | 河北科技大学 | Bundled round steel multi-vision visual identifying system and method for counting |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100347724C (en) * | 2005-09-20 | 2007-11-07 | 华中科技大学 | Cigarette batch counting method based on form matching and apparatus thereof |
CN101751603A (en) * | 2008-12-10 | 2010-06-23 | 东北大学 | Online bar section image automatic counting device and method |
JP5467624B2 (en) * | 2011-03-25 | 2014-04-09 | 日本たばこ産業株式会社 | Cigarette inspection device |
CN104574398B (en) * | 2015-01-04 | 2019-07-26 | 长沙理工大学 | A kind of vanning cigarette filter stick number system based on line scan camera |
CN104537671B (en) * | 2015-01-04 | 2017-12-29 | 长沙理工大学 | A kind of cigarette filter stick on-line counting and quality determining method based on machine vision |
CN105844205B (en) * | 2015-01-15 | 2019-05-31 | 新天科技股份有限公司 | Character information recognition methods based on image procossing |
CN107654811A (en) * | 2015-07-21 | 2018-02-02 | 于梁 | Mobile device shooting support frame |
CN106485708B (en) * | 2016-10-11 | 2018-12-28 | 南京航空航天大学 | A kind of round log method of counting based on image recognition |
-
2018
- 2018-12-25 CN CN201811592070.5A patent/CN109741303B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105718989A (en) * | 2014-11-30 | 2016-06-29 | 中国科学院沈阳自动化研究所 | Bar counting method based on machine vision |
CN108507484A (en) * | 2018-04-08 | 2018-09-07 | 河北科技大学 | Bundled round steel multi-vision visual identifying system and method for counting |
Non-Patent Citations (1)
Title |
---|
目标识别技术在钢筋计数***中的研究与应用;郭倩倩;《中国优秀硕士学位论文全文数据库 工程科技辑》;20160215(第02期);第10-13页 * |
Also Published As
Publication number | Publication date |
---|---|
CN109741303A (en) | 2019-05-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107747912B (en) | Workpiece edge track scanning device and scanning method | |
CN110766684A (en) | Stator surface defect detection system and detection method based on machine vision | |
CN109741303B (en) | Filter stick counting method and device based on image acquisition and recognition | |
CN107657604A (en) | A kind of polishing scratch three-dimensional appearance original position acquisition methods based near field non-standard light source | |
TW201416644A (en) | Detection system | |
CN105719275A (en) | Parallel combination image defect segmentation method | |
CN208636225U (en) | A kind of image acquisition mechanism and system of display screen | |
CN204039886U (en) | A kind of pavement damage crack detection system based on multiple stage camera stereoscopic shooting | |
CN108510544A (en) | A kind of striation localization method of feature based cluster | |
CN105242568A (en) | Tobacco leaf accurate rejecting control method based on digital image processing | |
CN108038901B (en) | Object space three-dimensional imaging data generation system | |
CN102890093A (en) | Machine vision detecting device of surface quality of master cylinder piston of automobile brake | |
CN110866975A (en) | Multi-vision-based rape image acquisition device and three-dimensional feature extraction method | |
CN103217108A (en) | Method for detecting geometrical parameters of spectacle frame | |
CN102866160A (en) | System and method for detecting surface quality of coin mold | |
CN203069156U (en) | Novel scraping processing surface automatic detection device | |
CN106643537B (en) | Bearing oil duct method for automatic measurement based on structure light | |
CN113012105A (en) | Yarn hairiness detection and rating method based on image processing | |
Farella et al. | Handling critical aspects in massive photogrammetric digitization of museum assets | |
JP2015059821A (en) | Amount-of-insolation predicting device and method | |
CN114688969A (en) | Optical lens size detection device and method | |
CN105973903B (en) | A kind of Oral liquid bottle lid detection method | |
CN205246550U (en) | Novel detritus fluoroscopic image high resolution scanner | |
CN203913635U (en) | A kind of foot laser scanner | |
CN112037233B (en) | Image binarization method based on Otsu method and K-means clustering algorithm combined optimization |
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 |