CN109127462A - A kind of sausage intelligent sorting method of view-based access control model guidance - Google Patents
A kind of sausage intelligent sorting method of view-based access control model guidance Download PDFInfo
- Publication number
- CN109127462A CN109127462A CN201810961428.0A CN201810961428A CN109127462A CN 109127462 A CN109127462 A CN 109127462A CN 201810961428 A CN201810961428 A CN 201810961428A CN 109127462 A CN109127462 A CN 109127462A
- Authority
- CN
- China
- Prior art keywords
- sausage
- point
- rest position
- line
- axis
- 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.)
- Granted
Links
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
Abstract
The invention discloses a kind of sausage intelligent sorting methods of view-based access control model guidance, using fixed threshold value by sausage image binaryzation；Extract the long axis of spindle of sausage in bianry image；Using the straightway of the long axis of spindle of Hough transform sausage, exclude to repeat straight line；Sausage both ends rest position is searched for, the deviation angle of sausage and the centre coordinate of sausage are calculated；Filter out invalid sausage.There is the present invention the stronger adaptation of product, higher sausage identification positioning accuracy and lower leakage to pick rate, it is thus possible to more effectively promote the sausage production efficiency of enterprise.
Description
Technical field
The present invention relates to a kind of sausage method for sorting, especially a kind of sausage intelligent sorting method of view-based access control model guidance.
Background technique
Automatic sorting is process common in manufacture course of products, and the efficiency and accuracy rate of sorting directly affect the production of product
Amount and quality.In sausage production process, automatic sorting is primarily to sausage is sequentially placed in baking pan, in order to by sausage
It send to being dried in drying box.
Currently, sausage automatic sorting method has the German robomotion for being dedicated to the research and development of robot automation's solution
Co., Ltd is sausage full-automation production line designed by certain enterprise, and perfume (or spice) at random on production line is mainly shot by camera
Intestines are identified and are positioned to sausage using after image processing algorithm, to guide industrial robot to the sausage on assembly line
Carry out automatic sorting.However, that there are the adaptation of product is weaker, omission factor is higher, positioning accuracy is lower, machine for the Automated Sorting System
Device people misses the problems such as snatch rate is higher, influences the yield of sausage.The main reason for generating problems is its image procossing
Algorithm can not carry out high-precision identification and positioning to the sausage on assembly line.
Summary of the invention
Technical problem to be solved by the invention is to provide a kind of sausage intelligent sorting methods of view-based access control model guidance, realize
To assembly line go to temple to pray intestines high-precision identification positioning.
In order to solve the above technical problems, the technical scheme adopted by the invention is that:
A kind of sausage intelligent sorting method of view-based access control model guidance, it is characterised in that comprise the steps of:
Step 1: use fixed threshold value by sausage image binaryzation；
Step 2: the long axis of spindle of sausage in bianry image is extracted；
Step 3: it using the straightway of the long axis of spindle of Hough transform sausage, excludes to repeat straight line；
Step 4: search sausage both ends rest position calculates the deviation angle of sausage and the centre coordinate of sausage；
Step 5: invalid sausage is filtered out.
Further, sausage image is grabbed by industrial camera in the step 1, and crawl process is conveyer belt with one
Constant speed degree transmits sausage, and towards the sausage on conveyer belt, industrial personal computer controls controller and sends stroboscopic to industrial camera light source direction
Signal, triggering camera, which take pictures to sausage, obtains sausage image.
Further, after the step 1 is specially camera acquisition image, two are carried out to sausage image using fixed threshold
Value, in binary image, sausage foreground target is black, and background parts are white, and binarization threshold is set as 125.
Further, the step 2 is specially that prospect line segment is both horizontally and vertically scanned, if the length along path
Degree is located at [0.8 × DStandard,1.5×DStandard] in section, extract candidate of the central point as vertical centre of the line segment
Point, DStandardFor sausage normal diameter, since set line segment length section is the middle line mark using single times of sausage diameter as criterion
Note selects axis mark line Ji Wei single sausage, therefore cannot extract two or axis when more sausages are sticked together side by side
Mark line also will appear the phenomenon that axis marks thread breakage, in order to promote the connectivity of long axis of spindle, to mark at simple adhesion
Note point carries out dilation operation.
Further, the step 3 is specially to utilize probability Hough straight-line detection, four points for extracting at least sausage length
One of the long axis of spindle of sausage of length straightway, the as potential long axis of spindle of sausage, the long axis of spindle of same root sausage holds
Easily detect a plurality of straight line, be potential sausage central axes, every time with certain linear search both ends to rest position before, be both needed to
Differentiate this straight line whether in the early time successful search to rest position straight line repeat, if be determined as be located at same root sausage,
It abandons searching for current straight line.
