CN106918595A - A kind of head rice rate batch assay method and its equipment - Google Patents
A kind of head rice rate batch assay method and its equipment Download PDFInfo
- Publication number
- CN106918595A CN106918595A CN201710175005.1A CN201710175005A CN106918595A CN 106918595 A CN106918595 A CN 106918595A CN 201710175005 A CN201710175005 A CN 201710175005A CN 106918595 A CN106918595 A CN 106918595A
- Authority
- CN
- China
- Prior art keywords
- rice
- grain
- head
- point
- assay method
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N2021/845—Objects on a conveyor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N2021/8466—Investigation of vegetal material, e.g. leaves, plants, fruits
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a kind of head rice rate batch assay method and its equipment, obtained comprising image, the grain of rice is uniformly scattered on a moving belt by vibrator, camera is taken pictures in surface and obtains grain of rice initial pictures；Image preprocessing, the grain of rice is extracted from background, and carries out denoising and smoothing processing；The separation of synechia grain of rice, the separation of synechia grain of rice is matched using concave point detection and concave point；Identification head milled rice, calculates grain length, so as to recognize head milled rice using Minimum Enclosing Rectangle method；Calculate head rice rate：Head rice rate is calculated using head rice rate formula HRY=S_hr/S_total × 100%.The present invention realizes the measurement of head rice rate continuous batch, improves measurement efficiency, and certainty of measurement is high.
Description
Technical field
The present invention relates to a kind of assay method and its equipment, particularly a kind of head rice rate batch assay method and its set
It is standby.
Background technology
With the development of computer vision technique, its (McCarthy and that have been widely used on agriculture field
Hancock et al.,2010；Sakamoto and Gitelson et al.,2012；Lee and Lee, 2013), big
It is also more and more on rice product Quality Research, including grain of rice geometric properties (Emadzadeh and Razavi et al., 2010；
Mebatsion and Paliwal et al.,2012；Bornhorst and Kostlan et al., 2013), analysis on cracks
(Lan and Fang et al.,2002；Shimizu and Haque et al.,2008；Lin and Chen et al.,
2012), chalk analyzes (Yoshioka and Iwata et al., 2007 in vain；Sun and Liu et al., 2014), transparency
Analysis (Fang and Hu et al., 2015) etc..
Research for carrying out rice head rice rate detection using computer vision technique also has certain progress, Yadav,
Et al. B.K. (Yadav and Jindal, 2001) is by extracting length, girth, the throwing of head milled rice and broken rice in two dimensional image
The characteristic parameters such as shadow area, set up the quantitative estimation model of head rice rate, and minimum RMSE is 1.1%.；van Dalen(van
Dalen, 2004) using platform scanner and image analysis technology detection head milled rice and broken rice, as a result show, the method is ensureing
While precision the plenty of time is shortened than manual detection.
But lack the description to head milled rice detection method system, such as structure of mass equipment, the detection of efficient head milled rice
The description of method.These prior arts are still within theoretical research stage, are all much to carry out polished rice rate meter in the ideal case
Calculate, and in actual production or measurement process, it is impossible to it is grain of rice marshalling or tiling is uniform, it is therefore desirable to which that one kind can be actual
The head rice rate batch assay method of utilization.
The content of the invention
The technical problems to be solved by the invention are to provide a kind of head rice rate batch assay method and its equipment, and it can
Head rice rate is rapidly and accurately obtained aborning.
In order to solve the above technical problems, the technical solution adopted in the present invention is：
A kind of head rice rate batch assay method, it is characterised in that comprise the steps of：
Step one：Image is obtained, and the grain of rice is uniformly scattered on a moving belt by vibrator, and camera is taken pictures in surface and obtained
Take grain of rice initial pictures；
Step 2：Image preprocessing, the grain of rice is extracted from background, and carries out denoising and smoothing processing；
Step 3：The separation of synechia grain of rice, the separation of synechia grain of rice is matched using concave point detection and concave point；
Step 4：Identification head milled rice, calculates grain length, so as to recognize head milled rice using Minimum Enclosing Rectangle method；
Step 5：Calculate head rice rate：Whole essence is calculated using head rice rate formula HRY=S_hr/S_total × 100%
Rice rate.
