CN104897671A - Identification system for fruit stem and calyx of fruit - Google Patents
Identification system for fruit stem and calyx of fruit Download PDFInfo
- Publication number
- CN104897671A CN104897671A CN201510230771.4A CN201510230771A CN104897671A CN 104897671 A CN104897671 A CN 104897671A CN 201510230771 A CN201510230771 A CN 201510230771A CN 104897671 A CN104897671 A CN 104897671A
- Authority
- CN
- China
- Prior art keywords
- fruit
- image
- height
- laser
- ccd 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.)
- Granted
Links
Abstract
The invention discloses an identification system for the fruit stem and the calyx of a fruit. The system comprises a CCD camera, a computer connected with the CCD camera, a linear array laser, a transmission device and at least one light source. The CCD camera and the linear array laser are disposed at the same height above the center line of the transmission device. A plane formed by the center line of the CCD camera, the center line of the linear array laser and the center line of the transmission device is perpendicular to the transmission device. Laser lines formed on the transmission device by the laser light emitted from the linear array laser are perpendicular to the center line of the transmission device. Meanwhile, the laser lines are right below the CCD camera. The light source is used for providing illumination on a fruit arranged on the transmission device. The computer is used for receiving the image of the fruit acquired by the CCD camera, and identifying the fruit stem and the calyx of the fruit based on the image of the fruit. According to the invention, the complexity of identifying the fruit stem and the calyx of the fruit through the positioning process of a mechanical device can be overcome. Meanwhile, the repeated training required for identifying the fruit stem and the calyx of the fruit based on the pattern recognition technique can be avoided. Moreover, the complex coding and decoding operation on a lattice structure based on the lighting technology can be overcome.
Description
Technical field
The present invention relates to agricultural product test technique automatic field, be specifically related to a kind of recognition system of fruit carpopodium calyx.
Background technology
External Defect is that fruit (as apple) quality reflects the most intuitively.At present, machine vision technique has been widely used in the detection of fruit external sort.After the surface image of collected by camera fruit, transfer to computing machine, then obtained the external sort feature such as size, shape, color, defect of fruit by the method for image procossing, and then according to the standard of sorted fruits, classification process is carried out to fruit.For apple, current apple sorting equipment can carry out robotization sorting according to the size of apple, color, shape.But due to the carpopodium calyx of apple very similar with defect in color with texture, therefore apple quality screening installation can't carry out grouping system according to the surface imperfection of apple.Identify carpopodium calyx and defect in, mainly through mechanical positioning methods, mode identification method and lattice structure light method.
Carpopodium calyx recognition methods based on machinery location increases assist, by the attitude of mechanical hook-up adjustment apple, makes the orientation of the carpopodium calyx of apple have fixing known location.Such mechanical hook-up more complicated, is unfavorable for quick identification and the location of apple stem calyx.
Mode based on pattern-recognition carries out selection and the extraction of feature before detection, and then training classifier is to realize the discriminant classification to carpopodium calyx and defect mode.But need repetition training sorter based on the method for pattern-recognition, and sorter height depends on the conditions such as selected characteristic sum illumination.
Apple stem calyx recognition methods based on lattice structure light is the surface by the structured light of dot matrix being beaten at apple, according to the change identification carpopodium of dot matrix and calyx.Method based on lattice structure light needs to carry out Code And Decode to the dot matrix of structured light, and operand is larger.
Summary of the invention
Technical matters to be solved by this invention how to reduce the complicacy of mechanical hook-up localization method determination carpopodium calyx, avoids repetition training required for mode identification method identification carpopodium calyx and reduces the problem of coding and decoding computing of lattice structure light technical sophistication.
For this purpose, the present invention proposes a kind of recognition system of fruit carpopodium calyx, comprising: CCD camera, the computing machine be connected with CCD camera, linear array diode laser, conveyer and at least one light source;
Wherein, described CCD camera and described linear array diode laser are arranged on the phase co-altitude above the center line of described conveyer, and the plane orthogonal that the center line of described CCD camera, linear array diode laser and conveyer is formed is in described conveyer;
Wherein, the laser lines that the laser that described linear array diode laser sends is formed on described conveyer and the central axis of described conveyer, and described laser lines are immediately below described CCD camera;
Wherein, described light source, for providing illumination to the fruit on described conveyer;
Wherein, described computing machine, for receiving the fruit image that described CCD camera gathers, and according to described fruit image, identify described fruit carpopodium calyx, wherein, described fruit image is the laser line image that described laser lines are formed on described fruit.
