CN117730655A - Quantitative analysis method, device, equipment and storage medium for vigor of rice seeds - Google Patents
Quantitative analysis method, device, equipment and storage medium for vigor of rice seeds Download PDFInfo
- Publication number
- CN117730655A CN117730655A CN202410189114.9A CN202410189114A CN117730655A CN 117730655 A CN117730655 A CN 117730655A CN 202410189114 A CN202410189114 A CN 202410189114A CN 117730655 A CN117730655 A CN 117730655A
- Authority
- CN
- China
- Prior art keywords
- image
- ncda
- rice seeds
- color
- images
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 235000007164 Oryza sativa Nutrition 0.000 title claims abstract description 288
- 235000009566 rice Nutrition 0.000 title claims abstract description 288
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000004445 quantitative analysis Methods 0.000 title claims abstract description 44
- 238000003860 storage Methods 0.000 title claims abstract description 24
- 240000007594 Oryza sativa Species 0.000 title 1
- 241000209094 Oryza Species 0.000 claims abstract description 287
- 238000006243 chemical reaction Methods 0.000 claims abstract description 14
- 238000005259 measurement Methods 0.000 claims description 48
- 238000000611 regression analysis Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 15
- 230000032683 aging Effects 0.000 claims description 10
- 230000003595 spectral effect Effects 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 6
- 230000035784 germination Effects 0.000 claims description 5
- 239000003086 colorant Substances 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 72
- 238000004364 calculation method Methods 0.000 abstract description 5
- 230000000694 effects Effects 0.000 description 13
- 238000012271 agricultural production Methods 0.000 description 9
- 238000007726 management method Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- ZKHQWZAMYRWXGA-KQYNXXCUSA-J ATP(4-) Chemical compound C1=NC=2C(N)=NC=NC=2N1[C@@H]1O[C@H](COP([O-])(=O)OP([O-])(=O)OP([O-])([O-])=O)[C@@H](O)[C@H]1O ZKHQWZAMYRWXGA-KQYNXXCUSA-J 0.000 description 2
- ZKHQWZAMYRWXGA-UHFFFAOYSA-N Adenosine triphosphate Natural products C1=NC=2C(N)=NC=NC=2N1C1OC(COP(O)(=O)OP(O)(=O)OP(O)(O)=O)C(O)C1O ZKHQWZAMYRWXGA-UHFFFAOYSA-N 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000701 chemical imaging Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003028 enzyme activity measurement method Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a quantitative analysis method, a device, equipment and a storage medium for rice seed vitality, which are characterized in that a conversion relation from a multispectral image of a sample rice seed to an nCDA image is analyzed to generate an nCDA image generation model and the nCDA image generation model is configured in an image acquisition device for warehousing detection, so that a warehousing detection personnel can realize warehousing detection judgment of the rice seed according to the rice seed color in an nCDA image photo of the warehousing rice seed shot by the image acquisition device, the vitality value of the rice seed is not required to be calculated, and the warehousing detection efficiency and the detection result recognition degree are improved; when the precise calculation of the seed vitality value is needed for the rice seeds after the rice seeds are placed in the warehouse, the vitality index of the batch of rice seeds can be precisely calculated by detecting the color value input vitality index of the rice seeds in the nCDA image photo and inputting a relation model of the color value of the nCDA image, and data support is provided for the quality fine classification of the rice seeds and the subsequent purchase of the rice seeds.
Description
Technical Field
The invention relates to the technical field of geological disaster prediction, in particular to a quantitative analysis method, a quantitative analysis device, quantitative analysis equipment and a quantitative analysis storage medium for vigor of rice seeds.
Background
The vigor of rice seeds is one of important indexes for measuring the quality of the seeds, and is a comprehensive reflection of the germination rate and the growth quantity of the seeds. The high-activity rice seeds have obvious growth advantages and production potential, and have extremely important significance for seed management and agricultural production. The activity of the rice seeds is highest when the seeds are physiologically mature, natural irreversible seed aging occurs along with the extension of the storage time, and the activity of the corresponding seeds is gradually reduced. Traditional rice seed activity detection is based on enzyme activity measurement, adenosine Triphosphate (ATP) content measurement, seedling growth measurement, germination speed measurement, hyperspectral imaging technology and the like, but has the defects of complex operation, long time consumption, damage to rice seeds and incapability of meeting nondestructive detection and quantitative detection. Although, there have been proposed methods for detecting seed vigor based on multispectral image analysis (for example, patent of the invention filed by the applicant in advance and published under the publication number CN116941380 a).
However, in practical applications of seed management and agricultural production, since rice seed purchasing has seasonal characteristics, there are generally large purchasing amount and purchasing frequency in a rice seed purchasing period (for example, a scenario in which a large number of rice planting individual households are subjected to rice seed purchasing in a country or a rice seed planting area), and under such a scenario, the in-house vigor detection of rice seeds needs to satisfy: the method is suitable for the requirements of different types of rice seeds for detection, high detection speed, strong identification of detection results, deliverable circulation of the detection results, storage of stubbles of the detection results and the like.
In the seed vitality detection scheme based on the multispectral image, which is proposed in the prior art, the detection of the seed vitality is mainly realized by directly calculating the seed vitality value, and the method has the following defects: (1) The detection time consumption is unnecessary in the detection of the warehousing activity, the detection of the warehousing activity of the rice seeds does not need the high-precision detection result such as the activity value of the seeds, and only the simple activity detection is needed for the sample of the rice seeds in the warehouse to judge whether to purchase the batch of rice seeds (the high-precision detection of the activity value of the seeds is needed when the quality of the rice seeds is finely divided after the purchase and the quality of the purchased rice seeds is evaluated to provide data support for the subsequent purchase and other links); (2) The identification of the seed vitality value as a detection result is not high, the warehousing vitality detection behavior performed during rice seed purchase is often performed by non-professional staff, and the purchase judgment is performed by the seed vitality value, so that the judgment error condition caused by the low identification degree exists; (3) When different types of rice seeds are detected, the different types of rice seeds have different standard seed vitality values, so that the judgment difficulty is further improved; (4) The method of directly calculating the seed vitality value cannot realize the deliverable circulation of the detection result and the storage of the stub of the detection result, so that the seed vitality value of the batch of rice seeds cannot be accurately detected and verified in the follow-up process.
Therefore, how to improve the adaptability of rice seed vitality detection to the demands of purchasing in different periods in practical scenes such as seed management, agricultural production and the like, namely, ensure the high-precision detection of selectivity after warehousing while ensuring the detection speed and the detection result discrimination of the warehousing vitality detection, is a technical problem to be solved urgently.
