CN106023223A - Orange fruit size describing method and organic fruit size grading method - Google Patents

Orange fruit size describing method and organic fruit size grading method Download PDF

Info

Publication number
CN106023223A
CN106023223A CN201610367397.7A CN201610367397A CN106023223A CN 106023223 A CN106023223 A CN 106023223A CN 201610367397 A CN201610367397 A CN 201610367397A CN 106023223 A CN106023223 A CN 106023223A
Authority
CN
China
Prior art keywords
fruit
size
image
citrusfruit
pixel
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
Application number
CN201610367397.7A
Other languages
Chinese (zh)
Inventor
曹乐平
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hunan Biological and Electromechanical Polytechnic
Original Assignee
Hunan Biological and Electromechanical Polytechnic
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hunan Biological and Electromechanical Polytechnic filed Critical Hunan Biological and Electromechanical Polytechnic
Priority to CN201610367397.7A priority Critical patent/CN106023223A/en
Publication of CN106023223A publication Critical patent/CN106023223A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10052—Images from lightfield camera
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20112—Image segmentation details
    • G06T2207/20152—Watershed segmentation

Landscapes

  • Sorting Of Articles (AREA)

Abstract

The invention discloses an orange fruit size describing method and an organic fruit size grading method, wherein the organic fruit size describing method comprises the steps of eliminating a fruit stalk part, which exceeds a fruit surface, of a tested fruit; acquiring original images of the fruit stalk surface and the side surface of the tested fruit; cutting the original images; performing background elimination on the cut images; performing edge detection and fruit area extraction on the images after background elimination; respectively counting a fruit contour pixel L1 and a fruit area pixel S1 in the fruit stalk surface image, a fruit contour pixel L2 and a fruit area pixel S2 in the side image, calculating an average fruit transverse diameter D1=4kS1/L1 and an average fruit longitudinal diameter D2=4kS2/L2; and describing the size of the orange fruit through D1 and D2. According to the orange fruit size describing method and the orange fruit size grading method, the size of the orange fruit are comprehensively described by means of the transverse diameter and the longitudinal diameter, and grade of the fruit size can be reflected in a more real manner; and furthermore a continuous fruit edge obtained through an improved watershed algorithm and boundary communication operation, thereby extracting a whole no-hole fruit area and realizing reliable result.