Optionally, described computing machine, comprising:
Receiving element, for receiving the fruit image that described CCD camera gathers; Described fruit image is the laser line image that described laser lines are formed on described fruit;
Recognition unit, for the fruit image received according to described receiving element, identifies described fruit carpopodium calyx.
Optionally, described recognition unit, comprising:
Fruit height obtains subelement, for according to pre-set image processing rule, obtains Pixel Information and the range information of the fruit image that described receiving element receives, and obtains the height of described fruit according to described Pixel Information and range information;
Fruit height draws subelement, for obtaining the fruit height that subelement obtains according to described fruit height, draws fruit height image;
Carpopodium calyx recognin unit, for drawing the fruit height image that subelement is drawn according to described fruit height, identifies fruit carpopodium calyx.
Optionally, the height h that described fruit height acquisition subelement obtains described fruit meets following formula:
Wherein, h is the maximum height of intersecting lens apart from described conveyer of fruit surface formation crossing with the laser that described linear array diode laser sends; L is the height of described CCD camera apart from described conveyer; S is the distance between described linear array diode laser and described CCD camera; The distance of the d intersection point distance datum line that to be described CCD camera crossing with the extended line of P point line and described conveyer;
Wherein, P point is the position that the intersecting lens of fruit surface formation crossing with the laser that described linear array diode laser sends is corresponding apart from the maximum height of described conveyer;
Wherein, described datum line is the position at the laser lines place that laser that described linear array diode laser sends is formed on described conveyer;
Wherein, d is obtained according to pre-set image processing rule by described fruit height acquisition subelement.
Optionally, described carpopodium calyx recognin unit, specifically for:
Draw according to described fruit height the fruit height image that subelement draws, ask for the luminance quantization value of maximum height value in fruit height image and minimum height values;
The fruit height image of described fruit height being drawn to subelement drafting carries out binary segmentation, obtains the region Mask image at fruit place;
Ask for the minimum circumscribed circle of described region Mask image, and record center of circle O and the radius R of minimum circumscribed circle;
Newly-built initial pictures Con, in described initial pictures Con, all pixel brightness values are zero;
In described initial pictures Con, the luminance quantization value setting described maximum height value is the brightness value of described center of circle O, and the luminance quantization value of setting minimum height values is the brightness value of pixel on radius R place annulus, obtains the first image Con;
Take O as the center of circle, with a pixel for step-length, described first image Con constructs donut, and the pixel on the annulus of same radius has identical height, namely has identical brightness value, obtains the second image Con;
Medium filtering process is carried out to described second image Con, fills the gap point between annulus in described second image Con, obtain the 3rd image Con;
Carry out mask process to described 3rd image Con, obtain the 4th image Con, described 4th image Con has identical boundary shape with the fruit image that described receiving element receives;
Described fruit height is drawn the fruit height image of subelement drafting divided by described 4th image Con, and then be multiplied by 255 acquisition ratio images Ratio;
According to the single threshold segmentation rule preset, carpopodium calyx region is extracted to described ratio images Ratio.
Compared to prior art; the recognition system of fruit carpopodium calyx of the present invention is the recognition system of a kind of fruit based on machine vision (as apple) carpopodium calyx; relate to agricultural product appearance quality detection field; for apple; this system obtains the height map of apple on travelling belt by linear array diode laser and area array cameras; then utilize image processing algorithm to build one and the height map that obtains has the height reconstruction figure of identical boundary shape, then utilize the identification of ratio algorithm realization carpopodium calyx.Instant invention overcomes the complicacy of mechanical hook-up localization method determination carpopodium calyx, avoid the repetition training required for mode identification method identification carpopodium calyx, and avoid the coding and decoding computing of lattice structure light technical sophistication.The present invention can be simple and quick the identification realizing carpopodium calyx, apple external sort detect in there is larger application potential.