Further, conveyer belt uses black belt in the step one.
Further, camera is vertically disposed in directly over conveyer belt at 30cm in the step one, conveyer belt uniform rotation,
Shot once every 5s.
Further, the step 2 from black background specifically, extracted the grain of rice by adaptive threshold fuzziness method
Out, all connected regions in image are marked, the connected region pixel count of noise is much smaller than grain of rice pixel count, sets and closes
Suitable threshold value removes noise spot, finally, medium filtering is carried out to image using 3*3 template pixels and realizes that grain of rice edge is smoothed
Treatment.
Further, step 3 bumps detection chooses the minimum rice of coordinate value specifically, set suitable template
Grain edge pixel point, centered on the point prolongs edge and walks clockwise, calculates the occupation rate of each template mesogranule pixel count,
ECMP value computing formula：
Wherein PF is grain of rice pixel count, and SM is template size.
Further, the step 3 convexity Point matching cooperates with constraints specifically, setting, and reaches the correct of many concave points
Matching：
1) using any concave point A as the basic point BP of matching, and the BP is set as the origin of coordinates sets up coordinate system, find
Grain of rice edge and ECMP template used intersection point M (a1, b1), N (a2, b2), connect straight line MA, NA, match point MP need to MA with
In the dashed region that NA is constituted, f (x) represents the scope of dashed region, and formula is expressed as：
If 2) there is 2 and above MP in dashed region, the MP nearest apart from BP is true MP；
If 3) none MP in dashed region, change next concave point repeat 1), 2) two step, until the matching of all concave points is tied
Beam；
4) after the completion of the matching of all concave points, the point for matching line two-by-two is realized using adaptive threshold fuzziness method
The final segmentation of the grain of rice.
Further, the step 4 is rotated up to 90 degree, every specifically, the profile of the target grain of rice is pressed into certain angle
During rotating to an angle, it is fitted with objective contour with the MER of horizontal positioned, after it have rotated certain angle,
The area of boundary rectangle has reached minimum, and now the length of MER is just the length of the target grain of rice, then by image and the grain of rice
Scaling calculates the physical length of the grain of rice.
Further, the rotation computing formula of the step 4 image rotation is,
If image rotates around origin (0,0), (x0,y0) be rotation before coordinate, (x1,y1) it is postrotational coordinate, rotation
Turn formula be
If around point (a, b) rotation, first coordinate translation to point (a, b), then rotating again, new original is finally moved to again
Point coordinates, point (c, d) is the center after rotation：
A kind of head rice rate batch sensing equipment, it is characterised in that：Comprising conveyer belt, vibrator, charging tray, camera and calculating
Machine, charging tray is arranged on conveyer belt one end, and vibrator is arranged on charging tray, and camera is vertically fixed on conveyer belt top, camera and meter
Calculation machine is connected, and a kind of software systems of head rice rate batch assay method are provided with computer.
The present invention compared with prior art, with advantages below and effect：Can be aborning the invention provides one kind
The head rice rate batch assay method of practical application, conveyer belt is coordinated by vibrator, and is processed with camera collection image,
The present invention solve the grain of rice it is disorderly and unsystematic in the case of head rice rate measurement, and realize continuous batch measurement, improve survey
Amount efficiency, and certainty of measurement is high.
Brief description of the drawings
Fig. 1 is the schematic diagram of head rice rate batch sensing equipment of the invention.
Fig. 2 is the schematic diagram of concave point matching of the invention.
Specific embodiment
The present invention is described in further detail below in conjunction with the accompanying drawings and by embodiment, and following examples are to this hair
Bright explanation and the invention is not limited in following examples.