Disclosure of Invention
The invention mainly aims to provide a quantitative analysis method, a quantitative analysis device, quantitative analysis equipment and a quantitative analysis storage medium for the vigor of rice seeds, and aims to solve the problems that the detection speed and the detection result of the in-warehouse vigor detection are low in discrimination degree, the vigor detection result delivery and transfer after the in-warehouse vigor detection and the storage of stubbles are difficult and the vigor detection precision is low in the current practical scenes such as seed management and agricultural production.
In order to achieve the above purpose, the invention provides a quantitative analysis method for the vigor of rice seeds, which comprises the following steps:
acquiring multispectral images of a plurality of groups of sample rice seeds, and converting the multispectral images into nCDA images according to the vitality index of each group of sample rice seeds;
carrying out regression analysis by using the vitality indexes of the rice seeds with different samples and the corresponding nCDA images, and establishing a relation model based on the vitality indexes and the color values of the nCDA images;
taking nCDA image pictures of rice seeds to be detected, placing the nCDA image pictures and a standard color card into an image acquisition room, acquiring color measurement images in the image acquisition room by using an image acquisition device, and determining nCDA image color values of the rice seeds to be detected based on the color measurement images;
and inputting the nCDA image color value into a relation model based on the vitality index and the nCDA image color value, and obtaining the vitality index of the rice seeds to be detected, which is output by the relation model.
Optionally, obtaining multispectral images of a plurality of groups of sample rice seeds, and converting the multispectral images into nCDA images according to the vitality index of each group of sample rice seeds, wherein the steps specifically comprise:
acquiring multispectral images of a plurality of groups of sample rice seeds; wherein each group of sample rice seeds comprises a plurality of rice seeds, and each group of sample rice seeds has different aging degrees;
placing a plurality of groups of sample rice seeds with different aging degrees into an incubator, and counting germination conditions of the sample rice seeds to generate vitality indexes of each group of sample rice seeds;
and converting the multispectral image corresponding to each group of sample rice seeds into an nCDA image according to the vitality index of each group of sample rice seeds.
Optionally, the step of converting the multispectral image corresponding to each group of sample rice seeds into an nCDA image according to the vitality index of each group of sample rice seeds specifically includes:
acquiring a first multispectral image corresponding to a first group of sample rice seeds with highest vitality indexes and a second multispectral image corresponding to a second group of sample rice seeds with lowest vitality indexes, and respectively endowing a first color value and a second color value to nCDA images corresponding to the first multispectral image and the second multispectral image;
extracting spectral features of the first multispectral image and the second multispectral image for normalization to be used as color discrimination standard features, obtaining multispectral images to be analyzed corresponding to a plurality of groups of sample rice seeds with other vitality indexes, extracting the spectral features, and performing normalization treatment to be used as color discrimination actual features;
based on the positions of a first color corresponding to the color discrimination standard feature of the first multispectral image and a second color corresponding to the color discrimination standard feature of the second multispectral image in a preset color map respectively, performing discrimination analysis on the target position of a target color corresponding to the color discrimination actual feature of the multispectral image to be analyzed in the preset color map;
and taking the target color corresponding to the target position of each multispectral image to be analyzed in the preset color map as the nCDA image color of the corresponding group of sample rice seeds, and generating the nCDA image of each group of sample rice seeds.
Optionally, performing regression analysis by using the vitality indexes of the rice seeds with different samples and corresponding nCDA images, and establishing a relationship model based on the vitality indexes and the color values of the nCDA images, which specifically comprises the following steps:
obtaining vitality indexes and corresponding nCDA images of rice seeds with different samples;
and extracting a color value L and a color value a of CIELAB values of the nCDA images of each group of sample rice seeds, carrying out regression analysis, and establishing a relationship model based on the vitality index and related to the color value L and the color value a.
Optionally, after the step of converting the multispectral image corresponding to each group of sample rice seeds into an nCDA image according to the vigor index of each group of sample rice seeds, the method further includes:
extracting spectral features of multispectral images corresponding to each group of sample rice seeds to form feature vectors, and extracting target positions of target colors corresponding to each group of sample rice seeds in a preset color map;
and respectively inputting the characteristic vector corresponding to each group of sample rice seeds and the target position of the target color in the preset color map as training data and training labels of training samples into a neural network model for training, and obtaining an nCDA image generation model after training is completed.
Optionally, the image acquisition device is configured with multispectral image acquisition equipment and an nCDA image generation controller, and the nCDA image generation controller stores an nCDA image generation model corresponding to the rice seed to be detected; taking nCDA image pictures of rice seeds to be detected, placing the nCDA image pictures and a standard color card into an image acquisition room, acquiring color measurement images in the image acquisition room by utilizing an image acquisition device, and determining nCDA image color values of the rice seeds to be detected based on the color measurement images, wherein the method specifically comprises the following steps:
driving multispectral image acquisition equipment in the image acquisition device to acquire a multispectral image to be detected of the rice seed to be detected, and driving an nCDA image generation controller in the image acquisition device to generate an nCDA image photo of the rice seed to be detected according to the multispectral image to be detected by using an nCDA image generation model;
placing the nCDA image photo and the standard color card into an image acquisition room, and acquiring a first color measurement image and a second color measurement image which contain the nCDA image photo and the standard color card and are positioned at two opposite positions in the image acquisition room;
according to the first RGB value of each color block of the standard color card and the CIEXYZ value of the color block in the first color measurement image and the second color measurement image, a color value conversion matrix is established, according to the second RGB value of the nCDA image in the first color measurement image and the second color measurement image and the color value conversion matrix, the CIEXYZ value of the nCDA image of the rice seed to be detected is determined, and the CIEXYZ value of the nCDA image is converted into the CIELAB value of the nCDA image.
Optionally, the step of inputting the color value of the nCDA image into a relationship model based on the vigor index and the color value of the nCDA image to obtain the vigor index of the rice seed to be measured output by the relationship model specifically includes:
extracting a color value L and a color value a in an nCDA image CIELAB value of the rice seed to be detected;
and inputting the color value L and the color value a into a relation model based on the vitality index and the nCDA image color value to obtain the vitality index of the rice seed to be detected.