Description

Citrusfruit size describes and stage division
Technical field
The invention belongs to a kind of citrusfruit size describe and stage division.
Background technology
In national standard and industry standard, citrusfruit size only carrys out quantitative description with maximum transverse diameter, and it is the most unilateral that this citrusfruit size describes method, only reflects horizontal size.Owing to citrusfruit outer shape differs, for pancake, spherical, elliposoidal Citrus, its size cannot be distinguished by.As it is shown in figure 1, when transverse diameter is identical, there is greatly different in size situation in citrusfruit.
Summary of the invention
It is an object of the invention to, for above-mentioned the deficiencies in the prior art, it is provided that the citrusfruit size that a kind of transverse diameter combines with vertical footpath describes and stage division.
For solving above-mentioned technical problem, the technical solution adopted in the present invention is:
A kind of citrusfruit size describes method, comprises the following steps:
Step one, removes tested fruit beyond the carpopodium part in fruit face；
Step 2, gathers tested fruit carpopodium face and the original image of side；
Step 3, cuts original image；
Step 4, goes background process to the image after cutting；
Step 5, carries out rim detection and fruit extracted region to the image after going background process；
Step 6, respectively fruit contour pixel L in the image of statistics carpopodium face1And fruit area pixel S1, fruit contour pixel L in side image2And fruit area pixel S2, calculate fruit average transverse diameter D1=4kS1/L1With average vertical footpath D2=4kS2/L2；With D1And D2Citrusfruit size is described；Wherein, the computational methods of k are: take the yellow table tennis of a 40mm diameter, after image acquisition, image cut, go background process, rim detection and extracted region, and statistics contour pixel L and area pixel S, try to achieve k=10L/S.
The present invention is the method utilizing transverse diameter with vertical footpath comprehensive description citrusfruit size, it is possible to reflect fruit size more realistically.
As a kind of optimal way, described step 2 includes: fruit is placed in 500 × 500 × 500mm3Lighting box bottom center, background black, digital camera is in lighting box center of top, and camera lens is away from fruit top 460～490mm, and case top is symmetrical uniform 4 60w electric filament lamp, collecting fruit carpopodium face and the digital picture of side centered by camera lens.
As a kind of optimal way, described step 3 includes: utilize digital imaging processing software that the original image gathered is carried out cutting of 1024 × 1024 pixel sizes.
As a kind of optimal way, described step 4 includes: statistics cuts the brightness Y=0.1770R+0.8124G+0.0106B rectangular histogram of rear citrusfruit image, and wherein, R, G, B respectively cut redness, green and the blue component of rear citrusfruit image；The trough brightness cut off value of bimodal of brightness histogram of extraction, as threshold value T, is set up luminance segmentation function, is put 1 less than the gray scale of cut off value, constant higher than the gray scale of cut off value.
As a kind of optimal way, described step 5 includes: the image after going background carries out the Prewitt operator filtering of horizontal and vertical directions, obtains filtering image ghAnd gv；Described filtering image is carried out Euclidean Distance Transform and obtains receiving basin distance d to watershedf；To dfCarry out watershed detection, labelling dfExternal constraint em, with local luminance gradient maximum size as condition, dynamically adjust threshold value, filter out higher than threshold value go background gray level image gray scale maximum be extended maximum conversion, calculate dfInternal constraint im；Em and im is utilized to reconstruct gradient map g2；To g2Do watershed detection, merge perimeter and interior zone, complete fruit margin detection, connect border, labelling fruit boundary profile, extract fruit region.
There is more serious over-segmentation problem in traditional watershed algorithm, in the present invention, modified model watershed algorithm carries out Grads threshold process on the basis of tradition watershed algorithm and internal constraint dynamically adjusts, and overcomes this shortcoming.
Based on same inventive concept, present invention also offers a kind of citrusfruit size fractionation method, utilize the citrusfruit size as described in any one of claim 1 to 5 to describe method and try to achieve fruit average transverse diameter D1=4kS1/L1With average vertical footpath D2=4kS2/L2；According to D1And D2Size citrusfruit size is carried out grade classification.
Test through a large amount of Citrus samples, obtain D1And D2The regularity of distribution, in conjunction with national standard, obtain weighing the grade retrieval table of fruit size；D according to tested fruit1And D2Inquiry grade retrieval table, if D1And D2Lay respectively at two intervals that same grade is corresponding, then this grade is exactly the grade of fruit size；If D1And D2Lay respectively at two intervals that different brackets is corresponding, then relatively low in these two grades grade that one-level is fruit size.