As illustrated, a kind of head rice rate batch sensing equipment of the invention, comprising conveyer belt 1, vibrator, charging tray 2, phase
Machine 3 and computer 4, charging tray are arranged on conveyer belt one end, and vibrator is arranged on charging tray, and camera is vertically fixed on conveyer belt
Side, camera is connected with computer.
A kind of head rice rate batch assay method, comprises the steps of：
Step one：Image is obtained, and the grain of rice is uniformly scattered on a moving belt by vibrator, and camera is taken pictures in surface and obtained
Take grain of rice initial pictures；
Experiment two representative kinds of selection, respectively connect round-grained rice No. 7 (japonica rice) and raise two excellent No. 6 (long-grained nonglutinous rices).
This research is (long by the conveyer belt with black background：30cm, it is wide：25cm；Voltage：220V；Speed：60mm/s) make
It is the flowing objective table that experiment is utilized, the grain of rice to be measured passes through vibrator (voltage：220V, frequency：20Hz) uniformly fall in conveyer belt
On, camera (NEX-5R；Sony, Japan) it is vertically disposed in directly over conveyer belt at 30cm, conveyer belt uniform rotation, every 5s
Shoot once.
Step 2：Image preprocessing, is read using im=imread (' picture path ') function in Matlab softwares and treated
Detection image.The grain of rice is extracted from background, and carries out denoising and smoothing processing；
Experiment conveyer belt used is black belt, by adaptive threshold fuzziness method (Ohtsu, 1979) by the grain of rice from black
Extracted in color background.This research is marked by all connected regions in image, the connected region pixel count of noise
Much smaller than grain of rice pixel count, setting suitable threshold value can remove noise spot.Finally, image is carried out using 3*3 template pixels
Medium filtering (Ko and Yong, 1991), realizes the smoothing processing at grain of rice edge.
Step 3：The separation of synechia grain of rice, is read in Matlab softwares using im=imread (' picture path ') function
Altimetric image to be checked.The separation of synechia grain of rice is matched using concave point detection and concave point；
Concave point is detected
Originally a kind of edge center template rule of three (ECMP, Edge center mode proportion are researched and proposed
Method), that is, suitable template is set, the minimum grain of rice edge pixel point of coordinate value is chosen, it is suitable to prolong edge centered on the point
Hour hands are walked, and calculate the occupation rate of each template mesogranule pixel count.ECMP values can represent the concavity and convexity at grain of rice edge, the value
Bigger expression edge is more recessed, is worth smaller expression edge more convex.ECMP value computing formula：
PF:pixels of foreground.SM:size of mode.
Concave point is matched
This research, by setting collaboration constraints, can reach many concave points on the basis of ECMP concave point detection methods
Correct matching：
1. using any concave point A as the basic point (BP, the basic point) of matching, and it is coordinate to set the BP
Origin sets up coordinate system, such as shown in figure (1), finds grain of rice edge and ECMP template used intersection point M (a1, b1), N (a2, b2),
Connection straight line MA, NA, match point (MP, the match point) need to be in the dashed regions that MA and NA are constituted.F (x) is represented
The scope of dashed region, formula is expressed as：
2., if there is 2 and above MP in dashed region, the MP nearest apart from BP is true MP；
If 3. none MP in dashed region, changes next concave point and repeats 1,2 rules, until the matching of all concave points terminates.
4th, after the completion of the matching of all concave points, by the point for matching line two-by-two, using adaptive threshold fuzziness method
(Ohtsu, 1979) realizes the final segmentation of the grain of rice.
Step 4：Identification head milled rice, is read using im=imread (' picture path ') function in Matlab softwares and treated
Detection image.Grain length is calculated using Minimum Enclosing Rectangle method, so as to recognize head milled rice；
The grain of rice split is calculated using Minimum Enclosing Rectangle method (MER) (Ying and Wang et al., 2002) long
Degree, its basic thought is that the profile of target is rotated by 90 ° by certain angle (such as 3 degree), in the process for often rotating to an angle
In, it is fitted with objective contour with the MER of horizontal positioned.After it have rotated certain angle, the area of boundary rectangle reaches
Minimum, now the length of MER is just the length of the target grain of rice, then calculates the grain of rice by the scaling of image and the grain of rice
Physical length.