In addition, in order to achieve the above purpose, the present invention also provides a quantitative analysis device for vigor of rice seeds, comprising:
the acquisition module is used for acquiring multispectral images of a plurality of groups of sample rice seeds, and converting the multispectral images into nCDA images according to the vitality index of each group of sample rice seeds;
the establishing module is used for carrying out regression analysis by utilizing the vitality indexes of the rice seeds with different samples and the corresponding nCDA images, and establishing a relation model based on the vitality indexes and the color values of the nCDA images;
the shooting module is used for shooting nCDA image photos of rice seeds to be detected, placing the nCDA image photos and a standard color card into an image acquisition room, acquiring color measurement images in the image acquisition room by using an image acquisition device, and determining nCDA image color values of the rice seeds to be detected based on the color measurement images;
and the output module is used for inputting the nCDA image color value into a relation model based on the vitality index and the nCDA image color value, and obtaining the vitality index of the rice seed to be detected, which is output by the relation model.
In addition, in order to achieve the above object, the present invention also provides a quantitative analysis apparatus for vigor of rice seeds, comprising: the quantitative analysis method for the vigor of the rice seeds comprises a memory, a processor and a quantitative analysis program for the vigor of the rice seeds, wherein the quantitative analysis program for the vigor of the rice seeds is stored in the memory and can run on the processor, and the quantitative analysis program for the vigor of the rice seeds is implemented by the processor.
In addition, in order to achieve the above object, the present invention also provides a storage medium, on which a quantitative analysis program for vigor of rice seeds is stored, which when executed by a processor, implements the steps of the quantitative analysis method for vigor of rice seeds described above.
The invention has the beneficial effects that: the invention provides a quantitative analysis method, a device, equipment and a storage medium for rice seed vitality, which are characterized in that a nCDA image generation model is generated by analyzing the conversion relation of a multispectral image of a sample rice seed to nCDA image conversion, and the nCDA image generation model is configured in an image acquisition device for warehousing detection, so that a warehousing detector can realize warehousing detection judgment of the rice seed according to the rice seed color in a nCDA image photo of the warehousing rice seed shot by the image acquisition device, and the rice seed vitality value is not required to be calculated, thereby improving the warehousing detection efficiency and the detection result identification; after that, the nCDA image photo and the rice seeds in the warehouse are circulated together, when the accurate calculation of the seed vitality value is needed for the rice seeds, the vitality index of the batch of rice seeds can be accurately calculated by detecting the color value of the rice seeds in the nCDA image photo and inputting the color value into a relation model of the vitality index and the nCDA image color value, and data support is provided for the quality fine classification of the rice seeds and the subsequent purchase of the rice seeds, so that the adaptability of the rice seed vitality detection to the needs of purchase in different periods in actual scenes such as seed management, agricultural production and the like is improved.
Drawings
FIG. 1 is a schematic diagram of a device structure of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flow chart of an embodiment of the quantitative analysis method for the vigor of rice seeds according to the present invention;
fig. 3 is a block diagram of a quantitative analysis device for vigor of rice seeds according to an embodiment of the invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic diagram of an apparatus structure of a hardware running environment according to an embodiment of the present invention.
As shown in fig. 1, the apparatus may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the arrangement of the apparatus shown in fig. 1 is not limiting and may include more or fewer components than shown, or certain components may be combined, or a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a rice seed vigor quantitative analysis program may be included in the memory 1005 as a computer storage medium.
In the terminal shown in fig. 1, the network interface 1004 is mainly used for connecting to a background server and performing data communication with the background server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be configured to call the quantitative analysis program for vigor of rice seeds stored in the memory 1005, and perform the following operations:
acquiring multispectral images of a plurality of groups of sample rice seeds, and converting the multispectral images into nCDA images according to the vitality index of each group of sample rice seeds;
carrying out regression analysis by using the vitality indexes of the rice seeds with different samples and the corresponding nCDA images, and establishing a relation model based on the vitality indexes and the color values of the nCDA images;
taking nCDA image pictures of rice seeds to be detected, placing the nCDA image pictures and a standard color card into an image acquisition room, acquiring color measurement images in the image acquisition room by using an image acquisition device, and determining nCDA image color values of the rice seeds to be detected based on the color measurement images;
and inputting the nCDA image color value into a relation model based on the vitality index and the nCDA image color value, and obtaining the vitality index of the rice seeds to be detected, which is output by the relation model.
The specific embodiment of the present invention applied to the apparatus is basically the same as the following embodiments of the quantitative analysis method for the vigor of rice seeds, and will not be described herein.
The embodiment of the invention provides a quantitative analysis method for the vigor of rice seeds, and referring to fig. 2, fig. 2 is a flow chart of an embodiment of the quantitative analysis method for the vigor of rice seeds.
In this embodiment, the quantitative analysis method for the vigor of the rice seeds comprises the following steps:
s100: acquiring multispectral images of a plurality of groups of sample rice seeds, and converting the multispectral images into nCDA images according to the vitality index of each group of sample rice seeds;
s200: carrying out regression analysis by using the vitality indexes of the rice seeds with different samples and the corresponding nCDA images, and establishing a relation model based on the vitality indexes and the color values of the nCDA images;
s300: taking nCDA image pictures of rice seeds to be detected, placing the nCDA image pictures and a standard color card into an image acquisition room, acquiring color measurement images in the image acquisition room by using an image acquisition device, and determining nCDA image color values of the rice seeds to be detected based on the color measurement images;
s400: and inputting the nCDA image color value into a relation model based on the vitality index and the nCDA image color value, and obtaining the vitality index of the rice seeds to be detected, which is output by the relation model.
It should be noted that, in the seed vitality detection scheme based on the multispectral image provided in the prior art, the problems of low recognition degree of detection speed and detection result of the in-warehouse vitality detection during the vitality detection of rice seeds in actual scenes such as seed management, agricultural production and the like, difficult delivery and diversion of the vitality detection result after in-warehouse, low storage difficulty of stubbles, low vitality detection precision and the like exist. In order to solve the above problems, in this embodiment, by analyzing the conversion relationship from the multispectral image of the sample rice seed to the nCDA image to generate an nCDA image generation model, the nCDA image generation model is configured in the image acquisition device for the in-house detection, so that the in-house detection personnel can realize in-house detection judgment of the rice seed according to the rice seed color in the nCDA image photograph of the in-house rice seed taken by the image acquisition device, without calculating the vitality value of the rice seed, and improving the in-house detection efficiency and the detection result identification; after that, the nCDA image photo and the rice seeds in the warehouse are circulated together, when the accurate calculation of the seed vitality value is needed for the rice seeds, the vitality index of the batch of rice seeds can be accurately calculated by detecting the color value of the rice seeds in the nCDA image photo and inputting the color value into a relation model of the vitality index and the nCDA image color value, and data support is provided for the quality fine classification of the rice seeds and the subsequent purchase of the rice seeds, so that the adaptability of the rice seed vitality detection to the needs of purchase in different periods in actual scenes such as seed management, agricultural production and the like is improved.
