CN109271867B - Automatic judgment method for strawberry maturity - Google Patents
Automatic judgment method for strawberry maturity Download PDFInfo
- Publication number
- CN109271867B CN109271867B CN201810945004.5A CN201810945004A CN109271867B CN 109271867 B CN109271867 B CN 109271867B CN 201810945004 A CN201810945004 A CN 201810945004A CN 109271867 B CN109271867 B CN 109271867B
- Authority
- CN
- China
- Prior art keywords
- image
- strawberry
- automatic
- binary
- determination 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
An automatic judgment method for the maturity of strawberries is characterized in that images shot by a camera under red light, green light and white light are subjected to a series of processing, and fruits with the Rate = (N3-N4)/(N2+ N3-N4) Rate being more than 0.90 are picked as mature fruits according to a formula. The whole process does not need manual intervention, and the possibility is provided for automatic strawberry picking of subsequent equipment.
Description
Technical Field
The invention relates to the technical field of agriculture, in particular to an automatic judgment method for strawberry maturity.
Background
Strawberry, a fruit with a short seasonal harvest period, must be picked in time after it is ripe. Labor shortages and complexity and labor intensity of strawberry picking have become important factors that have restricted the development of the strawberry growing industry. In order to improve the strawberry picking efficiency, various strawberry picking robots are developed by a plurality of enterprises or universities at home and abroad. In order to accurately realize the picking of the strawberry fruits by using the picking robot, an accurate judgment algorithm of the maturity of the strawberry fruits is needed so as to improve the picking precision of the strawberry fruits and reduce the wrong picking or missed picking.
Disclosure of Invention
Aiming at the defects in the prior art, the automatic strawberry maturity judging method can automatically judge whether the strawberries are mature or not.
The invention is realized by the following technical scheme: an automatic judgment method for strawberry maturity comprises the following steps:
the method comprises the steps of firstly, shooting an image of a strawberry fruit under red light illumination, taking an image of a red channel in a shot original image as a first image, wherein the mature strawberry fruit is red, and shooting the mature fruit by red light illumination, so that the obtained image is clearer.
And secondly, shooting an image of the strawberry fruit under the illumination of green light, taking the image of a green channel in the shot original image as a second image, wherein the immature strawberry fruit is green, and shooting with green light to obtain an image which better reflects gray information of the immature strawberry fruit.
Thirdly, shooting an image of the strawberry fruit under the illumination of white light, taking an image in a red channel in the shot original image as a third image, taking an image in a green channel in the shot original image as a fourth image,
fourthly, converting the first image into a first binary image by using an Otsu binarization method, removing noise points of the first binary image (deleting a small white area with an area smaller than a certain range of 300 pixels in the 2-value image), labeling the first binary image (labeling the binary image in a range of 0-65535, wherein each area corresponds to one label value), smoothing the obtained contour area (labeled single white area) (performing closed operation processing of image morphology for removing burrs and the like of the contour area) to obtain a first domain N1,
fifthly, converting the second image into a second binary image by using the Dajin binarization method, and converting the second image into a second binary image
Labeling the second binary image after the second binary image is processed with the first field N1, then smoothing the obtained contour region to obtain a second field N2,
sixthly, obtaining a difference image after the difference value is made between the third image and the fourth image, normalizing the difference image, carrying out binarization by an Otsu binarization method to obtain a third binary image, and carrying out AND processing on the third binary image and the first field to obtain a third field N3
Seventhly, taking a region obtained by intersecting the second domain N2 and the third domain N3 as a fourth domain N4,
the coloring Rate Rate is calculated according to the following formula
Rate=(N3-N4)/(N2+N3-N4)
Fruits with a Rate greater than 0.90 are picked as ripe fruits. The practical photographing test result of the strawberries shows that the fruits with the coloring rate of more than 0.9 are mature fruits.
In the above technical solution, preferably, in step 1, the wavelength range of the red light is 600nm to 650 nm.
In the above technical solution, preferably, in step 2, the wavelength range of the green light is 480nm to 520 nm.
In the above technical solution, specifically, in steps 1 to 3, the resolution of the captured image is 1280X 1024.
In the above technical solution, specifically, in steps 1 to 3, each shooting time is 50 ms.
The invention has the following beneficial effects: the method utilizes the shot pictures to process and judge whether the strawberries are mature or not, does not need manual intervention in the whole process, and provides possibility for automatic picking of the strawberries by subsequent equipment.
