CN102156129B - Beef quality intelligent grading system and method based on machine vision - Google Patents
Beef quality intelligent grading system and method based on machine vision Download PDFInfo
- Publication number
- CN102156129B CN102156129B CN2010105689366A CN201010568936A CN102156129B CN 102156129 B CN102156129 B CN 102156129B CN 2010105689366 A CN2010105689366 A CN 2010105689366A CN 201010568936 A CN201010568936 A CN 201010568936A CN 102156129 B CN102156129 B CN 102156129B
- Authority
- CN
- China
- Prior art keywords
- beef
- trunk
- level
- look
- square section
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a beef quality intelligent grading system and method based on machine vision. The system comprises a beef carcass placing platform, a camera obscura with a camera and a beef quality grading module, wherein the camera in the camera obscura is used as a collection device of the beef carcass information for collecting image signals of a beef carcass to be detected on the beef carcass holding platform; the output of the camera is connected with the beef quality grading module; and the output of the beef quality grading module is used as the output beef grading information of the beef quality intelligent grading system based on the machine vision. In the invention, a digital image processing technique is utilized to carry out relevant required processing on the collected cross section image of the beef carcass; three indexes, such as marbling, fat color and red beef color in an effective musculus ocularis area are utilized for analyzing, thus the whole beef carcass can be graded effectively, the shortage of misjudgement of the traditional beef grading system in which a single index is used can be overcome, and the accuracy and the objectivity of grading can be greatly improved.
Description
Technical field
The present invention relates to detection of beef quality rank and judgement, belong to national meat quality security control engineering, especially a kind of beef quality intelligence hierarchy system and method thereof based on machine vision.
Background technology
At present, in traditional beef processing industry, adopt manual measurement or ocular estimate to obtain of the classification of the rating information of ox trunk eye muscle tangent plane usually with realization beef.Evaluation index comprises marbling, beef color and luster, the physiological maturity degree of beef and the fatty look of beef etc. of beef, and wherein, beef marbling grade is topmost evaluation index.When carrying out the beef quality grading; Usually all be beef ranking teacher by specialty; At the beef processing site,, evaluate out the marbling grade of beef through observing the abundance of place, eye muscle square section intramuscular fat between ox trunk the 12nd～13 or the 6th～7 sternal rib; And then with reference to physiological maturity degree, muscle look or the fatty look of beef, final assessment goes out the quality grade of beef.Therefore, the present quality grade of beef in most of the cases, mainly is that the marbling grade by beef determines.Though it is artificial the evaluation has certain advantage,, subjective, go qualitatively to estimate because the valuation officer can be according to the personal experience; And because the influence of subjective factors such as environment and psychology is easy to generate people's kopiopia, degradation phenomenon under the assess effectiveness; Such evaluation process not only lacks fairness; But also having suitable mistake, efficient is low, sometimes even have a strong impact on the carrying out of whole beef quality on-line evaluation link.Beef is realized that effectively deciding grade and level is to improve first of market beef quality to close, and this problem must in time solve.In recent years, the country that some beef cattle industries are flourishing, early the automatic classification technique of beef has been launched relevant research, in theory research, obtained certain achievement, and Preliminary development goes out to be used for the real time machine vision system of the automatic classification of beef.Early being applied in the actual production is VIA beef assessment system, and this system uses more extensive in Denmark and France, and in practical application, is updated.The VIA Scan of RMS company of United States Department of Agriculture development is the computer image analysis system that is used for evaluating beef quality-class and output level, has obtained Preliminary Applications in states such as the U.S., the big sharp industry of Australia, North America, Europe.The big sharp industry of Australia is developed a kind of rating system, and it can be estimated out the ox trunk and respectively cut apart the edible quality grade of cube meat, and gives corresponding cooking method suggestion.Canadian ox trunk grading computer image system (CVS) can carry out image taking when trunk moves.Because rating system adopts expensive hardware to form automatically, cost is too high, and relatively heavier, and it is not very extensive using, and still estimates classification with full-time beef grade evaluation teacher ocular estimate generally.
Summary of the invention
The objective of the invention is can only be through the problem that effectively the marbling distribution situation is judged the beef grade in the eye muscle zone on the ox trunk square section to existing beef quality intelligence hierarchy system, proposes a kind of intelligent hierarchy system of the beef quality based on machine vision and method thereof that can thoroughly evaluating beef grade.