Accompanying drawing explanation
The recognition system structural drawing of a kind of fruit carpopodium calyx that Fig. 1 provides for the embodiment of the present invention;
The schematic diagram of the height h of the acquisition fruit that Fig. 2 provides for the embodiment of the present invention.
Embodiment
For making the object of the embodiment of the present invention, technical scheme and advantage clearly, below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly described, obviously, described embodiment is the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
As shown in Figure 1, the present embodiment discloses a kind of recognition system of fruit carpopodium calyx, and this system can comprise: CCD camera 1, the computing machine 2 be connected with CCD camera 1, linear array diode laser 3, conveyer 4 and at least one light source 5.
The system of the present embodiment comprises two light sources 5, and for providing illumination to the fruit on conveyer 4, and light source 5 is the paster LED linearly distributed.
In the present embodiment, CCD camera 1 and linear array diode laser 3 are arranged on the phase co-altitude above the center line of conveyer 4, and the plane orthogonal that CCD camera 1, linear array diode laser 3 and the center line of conveyer 4 are formed is in conveyer 4.
In the present embodiment, the laser lines (overlapping with the datum line in Fig. 1) that the laser that linear array diode laser 3 sends is formed on conveyer 4 and the central axis of conveyer 4, and described laser lines are immediately below CCD camera 1; Particularly, the laser plane that the laser that linear array diode laser 3 sends is formed is crossing with the travelling belt of conveyer 4 forms laser lines.
In the present embodiment, computing machine 2, for receiving the fruit image that CCD camera 1 gathers, and according to fruit image, identify described fruit carpopodium calyx, wherein, described fruit image is the laser line image that described laser lines are formed on described fruit.
In a concrete example, computing machine 2, comprising: receiving element and recognition unit;
Wherein, receiving element, for receiving the fruit image that CCD camera 1 gathers; Described fruit image is the laser line image that described laser lines are formed on described fruit;
Wherein, recognition unit, for the fruit image received according to receiving element, identifies described fruit carpopodium calyx.
In a concrete example, recognition unit, comprising: fruit height obtains subelement, fruit height draws subelement and carpopodium calyx recognin unit;
Wherein, fruit height obtains subelement, for according to pre-set image processing rule, obtains Pixel Information and the range information of the fruit image that described receiving element receives, and obtains the height of described fruit according to described Pixel Information and range information;
Wherein, fruit height draws subelement, for obtaining the fruit height that subelement obtains according to described fruit height, draws fruit height image;
Wherein, carpopodium calyx recognin unit, for drawing the fruit height image that subelement is drawn according to described fruit height, identifies fruit carpopodium calyx.
In a concrete example, as shown in Figure 2 (for convenience of describing, the fruit shape in this example is square), described fruit height obtains the height h that subelement obtains described fruit and meets following formula:
Wherein, h is the maximum height of intersecting lens apart from described conveyer 4 of fruit surface formation crossing with the laser that linear array diode laser 3 sends; L is the height of CCD camera 1 apart from conveyer 4; S is the distance between linear array diode laser 3 and CCD camera 1; The distance of the d intersection point distance datum line that to be CCD camera 1 crossing with the extended line of P point line and conveyer 4; Described datum line is the position at the laser lines place that laser that linear array diode laser 3 sends is formed on conveyer 4;
Wherein, P point is the position corresponding to maximum height of the intersecting lens distance conveyer 4 of fruit surface formation crossing with the laser that linear array diode laser 3 sends;
Wherein, d is obtained according to pre-set image processing rule by described fruit height acquisition subelement.