For the rotation of image, the situation that image rotates around origin (0,0), (x are first analyzed0,y0) be rotation before seat
Mark, (x1,y1) it is postrotational coordinate.The formula of rotation is as follows：
If around point (a, b) rotation, then just first coordinate translation to point (a, b), then rotate again, finally put down again
New origin is moved on to, point (c, d) is the center after rotation：
Step 5：Calculate head rice rate：Whole essence is calculated using head rice rate formula HRY=S_hr/S_total × 100%
Rice rate.
In national standard, head milled rice is head rice rate, the rice of same kind with the mass values of net paddy sample
Granule density and difference in thickness less, from m=ρ V, V=Sh, the quality of the grain of rice can be estimated by the area of the grain of rice.Two
In value image, prospect grain of rice pixel is 1, and background pixel is 0, pixel and represent net paddy sample that all prospect grain of rices are connected
Area, all length exceedes head milled rice average length 3/4ths and the grain of rice connected pixel number of the above represents head milled rice area.
Head rice rate computing formula：
HRY=S_hr/S_total × 100%
S_hr is head milled rice connected pixel number sum, and S_total is all grain of rice connected pixel number summations.
Above content described in this specification is only illustration made for the present invention.Technology belonging to of the invention
The technical staff in field can be made various modifications or supplement to described specific embodiment or be substituted using similar mode, only
Without departing from the content of description of the invention or to surmount scope defined in the claims, guarantor of the invention all should be belonged to
Shield scope.
Claims (9)
1. a kind of head rice rate batch assay method, it is characterised in that comprise the steps of：
Step one：Image is obtained, and the grain of rice is uniformly scattered on a moving belt by vibrator, and camera is taken pictures acquisition rice in surface
Grain initial pictures；
Step 2：Image preprocessing, the grain of rice is extracted from background, and carries out denoising and smoothing processing；
Step 3：The separation of synechia grain of rice, the separation of synechia grain of rice is matched using concave point detection and concave point；
Step 4：Identification head milled rice, calculates grain length, so as to recognize head milled rice using Minimum Enclosing Rectangle method；
Step 5：Calculate head rice rate：Head rice rate is calculated using head rice rate formula HRY=S_hr/S_total × 100%.
2. according to a kind of head rice rate batch assay method described in claim 1, it is characterised in that：Transmitted in the step one
Band uses black belt.
3. according to a kind of head rice rate batch assay method described in claim 1, it is characterised in that：Camera in the step one
It is vertically disposed in directly over conveyer belt at 30cm, conveyer belt uniform rotation shoots once every 5s.
4. according to a kind of head rice rate batch assay method described in claim 1, it is characterised in that：The step 2 is specific
For, the grain of rice is extracted from black background by adaptive threshold fuzziness method, rower is entered to all connected regions in image
Note, the connected region pixel count of noise is much smaller than grain of rice pixel count, sets suitable threshold value and removes noise spot, finally, uses
3*3 template pixels carry out the smoothing processing that medium filtering realizes grain of rice edge to image.
5. according to a kind of head rice rate batch assay method described in claim 1, it is characterised in that：The step 3 bumps
Detection chooses the minimum grain of rice edge pixel point of coordinate value specifically, set suitable template, and it is suitable to prolong edge centered on the point
Hour hands are walked, and calculate the occupation rate of each template mesogranule pixel count, ECMP value computing formula：
Wherein PF is grain of rice pixel count, and SM is template size.