Detailed Description
The present invention will be described in further detail with reference to specific embodiments.
An automatic judgment method for strawberry maturity comprises the following steps:
the method comprises the steps of firstly, shooting an image of a strawberry fruit under the illumination of red light, taking an image of a red channel in a shot original image as a first image, wherein the wavelength of the red light is 630 nm.
And secondly, shooting an image of the strawberry fruit under the illumination of green light, and taking an image of a green channel in the shot original image as a second image, wherein the wavelength of the green light is 500 nm.
And thirdly, shooting an image of the strawberry fruit under the illumination of white light, taking an image in a red channel in the shot original image as a third image, and taking an image in a green channel in the shot original image as a fourth image.
And fourthly, converting the first image into a first binary image by using an extra-large binary method, removing noise points of the first binary image, wherein the noise points removed in the embodiment are small white areas with the area smaller than 300 pixels in the 2-value image, labeling the binary image in the embodiment in the range of 0-65535, each area corresponds to a label value, and smoothing the obtained contour area, namely the labeled single white area to obtain the first field N1.
And fifthly, converting the second image into a second binary image by using an Otsu binarization method, performing hybridization processing on the second binary image and the first field N1, labeling, and performing smoothing processing on the obtained contour region to obtain a second field N2. ,
and sixthly, obtaining a difference image after the difference value is carried out on the third image and the fourth image, normalizing the difference image, namely dividing the difference image into 256 levels according to the gray level, then carrying out binarization on the difference image by using an Otsu binarization method to obtain a third binary image, and carrying out AND processing on the third binary image and the first field to obtain a third field N3.
And seventhly, taking a region obtained by intersecting the second domain N2 and the third domain N3 as a fourth domain N4.
The coloring Rate Rate is calculated according to the following formula
Rate=(N3-N4)/(N2+N3-N4)
Fruits with a Rate greater than 0.90 are picked as ripe fruits.
In this embodiment, preferably, in steps 1 to 3, the resolution of the captured image is 1280X 1024. Each shooting time is 50 ms.
Claims (8)
1. An automatic judgment method for strawberry maturity is characterized by comprising the following steps:
the first step is that an image of the strawberry fruit is shot under the illumination of red light, the image of a red channel in the shot original image is taken as a first image,
secondly, shooting an image of the strawberry fruit under the illumination of green light, taking an image of a green channel in the shot original image as a second image,
thirdly, shooting an image of the strawberry fruit under the illumination of white light, taking an image in a red channel in the shot original image as a third image, taking an image in a green channel in the shot original image as a fourth image,
fourthly, converting the first image into a first binary image by using an Otsu binarization method, labeling the first binary image, smoothing the obtained contour area to obtain a first field N1,
fifthly, converting the second image into a second binary image by using an Otsu binarization method, labeling the second binary image after carrying out the treatment on the second binary image and the first field N1, then carrying out the smoothing treatment on the obtained contour region to obtain a second field N2,
sixthly, obtaining a difference image after the difference value is made between the third image and the fourth image, normalizing the difference image, carrying out binarization by an Otsu binarization method to obtain a third binary image, and carrying out AND processing on the third binary image and the first field to obtain a third field N3
Seventhly, taking a region obtained by intersecting the second domain N2 and the third domain N3 as a fourth domain N4,
the coloring Rate Rate is calculated according to the following formula
Rate=(N3-N4)/(N2+N3-N4)
Fruits with a Rate greater than 0.90 are picked as ripe fruits.
2. The automatic strawberry maturity determination method according to claim 1, wherein: in step 1, the wavelength range of the red light is 600nm to 650 nm.
3. The automatic strawberry maturity determination method according to claim 1, wherein: in step 2, the wavelength range of the green light is 480nm to 520 nm.
4. The automatic strawberry maturity determination method according to claim 1, wherein: in steps 1 to 3, the resolution of the captured image is 1280X 1024.
5. The automatic strawberry maturity determination method according to claim 1, wherein: in steps 1 to 3, each shooting time is 50 ms.
6. The automatic strawberry maturity determination method according to claim 1, wherein: step 4, further comprising a step of removing noise, wherein the noise removal is to delete the white area smaller than 300 pixels in the first binary image.
7. The automatic strawberry maturity determination method according to claim 1, wherein: in steps 4 to 6, the labeling is a step of assigning a value to the binary image according to each region.