In a concrete example, described carpopodium calyx recognin unit, specifically for:
S1, to draw the fruit height image that subelement draws according to described fruit height, ask for the luminance quantization value of maximum height value in fruit height image and minimum height values;
S2, described fruit height drawn to the fruit height image that subelement draws and carry out binary segmentation, obtain the region Mask image at fruit place;
S3, ask for the minimum circumscribed circle of described region Mask image, and record center of circle O and the radius R of minimum circumscribed circle;
S4, newly-built initial pictures Con, in described initial pictures Con, all pixel brightness values are zero;
S5, in described initial pictures Con, the luminance quantization value setting described maximum height value is the brightness value of described center of circle O, and the luminance quantization value of setting minimum height values is the brightness value of pixel on radius R place annulus, obtains the first image Con;
S6, be the center of circle with O, with a pixel for step-length, described first image Con constructs donut, and the pixel on the annulus of same radius has identical height, namely has identical brightness value, obtains the second image Con;
S7, medium filtering process is carried out to described second image Con, fill the gap point between annulus in described second image Con, obtain the 3rd image Con;
S8, carry out mask process to described 3rd image Con, obtain the 4th image Con, described 4th image Con has identical boundary shape with the fruit image that described receiving element receives;
S9, described fruit height drawn fruit height image that subelement draws divided by described 4th image Con, and then be multiplied by 255 acquisition ratio images Ratio;
The single threshold segmentation rule that S10, basis are preset, extracts carpopodium calyx region to described ratio images Ratio.Single threshold segmentation rule in the present embodiment can adopt existing single threshold dividing method, and the present embodiment no longer describes in detail.
The recognition system of above-mentioned fruit carpopodium calyx, when not having fruit immediately below CCD camera 1, the laser lines that CCD camera 1 gathers are straight line; When fruit is immediately below CCD camera 1, owing to having certain distance s between linear array diode laser 3 and CCD camera 1, the laser lines that therefore CCD camera 1 gathers are a curve.Fruit height is higher, and it is more obvious that the laser lines that CCD camera 1 gathers depart from datum line (linear position when existing without object).
Utilize distance s can ask for the elevation information of fruit according to triangle analogue method.First CCD camera 1 is utilized to obtain the image of laser lines, image processing method is utilized to carry out refinement to image, ask for Pixel Information and the range information of the deviation between laser lines and datum line that the CCD camera 1 that causes due to distance s gathers, then utilize Similar Principle of Triangle, ask for height.Relational expression is:
L, for being known quantity, can record; S is known quantity, can record.
For whole fruit, above-mentioned triangle similarity relation can be utilized to ask for corresponding height information.Along with the transmission of travelling belt, fruit is lined by line scan, then can obtain the elevation information at apple every bit place, i.e. height map.
For apple, the carpopodium calyx of apple has the feature of depression, and therefore human eye can be easy to according to the depression in height map judge carpopodium calyx.But the edge of apple also has relatively low height, in order to make computing machine identify carpopodium calyx fast, the carpopodium calyx recognin unit in computing machine, performs following step S1 to S10:
S1, to draw the fruit height image that subelement draws according to described fruit height, ask for the luminance quantization value of maximum height value in fruit height image and minimum height values;
S2, described fruit height drawn to the fruit height image that subelement draws and carry out binary segmentation, obtain the region Mask image at fruit place;
S3, ask for the minimum circumscribed circle of described region Mask image, and record center of circle O and the radius R of minimum circumscribed circle;
S4, newly-built initial pictures Con, in described initial pictures Con, all pixel brightness values are zero;
S5, in described initial pictures Con, the luminance quantization value setting described maximum height value is the brightness value of described center of circle O, and the luminance quantization value of setting minimum height values is the brightness value of pixel on radius R place annulus, obtains the first image Con;
S6, be the center of circle with O, with a pixel for step-length, described first image Con constructs donut, and the pixel on the annulus of same radius r has identical height, namely has identical brightness value, obtains the second image Con; Wherein, to be the brightness value computing formula of pixel on the annulus of r be radius:
Wherein: I
intensityfor radius be r annulus on the brightness value of pixel; Max is the luminance quantization value of maximum height value; Min is the luminance quantization value of minimum height values;
S7, medium filtering process is carried out to described second image Con, fill the gap point between annulus in described second image Con, obtain the 3rd image Con;
S8, carry out mask process to described 3rd image Con, obtain the 4th image Con, described 4th image Con has identical boundary shape with the fruit image that described receiving element receives;
S9, described fruit height drawn fruit height image that subelement draws divided by described 4th image Con, and then be multiplied by 255 acquisition ratio images Ratio; By the notch characteristic of carpopodium calyx; in the height image of apple; carpopodium calyx presents lower brightness; and the height image built does not consider carpopodium calyx; after correspondence position pixel brightness value does division arithmetic; carpopodium calyx place (low-light level removes in high brightness) will present lower brightness value, and all the other positions (similar luminance value is divided by) then present higher brightness value.