Technical scheme of the present invention is:
A kind of beef quality intelligence hierarchy system based on machine vision; It comprises ox trunk placement platform, the camera bellows that has camera and beef quality diversity module; Camera in the camera bellows is positioned at the picture signal of ox trunk to be measured on the ox trunk placement platform as the harvester collection of ox trunk information; The output of camera is connected with the beef quality diversity module, and the output conduct of beef quality diversity module is based on the output beef class information of the beef quality intelligence hierarchy system of machine vision.
Ox trunk placement platform of the present invention comprises ox trunk mounting table and background board, and background board is connected with ox trunk mounting table.
Background board of the present invention is a black.
A kind of utilization method based on the beef quality of machine vision intelligence hierarchy system as above may further comprise the steps:
(a). the foundation in character image data storehouse, ox trunk square section: the foundation in character image data storehouse, ox trunk square section comprises the characteristic image at ox ectoloph, eye meat and three positions of last brain;
(b). ox trunk rank is judged the foundation of sorter: each image in the character image data storehouse, ox trunk square section carries out the extraction of relevant parameter index; Obtain on the ox trunk square section in the effective eye muscle zone on marbling distribution situation, the ox trunk square section in the effective eye muscle zone red meat color grade in effective eye muscle zone on the marbling color grade and ox trunk square section, obtain the ox trunk whole synthesis classification standard of correspondence then according to three indexs of gained;
(c). be positioned at the picture signal of ox trunk to be measured on the ox trunk placement platform and with its input beef quality diversity module through the camera collection in the camera bellows, adopt ox trunk rank to judge that sorter judges the beef grade and export the beef class information.
A kind of utilization method based on the beef quality of machine vision intelligence hierarchy system as above may further comprise the steps:
(a). the foundation in character image data storehouse, ox trunk square section: the foundation in character image data storehouse, ox trunk square section comprises the characteristic image at ox ectoloph, eye meat and three positions of last brain;
(b). ox trunk rank is judged the foundation of sorter: each image in the character image data storehouse, ox trunk square section carries out the extraction of relevant parameter index; Comprise on the ox trunk square section in the effective eye muscle zone on marbling distribution situation, the ox trunk square section in the effective eye muscle zone red meat color grade in effective eye muscle zone on the marbling color grade and ox trunk square section
On the described ox trunk square section effectively in the eye muscle zone parameter extraction step of marbling color and red meat color situation be:
The first, convert the rgb color space value into HIS color space value, distinguish effective color area, promptly extract fatty look and red meat color;
The fat look:
S level: 230≤R≤255; 230≤G≤255; 225≤B≤255
A level: 130≤R≤170; 140≤G≤160; 110≤B≤140
B level: 215≤R≤225; 220≤G≤240; 130≤B≤180
C level: 195≤R≤210; 190≤G≤210; 0≤B≤145
The red meat look:
S level: 185≤R≤255; 35≤G≤60; 40≤B≤60; G≤B; (G-B)＜10;
A level: 90≤R≤130; 15≤G≤45; 15≤B≤50; G≤B; (G-R)＜70; (B-G)≤5;
B level: 150≤R≤190; 60≤G≤95; 70≤B≤95; G≤B; (G-R)＜70; (B-G)≤5;
C level: 40≤R≤60; 0≤G≤40; 0≤B≤40; (R-B)＜15;
The second, the rgb value of fatty look and yellowish pink each pixel in the effective color area of statistics;
Three, respectively to averaging after fatty look and each the pixel rgb value stack of red meat look;
Four, the mean value that obtains fatty look and each pixel rgb value of red meat look is the interval respective value of grade of fatty look and red meat look;
On the described ox trunk square section effectively in the eye muscle zone parameter extraction step of marbling grade be:
The first, beef is cut apart cross-sectional view and look like to carry out the gray processing processing;
The second, the cross-sectional view that cuts meat of the ox behind the gray processing is looked like to carry out Threshold Segmentation, fat is white with background, and muscle is black;
Three, scan image line by line constitutes the zone with white point continuous and that quantity is maximum and becomes black, has promptly removed most of back fat;
Four, again the ox cross-sectional view that cuts meat is looked like to carry out profile and extracts, profile is a black, other some position white;
Five, the benefit that cross-sectional view looks like to carry out breakpoint that cuts meat of the ox after profile is extracted connects;
Six, scan image line by line, the profile area surrounded that girth is maximum keeps, and zone in addition all becomes white, and noting this maximum girth is C
r
Seven, add up the overall circumference of other point, be designated as C