8. The automatic strawberry maturity determination method according to claim 1, wherein: in step 6, the normalization is a step of assigning values to the difference image according to gray scales.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810945004.5A CN109271867B (en) | 2018-08-20 | 2018-08-20 | Automatic judgment method for strawberry maturity |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810945004.5A CN109271867B (en) | 2018-08-20 | 2018-08-20 | Automatic judgment method for strawberry maturity |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109271867A CN109271867A (en) | 2019-01-25 |
CN109271867B true CN109271867B (en) | 2021-11-02 |
Family
ID=65153930
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810945004.5A Active CN109271867B (en) | 2018-08-20 | 2018-08-20 | Automatic judgment method for strawberry maturity |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109271867B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111079530A (en) * | 2019-11-12 | 2020-04-28 | 青岛大学 | Mature strawberry identification method |
CN114258781B (en) * | 2022-01-06 | 2023-07-21 | 重庆邮电大学 | Morphology and color space-based strawberry stem picking point positioning method |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103793692A (en) * | 2014-01-29 | 2014-05-14 | 五邑大学 | Low-resolution multi-spectral palm print and palm vein real-time identity recognition method and system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9462749B1 (en) * | 2015-04-24 | 2016-10-11 | Harvest Moon Automation Inc. | Selectively harvesting fruits |
-
2018
- 2018-08-20 CN CN201810945004.5A patent/CN109271867B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103793692A (en) * | 2014-01-29 | 2014-05-14 | 五邑大学 | Low-resolution multi-spectral palm print and palm vein real-time identity recognition method and system |
Also Published As
Publication number | Publication date |
---|---|
CN109271867A (en) | 2019-01-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111666883B (en) | Grape picking robot target identification and fruit stalk clamping and cutting point positioning method | |
CN109271867B (en) | Automatic judgment method for strawberry maturity | |
CN108875747B (en) | Machine vision-based imperfect wheat grain identification method | |
CN111652326A (en) | Improved fruit maturity identification method and identification system based on MobileNet v2 network | |
CN112990103B (en) | String mining secondary positioning method based on machine vision | |
CN102279976A (en) | Method for constructing and identifying BP (Back Propagation) neural network for identifying different coarse rice seeds | |
CN103020924B (en) | Low-illumination monitored image enhancement method based on similar scenes | |
CN107301401A (en) | A kind of multiple target kiwifruit fruit recognition methods and image acquiring device | |
CN110956627A (en) | Intelligent optical detection sample characteristic and flaw intelligent lighting image capturing method and device | |
CN116363505A (en) | Target picking method based on picking robot vision system | |
CN105118028B (en) | A kind of grafting seam identification device of full-automatic grafting machine and seam recognition methods | |
Fu et al. | Kiwifruit recognition method at night based on fruit calyx image | |
CN111079831A (en) | Intelligent optical detection sample characteristic and flaw automatic marking method and device | |
CN107256549B (en) | Bamboo strip defect detection method based on machine vision | |
CN108090910B (en) | Night outdoor tomato plant image segmentation algorithm based on information entropy gradient simplified PCNN model | |
CN109596620A (en) | Product surface shape defect detection method and system based on machine vision | |
CN112750113B (en) | Glass bottle defect detection method and device based on deep learning and linear detection | |
CN111126402B (en) | Image processing method and device, electronic equipment and storage medium | |
CN110070086A (en) | A kind of Kiwi berry blade disease recognition method based on image recognition | |
CN115950892B (en) | Automatic spraying detection device for identifying microcracks on outer surface of stainless steel pipe based on image | |
CN111353432B (en) | Rapid clean selection method and system for honeysuckle medicinal materials based on convolutional neural network | |
CN110987957A (en) | Intelligent defect removing method based on machine vision and laser processing | |
CN108710850B (en) | Wolfberry fruit identification method and system | |
CN107248151A (en) | A kind of LCD panel intelligent detecting method and system based on machine vision | |
CN111401121A (en) | Method for realizing citrus segmentation based on super-pixel feature extraction |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: An automatic judgment method of strawberry maturity Effective date of registration: 20211225 Granted publication date: 20211102 Pledgee: Yongkang branch of the Industrial Commercial Bank of China Ltd. Pledgor: ZHEJIANG RONGYA INDUSTRY AND TRADE Co.,Ltd. Registration number: Y2021330002660 |