Further, it is described differentiate this straight line whether in the early time successful search to rest position straight line repetitive process
For
Condition 1: current straightway central point with to have detected oblique right half at a distance from sausage central point less than standard sausages
Diagonal length；
Condition 2: current straightway central point and the inclination angle for having detected sausage central point line and straight incline has been detected
The difference of angle is less than 30 degree；
If meeting two above condition simultaneously, differentiate that sausage locating for current straightway has been searched both ends cut-off
Position, is not repeated to search for, and directly gives up current straight line.
Further, the step 4 is specially that sausage middle section is more full sturdy, can closing waist to both ends along centre
Attenuate, searches for rest position to both ends by central axes, and then the centre coordinate of sausage is accurately positioned out, both ends must search
Rest position can be considered as a complete sausage；If extending point on central axes is background colour, this root sausage is considered as part perfume
Intestines, i.e., only part sausage is located in visual field, and sausage center calculated fails to embody the real center of this root sausage, therefore gives up
This root sausage is abandoned, is extended with a fixed step size to both ends along central axes and is searched for, according to axis point and radial point perpendicular to the axis
It whether is foreground pixel or background pixel, to differentiate the rest position at sausage both ends.
Further, the process of the rest position for differentiating box culvert both ends is
Define axis point A, four minutes diameter point B, internal diameter point C, outer diameter point D；
Axis point A is the point extended from straightway endpoint with a fixed step size to both ends on central axes；
Four points of diameter point B are to have at a distance from point A a quarter diameter from axial point A with point A on radial line at axial point A
Point；
Internal diameter point C be on the radial line at the place axial point A from axial point A and point A has the range points of 0.8 radius；
Outer diameter point D be on the radial line at the place axial point A from axial point A and point A has the point of 1.25 radiuses；
Wherein, there are two four points of diameter point B, two internal diameter point C, two outer diameter point D, four points of diameter point B to be mainly used on radial line
The case where differentiating axial adhesion, outer diameter point D are mainly used for the case where differentiating the adhesion of T word；
Judge the condition of sausage both ends rest position are as follows:
Condition 1: there are two put as background colour in axis point A and two internal diameter point C；
Condition 2: any point B is background colour in two four points of diameter point B at certain end；
3: two outer diameter point D of condition are foreground；
Axis point or radial line point only need to meet any of the above-described condition, that is, are considered as having searched the rest position at this end,
The deviation angle and centre coordinate of sausage can be calculated by the both ends rest position of sausage, and then calculate the length of sausage, if
This length sequences meets length threshold, that is, is considered as searching a sausage in visual field.
Further, the step 5 is specially that back gauge Boundary parameter and interval Margin parameter is arranged to differentiate nothing
Imitate sausage, criterion are as follows:
Condition 1: identified sausage center abscissa at left and right sides of visual field at a distance from be less than Boundary；
Condition 2: there are other sausages within the scope of identified sausage long axis edge distance interval Margin, i.e., with sausage radius
For step-length radiation, check that whether there is two or more pixels at radiation length along the clamping jaw length range of long axis direction is
Foreground pixel point.
Compared with prior art, the present invention having the following advantages that and effect: the sausage of view-based access control model guidance of the invention from
There is dynamic method for sorting the stronger adaptation of product, higher sausage identification positioning accuracy and lower leakage to pick rate, it is thus possible to
More effectively promote the sausage production efficiency of enterprise.
Detailed description of the invention
Fig. 1 is a kind of sorting system schematic diagram of the sausage intelligent sorting method of view-based access control model guidance of the invention.
Fig. 2 is sausage sample image of the invention.
Fig. 3 is binary image of the invention.
Fig. 4 is sausage long axis center line markings figure of the invention.
Fig. 5 is sausage long axis Graph of the invention.
Fig. 6 is search sausage both ends rest position schematic diagram of the invention.
Fig. 7 is sausage positioning result figure of the invention.
Fig. 8 is back gauge Boundary and interval Margin parameter schematic diagram of the invention.
Fig. 9 is of the invention to filter out result figure.
Specific embodiment
Below by specific embodiment, the present invention is described further, and following embodiment is explanation of the invention
And the invention is not limited to following embodiments.