f
Eight, calculate marblized Density Distribution rule μ=C
r/ C
fS level: μ>=2.5%; A level: 1.5%≤μ＜2.5%; B level: 0.5%≤μ＜1.5%; C level: μ＜0.5%;
Nine, the contour images after handling is carried out region growing, count the white point in the girth maximum region, promptly marblized area is designated as S
f
Ten, again region growing is carried out in the maximum zone of profile girth, make that the institute in the zone becomes white a little, count the sum of these white points, be designated as S
r
The 11, calculate marblized zone and occupy rule η=S
f/ S
r
S level: η>=17%; A level: 10%≤η＜17%; B level: 3%≤η＜10%; C level: η＜3%
Three indexs according to gained obtain corresponding ox trunk whole synthesis classification standard at last;
(c). be positioned at the picture signal of ox trunk to be measured on the ox trunk placement platform and with its input beef quality diversity module through the camera collection in the camera bellows, adopt ox trunk rank to judge that sorter judges the beef grade and export the beef class information; Described determination step is identical with step (b), and each image in the character image data storehouse, ox trunk square section is carried out the extraction of relevant parameter index, judges data in the sorter output respective level of comparing with ox trunk rank then.
Beneficial effect of the present invention:
Integrated utilization digital image processing techniques of the present invention and multilingual programming technique have been developed the beef quality intelligence hierarchy system based on machine vision; To the ox trunk cross-sectional view that the collects required processing that looks like to be correlated with; Utilize marbling in effective eye muscle zone, fatty color and three indexs of red meat color to analyze; Thereby realize whole piece ox trunk is effectively defined the level; Remedy present beef hierarchy system and utilized the single index deficiency of erroneous judgement easily, improved the accuracy and the objectivity of classification greatly.
Increased a special camera bellows that constant light environment is provided for system works among the present invention; The industrial camera and the special use of this built-in adjustment height of camera bellows while and the angle of pitch; The complex operation and the external system that brings of existing beef image hierarchy system light source that have the regulation putting position to bring owing to required detection agricultural product in traditional agricultural product information detection system of having forgone is too fat to move loaded down with trivial details, simple in structure.The camera heights and the angle of pitch can be adjusted as required in good time, have improved the convenience when total system is integrated; When carrying out each the parameter index rank judgement of ox trunk, the ox trunk directly is placed on the special metal platform, does not need system that special environment is provided, and the adaptability of system is better; Simultaneously, the layout of the selection of camera bellows internal color, casing, light source and ccd video camera has all been passed through the demonstration repeatedly of several times tests.
The frequency of operation of the color of the brightness of the polishing direction of used light source, light source, light source and light source also all is to prove repeatedly through well-designed and several times test among the present invention; A stable light environment can be provided for the work of system, can accomplish that no-reflection, no stroboscopic, polishing direction can adjust and bright colour stable as required in real time.
The special ox trunk metal placement platform of independent research is furnished with special background board among the present invention; This background board is an ox trunk tangent plane provides happy single constant and be different from the background of ox trunk fat color and ox trunk red meat color, the data distortion when having reduced the imaging of ox trunk to a great extent in magazine imaging.Simultaneously, this platform meets the hygienic standard of state food industry fully to manufacturing from selection.
Description of drawings
Fig. 1 is a structural representation of the present invention.
Fig. 2 is a beef quality intelligence classification synoptic diagram of the present invention.
Embodiment
Below in conjunction with accompanying drawing and embodiment the present invention is further described.
As shown in Figure 1; A kind of beef quality intelligence hierarchy system based on machine vision; It comprises ox trunk placement platform, the camera bellows that has camera and beef quality diversity module; Camera in the camera bellows is positioned at the picture signal of ox trunk to be measured on the ox trunk placement platform as the harvester collection of ox trunk information, and the output of camera is connected with the beef quality diversity module, and the output of beef quality diversity module is as the output beef class information based on the beef quality intelligence hierarchy system of machine vision.