In a preferred embodiment, a multispectral image of a plurality of groups of sample rice seeds is obtained, and the multispectral image is converted into an nCDA image according to the vitality index of each group of sample rice seeds, which specifically comprises the following steps: acquiring multispectral images of a plurality of groups of sample rice seeds; wherein each group of sample rice seeds comprises a plurality of rice seeds, and each group of sample rice seeds has different aging degrees; placing a plurality of groups of sample rice seeds with different aging degrees into an incubator, and counting germination conditions of the sample rice seeds to generate vitality indexes of each group of sample rice seeds; and converting the multispectral image corresponding to each group of sample rice seeds into an nCDA image according to the vitality index of each group of sample rice seeds.
In this embodiment, when obtaining sample rice seeds with different aging degrees, the sample rice seeds may be grouped and placed into an aging device to perform aging treatment with different durations, so that several groups of sample rice seeds have sample rice seeds with different rice seed vigor indexes.
In a preferred embodiment, the step of converting the multispectral image corresponding to each group of sample rice seeds into an nCDA image according to the vigor index of each group of sample rice seeds specifically includes: acquiring a first multispectral image corresponding to a first group of sample rice seeds with highest vitality indexes and a second multispectral image corresponding to a second group of sample rice seeds with lowest vitality indexes, and respectively endowing a first color value and a second color value to nCDA images corresponding to the first multispectral image and the second multispectral image; extracting spectral features of the first multispectral image and the second multispectral image for normalization to be used as color discrimination standard features, obtaining multispectral images to be analyzed corresponding to a plurality of groups of sample rice seeds with other vitality indexes, extracting the spectral features, and performing normalization treatment to be used as color discrimination actual features; based on the positions of a first color corresponding to the color discrimination standard feature of the first multispectral image and a second color corresponding to the color discrimination standard feature of the second multispectral image in a preset color map respectively, performing discrimination analysis on the target position of a target color corresponding to the color discrimination actual feature of the multispectral image to be analyzed in the preset color map; and taking the target color corresponding to the target position of each multispectral image to be analyzed in the preset color map as the nCDA image color of the corresponding group of sample rice seeds, and generating the nCDA image of each group of sample rice seeds.
In this embodiment, the multispectral image corresponding to each group of sample rice seeds is converted into an nCDA image by adopting a special nCDA (normalized canonical discriminant analysis, normalized standard discriminant analysis) processing method, mainly by acquiring multispectral images of two extreme values of the vigor index, after corresponding color values are given to the nCDA images of the two extreme values, the color values of the nCDA images of other sample rice seeds between the two extreme values can be distinguished according to the differences of the spectral features in the multispectral images, for example, when linear distinction is adopted, the colors of the nCDA images of the two extreme values are at two end positions in the color map, and the color values of the nCDA images of other sample rice seeds can be obtained by determining the positions corresponding to the linear proportions on the connecting line between the two end points according to the linear proportions of the multispectral features.
In a preferred embodiment, regression analysis is performed by using the vigor index of the rice seeds with different samples and corresponding nCDA images, and a relation model step based on the vigor index and the color value of the nCDA images is established, which specifically includes: obtaining vitality indexes and corresponding nCDA images of rice seeds with different samples; and extracting a color value L and a color value a of CIELAB values of the nCDA images of each group of sample rice seeds, carrying out regression analysis, and establishing a relationship model based on the vitality index and related to the color value L and the color value a.
In this embodiment, after obtaining the vigor index and the corresponding nCDA image of the rice seed with different samples, regression analysis is performed by extracting the color value L and the color value a of the CIELAB value of the nCDA image, so as to obtain a relationship model based on the vigor index with respect to the color value L and the color value a. In the specific example of regression analysis, the analysis results obtained were as follows:
| Multiple R | 0.999185374 |
| R Square | 0.998371411 |
| Adjusted R Square | 0.995114234 |
table 1: regression effect parameters
Wherein, multiplex R, R Square and Adjusted R Square are 3 evaluation indexes of regression equation, 3 values are between 0 and 1, and the closer to 1, the better the effect.
| Coefficients | Standard error of | t Stat | P-value | |
| Intercept | 1.049608636 | 0.074677431 | 14.05523233 | 0.045217953 |
| L | -0.009678807 | 0.000847545 | -11.41981926 | 0.055605085 |
| a | -0.007616526 | 0.00033428 | -22.78483949 | 0.027922579 |
Table 2: regression analysis results
Here, intersett is a constant term, L is a coefficient of the color value L, and a is a coefficient of the color value a. Wherein, the P value of the constant term and a is less than 0.05, and the difference is obvious.
Thus, the expression of the relationship model based on the vitality index with respect to the color value L and the color value a in the specific embodiment is obtained as follows: vitality index = -0.009679L-0.00757a+1.0496.
In a preferred embodiment, after the step of converting the multispectral image corresponding to each set of sample rice seeds into an nCDA image according to the vigor index of each set of sample rice seeds, the method further comprises: extracting spectral features of multispectral images corresponding to each group of sample rice seeds to form feature vectors, and extracting target positions of target colors corresponding to each group of sample rice seeds in a preset color map; and respectively inputting the characteristic vector corresponding to each group of sample rice seeds and the target position of the target color in the preset color map as training data and training labels of training samples into a neural network model for training, and obtaining an nCDA image generation model after training is completed.
On the basis, the image acquisition device is provided with multispectral image acquisition equipment and an nCDA image generation controller, and the nCDA image generation controller stores an nCDA image generation model corresponding to the rice seeds to be detected; taking nCDA image pictures of rice seeds to be detected, placing the nCDA image pictures and a standard color card into an image acquisition room, acquiring color measurement images in the image acquisition room by utilizing an image acquisition device, and determining nCDA image color values of the rice seeds to be detected based on the color measurement images, wherein the method specifically comprises the following steps: driving multispectral image acquisition equipment in the image acquisition device to acquire a multispectral image to be detected of the rice seed to be detected, and driving an nCDA image generation controller in the image acquisition device to generate an nCDA image photo of the rice seed to be detected according to the multispectral image to be detected by using an nCDA image generation model; placing the nCDA image photo and the standard color card into an image acquisition room, and acquiring a first color measurement image and a second color measurement image which contain the nCDA image photo and the standard color card and are positioned at two opposite positions in the image acquisition room; according to the first RGB value of each color block of the standard color card and the CIEXYZ value of the color block in the first color measurement image and the second color measurement image, a color value conversion matrix is established, according to the second RGB value of the nCDA image in the first color measurement image and the second color measurement image and the color value conversion matrix, the CIEXYZ value of the nCDA image of the rice seed to be detected is determined, and the CIEXYZ value of the nCDA image is converted into the CIELAB value of the nCDA image.