6. according to a kind of head rice rate batch assay method described in claim 1, it is characterised in that：The step 3 bumps
Matching cooperates with constraints specifically, setting, and reaches the correct matching of many concave points：
1) using any concave point A as the basic point BP of matching, and the BP is set as the origin of coordinates sets up coordinate system, find the grain of rice
Edge and ECMP template used intersection point M (a1, b1), N (a2, b2), connect straight line MA, NA, and match point MP need to be in MA and NA institutes
In the dashed region of composition, f (x) represents the scope of dashed region, and formula is expressed as：
If 2) there is 2 and above MP in dashed region, the MP nearest apart from BP is true MP；
If 3) none MP in dashed region, change next concave point repeat 1), 2) two step, until all concave points are matched terminating；
4) after the completion of the matching of all concave points, by the point for matching line two-by-two, the grain of rice is realized using adaptive threshold fuzziness method
Final segmentation.
7. according to a kind of head rice rate batch assay method described in claim 1, it is characterised in that：The step 4 is specific
For, the profile of the target grain of rice is pressed into certain angle rotation up to 90 degree, during often rotating to an angle, use horizontal positioned
MER be fitted with objective contour, after it have rotated certain angle, the area of boundary rectangle has reached minimum, now MER
Length be just the length of the target grain of rice, the physical length of the grain of rice is then calculated by the scaling of image and the grain of rice.
8. according to a kind of head rice rate batch assay method described in claim 7, it is characterised in that：The step 4 image rotation
Turn rotation computing formula be,
If image rotates around origin (0,0), (x0,y0) be rotation before coordinate, (x1,y1) it is postrotational coordinate, rotation
Formula is
If around point (a, b) rotation, first coordinate translation to point (a, b), then rotating again, new origin is finally moved to again and is sat
Mark, point (c, d) is the center after rotation：
9. a kind of head rice rate batch sensing equipment, it is characterised in that：Comprising conveyer belt, vibrator, charging tray, camera and calculating
Machine, charging tray is arranged on conveyer belt one end, and vibrator is arranged on charging tray, and camera is vertically fixed on conveyer belt top, camera and meter
Calculation machine is connected, and a kind of software systems of the head rice rate batch assay method having the right described in 1-8 are set in computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710175005.1A CN106918595A (en) | 2017-03-22 | 2017-03-22 | A kind of head rice rate batch assay method and its equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710175005.1A CN106918595A (en) | 2017-03-22 | 2017-03-22 | A kind of head rice rate batch assay method and its equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106918595A true CN106918595A (en) | 2017-07-04 |
Family
ID=59462070
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710175005.1A Pending CN106918595A (en) | 2017-03-22 | 2017-03-22 | A kind of head rice rate batch assay method and its equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106918595A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107843283A (en) * | 2017-09-26 | 2018-03-27 | 中国水稻研究所 | A kind of head rice rate method for predicting medium-length brown rice |
| CN108872235A (en) * | 2018-06-23 | 2018-11-23 | 安盛机器人技术（盘锦）有限公司 | Broken rice rate and rate of kernels with remained germ analysis machine |
| CN111489336A (en) * | 2020-04-07 | 2020-08-04 | 内蒙古工业大学 | Method and device for detecting length of carding cashmere based on pixel calculation |
| CN112070741A (en) * | 2020-09-07 | 2020-12-11 | 浙江师范大学 | Rice whiteness degree detection system based on image saliency region extraction method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06138715A (en) * | 1992-10-27 | 1994-05-20 | Dainippon Printing Co Ltd | Toner for wet processing and its production |
| CN101281112A (en) * | 2008-04-30 | 2008-10-08 | 浙江理工大学 | Image type automatic analysis method for mesh adhesion rice corn |
| CN101968479A (en) * | 2010-09-27 | 2011-02-09 | 中国水稻研究所 | Method for rapidly identifying milled rice rate of indica type rice variety |
| CN106295789A (en) * | 2015-06-10 | 2017-01-04 | 浙江托普云农科技股份有限公司 | A kind of crop seed method of counting based on image procossing |
