CN109127462B - Intelligent sausage sorting method based on visual guidance - Google Patents
Intelligent sausage sorting method based on visual guidance Download PDFInfo
- Publication number
- CN109127462B CN109127462B CN201810961428.0A CN201810961428A CN109127462B CN 109127462 B CN109127462 B CN 109127462B CN 201810961428 A CN201810961428 A CN 201810961428A CN 109127462 B CN109127462 B CN 109127462B
- Authority
- CN
- China
- Prior art keywords
- sausage
- point
- line
- axis
- center
- 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
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C2501/00—Sorting according to a characteristic or feature of the articles or material to be sorted
- B07C2501/0081—Sorting of food items
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an intelligent sausage sorting method based on visual guidance, which is characterized in that a sausage image is binarized by using a fixed threshold value; extracting a sausage long axis central line in the binary image; changing a straight line segment of the central line of the long axis of the sausage by using Hough, and removing repeated straight lines; searching cut-off positions of two ends of the sausage, and calculating the deviation angle of the sausage and the center coordinate of the sausage; invalid sausages are filtered out. The sausage sorting machine has stronger product adaptability, higher sausage identification and positioning accuracy and lower sorting omission rate, so that the sausage production efficiency of enterprises can be more effectively improved.
Description
Technical Field
The invention relates to a sausage sorting method, in particular to an intelligent sausage sorting method based on visual guidance.
Background
Automatic sorting is a common process in the product manufacturing process, and the efficiency and accuracy of sorting directly affect the yield and quality of products. In the sausage production process, the automatic sorting is mainly used for sequentially placing the sausages in the baking tray so as to be convenient for conveying the sausages into the drying box for drying.
At present, an automatic sausage sorting method is a full-automatic sausage production line designed for a certain enterprise by German robomotion Limited, which is dedicated to the research and development of a robot automation solution, and mainly shoots scattered sausages on the production line through a camera, and identifies and positions the sausages by utilizing an image processing algorithm, so that an industrial robot is guided to automatically sort the sausages on the production line. However, the automatic sorting system has the problems of weak product adaptability, high missing rate, low positioning precision, high robot mistaken grabbing rate and the like, and the yield of the sausages is influenced. The main reason for such problems is that the image processing algorithm cannot identify and locate the sausages on the production line with high precision.
Disclosure of Invention
The invention aims to solve the technical problem of providing an intelligent sausage sorting method based on visual guidance to realize high-precision recognition and positioning of sausages on a production line.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
an intelligent sausage sorting method based on visual guidance is characterized by comprising the following steps:
the method comprises the following steps: binarizing the sausage image by using a fixed threshold value;
step two: extracting a sausage long axis central line in the binary image;
step three: changing a straight line segment of the central line of the long axis of the sausage by using Hough, and removing repeated straight lines;
step four: searching cut-off positions of two ends of the sausage, and calculating the deviation angle of the sausage and the center coordinate of the sausage;
step five: invalid sausages are filtered out.
Furthermore, the sausage image in the first step is captured by an industrial camera, the sausage is conveyed by the conveyor belt at a certain speed in the capturing process, the light source direction faces the sausage on the conveyor belt, the industrial personal computer controls the controller to send a stroboscopic signal to the industrial camera, and the camera is triggered to shoot the sausage to obtain the sausage image.
Further, the first step is specifically that after the camera collects an image, a fixed threshold value is adopted to carry out binarization on the sausage image, in the binarized image, the sausage foreground target is black, the background part is white, and the binarized threshold value is set to be 125.
Further, the second step is to scan the foreground line segment in both horizontal and vertical directions, if the length of the line segment is [0.8 × D ]Standard,1.5×DStandard]Within the interval, the center point of the line segment is extracted as a candidate point of the vertical center, DStandardThe sausage standard diameter is set, the set line segment length interval takes the single-time sausage diameter as a criterion, and the central line mark point is the central axis mark line of a single sausage, so that the central axis mark line when two or more sausages are adhered together side by side cannot be extracted, the phenomenon that the central axis mark line is broken can also occur at the simple adhesion part, and the mark point is subjected to expansion operation in order to improve the connectivity of the central line of the long axis.