The single threshold segmentation rule that S10, basis are preset, extracts carpopodium calyx region to described ratio images Ratio.Single threshold segmentation rule in the present embodiment can adopt existing single threshold dividing method, and the present embodiment no longer describes in detail.
Those skilled in the art can understand, although embodiments more described herein to comprise in other embodiment some included feature instead of further feature, the combination of the feature of different embodiment means and to be within scope of the present invention and to form different embodiments.
Although describe embodiments of the present invention by reference to the accompanying drawings, but those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, such amendment and modification all fall into by within claims limited range.
Claims (5)
1. a recognition system for fruit carpopodium calyx, is characterized in that, comprising: CCD camera, the computing machine be connected with CCD camera, linear array diode laser, conveyer and at least one light source;
Wherein, described CCD camera and described linear array diode laser are arranged on the phase co-altitude above the center line of described conveyer, and the plane orthogonal that the center line of described CCD camera, linear array diode laser and conveyer is formed is in described conveyer;
Wherein, the laser lines that the laser that described linear array diode laser sends is formed on described conveyer and the central axis of described conveyer, and described laser lines are immediately below described CCD camera;
Wherein, described light source, for providing illumination to the fruit on described conveyer;
Wherein, described computing machine, for receiving the fruit image that described CCD camera gathers, and according to described fruit image, identify described fruit carpopodium calyx, wherein, described fruit image is the laser line image that described laser lines are formed on described fruit.
2. system according to claim 1, is characterized in that, described computing machine, comprising:
Receiving element, for receiving the fruit image that described CCD camera gathers; Described fruit image is the laser line image that described laser lines are formed on described fruit;
Recognition unit, for the fruit image received according to described receiving element, identifies described fruit carpopodium calyx.
3. system according to claim 2, is characterized in that, described recognition unit, comprising:
Fruit height obtains subelement, for according to pre-set image processing rule, obtains Pixel Information and the range information of the fruit image that described receiving element receives, and obtains the height of described fruit according to described Pixel Information and range information;
Fruit height draws subelement, for obtaining the fruit height that subelement obtains according to described fruit height, draws fruit height image;
Carpopodium calyx recognin unit, for drawing the fruit height image that subelement is drawn according to described fruit height, identifies fruit carpopodium calyx.
4. system according to claim 3, is characterized in that, the height h that described fruit height acquisition subelement obtains described fruit meets following formula:
Wherein, h is the maximum height of intersecting lens apart from described conveyer of fruit surface formation crossing with the laser that described linear array diode laser sends; L is the height of described CCD camera apart from described conveyer; S is the distance between described linear array diode laser and described CCD camera; The distance of the d intersection point distance datum line that to be described CCD camera crossing with the extended line of P point line and described conveyer;
Wherein, P point is the position that the intersecting lens of fruit surface formation crossing with the laser that described linear array diode laser sends is corresponding apart from the maximum height of described conveyer;
Wherein, described datum line is the position at the laser lines place that laser that described linear array diode laser sends is formed on described conveyer;
Wherein, d is obtained according to pre-set image processing rule by described fruit height acquisition subelement.