The step of inputting the color value of the nCDA image into a relation model based on the vitality index and the color value of the nCDA image to obtain the vitality index of the rice seed to be detected, which is output by the relation model, specifically comprises the following steps: extracting a color value L and a color value a in an nCDA image CIELAB value of the rice seed to be detected; and inputting the color value L and the color value a into a relation model based on the vitality index and the nCDA image color value to obtain the vitality index of the rice seed to be detected.
In the embodiment, through analyzing the conversion relation of the multispectral image of the sample rice seeds to the nCDA image conversion, an nCDA image generation model is generated, and the nCDA image generation model is configured in an image acquisition device for warehousing detection, so that a warehousing detection personnel can realize warehousing detection judgment of the rice seeds according to the rice seed color in the nCDA image photo of the warehousing rice seeds shot by the image acquisition device, and the calculation of the vitality value of the rice seeds is not needed, so that the warehousing detection efficiency and the detection result discrimination are improved; after that, the nCDA image photo and the rice seeds in the warehouse are circulated together, when the accurate calculation of the seed vitality value is needed for the rice seeds, the vitality index of the batch of rice seeds can be accurately calculated by detecting the color value of the rice seeds in the nCDA image photo and inputting the color value into a relation model of the vitality index and the nCDA image color value, and data support is provided for the quality fine classification of the rice seeds and the subsequent purchase of the rice seeds, so that the adaptability of the rice seed vitality detection to the needs of purchase in different periods in actual scenes such as seed management, agricultural production and the like is improved.
The detection method for the color value of the rice seeds in the nCDA image photo adopts the following modes: placing the nCDA image photo and the standard color card into an image acquisition room, wherein a shooting light source is arranged in the image acquisition room, the whole sealing design is adopted, the external light source is prevented from entering the image acquisition room, the influence caused by environmental change in the rice seed color measurement process is reduced, and the image acquisition room comprises a first color measurement image and a second color measurement image which are of the nCDA image photo and the standard color card and are positioned at two opposite positions in the image acquisition room; taking the average value of the first RGB value of each color block in the first color measurement image and the first RGB value of each color block in the second color measurement image as the RGB value of each color block in the standard color card for removing environmental interference, establishing a color value conversion matrix according to the RGB value and the CIEXYZ value of the color block, determining the CIEXYZ value of the nCDA image of the rice seed to be measured according to the second RGB value of the nCDA image in the first color measurement image and the second color measurement image and the color value conversion matrix, and converting the CIEXYZ value of the nCDA image into the CIELAB value of the nCDA image; therefore, the high-precision detection of the rice seed color value in the nCDA image photo is realized, the problem of low detection precision caused by a human eye observation mode is avoided, and the vitality index of the rice seeds to be detected can be determined according to the rice seed color value detected with high precision, so that data support is provided for fine classification of the quality of the rice seeds and subsequent rice seed purchase.
According to the embodiment, the primary detection of the rice seeds in the warehouse and the accurate detection after the warehouse are separated, so that the problems that the detection speed and the detection result of the warehouse-in vitality detection are low in discrimination degree, the vitality detection result delivery and the storage of stubbles are difficult and the vitality detection precision is low in the existing detection of the vitality of the rice seeds in actual scenes such as seed management and agricultural production are solved, and the method has good scene adaptability.
In addition, in order to achieve the above purpose, the present invention also provides a quantitative analysis device for vigor of rice seeds, comprising:
referring to fig. 3, fig. 3 is a block diagram showing the structure of an embodiment of the quantitative analyzer for the vigor of rice seeds according to the present invention.
As shown in fig. 3, the quantitative analysis device for vigor of rice seeds according to the embodiment of the invention includes:
the acquisition module 10 is used for acquiring multispectral images of a plurality of groups of sample rice seeds, and converting the multispectral images into nCDA images according to the vitality index of each group of sample rice seeds;
the establishing module 20 is configured to perform regression analysis by using the vitality indexes of the rice seeds with different samples and the corresponding nCDA images, and establish a relationship model based on the vitality indexes and the color values of the nCDA images;
the shooting module 30 is configured to shoot an nCDA image photo of a rice seed to be detected, put the nCDA image photo and a standard color card into an image acquisition room, acquire a color measurement image in the image acquisition room by using an image acquisition device, and determine an nCDA image color value of the rice seed to be detected based on the color measurement image;
and the output module 40 is used for inputting the color value of the nCDA image into a relation model based on the vitality index and the color value of the nCDA image to obtain the vitality index of the rice seed to be tested, which is output by the relation model.
Other embodiments or specific implementation manners of the quantitative analysis device for vigor of rice seeds can refer to the above method embodiments, and are not repeated here.
In addition, the invention also provides quantitative analysis equipment for the vigor of the rice seeds, which comprises the following components: the quantitative analysis method for the vigor of the rice seeds comprises a memory, a processor and a quantitative analysis program for the vigor of the rice seeds, wherein the quantitative analysis program for the vigor of the rice seeds is stored in the memory and can run on the processor, and the quantitative analysis program for the vigor of the rice seeds is implemented by the processor.
The specific implementation manner of the quantitative analysis device for the activity of the rice seeds is basically the same as that of each embodiment of the quantitative analysis method for the activity of the rice seeds, and is not repeated here.
In addition, the invention also provides a readable storage medium, which comprises a computer readable storage medium, and the quantitative analysis program of the vigor of the rice seeds is stored on the computer readable storage medium. The readable storage medium may be a Memory 1005 in the terminal of fig. 1, or may be at least one of a ROM (Read-Only Memory)/RAM (Random Access Memory ), a magnetic disk, and an optical disk, and the readable storage medium includes a plurality of instructions for causing a quantitative analysis device for rice seed vigor having a processor to perform the quantitative analysis method for rice seed vigor according to the embodiments of the present invention.
The specific implementation manner of the readable storage medium is basically the same as the above embodiments of the quantitative analysis method for the vigor of rice seeds, and is not repeated here.