Further, the third step is specifically to utilize probability Hough linear detection to extract linear segments of sausage long axis central lines of at least one quarter of the sausage length, namely the potential sausage long axis central lines, wherein multiple linear lines are easily detected from the long axis central line of the same sausage and are all the potential sausage central lines, each time one linear line is used for searching two ends to the front of the cut-off position, whether the linear line is repeated with the linear line which is successfully searched to the cut-off position in the past needs to be judged, and if the linear line is judged to be located in the same sausage, the current linear line is abandoned.
Further, the repeated process of judging whether the straight line is successfully searched to the cut-off position before is that
Condition 1: the distance between the center point of the current straight line segment and the center point of the detected sausage is less than the length of a half diagonal line of the standard sausage;
condition 2: the difference between the inclination angle of the connecting line of the center point of the current straight line segment and the center point of the detected sausage and the inclination angle of the detected straight line is less than 30 degrees;
if the two conditions are met simultaneously, judging that the sausage where the current straight line segment is located is searched for the cut-off positions at the two ends, and directly abandoning the current straight line without repeated searching.
Further, the fourth step is that the sausage is full and thick in the middle, becomes thin by narrowing along the middle to the two ends, and then the cut-off positions are searched for from the two ends through the central axis, so that the central coordinate of the sausage is accurately positioned, and the cut-off positions are searched for from the two ends, so that the sausage can be regarded as a complete sausage; if the extension point on the central axis is the background color, the sausage is regarded as a partial sausage, namely only a part of the sausage is positioned in the visual field, and the calculated sausage center can not reflect the real center of the sausage, so the sausage is abandoned, the sausage is extended and searched towards two ends with a certain step length along the central axis, and the cut-off positions of the two ends of the sausage are judged according to whether the axis point and the radial point vertical to the axis are foreground pixels or background pixels.
Further, the process of judging the cut-off positions at the two ends of the box culvert is
Defining an axis point A, a four-radius point B, an inner diameter point C and an outer diameter point D;
the axis point A is a point which extends from the end point of the straight line section to the two ends in a certain step length on the central axis;
the quartering point B is a distance point which is one fourth of the diameter of the point A from the axial point A on a radial line of the axial point A;
the inner diameter point C is a distance point which is 0.8 radius from the axial point A to the point A on a radial line of the axial point A;
the outer diameter point D is a point which has 1.25 radiuses from the axial point A to the point A on a radial line of the axial point A;
the radial line is provided with two four-diameter-dividing points B, two inner diameter points C and two outer diameter points D, the four-diameter-dividing points B are mainly used for judging the condition of axial adhesion, and the outer diameter points D are mainly used for judging the condition of T-shaped adhesion;
the conditions for judging the cut-off positions of the two ends of the sausage are as follows:
condition 1: two points of the axis point A and the two inner diameter points C are background colors;
condition 2: any one point B of the two four-path points B at a certain end is a background color;
condition 3: the two outer diameter points D are both foreground colors;
the axis point or the radial line point only needs to meet any one of the above conditions, namely the end position at the end is considered to be searched, the deflection angle and the center coordinate of the sausage can be calculated according to the end positions at the two ends of the sausage, the length of the sausage is further calculated, and if the length result meets the length threshold value, the sausage is considered to be searched in the visual field.
Further, the fifth step is specifically to set a Margin Boundary parameter and an interval Margin parameter to discriminate invalid sausages, and the discrimination conditions are as follows:
condition 1: the distance between the identified sausage center abscissa and the left side and the right side of the visual field is smaller than Boundary;
condition 2: other sausages exist in the range of the recognized sausage long axis edge distance interval Margin, namely the sausage radius is used as the step length for radiation, and whether two or more pixel points exist in the range of the clamping jaw length along the long axis direction at the radiation distance is checked to be the foreground pixel points.
Compared with the prior art, the invention has the following advantages and effects: the automatic sausage sorting method based on visual guidance has stronger product adaptability, higher sausage identification and positioning accuracy and lower sorting missing rate, so that the sausage production efficiency of enterprises can be more effectively improved.
Drawings
Fig. 1 is a schematic diagram of a sorting system of the sausage intelligent sorting method based on visual guidance.
Fig. 2 is an image of a sausage sample of the present invention.
Fig. 3 is a binarized image according to the present invention.
Fig. 4 is a long axis midline marking of the sausage of the invention.