As shown in Figure 1, sausage Automated Sorting System of the invention is by industrial personal computer 1, controller 2, industrial robot 3, industry
Camera 4, light source 5 and conveyer belt 6 form, and industrial robot 3 is located at 6 top of conveyer belt, and industrial camera 4 is fixed on industrial machine
An annular light source 5 is placed right above the upstream of 3 crawl position of people and conveyer belt 6, immediately below industrial camera 4 for keeping sausage
By uniform illumination.The working principle of system is: conveyer belt transmits sausage with certain speed, and light source direction is towards on conveyer belt
Sausage, industrial personal computer control controller and send strobe signal to industrial camera, and triggering camera, which take pictures to sausage, obtains sausage figure
Picture handles image after sausage image transmitting to industrial personal computer, obtains the deviation angle of sausage and the vertical central axis line of sausage
Coordinate, industrial personal computer combine the movement for having carried out the industrial camera of hand and eye calibrating and the nominal data of industrial robot and conveyer belt
Speed calculates the movement position of Industrial Robot Manipulator using the deviation angle of sausage and the vertical central axis line coordinates of sausage
And crawl posture, the sausage on conveyer belt is grabbed to control industrial robot by controller.
The treatment effect that can be seen that visual component from above system working principle directly affects the property of entire sorting system
Can, when visual component is to the sausage identification positioning mistake on conveyer belt or even fails, industrial machine per capita can not be to sausage
It is grabbed.
A kind of sausage intelligent sorting method of view-based access control model guidance of the invention, includes five steps:
Step 1: use fixed threshold value by sausage image binaryzation；
Quality of the sausage in image directly affects the precision of its identification positioning, by optimizing and revising light-source brightness
The image quality of sausage can be greatly promoted with the camera exposure time.After camera acquires image, using fixed threshold to sausage figure
As progress binaryzation (as shown in Figure 2), in binary image (as shown in Figure 3), determine that sausage foreground target is black, background
Part is white.Since conveyer belt is white, vulnerable to contamination, to reduce influence of the background area to foreground target, binaryzation threshold
Value is usually arranged as 125.
Step 2: the long axis of spindle of sausage in bianry image is extracted；
Due to the elongated shape of sausage, there is preferable linearity, therefore can be realized by extracting long axis of spindle to perfume (or spice)
The positioning of intestines.Prospect line segment is both horizontally and vertically scanned, if the line segment length is located in suitable interval, extracts the line
Candidate point of the central point of section as vertical centre.With sausage normal diameter DStandardOn the basis of, when sausage is in ± 45 ° of inclinations
When, the line segment length of horizontal or vertical direction can elongated be 1.414 × DStandard.When sausage bending, it is bent angled portion
Line segment length is about 0.8 × DStandard, therefore, set line segment length section are as follows: [0.8 × DStandard,1.5×DStandard].Figure
4 be sausage long axis center line markings figure, and red line mark is the centerline that horizontal sweep obtains, and Green Marker is then that vertical scanning obtains
Centerline, color is brighter for Green Marker in black white image.Since set line segment length section is with single times of sausage
Diameter is criterion, and center line markings select the axis mark line be single sausage, therefore cannot extract two or more sausages side by side
Axis mark line when being sticked together also will appear the phenomenon that axis marks thread breakage at simple adhesion.In order to promote length
The connectivity of axis of spindle carries out dilation operation to mark point.
Step 3: it using the straightway of the long axis of spindle of Hough transform sausage, excludes to repeat straight line；
Using probability Hough straight-line detection, the straightway for meeting the long axis of spindle of sausage of certain length is extracted, it is as potential
The long axis of spindle of sausage, the length threshold of long axis of spindle is a quarter of at least sausage length, in Fig. 5, purple lines mark
Note (the brighter line markings of color) is the long axis of spindle of sausage extracted using probability Hough straight-line detection.Same root
The long axis of spindle of sausage is easy to detect a plurality of straight line, is potential sausage central axes.Every time with certain linear search both ends
To rest position, be both needed to differentiate this straight line whether with the straight line of successful search to rest position repeats in the early time.
If being determined as being located at same root sausage, that is, abandon searching for current straight line.Wherein, differentiate the condition for repeating straight line are as follows:
1. current straightway central point is less than half of clinodiagonal of standard sausages with having detected at a distance from sausage central point
Length；
2. current straightway central point with detected sausage central point line inclination angle and detected straight incline angle
Difference less than 30 degree.
If meeting two above condition simultaneously, differentiate that sausage locating for current straightway has been searched both ends cut-off
Position, should not repeat search, directly give up current straight line.