Compared with prior art, the present invention utilizes transverse diameter and vertical footpath comprehensive description citrusfruit size, it is possible to reflection fruit size grade more realistically；Utilize improvement watershed algorithm and boundary connected operation to obtain coherent continual fruit margin, extract complete imperforate fruit region, reliable results simultaneously.
Accompanying drawing explanation
Fig. 1 is same transverse diameter different size of citrusfruit comparison diagram.
Fig. 2 is the image after cutting.
Fig. 3 is brightness histogram.
Fig. 4 is the image after background process.
Fig. 5 is fruit margin and fruit administrative division map.
Detailed description of the invention
The present invention is that a kind of citrusfruit size describes and stage division, using satsuma mandarin as measurand, comprises the following steps:
Step one, by concordant for carpopodium fruit face, cuts off tested fruit beyond the carpopodium part in fruit face；
Step 2, gathers tested fruit carpopodium face and the original image of side；
Fruit is placed in 500 × 500 × 500mm3Lighting box bottom center, background black, digital camera is in lighting box center of top, and camera lens is away from fruit top 460～490mm, and case top is symmetrical uniform 4 60w electric filament lamp, collecting fruit carpopodium face and the digital picture of side centered by camera lens.
Step 3, cuts original image；
Utilize digital imaging processing software that the original image gathered is carried out cutting of 1024 × 1024 pixel sizes, obtain image as shown in Figure 2.
Step 4, goes background process to the image after cutting；
Statistics cuts the brightness Y=0.1770R+0.8124G+0.0106B rectangular histogram of rear citrusfruit image, and wherein, R, G, B respectively cut redness, green and the blue component of rear citrusfruit image；The trough brightness cut off value of bimodal of brightness histogram of extraction, as threshold value T, is set up luminance segmentation function, is put 1 less than the gray scale of cut off value, constant higher than the gray scale of cut off value.Brightness histogram is as shown in Figure 3.After treatment, as shown in Figure 4, the background outside major part citrusfruit region is eliminated.
Step 5, carries out rim detection and fruit extracted region to the image after going background process；
Image after going background is carried out the Prewitt operator filtering of horizontal and vertical directions, obtains filtering image ghAnd gv；Computed range functionDescribed filtering image is carried out Euclidean Distance Transform and obtains receiving basin distance d to watershedf；To dfCarry out watershed detection, labelling dfExternal constraint em, with local luminance gradient maximum size as condition, dynamically adjust threshold value, filter out higher than threshold value go background gray level image gray scale maximum be extended maximum conversion, calculate dfInternal constraint im；Em and im is utilized to reconstruct gradient map g2；To g2Do watershed detection, merge perimeter and interior zone, complete fruit margin detection, connect border, labelling fruit boundary profile, extract fruit region.As it is shown in figure 5, after treatment, fruit margin is coherent uninterrupted, and fruit region is complete without hole.
Step 6, respectively fruit contour pixel L in the image of statistics carpopodium face1And fruit area pixel S1, fruit contour pixel L in side image2And fruit area pixel S2, calculate fruit average transverse diameter D1=4kS1/L1With average vertical footpath D2=4kS2/L2；With D1And D2Citrusfruit size is described；Wherein, the computational methods of k are: take the yellow table tennis of a 40mm diameter, after image acquisition, image cut, go background process, rim detection and extracted region, and statistics contour pixel L and area pixel S, try to achieve k=10L/S.
During size fractionation, describe method first with described citrusfruit size and try to achieve fruit average transverse diameter D1=4kS1/L1With average vertical footpath D2=4kS2/L2；Further according to D1And D2Size citrusfruit size is carried out grade classification.During classification, need according to national standard and sampling test, obtain D1And D2The regularity of distribution, obtain weigh fruit size grade retrieval table, as shown in table 1；D further according to tested fruit1And D2Inquiry grade retrieval table, if D1And D2Lay respectively at two intervals that same grade is corresponding, then this grade is exactly the grade of fruit size；If D1And D2Lay respectively at two intervals that different brackets is corresponding, then relatively low in these two grades grade that one-level is fruit size.
Average transverse diameter Average vertical footpath Group
45～50 <43 Micro-fruit
50～55 41～45 Fruitlet
55～60 43～47 Middle fruit
60～65 45～50 Big fruit
65～75 48～56 Especially big fruit
Table 1 satsuma mandarin order of magnitude retrieval table (unit: millimeter).