Fig. 5 is a long axis line graph of the sausage of the invention.
Fig. 6 is a schematic diagram of the end positions of the search sausage of the invention.
Fig. 7 is a diagram of the sausage positioning results of the present invention.
FIG. 8 is a diagram of the Margin Boundary and interval Margin parameters of the present invention.
FIG. 9 is a graph of the filtering results of the present invention.
Detailed Description
The present invention is further illustrated by the following specific examples, which are illustrative of the present invention and are not to be construed as being limited thereto.
As shown in figure 1, the sausage automatic sorting system comprises an industrial personal computer 1, a controller 2, an industrial robot 3, an industrial camera 4, a light source 5 and a conveyor belt 6, wherein the industrial robot 3 is positioned above the conveyor belt 6, the industrial camera 4 is fixed at the upstream of the grabbing position of the industrial robot 3 and right above the conveyor belt 6, and an annular light source 5 is arranged right below the industrial camera 4 and used for keeping sausages uniformly illuminated. The working principle of the system is as follows: the conveying belt transmits sausages at a certain speed, the light source direction faces the sausages on the conveying belt, the industrial personal computer controls the controller to send a stroboscopic signal to the industrial camera, the camera is triggered to shoot the sausages to obtain sausage images, the sausage images are transmitted to the industrial personal computer and then processed to obtain the deviation angle of the sausages and the vertical central axis coordinate of the sausages, the industrial personal computer combines the calibration data of the industrial camera and the industrial robot which are calibrated by hands and the moving speed of the conveying belt, the moving position and the grabbing posture of the manipulator of the industrial robot are calculated by utilizing the deviation angle of the sausages and the vertical central axis coordinate of the sausages, and therefore the industrial robot is controlled to grab the sausages on the conveying.
According to the working principle of the system, the processing effect of the visual part directly influences the performance of the whole sorting system, and when the visual part identifies and positions sausages on the conveying belt wrongly or even fails, the industrial robot cannot grab the sausages.
The invention relates to an intelligent sausage sorting method based on visual guidance, which comprises five steps:
the method comprises the following steps: binarizing the sausage image by using a fixed threshold value;
the quality of the sausage in an imaging image directly influences the identification and positioning precision of the sausage, and the imaging quality of the sausage can be greatly improved by optimizing and adjusting the light source brightness and the camera exposure time. After the camera collects an image, a sausage image (shown in figure 2) is binarized by adopting a fixed threshold value, and in the binarized image (shown in figure 3), the sausage foreground object is determined to be black, and the background part is determined to be white. Since the conveyor belt is white and is vulnerable to contamination, the binarization threshold is usually set to 125 in order to reduce the influence of the background area on the foreground object.
Step two: extracting a sausage long axis central line in the binary image;
because the sausage is in a strip shape and has better linearity, the sausage can be positioned by extracting the central line of the long shaft. And scanning the foreground line segment in the horizontal direction and the vertical direction, and if the length of the line segment is within a proper interval, extracting the center point of the line segment as a candidate point of a vertical center. With a standard sausage diameter DStandardFor reference, when the sausage is inclined at an angle of +/-45 degrees, the length of the line segment in the horizontal or vertical direction can be lengthened to be 1.414 × DStandardWhen the sausage is bent, the length of the line segment of the bent angle part is about 0.8 × DStandardTherefore, the segment length interval is set to [0.8 × D ]Standard,1.5×DStandard]. Fig. 4 is a diagram of a midline marker of the long axis of the sausage, wherein a red line is marked as a midline point obtained by horizontal scanning, a green mark is marked as a midline point obtained by vertical scanning, and a lighter color in a black-and-white image is marked as a green mark. Because the set segment length interval takes the single-time sausage diameter as the criterion, and the middle line mark point is the middle axis mark line of a single sausage, two or more sausage can not be extractedWhen the sausages are adhered together side by side, the phenomenon that the middle axis marking line is broken can also occur at the simple adhesion position. And performing expansion operation on the marked points in order to improve the connectivity of the central line of the long axis.