It is appreciated that in the description herein, reference to the terms "one embodiment," "another embodiment," "other embodiments," or "first through nth embodiments," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. The quantitative analysis method for the vigor of the rice seeds is characterized by comprising the following steps of:
acquiring multispectral images of a plurality of groups of sample rice seeds, and converting the multispectral images into nCDA images according to the vitality index of each group of sample rice seeds;
carrying out regression analysis by using the vitality indexes of the rice seeds with different samples and the corresponding nCDA images, and establishing a relation model based on the vitality indexes and the color values of the nCDA images;
taking nCDA image pictures of rice seeds to be detected, placing the nCDA image pictures and a standard color card into an image acquisition room, acquiring color measurement images in the image acquisition room by using an image acquisition device, and determining nCDA image color values of the rice seeds to be detected based on the color measurement images;
and inputting the nCDA image color value into a relation model based on the vitality index and the nCDA image color value, and obtaining the vitality index of the rice seeds to be detected, which is output by the relation model.
2. The quantitative analysis method for vigor of rice seeds according to claim 1, wherein the step of obtaining multispectral images of a plurality of groups of sample rice seeds and converting the multispectral images into nCDA images according to the vigor index of each group of sample rice seeds comprises the steps of:
acquiring multispectral images of a plurality of groups of sample rice seeds; wherein each group of sample rice seeds comprises a plurality of rice seeds, and each group of sample rice seeds has different aging degrees;
placing a plurality of groups of sample rice seeds with different aging degrees into an incubator, and counting germination conditions of the sample rice seeds to generate vitality indexes of each group of sample rice seeds;
and converting the multispectral image corresponding to each group of sample rice seeds into an nCDA image according to the vitality index of each group of sample rice seeds.
3. The quantitative analysis method for vigor of rice seeds according to claim 2, wherein the step of converting the multispectral image corresponding to each group of sample rice seeds into an nCDA image according to the vigor index of each group of sample rice seeds comprises the following steps:
acquiring a first multispectral image corresponding to a first group of sample rice seeds with highest vitality indexes and a second multispectral image corresponding to a second group of sample rice seeds with lowest vitality indexes, and respectively endowing a first color value and a second color value to nCDA images corresponding to the first multispectral image and the second multispectral image;
extracting spectral features of the first multispectral image and the second multispectral image for normalization to be used as color discrimination standard features, obtaining multispectral images to be analyzed corresponding to a plurality of groups of sample rice seeds with other vitality indexes, extracting the spectral features, and performing normalization treatment to be used as color discrimination actual features;
based on the positions of a first color corresponding to the color discrimination standard feature of the first multispectral image and a second color corresponding to the color discrimination standard feature of the second multispectral image in a preset color map respectively, performing discrimination analysis on the target position of a target color corresponding to the color discrimination actual feature of the multispectral image to be analyzed in the preset color map;
and taking the target color corresponding to the target position of each multispectral image to be analyzed in the preset color map as the nCDA image color of the corresponding group of sample rice seeds, and generating the nCDA image of each group of sample rice seeds.
4. The quantitative analysis method for vigor of rice seeds according to claim 3, wherein the step of establishing a relationship model based on the vigor index and the color value of the nCDA image by performing regression analysis using the vigor index of the rice seeds of different samples and the corresponding nCDA image specifically comprises:
obtaining vitality indexes and corresponding nCDA images of rice seeds with different samples;
and extracting a color value L and a color value a of CIELAB values of the nCDA images of each group of sample rice seeds, carrying out regression analysis, and establishing a relationship model based on the vitality index and related to the color value L and the color value a.
5. The quantitative analysis method for vigor of rice seeds according to claim 3, wherein after the step of converting the multispectral image corresponding to each group of sample rice seeds into an nCDA image according to the vigor index of each group of sample rice seeds, the method further comprises:
extracting spectral features of multispectral images corresponding to each group of sample rice seeds to form feature vectors, and extracting target positions of target colors corresponding to each group of sample rice seeds in a preset color map;
and respectively inputting the characteristic vector corresponding to each group of sample rice seeds and the target position of the target color in the preset color map as training data and training labels of training samples into a neural network model for training, and obtaining an nCDA image generation model after training is completed.
6. The quantitative analysis method for vigor of rice seeds according to claim 5, wherein the image acquisition device is provided with a multispectral image acquisition device and an nCDA image generation controller, and the nCDA image generation controller stores an nCDA image generation model corresponding to rice seeds to be detected; taking nCDA image pictures of rice seeds to be detected, placing the nCDA image pictures and a standard color card into an image acquisition room, acquiring color measurement images in the image acquisition room by utilizing an image acquisition device, and determining nCDA image color values of the rice seeds to be detected based on the color measurement images, wherein the method specifically comprises the following steps:
driving multispectral image acquisition equipment in the image acquisition device to acquire a multispectral image to be detected of the rice seed to be detected, and driving an nCDA image generation controller in the image acquisition device to generate an nCDA image photo of the rice seed to be detected according to the multispectral image to be detected by using an nCDA image generation model;
placing the nCDA image photo and the standard color card into an image acquisition room, and acquiring a first color measurement image and a second color measurement image which contain the nCDA image photo and the standard color card and are positioned at two opposite positions in the image acquisition room;
according to the first RGB value of each color block of the standard color card and the CIEXYZ value of the color block in the first color measurement image and the second color measurement image, a color value conversion matrix is established, according to the second RGB value of the nCDA image in the first color measurement image and the second color measurement image and the color value conversion matrix, the CIEXYZ value of the nCDA image of the rice seed to be detected is determined, and the CIEXYZ value of the nCDA image is converted into the CIELAB value of the nCDA image.
7. The quantitative analysis method for the vigor of rice seeds according to claim 6, wherein the step of inputting the color value of the nCDA image into a relation model based on the vigor index and the color value of the nCDA image to obtain the vigor index of the rice seeds to be measured outputted by the relation model comprises the following steps:
extracting a color value L and a color value a in an nCDA image CIELAB value of the rice seed to be detected;
and inputting the color value L and the color value a into a relation model based on the vitality index and the nCDA image color value to obtain the vitality index of the rice seed to be detected.
8. A quantitative analysis device for the vigor of rice seeds, which is characterized by comprising:
the acquisition module is used for acquiring multispectral images of a plurality of groups of sample rice seeds, and converting the multispectral images into nCDA images according to the vitality index of each group of sample rice seeds;
the establishing module is used for carrying out regression analysis by utilizing the vitality indexes of the rice seeds with different samples and the corresponding nCDA images, and establishing a relation model based on the vitality indexes and the color values of the nCDA images;
the shooting module is used for shooting nCDA image photos of rice seeds to be detected, placing the nCDA image photos and a standard color card into an image acquisition room, acquiring color measurement images in the image acquisition room by using an image acquisition device, and determining nCDA image color values of the rice seeds to be detected based on the color measurement images;
and the output module is used for inputting the nCDA image color value into a relation model based on the vitality index and the nCDA image color value, and obtaining the vitality index of the rice seed to be detected, which is output by the relation model.