Step 4: search sausage both ends rest position calculates the deviation angle of sausage and the centre coordinate of sausage；
After searching straightway using Hough transform, the rest position at sausage central axes both ends can be searched further for.Sausage
Middle section is more full sturdy, attenuates along centre to both ends meeting closing waist, therefore search for rest position to both ends by central axes,
And then the centre coordinate of sausage could be accurately positioned out.Both ends must search rest position, can be considered as a complete perfume
Intestines.If extending point (middle branch) on central axes is background colour, this root sausage is considered as part sausage, i.e., only part sausage is located at
In visual field, sausage center calculated fails to embody the real center of this root sausage, therefore gives up this root sausage.Fig. 6 is shown
Search for sausage both ends rest position schematic diagram, along central axes with a fixed step size to both ends extend search for, according to axis point and with
Whether the vertical radial point of axis is foreground pixel or background pixel, to differentiate the rest position at sausage both ends.
Define axis point A, four minutes diameter point B, internal diameter point C, outer diameter point D:
Axis point A is the point extended from straightway endpoint with a fixed step size to both ends on central axes；
Four points of diameter point B are to have point A tetra- minutes with point A from axial point A on radial line (or for vertical separated time) at axial point A
One of diameter range points；
Internal diameter point C be on the radial line at the place axial point A from axial point A and point A has the range points of 0.8 radius；
Outer diameter point D be axial point A place radial line on from axial point A and point A have 1.25 radiuses.
Wherein, there are two four points of diameter point B, two internal diameter point C, two outer diameter point D, four points of diameter points on radial line (vertical separated time)
B is mainly used for the case where differentiating axial adhesion, and outer diameter point D is mainly used for the case where differentiating the adhesion of T word.
Judge the condition of sausage both ends rest position are as follows:
1. there are two put as background colour in axis point A and two internal diameter point C；
2. any point B is background colour in two four points of diameter point B at certain end
3. two outer diameter point D are foreground.
Axis point or radial line point only need to meet any of the above-described condition, that is, are considered as having searched the rest position at this end.
The deviation angle and centre coordinate of sausage can be calculated by the both ends rest position of sausage, and then can calculate the length of sausage,
If this length sequences meets length threshold, that is, it is considered as searching a sausage in visual field.
Have four sausages in sample image, can be seen that from sausage positioning result (as shown in Figure 7) successfully orient No. 1,
No. 2, No. 3 three sausages, No. 4 sausages are not filtered completely into visual field.No. 1 sausage individualism, use condition is 1.
Orient the both ends rest position of No. 1 sausage.No. 2, No. 3 sausages be that T font is sticked together.1. use condition can position No. 2
2. the left end rest position of sausage, use condition orient the right end rest position of No. 2, No. 3 sausages, 1. use condition is oriented
The left end rest position of No. 3 sausages.
Step 5: invalid sausage is filtered out.
Clamp sausage using clamping jaw, in order to guarantee clamp sausage when it is interference-free, close to transmission belt edge sausage and
Other sausages of attachment are considered as invalid sausage.Back gauge Boundary parameter and (the corresponding signal of interval Margin parameter are set
Figure is shown in Fig. 8) to differentiate invalid sausage, detailed criterion are as follows: 1. identified sausage center abscissa and visual field or so two
The distance of side is less than Boundary；2. having other sausages within the scope of identified sausage long axis edge distance interval Margin, i.e.,
Using sausage radius as step-length radiate, check radiation length at along the clamping jaw length range of long axis direction with the presence or absence of two or with
Upper pixel is foreground pixel point.Fig. 9, which is shown, to be filtered out as a result, 1,2, No. 4 sausage of green filament mark is due to nearby there is perfume (or spice)
Intestines interference cannot be grabbed by clamping jaw, and No. 4 sausages of the thick frame of purple can be grabbed by clamping jaw.
Compared with the sausage automatic sorting scheme that robomotion Co., Ltd of existing Germany is proposed, the present invention is proposed
View-based access control model guidance sausage automatic sorting method have the stronger adaptation of product, higher sausage identification positioning accuracy and
Lower leakage picks rate, it is thus possible to more effectively promote the sausage production efficiency of enterprise.
Above content is only illustrations made for the present invention described in this specification.Technology belonging to the present invention
The technical staff in field can make various modifications or additions to the described embodiments or by a similar method
Substitution, content without departing from description of the invention or beyond the scope defined by this claim should belong to this
The protection scope of invention.
