CN116523910B - Intelligent walnut maturity detection method based on image data - Google Patents
Intelligent walnut maturity detection method based on image data Download PDFInfo
- Publication number
- CN116523910B CN116523910B CN202310796581.3A CN202310796581A CN116523910B CN 116523910 B CN116523910 B CN 116523910B CN 202310796581 A CN202310796581 A CN 202310796581A CN 116523910 B CN116523910 B CN 116523910B
- Authority
- CN
- China
- Prior art keywords
- maturity
- walnut
- saturation
- pixel point
- image
- 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
- 235000020234 walnut Nutrition 0.000 title claims abstract description 132
- 235000009496 Juglans regia Nutrition 0.000 title claims abstract description 130
- 238000001514 detection method Methods 0.000 title claims abstract description 23
- 240000007049 Juglans regia Species 0.000 title 1
- 235000013399 edible fruits Nutrition 0.000 claims abstract description 148
- 241000758789 Juglans Species 0.000 claims abstract description 129
- 230000035800 maturation Effects 0.000 claims abstract description 36
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 27
- 238000009826 distribution Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 abstract 1
- 230000005070 ripening Effects 0.000 description 6
- 239000003086 colorant Substances 0.000 description 4
- 241000132456 Haplocarpha Species 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 241000758791 Juglandaceae Species 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004345 fruit ripening Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/68—Food, e.g. fruit or vegetables
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30128—Food products
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention relates to the field of image data processing, in particular to an intelligent detection method for walnut maturity based on image data, which comprises the following steps: collecting an image and preprocessing to obtain a walnut fruit image; obtaining a histogram of S component saturation according to the walnut fruit image; obtaining the maturation possibility of any pixel point according to the histogram of the S component saturation of the walnut fruit image; obtaining the maturation rate of any pixel point according to the maturation possibility of any pixel point and the number and the area of connected domains formed by the pixel points with the same maturation possibility; obtaining the maturity of the walnut fruit image according to the maturity possibility of any one pixel point and the maturity rate of any one pixel point; and obtaining a detection result of the ripeness of the walnut fruits according to the ripeness degree of the walnut fruit image and a preset threshold value. According to the invention, the current image data is analyzed and processed in an image data processing mode to obtain the optimal category number, so that the abnormal region detection is more accurate.
Description
Technical Field
The invention relates to the technical field of image data processing, in particular to an intelligent walnut maturity detection method based on image data.
Background
After the batch walnuts are ripe and picked, few individual immature walnut fruits exist, because the colors of the walnut fruits with different maturity are very similar, the maturity of the walnut fruits cannot be detected by the existing intelligent recognition technology, and the production quality is reduced.
The method solves the problem that few individual immature walnut fruits exist after the walnut is ripe and picked in batches, the image is converted into the HSV color space from the RGB image, so that the component histograms of the three components H, S, V obtained from the HSV color space with different maturity are analyzed, and the S component is obvious in expression difference between the walnut ripe and the immature walnut, so that the walnut ripe of the image data can be obtained by obtaining the S component histogram through the image.
Disclosure of Invention
The invention provides an intelligent detection method for walnut maturity based on image data, which aims to solve the existing problems.
The intelligent detection method of the walnut maturity based on the image data adopts the following technical scheme:
the embodiment of the invention provides an intelligent detection method for walnut maturity based on image data, which comprises the following steps:
collecting original image data and preprocessing to obtain a walnut fruit image;
obtaining a histogram of S component saturation of the HSV color space according to the walnut fruit image; obtaining the saturation range length of the walnut fruit image and the kurtosis of the fitted Gaussian function according to the histogram of the S component saturation of the HSV color space;
obtaining the maturation possibility of any one pixel according to the kurtosis of the Gaussian function, the saturation range length of the walnut fruit image and the difference between the saturation corresponding to any one pixel and the saturation mean value of all pixels;
obtaining the maturation rate of any pixel point according to the maturation possibility of any pixel point, the number of connected domains formed by the pixel points with the same maturation possibility, the sum of the areas of the connected domains formed by the pixel points with the same maturation possibility and the total area of the walnut fruit image;
obtaining the maturity of the walnut fruit image according to the maturity possibility of any one pixel point and the maturity rate of any one pixel point;
and obtaining a detection result of the ripeness of the walnut fruits according to the ripeness degree of the walnut fruit image and a preset threshold value.
Further, the specific acquisition method of the histogram of the saturation of the S component of the HSV color space comprises the following steps:
presetting a plurality of saturation levels, constructing a rectangular coordinate system by taking the saturation level as a horizontal axis and the number of pixels corresponding to the saturation level as a vertical axis, and obtaining a histogram of S component saturation of the HSV color space according to the distribution of the pixels of the walnut fruit image in the constructed rectangular coordinate system.
Further, the specific method for obtaining the maturation possibility of any pixel point is as follows:
the maturation probability formula of any one pixel point is as follows:
wherein E represents the kurtosis of the Gaussian function fitted by the S component histogram, F represents the ratio between the saturation range length in the S component histogram and the total saturation range length of the S component histogram,representing the absolute value of the difference between the saturation level corresponding to the ith pixel point and the average of the saturation levels of all pixel points, H representing the total length of the S component histogram saturation range,/->Expressing the maturation possibility corresponding to the ith pixel point in the walnut fruit image data; the saturation range length is the difference between the lowest saturation level and the highest saturation level in the walnut fruit image data multiplied by 1%; the total length of the saturation range is the difference between the saturation level maximum and the saturation level minimum multiplied by 1%.