Step three: changing a straight line segment of the central line of the long axis of the sausage by using Hough, and removing repeated straight lines;
and (3) extracting a straight line segment of the sausage long axis central line meeting a certain length by utilizing probability Hough linear detection, namely the potential sausage long axis central line, wherein the length threshold of the long axis central line is at least one fourth of the sausage length, and in the figure 5, a purple line mark (a line mark with a lighter color) is the sausage long axis central line extracted by utilizing probability Hough linear detection. A plurality of straight lines are easily detected from the central line of the long shaft of the same sausage, and are all potential sausage central axes. Before searching both ends to the cut-off position by a certain straight line, whether the straight line is repeated with the straight line which is successfully searched to the cut-off position before is judged.
And if the sausage is judged to be positioned on the same sausage, the search for the current straight line is abandoned. The conditions for distinguishing the repeated straight lines are as follows:
the distance between the center point of the current straight line segment and the center point of the detected sausage is smaller than the length of a half diagonal line of the standard sausage;
and the difference between the inclination angle of the connecting line of the center point of the current straight line segment and the center point of the detected sausage and the inclination angle of the detected straight line is less than 30 degrees.
If the two conditions are met simultaneously, judging that the sausage where the current straight line segment is located is searched for the cut-off positions at the two ends, and directly abandoning the current straight line without repeated searching.
Step four: searching cut-off positions of two ends of the sausage, and calculating the deviation angle of the sausage and the center coordinate of the sausage;
after searching straight line segments by using Hough transformation, the cut-off positions of the two ends of the central axis of the sausage can be further searched. The sausage is full and thick in the middle and becomes thin by bowing along the middle to two ends, so that the cut-off positions are searched for from the middle axis to the two ends, and the center coordinate of the sausage can be accurately positioned. The two ends are required to search the cut-off positions, so that the sausage can be regarded as a complete sausage. If the extension point (middle division point) on the middle axis is the background color, the sausage is regarded as a partial sausage, namely only a part of the sausage is positioned in the visual field, and the calculated sausage center can not embody the real center of the sausage, so the sausage is abandoned. Fig. 6 is a schematic diagram showing the cut-off positions of two ends of the sausage, the cut-off positions of the two ends of the sausage are judged according to whether the axis point and the radial point vertical to the axis are foreground pixels or background pixels by extending and searching towards the two ends with a certain step length along the central axis.
Defining an axis point A, a four-radius point B, an inner diameter point C and an outer diameter point D:
the axis point A is a point which extends from the end point of the straight line section to the two ends in a certain step length on the central axis;
the quartering point B is a distance point which is on a radial line (or called as a vertical branching line) at the axial point A and has a diameter of one fourth of the point A from the axial point A to the point A;
the inner diameter point C is a distance point which is 0.8 radius from the axial point A to the point A on a radial line of the axial point A;
the outer diameter point D is 1.25 radii from the axial point a on the radial line at the axial point a.
The radial lines (vertical branching lines) are provided with two four-branch points B, two inner diameter points C and two outer diameter points D, the four-branch points B are mainly used for judging the condition of axial adhesion, and the outer diameter points D are mainly used for judging the condition of T-shaped adhesion.
The conditions for judging the cut-off positions of the two ends of the sausage are as follows:
firstly, two points of an axis point A and two inner diameter points C are background colors;
any one B of the two four-way points B at a certain end is a background color
And the two outer diameter points D are both foreground colors.
The axis point or radial line point only needs to satisfy either of the above conditions, i.e., is considered to have searched for a cutoff position at this end. The deviation angle and the center coordinate of the sausage can be calculated according to the cut-off positions of the two ends of the sausage, the length of the sausage can be further calculated, and if the length result meets the length threshold value, a sausage is considered to be searched in the visual field.
Four sausages are arranged in the sample image, and as can be seen from the sausage positioning result (shown in figure 7), three sausages of No. 1, No. 2 and No. 3 are successfully positioned, and the No. 4 sausage does not completely enter the visual field and is filtered out. The No. 1 sausage exists independently, and the using condition is that the cut-off positions of the two ends of the No. 1 sausage can be positioned. The No. 2 sausage and the No. 3 sausage are adhered together in a T shape. The using condition is that the stopping position of the left end of the No. 2 sausage can be positioned, the using condition is that the stopping positions of the right ends of the No. 2 and No. 3 sausages are positioned, and the using condition is that the stopping position of the left end of the No. 3 sausage is positioned.
Step five: invalid sausages are filtered out.