5. system according to claim 4, is characterized in that, described carpopodium calyx recognin unit, specifically for:
Draw according to described fruit height the fruit height image that subelement draws, ask for the luminance quantization value of maximum height value in fruit height image and minimum height values;
The fruit height image of described fruit height being drawn to subelement drafting carries out binary segmentation, obtains the region Mask image at fruit place;
Ask for the minimum circumscribed circle of described region Mask image, and record center of circle O and the radius R of minimum circumscribed circle;
Newly-built initial pictures Con, in described initial pictures Con, all pixel brightness values are zero;
In described initial pictures Con, the luminance quantization value setting described maximum height value is the brightness value of described center of circle O, and the luminance quantization value of setting minimum height values is the brightness value of pixel on radius R place annulus, obtains the first image Con;
Take O as the center of circle, with a pixel for step-length, described first image Con constructs donut, and the pixel on the annulus of same radius has identical height, namely has identical brightness value, obtains the second image Con;
Medium filtering process is carried out to described second image Con, fills the gap point between annulus in described second image Con, obtain the 3rd image Con;
Carry out mask process to described 3rd image Con, obtain the 4th image Con, described 4th image Con has identical boundary shape with the fruit image that described receiving element receives;
Described fruit height is drawn the fruit height image of subelement drafting divided by described 4th image Con, and then be multiplied by 255 acquisition ratio images Ratio;
According to the single threshold segmentation rule preset, carpopodium calyx region is extracted to described ratio images Ratio.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510230771.4A CN104897671B (en) | 2015-05-07 | 2015-05-07 | A kind of identifying system of fruit carpopodium calyx |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510230771.4A CN104897671B (en) | 2015-05-07 | 2015-05-07 | A kind of identifying system of fruit carpopodium calyx |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104897671A true CN104897671A (en) | 2015-09-09 |
| CN104897671B CN104897671B (en) | 2018-09-11 |
Family
ID=54030472
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510230771.4A Active CN104897671B (en) | 2015-05-07 | 2015-05-07 | A kind of identifying system of fruit carpopodium calyx |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104897671B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108445003A (en) * | 2018-03-19 | 2018-08-24 | 烟台大学 | A kind of fruit quality detection device and detection method |
| CN108801942A (en) * | 2018-03-01 | 2018-11-13 | 上海交通大学 | The adjustable linear array laser detection electromechanical assembly and method, system that rice tillering counts |
| CN109489572A (en) * | 2018-12-28 | 2019-03-19 | 浙江农林大学 | A kind of air conditioning for automobiles piston Internal Spherical Surface apparatus for detecting diameter |
| CN109650009A (en) * | 2019-02-02 | 2019-04-19 | 塔里木大学 | A kind of bergamot pear azimuth adjustment device and method |
| CN110495624A (en) * | 2019-08-29 | 2019-11-26 | 贵州大学 | A kind of fruit based on image recognition removes speed governor |
| CN111811416A (en) * | 2020-06-28 | 2020-10-23 | 江苏理工学院 | Device and method for detecting height difference of plane of cooling fan |
| CN111811417A (en) * | 2020-06-28 | 2020-10-23 | 江苏理工学院 | Large-height-difference stepped shaft detection device and detection method |
| CN113051992A (en) * | 2020-11-16 | 2021-06-29 | 泰州无印广告传媒有限公司 | Uniform speed identification system applying transparent card slot |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102854192A (en) * | 2012-08-22 | 2013-01-02 | 北京农业智能装备技术研究中心 | System and method for detecting apple surface defect |
| CN103697833A (en) * | 2013-12-30 | 2014-04-02 | 北京农业智能装备技术研究中心 | Agricultural product shape detecting method and device |
| CN104569154A (en) * | 2015-01-04 | 2015-04-29 | 浙江大学 | Rapid fruit texture non-destructive detection method and detection device |
-
2015
- 2015-05-07 CN CN201510230771.4A patent/CN104897671B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102854192A (en) * | 2012-08-22 | 2013-01-02 | 北京农业智能装备技术研究中心 | System and method for detecting apple surface defect |
| CN103697833A (en) * | 2013-12-30 | 2014-04-02 | 北京农业智能装备技术研究中心 | Agricultural product shape detecting method and device |