Claims (6)

1. a citrusfruit size describes method, it is characterised in that comprise the following steps:
Step one, removes tested fruit beyond the carpopodium part in fruit face；
Step 2, gathers tested fruit carpopodium face and the original image of side；
Step 3, cuts original image；
Step 4, goes background process to the image after cutting；
Step 5, carries out rim detection and fruit extracted region to the image after going background process；
Step 6, respectively fruit contour pixel L in the image of statistics carpopodium face1And fruit region picture Element S1, fruit contour pixel L in side image2And fruit area pixel S2, calculate fruit and put down All transverse diameter D1=4kS1/L1With average vertical footpath D2=4kS2/L2；With D1And D2Citrus fruit is described Real size；Wherein, the computational methods of k are: take the yellow table tennis of a 40mm diameter, warp Cross image acquisition, image cuts, go background process, rim detection and extracted region after, statistics Contour pixel L and area pixel S, try to achieve k=10L/S.
2. citrusfruit size as claimed in claim 1 describes method, it is characterised in that Described step 2 includes: fruit is placed in 500 × 500 × 500mm3Lighting box bottom in Centre, background black, digital camera in lighting box center of top, camera lens away from fruit top 460～ 490mm, case top is symmetrical uniform 4 60w electric filament lamp centered by camera lens, gather fruit Real carpopodium face and the digital picture of side.
3. citrusfruit size as claimed in claim 1 describes method, it is characterised in that Described step 3 includes: utilize digital imaging processing software to carry out the original image gathered Cutting of 1024 × 1024 pixel sizes.
4. citrusfruit size as claimed in claim 1 describes method, it is characterised in that Described step 4 includes: statistics cuts the brightness of rear citrusfruit image Y=0.1770R+0.8124G+0.0106B rectangular histogram, wherein, after R, G, B respectively cut The redness of citrusfruit image, green and blue component；Extract the ripple of bimodal of brightness histogram Paddy brightness cut off value, as threshold value T, sets up luminance segmentation function, puts less than the gray scale of cut off value 1, constant higher than the gray scale of cut off value.
5. citrusfruit size as claimed in claim 1 describes method, it is characterised in that Described step 5 includes: the image after going background is carried out horizontal and vertical directions Prewitt operator filtering, obtains filtering image ghAnd gv；Described filtering image is carried out Euclidean Range conversion obtains receiving basin distance d to watershedf；To dfCarry out watershed detection, Labelling dfExternal constraint em, with local luminance gradient maximum size as condition, dynamically adjust Whole threshold value, filters out and is extended greatly higher than the background gray level image gray scale maximum of going of threshold value Value conversion, calculates dfInternal constraint im；Em and im is utilized to reconstruct gradient map g2；To g2 Do watershed detection, merge perimeter and interior zone, complete fruit margin detection, connection Border, labelling fruit boundary profile, extracts fruit region.
6. a citrusfruit size fractionation method, it is characterised in that utilize such as claim 1 Describe method to the citrusfruit size described in 5 any one and try to achieve the average transverse diameter of fruit D1=4kS1/L1With average vertical footpath D2=4kS2/L2；According to D1And D2Size to citrusfruit Size carries out grade classification.
CN201610367397.7A 2016-05-30 2016-05-30 Orange fruit size describing method and organic fruit size grading method Pending CN106023223A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610367397.7A CN106023223A (en) 2016-05-30 2016-05-30 Orange fruit size describing method and organic fruit size grading method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610367397.7A CN106023223A (en) 2016-05-30 2016-05-30 Orange fruit size describing method and organic fruit size grading method

Publications (1)

Publication Number Publication Date
CN106023223A true CN106023223A (en) 2016-10-12

Family

ID=57092292

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610367397.7A Pending CN106023223A (en) 2016-05-30 2016-05-30 Orange fruit size describing method and organic fruit size grading method

Country Status (1)

Country Link
CN (1) CN106023223A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106407962A (en) * 2016-11-15 2017-02-15 融安县植保植检站 Citrus fruit fly harm fruit-drop rate statistics system
CN109800619A (en) * 2017-11-16 2019-05-24 湖南生物机电职业技术学院 Maturity period citrusfruit image-recognizing method
CN110495624A (en) * 2019-08-29 2019-11-26 贵州大学 A kind of fruit based on image recognition removes speed governor
CN113277101A (en) * 2021-03-09 2021-08-20 温州市勘察测绘研究院 Unmanned aerial vehicle collection system based on intelligent aerial image recognition technology

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103065149A (en) * 2012-12-21 2013-04-24 上海交通大学 Netted melon fruit phenotype extraction and quantization method
CN103512494A (en) * 2013-07-16 2014-01-15 宁波职业技术学院 Visual inspection system and method for scale micro changes of plant fruits
CN103913124A (en) * 2014-03-18 2014-07-09 北京农业信息技术研究中心 Automatic monitoring system and method for fruit appearance quality

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103065149A (en) * 2012-12-21 2013-04-24 上海交通大学 Netted melon fruit phenotype extraction and quantization method
CN103512494A (en) * 2013-07-16 2014-01-15 宁波职业技术学院 Visual inspection system and method for scale micro changes of plant fruits
CN103913124A (en) * 2014-03-18 2014-07-09 北京农业信息技术研究中心 Automatic monitoring system and method for fruit appearance quality