The sausage is clamped by using the clamping jaws, and in order to ensure that the clamping of the sausage is not interfered, the sausage close to the edge of the conveyor belt and other sausages attached to the conveyor belt are regarded as invalid sausages. Setting a Margin Boundary parameter and a gap Margin parameter (corresponding to a schematic diagram shown in figure 8) to judge invalid sausages, wherein the detailed judgment conditions are as follows: firstly, the distance between the central abscissa of the identified sausage and the left side and the right side of a visual field is less than Boundary; secondly, other sausages exist in the range of the distance between the long axis edges of the identified sausages and the Margin interval Margin, namely, the sausages are radiated by taking the radius of the sausages as a step length, and whether two or more pixel points exist in the range of the length of the clamping jaw at the radiation distance along the long axis direction or not is checked to be taken as a foreground pixel point. Fig. 9 shows the result of the filtering, and the sausages No. 1, 2 and 4 marked by green thin lines can not be grabbed by the clamping jaws due to the interference of the sausages nearby, while the sausage No. 4 marked by purple thick frames can be grabbed by the clamping jaws.
Compared with the existing sausage automatic sorting scheme provided by the German robomotion Co., Ltd, the sausage automatic sorting method based on visual guidance provided by the invention has stronger product adaptability, higher sausage identification and positioning accuracy and lower picking missing rate, so that the sausage production efficiency of enterprises can be more effectively improved.
The above description of the present invention is intended to be illustrative. Various modifications, additions and substitutions for the specific embodiments described may be made by those skilled in the art without departing from the scope of the invention as defined in the accompanying claims.
Claims (7)
1. An intelligent sausage sorting method based on visual guidance is characterized by comprising the following steps:
the method comprises the following steps: binarizing the sausage image by using a fixed threshold value;
step two: extracting a sausage long axis central line in the binary image;
the second step is to scan the foreground line segment in both horizontal and vertical directions, if the length of the line segment is [0.8 × D ]Standard,1.5×DStandard]Within the interval, the center point of the line segment is extracted as a candidate point of the vertical center, DStandardThe sausage standard diameter is set, the set line segment length interval takes the single-time sausage diameter as a criterion, and the central line mark point is the central axis mark line of a single sausage, so that the central axis mark line when two or more sausages are adhered together side by side cannot be extracted, the phenomenon of central axis mark line breakage also occurs at the simple adhesion part, and the mark point is subjected to expansion operation in order to improve the connectivity of the central line of the long axis;
step three: changing a straight line segment of the central line of the long axis of the sausage by using Hough, and removing repeated straight lines;
the third step is specifically that probability Hough linear detection is utilized, linear segments of sausage long shaft center lines with at least one fourth of the sausage length are extracted, namely potential sausage long shaft center lines, a plurality of linear lines are easily detected from the long shaft center line of the same sausage, all the linear lines are potential sausage center lines, whether the linear line is repeated with a linear line which is successfully searched to the cut-off position in the early time is required to be judged every time the linear line is used for searching two ends to the cut-off position in the early time, and if the linear line is judged to be located in the same sausage, the current linear line is abandoned to be searched;
step four: searching cut-off positions of two ends of the sausage, and calculating the deviation angle of the sausage and the center coordinate of the sausage;
step five: invalid sausages are filtered out.
2. The sausage intelligent sorting method based on visual guidance as claimed in claim 1, wherein: and in the first step, the sausage image is captured by the industrial camera, the sausage is transmitted by the conveyor belt at a certain speed in the capturing process, the light source direction faces the sausage on the conveyor belt, the industrial computer controls the controller to send a stroboscopic signal to the industrial camera, and the camera is triggered to photograph the sausage to obtain the sausage image.
3. The sausage intelligent sorting method based on visual guidance as claimed in claim 1, wherein: the first step is specifically that after the camera collects an image, a fixed threshold value is adopted to carry out binarization on the sausage image, in the binarized image, the sausage foreground target is black, the background part is white, and the binarized threshold value is set to be 125.
4. The sausage intelligent sorting method based on visual guidance as claimed in claim 1, wherein: the repeated process of judging whether the straight line is repeated with the straight line which is successfully searched to the cut-off position in the past is that
Condition 1: the distance between the center point of the current straight line segment and the center point of the detected sausage is less than the length of a half diagonal line of the standard sausage;
condition 2: the difference between the inclination angle of the connecting line of the center point of the current straight line segment and the center point of the detected sausage and the inclination angle of the detected straight line is less than 30 degrees;
if the two conditions are met simultaneously, judging that the sausage where the current straight line segment is located is searched for the cut-off positions at the two ends, and directly abandoning the current straight line without repeated searching.