9. The quantitative analysis equipment for the vigor of the rice seeds is characterized by comprising the following components: a memory, a processor and a quantitative analysis program of vigor of rice seeds stored on the memory and operable on the processor, which when executed by the processor, implements the steps of the quantitative analysis method of vigor of rice seeds as claimed in any one of claims 1 to 7.
10. A storage medium, wherein a quantitative analysis program for vigor of rice seeds is stored on the storage medium, and when the quantitative analysis program for vigor of rice seeds is executed by a processor, the quantitative analysis method for vigor of rice seeds according to any one of claims 1 to 7 is implemented.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410189114.9A CN117730655B (en) | 2024-02-20 | 2024-02-20 | Quantitative analysis method, device, equipment and storage medium for vigor of rice seeds |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410189114.9A CN117730655B (en) | 2024-02-20 | 2024-02-20 | Quantitative analysis method, device, equipment and storage medium for vigor of rice seeds |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117730655A true CN117730655A (en) | 2024-03-22 |
| CN117730655B CN117730655B (en) | 2024-05-14 |
Family
ID=90277784
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410189114.9A Active CN117730655B (en) | 2024-02-20 | 2024-02-20 | Quantitative analysis method, device, equipment and storage medium for vigor of rice seeds |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117730655B (en) |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102013021A (en) * | 2010-08-19 | 2011-04-13 | 汪建 | Tea tender shoot segmentation and identification method based on color and region growth |
| CN104126347A (en) * | 2014-07-07 | 2014-11-05 | 贵州省烟草科学研究院 | Method for detecting seed maturity and method for picking mature seeds |
| CN105606543A (en) * | 2016-03-29 | 2016-05-25 | 温州大学 | Portable banana maturity detector |
| CN107505046A (en) * | 2017-07-31 | 2017-12-22 | 征图新视（江苏）科技有限公司 | Multispectral color measurement method |
| US20180014452A1 (en) * | 2015-03-25 | 2018-01-18 | 360 Yield Center, Llc | Agronomic systems, methods and apparatuses |
| CN108549910A (en) * | 2018-04-17 | 2018-09-18 | 中国农业大学 | A kind of corn seed producing fruit ear image preliminary classification method based on convolutional neural networks |
| CN110610506A (en) * | 2019-09-17 | 2019-12-24 | 北京中环易达设施园艺科技有限公司 | Image processing technology-based agaricus blazei murill fruiting body growth parameter detection method |
| US20200117897A1 (en) * | 2018-10-15 | 2020-04-16 | Walt Froloff | Adaptive Artificial Intelligence Training Data Acquisition and Plant Monitoring System |
| FR3087541A1 (en) * | 2018-10-22 | 2020-04-24 | Commissariat A L'energie Atomique Et Aux Energies Alternatives | PROCESS FOR THE DISCRIMINATION OF A HEALTHY OR SICK PLANT BY COLORIMETRY. |
| CN111562010A (en) * | 2020-05-14 | 2020-08-21 | 北京大学 | Method and device for automatic image color calibration |
| CN113128405A (en) * | 2021-04-20 | 2021-07-16 | 北京航空航天大学 | Plant identification and model construction method combining semantic segmentation and point cloud processing |
| CN115643874A (en) * | 2022-11-02 | 2023-01-31 | 西南大学 | Agricultural automatic accurate control variable rate fertilization method |
| CN116806485A (en) * | 2023-08-25 | 2023-09-29 | 云南省农业科学院质量标准与检测技术研究所 | Quantitative detection and analysis method for rice seed viability based on CIELAB color space |
| CN116941380A (en) * | 2023-08-31 | 2023-10-27 | 云南省农业科学院质量标准与检测技术研究所 | Rice seed vitality detection method based on multispectral image analysis |
| CN117232651A (en) * | 2022-06-06 | 2023-12-15 | 云南省农业科学院质量标准与检测技术研究所 | Method for rapidly identifying moisture content and moisture distribution condition of corn seeds |
| CN117315490A (en) * | 2023-11-23 | 2023-12-29 | 成都中医药大学 | Method for detecting germination rate of seeds, model, storage medium and modeling method |
| CN117337691A (en) * | 2023-09-21 | 2024-01-05 | 仲恺农业工程学院 | Pitaya picking method and picking robot based on deep neural network |
| CN117546800A (en) * | 2023-11-17 | 2024-02-13 | 江苏省家禽科学研究所 | Internet of things intelligent detection and distinguishing device and method for black eggs and common eggs |
-
2024
- 2024-02-20 CN CN202410189114.9A patent/CN117730655B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102013021A (en) * | 2010-08-19 | 2011-04-13 | 汪建 | Tea tender shoot segmentation and identification method based on color and region growth |
| CN104126347A (en) * | 2014-07-07 | 2014-11-05 | 贵州省烟草科学研究院 | Method for detecting seed maturity and method for picking mature seeds |
| US20180014452A1 (en) * | 2015-03-25 | 2018-01-18 | 360 Yield Center, Llc | Agronomic systems, methods and apparatuses |
| CN105606543A (en) * | 2016-03-29 | 2016-05-25 | 温州大学 | Portable banana maturity detector |
| CN107505046A (en) * | 2017-07-31 | 2017-12-22 | 征图新视（江苏）科技有限公司 | Multispectral color measurement method |
| CN108549910A (en) * | 2018-04-17 | 2018-09-18 | 中国农业大学 | A kind of corn seed producing fruit ear image preliminary classification method based on convolutional neural networks |
| US20200117897A1 (en) * | 2018-10-15 | 2020-04-16 | Walt Froloff | Adaptive Artificial Intelligence Training Data Acquisition and Plant Monitoring System |
| FR3087541A1 (en) * | 2018-10-22 | 2020-04-24 | Commissariat A L'energie Atomique Et Aux Energies Alternatives | PROCESS FOR THE DISCRIMINATION OF A HEALTHY OR SICK PLANT BY COLORIMETRY. |
| CN110610506A (en) * | 2019-09-17 | 2019-12-24 | 北京中环易达设施园艺科技有限公司 | Image processing technology-based agaricus blazei murill fruiting body growth parameter detection method |