-
2017
- 2017-03-22 CN CN201710175005.1A patent/CN106918595A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06138715A (en) * | 1992-10-27 | 1994-05-20 | Dainippon Printing Co Ltd | Toner for wet processing and its production |
| CN101281112A (en) * | 2008-04-30 | 2008-10-08 | 浙江理工大学 | Image type automatic analysis method for mesh adhesion rice corn |
| CN101968479A (en) * | 2010-09-27 | 2011-02-09 | 中国水稻研究所 | Method for rapidly identifying milled rice rate of indica type rice variety |
| CN106295789A (en) * | 2015-06-10 | 2017-01-04 | 浙江托普云农科技股份有限公司 | A kind of crop seed method of counting based on image procossing |
Non-Patent Citations (1)
| Title |
|---|
| YUAN YAO ET AL.: "Head rice rate measurement based on concave point matching", 《SCIENTIFIC REPORTS》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107843283A (en) * | 2017-09-26 | 2018-03-27 | 中国水稻研究所 | A kind of head rice rate method for predicting medium-length brown rice |
| CN108872235A (en) * | 2018-06-23 | 2018-11-23 | 安盛机器人技术（盘锦）有限公司 | Broken rice rate and rate of kernels with remained germ analysis machine |
| CN108872235B (en) * | 2018-06-23 | 2021-02-26 | 辽宁美骏智能装备有限公司 | Broken rice rate and embryo remaining rate analyzer |
| CN111489336A (en) * | 2020-04-07 | 2020-08-04 | 内蒙古工业大学 | Method and device for detecting length of carding cashmere based on pixel calculation |
| CN111489336B (en) * | 2020-04-07 | 2023-07-25 | 内蒙古工业大学 | Method and device for detecting length of carding cashmere based on pixel calculation |
| CN112070741A (en) * | 2020-09-07 | 2020-12-11 | 浙江师范大学 | Rice whiteness degree detection system based on image saliency region extraction method |
| CN112070741B (en) * | 2020-09-07 | 2024-02-23 | 浙江师范大学 | Rice chalkiness degree detecting system based on image salient region extracting method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106918595A (en) | A kind of head rice rate batch assay method and its equipment | |
| CN105740899B (en) | A kind of detection of machine vision image characteristic point and match compound optimization method | |
| CN107941808B (en) | 3D printing forming quality detection system and method based on machine vision | |
| CN106934813A (en) | A kind of industrial robot workpiece grabbing implementation method of view-based access control model positioning | |
| CN106446894B (en) | A method of based on outline identification ball-type target object location | |
| CN102136142B (en) | Nonrigid medical image registration method based on self-adapting triangular meshes | |
| CN109886925A (en) | A kind of aluminium material surface defect inspection method that Active Learning is combined with deep learning | |
| CN112233107B (en) | Sunflower seed grade classification method based on image processing technology | |
| CN106651825A (en) | Workpiece positioning and identification method based on image segmentation | |
| CN103699900A (en) | Automatic batch extraction method for horizontal vector contour of building in satellite image | |
| CN110097048A (en) | A kind of SOT chip image quickly corrects and character identifying method | |
| CN107610138A (en) | A kind of bill seal regional sequence dividing method | |
| TW200810518A (en) | System and method for boundary scan of an image | |
| CN113706566B (en) | Edge detection-based perfuming and spraying performance detection method | |
| Vyas et al. | Quality inspection and classification of mangoes using color and size features | |
| CN105404868A (en) | Interaction platform based method for rapidly detecting text in complex background | |
| CN110335280A (en) | A kind of financial documents image segmentation and antidote based on mobile terminal | |
| CN104091148B (en) | A kind of man face characteristic point positioning method and device | |
| Fang et al. | ID card identification system based on image recognition | |
| CN108109154A (en) | A kind of new positioning of workpiece and data capture method | |
| CN111612767B (en) | Vision-based precision structural part identification method | |
| CN105528782B (en) | A kind of milk carton suction pipe whether there is or not detection method | |
| CN104392225B (en) | Online palmprint effective coverage fast partition method based on gradient direction template | |
| CN108269264A (en) | The denoising of beans seed image and fractal method | |
| Wang et al. | Detection of potato’s size based on centroidal principal axis |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170704 |
|
| RJ01 | Rejection of invention patent application after publication |