5. The sausage intelligent sorting method based on visual guidance as claimed in claim 1, wherein: the fourth step is that the sausage is full and thick in the middle, can be narrowed down from the middle to the two ends, and then the cut-off positions are searched for from the middle axis to the two ends, so that the center coordinate of the sausage is accurately positioned, and the cut-off positions are searched for from the two ends, so that the sausage can be regarded as a complete sausage; if the extension point on the central axis is the background color, the sausage is regarded as a partial sausage, namely only a part of the sausage is positioned in the visual field, and the calculated sausage center can not reflect the real center of the sausage, so the sausage is abandoned, the sausage is extended and searched towards two ends with a certain step length along the central axis, and the cut-off positions of the two ends of the sausage are judged according to whether the axis point and the radial point vertical to the axis are foreground pixels or background pixels.
6. The sausage intelligent sorting method based on visual guidance as claimed in claim 5, wherein: the process of judging the cut-off positions of the two ends of the sausage is
Defining an axis point A, a four-radius point B, an inner diameter point C and an outer diameter point D;
the axis point A is a point which extends from the end point of the straight line section to the two ends in a certain step length on the central axis;
the quartering point B is a distance point which is one fourth of the diameter of the point A from the axial point A on a radial line of the axial point A;
the inner diameter point C is a distance point which is 0.8 radius from the axial point A to the point A on a radial line of the axial point A;
the outer diameter point D is a point which has 1.25 radiuses from the axial point A to the point A on a radial line of the axial point A;
the radial line is provided with two four-diameter-dividing points B, two inner diameter points C and two outer diameter points D, the four-diameter-dividing points B are mainly used for judging the condition of axial adhesion, and the outer diameter points D are mainly used for judging the condition of T-shaped adhesion;
the conditions for judging the cut-off positions of the two ends of the sausage are as follows:
condition 1: two points of the axis point A and the two inner diameter points C are background colors;
condition 2: any one point B of the two four-path points B at a certain end is a background color;
condition 3: the two outer diameter points D are both foreground colors;
the axis point or the radial line point only needs to meet any one of the above conditions, namely the end position at the end is considered to be searched, the deflection angle and the center coordinate of the sausage can be calculated according to the end positions at the two ends of the sausage, the length of the sausage is further calculated, and if the length result meets the length threshold value, the sausage is considered to be searched in the visual field.
7. The sausage intelligent sorting method based on visual guidance as claimed in claim 1, wherein: the fifth step is to set a Margin Boundary parameter and an interval Margin parameter to judge invalid sausages, and the judging conditions are as follows:
condition 1: the distance between the identified sausage center abscissa and the left side and the right side of the visual field is smaller than Boundary;
condition 2: other sausages exist in the range of the recognized sausage long axis edge distance interval Margin, namely the sausage radius is used as the step length for radiation, and whether two or more pixel points exist in the range of the clamping jaw length along the long axis direction at the radiation distance is checked to be the foreground pixel points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810961428.0A CN109127462B (en) | 2018-08-22 | 2018-08-22 | Intelligent sausage sorting method based on visual guidance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810961428.0A CN109127462B (en) | 2018-08-22 | 2018-08-22 | Intelligent sausage sorting method based on visual guidance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109127462A CN109127462A (en) | 2019-01-04 |
| CN109127462B true CN109127462B (en) | 2020-09-04 |
Family
ID=64790903
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810961428.0A Expired - Fee Related CN109127462B (en) | 2018-08-22 | 2018-08-22 | Intelligent sausage sorting method based on visual guidance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109127462B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110575973B (en) * | 2019-10-21 | 2021-08-10 | 台州学院 | Crop seed quality detection and screening system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202002619U (en) * | 2011-03-29 | 2011-10-05 | 浙江大学 | Multi-parameter automatic measuring equipment of rolling bearing outer rings based on comparison measuring method |