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
XIANG LI AND ZHENLONG BAI: "Fruit Quality Detection System Based on Video Image Analysis", 《THE 11TH NATIONAL ANUUAL SYMPOSIUM ON INDUSTRIAL TECHNOLOGY OF ECONOMIC MANAGEMENT INSTITUTIONS》 *
曹乐平，温芝元: "基于统计复杂性测度、多重分形谱等方法的柑橘品质分级", 《浙江大学学报（农业与生命科学版）》 *
曹乐平: "基于周长和面积分形维数的柑橘品种机器识别", 《农业工程学报》 *
温芝元，曹乐平: "基于补偿模糊神经网络的脐橙不同病虫害图像识别", 《农业工程学报》 *
苏金玲: "融合显著性与GraphCut的自然场景图像分割", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *
邓秀新，彭抒昂: "《现代农业科技专著大系—柑橘学》", 30 June 2013 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106407962A (en) * 2016-11-15 2017-02-15 融安县植保植检站 Citrus fruit fly harm fruit-drop rate statistics system
CN109800619A (en) * 2017-11-16 2019-05-24 湖南生物机电职业技术学院 Maturity period citrusfruit image-recognizing method
CN109800619B (en) * 2017-11-16 2022-07-01 湖南生物机电职业技术学院 Image recognition method for citrus fruits in mature period
CN110495624A (en) * 2019-08-29 2019-11-26 贵州大学 A kind of fruit based on image recognition removes speed governor
CN113277101A (en) * 2021-03-09 2021-08-20 温州市勘察测绘研究院 Unmanned aerial vehicle collection system based on intelligent aerial image recognition technology
CN113277101B (en) * 2021-03-09 2022-06-03 温州市勘察测绘研究院有限公司 Unmanned aerial vehicle collection system based on intelligent aerial image recognition technology

Similar Documents

Publication Publication Date Title
CN106651872B (en) Pavement crack identification method and system based on Prewitt operator
Longsheng et al. Kiwifruit recognition at nighttime using artificial lighting based on machine vision
CN105354865B (en) The automatic cloud detection method of optic of multispectral remote sensing satellite image and system
Zhang et al. Method of famous tea sprout identification and segmentation based on improved watershed algorithm
Patel et al. Automatic segmentation and yield measurement of fruit using shape analysis
WO2020224458A1 (en) Method for detecting corona discharge employing image processing
CN111753577B (en) Apple identification and positioning method in automatic picking robot
WO2016172827A1 (en) Stepwise-refinement pavement crack detection method
CN109255757B (en) Method for segmenting fruit stem region of grape bunch naturally placed by machine vision
CN106023223A (en) Orange fruit size describing method and organic fruit size grading method
CN106296670B (en) A kind of Edge detection of infrared image based on the watershed Retinex--Canny operator
CN104075965B (en) A kind of micro-image grain graininess measuring method based on watershed segmentation
CN106294705A (en) A kind of batch remote sensing image preprocess method
CN109145848B (en) Wheat ear counting method
CN106702870B (en) A kind of crack on road detecting system
CN105139391B (en) A kind of haze weather traffic image edge detection method
CN102024259A (en) Bacterial colony automatic detection method
CN102855641A (en) Fruit level classification system based on external quality
CN104732229A (en) Segmentation method for overlapping cells in cervical smear image
CN113255434B (en) Apple identification method integrating fruit characteristics and deep convolutional neural network
Shin et al. Postharvest citrus mass and size estimation using a logistic classification model and a watershed algorithm
CN109886170A (en) A kind of identification of oncomelania intelligent measurement and statistical system
CN110428374B (en) Small-size pest automatic detection method and system
CN108416814A (en) Quick positioning and recognition methods and the system on a kind of pineapple head
CN110335233A (en) Express-way guard-rail plates defect detecting system and method based on image processing techniques

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20161012

RJ01 Rejection of invention patent application after publication