| CN111562010A (en) * | 2020-05-14 | 2020-08-21 | 北京大学 | Method and device for automatic image color calibration |
| CN113128405A (en) * | 2021-04-20 | 2021-07-16 | 北京航空航天大学 | Plant identification and model construction method combining semantic segmentation and point cloud processing |
| CN117232651A (en) * | 2022-06-06 | 2023-12-15 | 云南省农业科学院质量标准与检测技术研究所 | Method for rapidly identifying moisture content and moisture distribution condition of corn seeds |
| CN115643874A (en) * | 2022-11-02 | 2023-01-31 | 西南大学 | Agricultural automatic accurate control variable rate fertilization method |
| CN116806485A (en) * | 2023-08-25 | 2023-09-29 | 云南省农业科学院质量标准与检测技术研究所 | Quantitative detection and analysis method for rice seed viability based on CIELAB color space |
| CN116941380A (en) * | 2023-08-31 | 2023-10-27 | 云南省农业科学院质量标准与检测技术研究所 | Rice seed vitality detection method based on multispectral image analysis |
| CN117337691A (en) * | 2023-09-21 | 2024-01-05 | 仲恺农业工程学院 | Pitaya picking method and picking robot based on deep neural network |
| CN117546800A (en) * | 2023-11-17 | 2024-02-13 | 江苏省家禽科学研究所 | Internet of things intelligent detection and distinguishing device and method for black eggs and common eggs |
| CN117315490A (en) * | 2023-11-23 | 2023-12-29 | 成都中医药大学 | Method for detecting germination rate of seeds, model, storage medium and modeling method |
Non-Patent Citations (13)
| Title |
|---|
| QIAO, JX等: "Vigour testing for the rice seed with computer vision-based techniques", FRONTIERS IN PLANT SCIENCE, vol. 14, 18 September 2023 (2023-09-18), pages 1 - 10 * |
| XUEMENG WANG等: "Non-Destructive Identification of Naturally Aged Alfalfa Seeds via Multispectral Imaging Analysis", SENSORS, vol. 21, no. 17, 28 August 2021 (2021-08-28), pages 1 - 13 * |
| 何欣等: "基于卷积神经网络的牧草种子图像识别", 草业科学, vol. 39, no. 11, 15 November 2022 (2022-11-15), pages 2338 - 2349 * |
| 倪浩然等: "基于多光谱成像技术鉴别不同紫花苜蓿品种的种子", 草地学报, vol. 31, no. 10, 4 August 2023 (2023-08-04), pages 2985 - 2991 * |
| 孙俊等: "采用高光谱图像深度特征检测水稻种子活力等级", 农业工程学报, vol. 37, no. 14, 23 July 2021 (2021-07-23), pages 171 - 178 * |
| 岳佳铭等: "多光谱成像技术在种子质量检测研究中的应用", 种子, vol. 10, no. 10, 25 October 2021 (2021-10-25), pages 129 - 135 * |
| 张鹏等: "基于高光谱3D成像技术的不同成熟度玉米种子表型特征分析研究", 江西农业学报, vol. 34, no. 3, 15 March 2022 (2022-03-15), pages 22 - 27 * |
| 李亚萍: "视觉检测中颜色测量模型以及色卡设计研究", 中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑, no. 1, 15 January 2020 (2020-01-15), pages 024 - 848 * |
| 李兴旺等: "基于多光谱成像的种子外观与纯度检测方法研究", 中国优秀硕士学位论文全文数据库 农业科技辑, no. 5, 15 May 2022 (2022-05-15), pages 045 - 4 * |
| 李振华等: "基于CIELAB颜色空间判别烤烟蒴果发育与种子活力变化", 中国烟草科学, vol. 36, no. 4, 15 August 2015 (2015-08-15), pages 24 - 28 * |
| 李振等: "基于机器视觉技术的蔬菜种子质量检测方法研究及系统设计", 中国优秀硕士学位论文全文数据库 信息科技辑, no. 10, 15 October 2016 (2016-10-15), pages 138 - 448 * |
| 王雪萌等: "基于多光谱成像技术快速无损检测紫花苜蓿人工老化种子", 草业学报, vol. 31, no. 7, 16 May 2022 (2022-05-16), pages 197 - 208 * |
| 黄晟: "基于光谱及图像技术的农作物种子质量检测方法研究", 中国优秀硕士学位论文全文数据库 农业科技辑, no. 6, 15 June 2022 (2022-06-15), pages 045 - 2 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117730655B (en) | 2024-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103955938B (en) | A kind of wheat growth method for diagnosing status based on mobile Internet pattern and leaf color analysis | |
| EP1428016B1 (en) | Method of quantitative video-microscopy and associated system and computer software program product | |
| CN111242961B (en) | Automatic film reading method and system for PD-L1 antibody staining section | |
| US6819787B2 (en) | Robust stain detection and quantification for histological specimens based on a physical model for stain absorption | |
| CN106991679A (en) | One kind quantifies recognition methods based on cloud platform urine test paper physical signs | |
| US20230360735A1 (en) | Phenotype measurement systems and methods | |
| CN105181912A (en) | Method for detection of freshness during rice storage | |
| CN113109240B (en) | Method and system for determining imperfect grains of grains implemented by computer | |
| CN105466921A (en) | Simultaneous detection method of many samples | |
| CN110926609A (en) | Spectrum reconstruction method based on sample feature matching | |
| KR102095539B1 (en) | Method for measuring growth amount by image analyzing ginseng | |
| CN109827957A (en) | A kind of rice leaf SPAD value estimating and measuring method based on computer vision and system | |
| CN110044485B (en) | Image type fabric color measuring method | |
| CN115393645A (en) | Automatic soil classification and naming method and system, storage medium and intelligent terminal | |
| CN117730655B (en) | Quantitative analysis method, device, equipment and storage medium for vigor of rice seeds | |
| CN113570538B (en) | Blade RGB image bias distribution parameter information acquisition and analysis method | |
| CN106778536B (en) | Real-time hyperspectral microimage cell classification method based on FPGA | |
| CN109030321B (en) | Data processing method for flow cytometer | |
| Chen et al. | Preliminary research on total nitrogen content prediction of sandalwood using the error-in-variable models based on digital image processing | |
| CN115147659A (en) | Image analysis method and system for plant fruit external surface DUS test characters | |
| Kibria et al. | Smartphone-based point-of-care urinalysis assessment | |
| CN112651305A (en) | Method for identifying microorganism species | |
| CN113177591A (en) | pH detection method | |
| CN109545375A (en) | A kind of multifunction test platform for visiting cell marrow profession | |
| CN117808900B (en) | Method and device for classifying color development intensity of maize anthocyanin |
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 |