| CN102706893A (en) * | 2012-01-15 | 2012-10-03 | 河南科技大学 | Method for quickly scanning and detecting appearance and quality of emulsion-type sausage food product based on machine vision |
| CN103426164A (en) * | 2013-06-09 | 2013-12-04 | 大连海事大学 | Scallop size calculation method and scallop sorting system based on Opencv image analysis |
| CN105678749A (en) * | 2015-12-30 | 2016-06-15 | 中国水产科学研究院渔业机械仪器研究所 | Fresh fish direction discrimination method based on visual sense |
| WO2017150968A1 (en) * | 2016-03-04 | 2017-09-08 | De Greef's Wagen-, Carrosserie- En Machinebouw B.V. | Packaging device and sorting system for directional packaging of products and method therefor |
| CN107497706A (en) * | 2017-08-07 | 2017-12-22 | 华中农业大学 | A kind of Chinese chestnut sorting unit and method |
-
2018
- 2018-08-22 CN CN201810961428.0A patent/CN109127462B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202002619U (en) * | 2011-03-29 | 2011-10-05 | 浙江大学 | Multi-parameter automatic measuring equipment of rolling bearing outer rings based on comparison measuring method |
| CN102706893A (en) * | 2012-01-15 | 2012-10-03 | 河南科技大学 | Method for quickly scanning and detecting appearance and quality of emulsion-type sausage food product based on machine vision |
| CN103426164A (en) * | 2013-06-09 | 2013-12-04 | 大连海事大学 | Scallop size calculation method and scallop sorting system based on Opencv image analysis |
| CN105678749A (en) * | 2015-12-30 | 2016-06-15 | 中国水产科学研究院渔业机械仪器研究所 | Fresh fish direction discrimination method based on visual sense |
| WO2017150968A1 (en) * | 2016-03-04 | 2017-09-08 | De Greef's Wagen-, Carrosserie- En Machinebouw B.V. | Packaging device and sorting system for directional packaging of products and method therefor |
| CN107497706A (en) * | 2017-08-07 | 2017-12-22 | 华中农业大学 | A kind of Chinese chestnut sorting unit and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109127462A (en) | 2019-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107138431A (en) | A kind of parts identification method for separating and system based on machine vision | |
| JP2017096750A (en) | Positioning method, positioning apparatus, program and computer readable recording medium | |
| CN117557570B (en) | Rail vehicle abnormality detection method and system | |
| CN102879404B (en) | System for automatically detecting medical capsule defects in industrial structure scene | |
| CN115082410A (en) | Detection method of circlip defect based on image processing | |
| CN115082466B (en) | PCB surface welding spot defect detection method and system | |
| CN110216082B (en) | Method and system for dynamic identification of fluorescently labeled seeds | |
| CN102175692A (en) | System and method for detecting defects of fabric gray cloth quickly | |
| CN112697588B (en) | A vision-based cable sheath elongation measurement device and use method | |
| CN115147407B (en) | Bearing quality detection method based on computer vision | |
| CN111524154B (en) | Image-based tunnel segment automatic segmentation method | |
| CN114463296B (en) | Light-weight part defect detection method based on single sample learning | |
| CN105784719A (en) | Machine vision inspection terminal capable of sorting goods | |
| CN109127462B (en) | Intelligent sausage sorting method based on visual guidance | |
| CN109583306B (en) | A method for detecting residual yarn in bobbins based on machine vision | |
| CN113192061A (en) | LED package appearance detection image extraction method and device, electronic equipment and storage medium | |
| CN106906519A (en) | Electronic recognition simultaneously selects the method and its silk cocoon screening system of inferior silk cocoon | |
| CN109461150B (en) | Yarn tube color sorting method based on machine vision | |
| CN119880905A (en) | Flaw detection method based on coordination of line-up laser and mechanical arm | |
| CN110856847A (en) | Capacitance character detection method and device based on intelligent vision | |
| CN109701890A (en) | Magnetic tile surface defect detection and method for sorting | |
| CN106906520A (en) | The method and its silk cocoon screening system of the inferior silk cocoon of electronic recognition | |
| CN116840241A (en) | Defect detection method on negative electrode surface of cylindrical dry battery based on machine vision | |
| CN110857919A (en) | A method for detecting the defect of the tail wire of the packaged filament | |
| KR101071144B1 (en) | Automatic grading method of lumber |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200904 Termination date: 20210822 |