Employed ox trunk placement platform comprises ox trunk mounting table and background board in this beef quality intelligence hierarchy system, and background board realizes that through nearly no seam welding with ox trunk mounting table be that the ox trunk is placed being connected of special of metal.Whole flat adopts absolute construction to design, and is unconnected with other functional modules in the beef quality intelligence hierarchy system, can independently move, and is convenient to the matching adjustment of each functional module of system under the different occasions.Simultaneously, this platform uses the processing and manufacturing of high-quality stainless steel material, meets the hygienic standard of state food industry fully, and is both artistic and practical.Wherein, special of metal of ox trunk placement is used to place the ox trunk; Background board mainly is for the imaging of ox trunk square section in industrial camera stable a, no-reflection and the low background of disturbing to be provided; This background board is selected black look as a setting for use through after the repetition test; Do not produce reflective phenomenon for background board when illumination is arranged simultaneously, so seal one deck black nylon taffeta that tacked down through special adhesion mode in its surface.
A kind of method of utilizing aforesaid beef quality intelligence hierarchy system based on machine vision may further comprise the steps:
(a). the foundation in character image data storehouse, ox trunk square section: the foundation in character image data storehouse, ox trunk square section comprises the characteristic image at ox ectoloph, eye meat and three positions of last brain;
(b). ox trunk rank is judged the foundation of sorter: each image in the character image data storehouse, ox trunk square section carries out the extraction of relevant parameter index; Obtain on the ox trunk square section in the effective eye muscle zone on marbling distribution situation, the ox trunk square section in the effective eye muscle zone red meat color grade in effective eye muscle zone on the marbling color grade and ox trunk square section, obtain the ox trunk whole synthesis classification standard of correspondence then according to three indexs of gained;
(c). be positioned at the picture signal of ox trunk to be measured on the ox trunk placement platform and with its input beef quality diversity module through the camera collection in the camera bellows, adopt ox trunk rank to judge that sorter judges the beef grade and export the beef class information.
A kind of utilization method based on the beef quality of machine vision intelligence hierarchy system as above may further comprise the steps:
(a). the foundation in character image data storehouse, ox trunk square section: the foundation in character image data storehouse, ox trunk square section comprises the characteristic image at ox ectoloph, eye meat and three positions of last brain;
(b). ox trunk rank is judged the foundation of sorter: each image in the character image data storehouse, ox trunk square section carries out the extraction of relevant parameter index; Comprise on the ox trunk square section in the effective eye muscle zone on marbling distribution situation, the ox trunk square section in the effective eye muscle zone red meat color grade in effective eye muscle zone on the marbling color grade and ox trunk square section
On the described ox trunk square section effectively in the eye muscle zone parameter extraction step of marbling color and red meat color situation be:
The first, convert the rgb color space value into HIS color space value, distinguish effective color area, promptly extract fatty look and red meat color;
The fat look:
S level: 230≤R≤255; 230≤G≤255; 225≤B≤255
A level: 130≤R≤170; 140≤G≤160; 110≤B≤140
B level: 215≤R≤225; 220≤G≤240; 130≤B≤180
C level: 195≤R≤210; 190≤G≤210; 0≤B≤145
The red meat look:
S level: 185≤R≤255; 35≤G≤60; 40≤B≤60; G≤B; (G-B)＜10;
A level: 90≤R≤130; 15≤G≤45; 15≤B≤50; G≤B; (G-R)＜70; (B-G)≤5;
B level: 150≤R≤190; 60≤G≤95; 70≤B≤95; G≤B; (G-R)＜70; (B-G)≤5;
C level: 40≤R≤60; 0≤G≤40; 0≤B≤40; (R-B)＜15;
The second, the rgb value of fatty look and yellowish pink each pixel in the effective color area of statistics;
Three, respectively to averaging after fatty look and each the pixel rgb value stack of red meat look;
Four, the mean value that obtains fatty look and each pixel rgb value of red meat look is the interval respective value of grade of fatty look and red meat look;
On the described ox trunk square section effectively in the eye muscle zone parameter extraction step of marbling grade be:
The first, beef is cut apart cross-sectional view and look like to carry out the gray processing processing;
The second, the cross-sectional view that cuts meat of the ox behind the gray processing is looked like to carry out Threshold Segmentation, fat is white with background, and muscle is black;
Three, scan image line by line constitutes the zone with white point continuous and that quantity is maximum and becomes black, has promptly removed most of back fat;
Four, again the ox cross-sectional view that cuts meat is looked like to carry out profile and extracts, profile is a black, other some position white;
Five, the benefit that cross-sectional view looks like to carry out breakpoint that cuts meat of the ox after profile is extracted connects;
Six, scan image line by line, the profile area surrounded that girth is maximum keeps, and zone in addition all becomes white, and noting this maximum girth is C
r
Seven, add up the overall circumference of other point, be designated as C
f
Eight, calculate marblized Density Distribution rule μ=C
r/ C
f
S level: μ>=2.5%; A level: 1.5%≤μ＜2.5%; B level: 0.5%≤μ＜1.5%; C level: μ＜0.5%;
Nine, the contour images after handling is carried out region growing, count the white point in the girth maximum region, promptly marblized area is designated as S
f
Ten, again region growing is carried out in the maximum zone of profile girth, make that the institute in the zone becomes white a little, count the sum of these white points, be designated as S
r
The 11, calculate marblized zone and occupy rule η=S
f/ S
r
S level: η>=17%; A level: 10%≤η＜17%; B level: 3%≤η＜10%; C level: η＜3%
Three indexs according to gained obtain corresponding ox trunk whole synthesis classification standard at last;
(c). be positioned at the picture signal of ox trunk to be measured on the ox trunk placement platform and with its input beef quality diversity module through the camera collection in the camera bellows, adopt ox trunk rank to judge that sorter judges the beef grade and export the beef class information; Described determination step is identical with step (b), and each image in the character image data storehouse, ox trunk square section is carried out the extraction of relevant parameter index, judges data in the sorter output respective level of comparing with ox trunk rank then.
The present invention does not relate to all identical with the prior art prior art that maybe can adopt of part and realizes.
Claims (1)
1. method based on the beef quality of machine vision intelligence hierarchy system is characterized in that it may further comprise the steps:
(a). the foundation in character image data storehouse, ox trunk square section: the foundation in character image data storehouse, ox trunk square section comprises the characteristic image at ox ectoloph, eye meat and three positions of last brain;
(b). ox trunk rank is judged the foundation of sorter: each image in the character image data storehouse, ox trunk square section carries out the extraction of relevant parameter index; Comprise on the ox trunk square section in the effective eye muscle zone on marbling distribution situation, the ox trunk square section in the effective eye muscle zone red meat color grade in effective eye muscle zone on the marbling color grade and ox trunk square section
On the described ox trunk square section effectively in the eye muscle zone parameter extraction step of marbling color and red meat color situation be:
The first, convert the rgb color space value into HIS color space value, distinguish effective color area, promptly extract fatty look and red meat color;
The fat look:
S level: 230≤R≤255; 230≤G≤255; 225≤B≤255
A level: 130≤R≤170; 140≤G≤160; 110≤B≤140
B level: 215≤R≤225; 220≤G≤240; 130≤B≤180
C level: 195≤R≤210; 190≤G≤210; 0≤B≤145
The red meat look:
S level: 185≤R≤255; 35≤G≤60; 40≤B≤60; G≤B; (G-B)＜10;
A level: 90≤R≤130; 15≤G≤45; 15≤B≤50; G≤B; (G-R)＜70; (B-G)≤5;
B level: 150≤R≤190; 60≤G≤95; 70≤B≤95; G≤B; (G-R)＜70; (B-G)≤5;
C level: 40≤R≤60; 0≤G≤40; 0≤B≤40; (R-B)＜15;
The second, the rgb value of fatty look and each pixel of red meat look in the effective color area of statistics;
Three, respectively to averaging after fatty look and each the pixel rgb value stack of red meat look;
Four, the mean value that obtains fatty look and each pixel rgb value of red meat look is the interval respective value of grade of fatty look and red meat look;
On the described ox trunk square section effectively in the eye muscle zone parameter extraction step of marbling grade be:
The first, beef is cut apart cross-sectional view and look like to carry out the gray processing processing;
The second, the beef behind the gray processing is cut apart cross-sectional view and look like to carry out Threshold Segmentation, fat and background are white, and muscle is black;