Claims (9)
1. a kind of sausage intelligent sorting method of view-based access control model guidance, it is characterised in that comprise the steps of:
Step 1: use fixed threshold value by sausage image binaryzation；
Step 2: the long axis of spindle of sausage in bianry image is extracted；
Step 3: it using the straightway of the long axis of spindle of Hough transform sausage, excludes to repeat straight line；
Step 4: search sausage both ends rest position calculates the deviation angle of sausage and the centre coordinate of sausage；
Step 5: invalid sausage is filtered out.
2. a kind of sausage intelligent sorting method of view-based access control model guidance described in accordance with the claim 1, it is characterised in that: the step
Sausage image is grabbed by industrial camera in rapid one, and crawl process is conveyer belt with certain speed transmission sausage, light source direction
Towards the sausage on conveyer belt, industrial personal computer controls controller and sends strobe signal to industrial camera, and triggering camera carries out sausage
It takes pictures and obtains sausage image.
3. a kind of sausage intelligent sorting method of view-based access control model guidance described in accordance with the claim 1, it is characterised in that: the step
Rapid one is specially to carry out binaryzation, in binary image, sausage to sausage image using fixed threshold after camera acquires image
Foreground target is black, and background parts are white, and binarization threshold is set as 125.
4. a kind of sausage intelligent sorting method of view-based access control model guidance described in accordance with the claim 1, it is characterised in that: the step
Rapid two be specially that prospect line segment is both horizontally and vertically scanned, if the line segment length is located at [0.8 × DStandard,1.5×
DStandard] in section, extract candidate point of the central point as vertical centre of the line segment, DStandardFor sausage normal diameter, by
It is using single times of sausage diameter as criterion in set line segment length section, center line markings select the axis label be single sausage
Line, therefore two cannot be extracted or axis mark line when more sausages are sticked together side by side, can also it go out at simple adhesion
The phenomenon that existing axis label thread breakage, carries out dilation operation to mark point to promote the connectivity of long axis of spindle.
5. a kind of sausage intelligent sorting method of view-based access control model guidance described in accordance with the claim 1, it is characterised in that: the step
Rapid three be specially to utilize probability Hough straight-line detection, extracts the long axis of spindle of sausage of at least a quarter length of sausage length
Straightway, the as potential long axis of spindle of sausage, it is latent that the long axis of spindle of same root sausage, which is easy to detect a plurality of straight line,
Sausage central axes, every time with certain linear search both ends to rest position before, be both needed to differentiate this straight line whether in the early time
The straight line of successful search to rest position repeats, if being determined as being located at same root sausage, that is, abandons searching for current straight line.
6. a kind of sausage intelligent sorting method of view-based access control model guidance according to claim 5, it is characterised in that: described to sentence
Not this straight line whether with the straight line repetitive process of successful search to rest position is in the early time
Condition 1: current straightway central point is less than half of clinodiagonal of standard sausages with having detected at a distance from sausage central point
Length；
Condition 2: current straightway central point and the inclination angle for having detected sausage central point line and straight incline angle has been detected
Difference less than 30 degree；
If meeting two above condition simultaneously, differentiate that sausage locating for current straightway has been searched both ends cut-off position
It sets, is not repeated to search for, directly give up current straight line.
7. a kind of sausage intelligent sorting method of view-based access control model guidance described in accordance with the claim 1, it is characterised in that: the step
Rapid four be specially that sausage middle section is more full sturdy, attenuates along centre to both ends meeting closing waist, is searched by central axes to both ends
Rope rest position, and then the centre coordinate of sausage is accurately positioned out, both ends must search rest position, can be considered as one it is complete
Whole sausage；If extending point on central axes is background colour, this root sausage is considered as part sausage, i.e., only part sausage is located at view
In, sausage center calculated fails to embody the real center of this root sausage, therefore gives up this root sausage, along central axes with
Whether one fixed step size extends to both ends is searched for, be foreground pixel or background picture according to axis point and radial point perpendicular to the axis
Element, to differentiate the rest position at sausage both ends.