| CN104569154A (en) * | 2015-01-04 | 2015-04-29 | 浙江大学 | Rapid fruit texture non-destructive detection method and detection device |
Non-Patent Citations (1)
| Title |
|---|
| 黄文倩等: "基于类球形亮度变换的水果表面缺陷提取", 《农业机械学报》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108801942A (en) * | 2018-03-01 | 2018-11-13 | 上海交通大学 | The adjustable linear array laser detection electromechanical assembly and method, system that rice tillering counts |
| CN108801942B (en) * | 2018-03-01 | 2020-07-24 | 上海交通大学 | Linear array laser imaging method for rice tillering counting |
| CN108445003A (en) * | 2018-03-19 | 2018-08-24 | 烟台大学 | A kind of fruit quality detection device and detection method |
| CN109489572A (en) * | 2018-12-28 | 2019-03-19 | 浙江农林大学 | A kind of air conditioning for automobiles piston Internal Spherical Surface apparatus for detecting diameter |
| CN109489572B (en) * | 2018-12-28 | 2020-08-11 | 浙江农林大学 | Automobile air conditioner piston inner spherical surface diameter detection device |
| CN109650009A (en) * | 2019-02-02 | 2019-04-19 | 塔里木大学 | A kind of bergamot pear azimuth adjustment device and method |
| CN110495624A (en) * | 2019-08-29 | 2019-11-26 | 贵州大学 | A kind of fruit based on image recognition removes speed governor |
| CN111811416A (en) * | 2020-06-28 | 2020-10-23 | 江苏理工学院 | Device and method for detecting height difference of plane of cooling fan |
| CN111811417A (en) * | 2020-06-28 | 2020-10-23 | 江苏理工学院 | Large-height-difference stepped shaft detection device and detection method |
| CN111811417B (en) * | 2020-06-28 | 2022-03-25 | 江苏理工学院 | Large-height-difference stepped shaft detection device and detection method |
| CN113051992A (en) * | 2020-11-16 | 2021-06-29 | 泰州无印广告传媒有限公司 | Uniform speed identification system applying transparent card slot |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104897671B (en) | 2018-09-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104897671A (en) | Identification system for fruit stem and calyx of fruit | |
| Liu et al. | Improved kiwifruit detection using pre-trained VGG16 with RGB and NIR information fusion | |
| Du et al. | Car detection for autonomous vehicle: LIDAR and vision fusion approach through deep learning framework | |
| CN103927526B (en) | Vehicle detecting method based on Gauss difference multi-scale edge fusion | |
| Kong et al. | General road detection from a single image | |
| CN110598690B (en) | End-to-end optical character detection and recognition method and system | |
| CN104700085B (en) | A kind of chip positioning method based on template matches | |
| CN104597057B (en) | A kind of column Diode facets defect detecting device based on machine vision | |
| Bruls et al. | The right (angled) perspective: Improving the understanding of road scenes using boosted inverse perspective mapping | |
| US20190188451A1 (en) | Lightweight 3D Vision Camera with Intelligent Segmentation Engine for Machine Vision and Auto Identification | |
| CN102646193A (en) | Segmentation method of character images distributed in ring shape | |
| CN104881665A (en) | Chip character identification and verification method and apparatus | |
| JP2007235951A (en) | Vehicle image recognition apparatus and its method | |
| US9305224B1 (en) | Method for instant recognition of traffic lights countdown image | |
| CN205862589U (en) | A kind of automatic Vehicle Recognition System | |
| CN108288289B (en) | LED visual detection method and system for visible light positioning | |
| CN102096802A (en) | Face detection method and device | |
| CN111160328A (en) | Automatic traffic marking extraction method based on semantic segmentation technology | |
| CN105893970A (en) | Nighttime road vehicle detection method based on luminance variance characteristics | |
| CN110599453A (en) | Panel defect detection method and device based on image fusion and equipment terminal | |
| CN114387269B (en) | Fiber yarn defect detection method based on laser | |
| CN111695373B (en) | Zebra stripes positioning method, system, medium and equipment | |
| Sathiya et al. | Real time recognition of traffic light and their signal count-down timings | |
| Nguyen et al. | Fast traffic sign detection under challenging conditions | |
| CN204576547U (en) | A kind of chip character check device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 1107, block a, Nongke building, No. 11, Shuguang garden middle road, Haidian District, Beijing, 100097 Patentee after: Intelligent equipment technology research center of Beijing Academy of agricultural and Forestry Sciences Address before: 318b, block a, Beijing Agricultural Science Building, 11 Shuguang Huayuan Middle Road, Haidian District, Beijing 100097 Patentee before: BEIJING RESEARCH CENTER OF INTELLIGENT EQUIPMENT FOR AGRICULTURE |