Three, scan image line by line constitutes the zone with white point continuous and that quantity is maximum and becomes black, has promptly removed most of back fat;
Four, again beef is cut apart cross-sectional view and look like to carry out the profile extraction, profile is a black, and other point is white;
Five, the beef after the profile extraction is cut apart the benefit company that cross-sectional view looks like to carry out breakpoint;
Six, scan image line by line; The profile area surrounded that girth is maximum keeps; Zone in addition all becomes white, notes this maximum girth for
;
Seven, add up the overall circumference of other point, be designated as
;
Eighth, calculate the density distribution of marbling law μ =
/
;
S level:
; A level:
; B level:
; C level:
;
Nine, the contour images after handling is carried out region growing; Count the white point in the girth maximum region; Be marblized area, be designated as
;
Ten, again region growing is carried out in the maximum zone of profile girth; Make the institute in the zone become white a little; Count the sum of these white points, be designated as
;
Eleventh, calculate the area occupied marbled law η =
/
;
S level:
; A level:
; B level:
; C level:
Three indexs according to gained obtain corresponding ox trunk whole synthesis classification standard at last;
(c). be positioned at the picture signal of ox trunk to be measured on the ox trunk placement platform and with its input beef quality diversity module through the camera collection in the camera bellows, adopt ox trunk rank to judge that sorter judges the beef grade and export the beef class information; Described determination step is identical with step (b), and each image in the character image data storehouse, ox trunk square section is carried out the extraction of relevant parameter index, judges data in the sorter output respective level of comparing with ox trunk rank then.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010105689366A CN102156129B (en) | 2009-12-02 | 2010-12-01 | Beef quality intelligent grading system and method based on machine vision |
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910232148 | 2009-12-02 | ||
| CN200910232148.7 | 2009-12-02 | ||
| CN2010105689366A CN102156129B (en) | 2009-12-02 | 2010-12-01 | Beef quality intelligent grading system and method based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102156129A CN102156129A (en) | 2011-08-17 |
| CN102156129B true CN102156129B (en) | 2012-10-03 |
Family
ID=44437704
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010105689366A Expired - Fee Related CN102156129B (en) | 2009-12-02 | 2010-12-01 | Beef quality intelligent grading system and method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102156129B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108007929A (en) * | 2017-12-01 | 2018-05-08 | 南京农业大学 | A kind of automatic judging method of beef physiological makeup |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102252977A (en) * | 2011-04-28 | 2011-11-23 | 南京农业大学 | Portable beef quality classification detector based on embedded machine vision technique |
| CN102404602A (en) * | 2011-09-23 | 2012-04-04 | 浙江工业大学 | Vidicon definition detection method based on definition test card |
| CN102608118A (en) * | 2012-01-13 | 2012-07-25 | 南京农业大学 | Image acquisition device of portable beef quality grading system based on embedded machine vision technology |
| CN103175834B (en) * | 2013-01-28 | 2016-05-18 | 宁波江丰生物信息技术有限公司 | A kind of digital pathological section quality determining method and system |
| CN103940751B (en) * | 2014-04-23 | 2016-11-09 | 成都大学 | A kind of assessment method of cold fresh meat quality based on image processing techniques |
| CN104616204B (en) * | 2015-01-30 | 2018-04-06 | 南京航空航天大学 | A kind of polynary, fine, intelligent trunk meat stage division on automatic pig slaughtering line |
| CN104865198A (en) * | 2015-04-28 | 2015-08-26 | 青岛农业大学 | Machine vision-based fresh fat liver quality automatic grading system and method |
| CN105447891B (en) * | 2015-12-02 | 2018-03-30 | 中国肉类食品综合研究中心 | The appraisal procedure and system of chilled meat freshness |
| CN105651776A (en) * | 2015-12-30 | 2016-06-08 | 中国农业大学 | Device and method for automatically grading beef carcass meat yield based on computer vision |
| CN107819812B (en) * | 2016-09-14 | 2022-10-04 | 佛山市顺德区美的电热电器制造有限公司 | Cooking quality evaluation method and device |
| CN106465742B (en) * | 2016-09-23 | 2018-09-25 | 中国农业科学院农产品加工研究所 | Sheep and goat carcass computer vision auxiliary partition system and its segmenting device |
| CN107590801B (en) * | 2017-09-08 | 2020-03-17 | 王虎峰 | Image processing method for beef eye muscle marbling segmentation and grading |