8. a kind of sausage intelligent sorting method of view-based access control model guidance according to claim 7, it is characterised in that: described to sentence
The process of the rest position at other box culvert both ends is to define axis point A, four minutes diameter point B, internal diameter point C, outer diameter point D；
Axis point A is the point extended from straightway endpoint with a fixed step size to both ends on central axes；
Four points of diameter point B be on the radial line at the place axial point A from axial point A and point A has the range points of point A a quarter diameter；
Internal diameter point C be on the radial line at the place axial point A from axial point A and point A has the range points of 0.8 radius；
Outer diameter point D be on the radial line at the place axial point A from axial point A and point A has the point of 1.25 radiuses；
Wherein, there are two four points of diameter point B, two internal diameter point C, two outer diameter point D, four points of diameter point B to be mainly used for differentiating on radial line
The case where axial adhesion, outer diameter point D are mainly used for the case where differentiating the adhesion of T word；
Judge the condition of sausage both ends rest position are as follows:
Condition 1: there are two put as background colour in axis point A and two internal diameter point C；
Condition 2: any point B is background colour in two four points of diameter point B at certain end；
3: two outer diameter point D of condition are foreground；
Axis point or radial line point only need to meet any of the above-described condition, that is, are considered as having searched the rest position at this end, by perfume (or spice)
The both ends rest position of intestines can calculate the deviation angle and centre coordinate of sausage, and then calculate the length of sausage, if this grows
Degree result meets length threshold, that is, is considered as searching a sausage in visual field.
9. a kind of sausage intelligent sorting method of view-based access control model guidance described in accordance with the claim 1, it is characterised in that: the step
Rapid five be specially setting back gauge Boundary parameter and interval Margin parameter to differentiate invalid sausage, criterion are as follows:
Condition 1: identified sausage center abscissa at left and right sides of visual field at a distance from be less than Boundary；
Condition 2: there are other sausages within the scope of identified sausage long axis edge distance interval Margin, i.e., be step with sausage radius
Long radiation checks that whether there is two or more pixels at radiation length along the clamping jaw length range of long axis direction is prospect
Pixel.
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 true CN109127462A (en) | 2019-01-04 |
| CN109127462B 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) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110575973A (en) * | 2019-10-21 | 2019-12-17 | 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 dimension calculating method based on Opencv image analysis and scallop sorting system |
| 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 dimension calculating method based on Opencv image analysis and scallop sorting system |
| 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 |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110575973A (en) * | 2019-10-21 | 2019-12-17 | 台州学院 | crop seed quality detection and screening system |
| CN110575973B (en) * | 2019-10-21 | 2021-08-10 | 台州学院 | Crop seed quality detection and screening system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109127462B (en) | 2020-09-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7167579B2 (en) | Method and apparatus for determining the sex of a fertilized egg | |
| CN105654097B (en) | The detection method of quadrangle marker in image | |
| CN106546263B (en) | A kind of laser leveler shoot laser line detecting method based on machine vision | |
| CN105488503B (en) | A kind of non-coding circular ring shape mark point center of circle image coordinate detection method | |
| CN102704215B (en) | Automatic cutting method of embroidery cloth based on combination of DST file parsing and machine vision | |
| CN104992449A (en) | Information identification and surface defect on-line detection method based on machine visual sense | |
| CN109693140A (en) | A kind of intelligent flexible production line and its working method | |
| CN108890692A (en) | A kind of material color identification method for industrial robot vision's sorting | |
| CA2552168A1 (en) | Artificial vision inspection method and system | |
| CN104122271A (en) | Automated optical inspection (AOI)-based bullet apparent defect detection method | |
| CN106052793A (en) | Machine vision based liquid level sub-quality product marking method | |
| CN106546185B (en) | A kind of profile quality determining method based on Machine Vision Detection | |
| CN109324056B (en) | Sewing thread trace measuring method based on machine vision | |
| CN109003271A (en) | A kind of Wiring harness connector winding displacement quality determining method based on deep learning YOLO algorithm | |
| CN104966302B (en) | A kind of detection localization method of any angle laser cross | |
| CN109127462A (en) | A kind of sausage intelligent sorting method of view-based access control model guidance | |
| CN105404900B (en) | A kind of localization method and device of diode side by side | |
| CN206920024U (en) | Colour of insulated conductor sequencing system | |
| CN107516329B (en) | Positioning method for oil holes of speed reducer | |
| CN108520260A (en) | The recognition methods of visible foreign matters in bottled oral solution | |
| CN113506255B (en) | Automatic detection method for clothing suture defects based on high-precision digital image | |
| CN106767425A (en) | A kind of vision measuring method of bearing snap spring gap | |
| CN114926415A (en) | Steel rail surface detection method based on PCNN and deep learning | |
| CN109945842B (en) | Method for detecting label missing and analyzing labeling error of end face of bundled round steel | |
| CN103718025B (en) | Container mouth portion inspection method and device |
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 |