| US11497221B2 (en) | 2019-07-19 | 2022-11-15 | Walmart Apollo, Llc | Systems and methods for managing meat cut quality |
| CN112906773A (en) * | 2021-02-04 | 2021-06-04 | 中国农业大学 | Pig slaughtering line carcass quality grading and monitoring method and system based on cloud service |
| CN116391740B (en) * | 2023-04-11 | 2023-09-19 | 浙江丰隆食品加工有限公司 | Beef processing system based on intelligent classification |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1603801A (en) * | 2004-11-02 | 2005-04-06 | 江苏大学 | Method and device for computer vision detection and classification of beef carcase quality |
| CN101561402A (en) * | 2009-05-07 | 2009-10-21 | 浙江大学 | Machine vision-based real-time detection and grading method and machine vision-based real-time detection and grading device for pork appearance quality |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008039610A (en) * | 2006-08-07 | 2008-02-21 | Gifu Prefecture | Digitizing method of marbled state of edible meat, digitizing device of marbled state of edible meat, and program |
-
2010
- 2010-12-01 CN CN2010105689366A patent/CN102156129B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1603801A (en) * | 2004-11-02 | 2005-04-06 | 江苏大学 | Method and device for computer vision detection and classification of beef carcase quality |
| CN101561402A (en) * | 2009-05-07 | 2009-10-21 | 浙江大学 | Machine vision-based real-time detection and grading method and machine vision-based real-time detection and grading device for pork appearance quality |
Non-Patent Citations (3)
| Title |
|---|
| JP特开2008-39610A 2008.02.21 |
| 屠康等.计算机视觉在牛肉大理石花纹分级中的应用研究.《粮油加工与食品机械》.2003,(第10期),43-45. * |
| 陈坤杰等.机器视觉技术在分析牛肉颜色变化特征中的应用.《食品科学》.2008,第29卷(第9期),92-96. * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108007929A (en) * | 2017-12-01 | 2018-05-08 | 南京农业大学 | A kind of automatic judging method of beef physiological makeup |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102156129A (en) | 2011-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102156129B (en) | Beef quality intelligent grading system and method based on machine vision | |
| CN100480680C (en) | Multiple spectrum meat freshness artificial intelligence measurement method and system | |
| DE69910182T2 (en) | MEAT COLOR IMAGE GENERATION SYSTEM TO PRESENT TASTE AND YIELD | |
| CN103076288B (en) | A kind of flesh of fish self-grading device based on computer vision and method | |
| CN106338517A (en) | Intelligent judgment method for fruit freshness based on coordination of visual information and olfactory information | |
| CN102147402A (en) | Machine vision technology based method for rapidly detecting egg freshness | |
| CN108613989A (en) | A kind of detection method of paddy unsound grain | |
| US8260005B2 (en) | Portable tool for determining meat quality | |
| CN107564000B (en) | Hericium erinaceus non-destructive testing stage division based on computer vision | |
| CN108318494B (en) | The red online vision detection and classification devices and methods therefor for proposing fruit powder | |
| CN104256882A (en) | Method for measuring proportion of reconstituted tobacco in cut tobacco on basis of computer vision | |
| CN103528967A (en) | Hyperspectral image based overripe Lonicera edulis fruit identification method | |
| CN104198325A (en) | Method for measuring ratio of cut stem to cut tobacco based on computer vision | |
| CN100376888C (en) | Method and device for computer vision detection and classification of beef carcase quality | |
| CN106845366A (en) | Sugarcane coverage automatic testing method based on image | |
| CN112634274B (en) | Machine vision-based fattening pork quality evaluation method and system | |
| Ji et al. | Apple color automatic grading method based on machine vision | |
| CN103344571A (en) | Method and device for evaluating tolerance quality of negotiable securities | |
| CN103411929A (en) | Method for detecting rice transparency | |
| CN101091649A (en) | Method for picking-up gray-scaled images of fruit flies | |
| Yumang et al. | Computer vision-based non-invasive sweetness assessment of mangifera indica l. fruit using k-means clustering and cnn | |
| Narendra et al. | An intelligent system for identification of Indian Lentil types using Artificial Neural Network (BPNN) | |
| Zhang et al. | On-line sorting maturity of cherry tomato bymachine vision | |
| CN104865198A (en) | Machine vision-based fresh fat liver quality automatic grading system and method | |
| CN201051074Y (en) | Multi-spectrum flesh verdure artificial intelligence measurement system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| 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: 20121003 Termination date: 20161201 |