Further, the specific method for obtaining the maturation rate of any one pixel point comprises the following steps:
the formula of the maturation rate of any one pixel point is as follows:
in the method, in the process of the invention,expressing the maturation possibility corresponding to the ith pixel point in the walnut fruit image; />Expressing the maturity corresponding to the ith pixel point in the walnut fruit image; s represents the total area of the walnut fruit image;
acquiring the maturity probability of all pixel points, and counting that the maturity probability is equal toThe number of connected domains formed by Q is marked as +.>The sum of the areas of the connected domains formed by all the pixels in Q is denoted as +.>。
Further, the specific method for acquiring the maturity of the walnut fruit image comprises the following steps:
the maturity formula of the walnut fruit image is as follows:
in the method, in the process of the invention,indicating the maturation possibility corresponding to the ith pixel point in the walnut fruit image,/for>Representing the corresponding point of the ith pixel in the walnut fruit imageN represents the total number of pixels in the walnut fruit image, and Z represents the overall maturity of the walnut fruit image.
Further, the specific acquisition method of the detection result of the ripeness of the walnut fruits comprises the following steps:
and (3) presetting a threshold value, and comparing the maturity of the obtained walnut fruit image with the preset threshold value to judge that the walnut fruit is mature when the maturity of the walnut fruit image is greater than the preset threshold value.
The technical scheme of the invention has the beneficial effects that: the advantages over the prior art are: the problem of have few individual immature walnut fruits after the ripe picking of batch walnut is solved, because the ripe degree of the walnut fruit of different ripe degrees colour is very similar, and current intelligent identification technology can't detect the ripe degree of walnut fruit, leads to production quality reduction is solved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of steps of the intelligent walnut maturity detection method based on image data.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects of the intelligent detection method for walnut maturity based on image data according to the invention with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The specific scheme of the intelligent walnut maturity detection method based on the image data provided by the invention is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of steps of a method for intelligently detecting maturity of walnut based on image data according to an embodiment of the present invention is shown, the method includes the following steps:
step S001: and acquiring original image data and preprocessing to obtain walnut fruit image data.
The picked walnuts are placed on a conveyor belt, a camera is arranged above the conveyor belt to collect images, and the collected images are recorded as original images. Because the original image directly collected by the camera is provided with soil, branches and leaves, the detection of the maturity of the walnut is interfered, the walnut fruits in the original image are firstly segmented by adopting a neural network semantic segmentation algorithm, and the walnut fruit image data are obtained.
So far, the image data acquisition of the walnut fruits is completed.
Step S002: acquiring an S component histogram in the HSV space according to the image characteristics, acquiring the maturity probability and the walnut maturity rate of the walnut according to the S component histogram, and acquiring the overall maturity of the walnut fruit image data according to the maturity probability and the walnut maturity rate of the walnut.
Note that, since the colors of the walnut fruits with different maturity are extremely close, R, G, B components in the RGB image of the walnut fruits show high correlation. The walnut fruit image has no obvious distribution rule in the three components, so the RGB space is not suitable for the subsequent processing of the walnut fruit image. Therefore, the walnut fruit image is converted from the RGB image to the HSV color space, and then a component histogram of H, S, V three components is obtained according to the HSV color space corresponding to the walnut fruit.
Analysis of component histograms of H, S, V components obtained from HSV color spaces with different maturity shows that the color of the walnut fruit is green in different maturity periods, and the H component histogram in the HSV color space image of the walnut fruit is not obvious in the differences of the H component histograms in the HSV color space images of the walnut fruit in the three components of the HSV color space because the H component in the HSV color space represents the hue.
As the fruit maturity is improved, the green color of the fruit is deeper and deeper, so that the change in the fruit can be obviously seen through the S component histogram in the HSV color space image, and as the fruit maturity is improved, the average value of the data set in the S component histogram is gradually reduced, so that the maturity possibility can be obtained through analyzing the S component histogram and the data characteristics of the S component histogram.
It should be further noted that, because the fruits may have colors with different degrees of shades on one fruit through different environments, such as illumination, positions of the fruits on the tree, etc., the ripening rate is obtained through the data of the ripening possibility and the distribution of the corresponding pixels in the image of the walnut fruits.
And obtaining the maturity corresponding to each pixel point according to the maturity probability and the maturity rate corresponding to each pixel point, and averaging the sum of the maturity of each pixel point to obtain the maturity of the walnut fruits, wherein the higher the maturity is, the higher the maturity is.
Specifically, the walnut fruit image is converted from the RGB color space to the HSV color space, and H, S, V three components are acquired respectively, wherein the S component represents the saturation of each pixel point on the walnut fruit image, and a component histogram of the S component is obtained and recorded as an S component histogram.
It should be noted that, as the fruit maturity increases, the green color of the fruit becomes deeper and deeper, so that the change in the S component histogram in the HSV color space image can be obviously seen, as the fruit maturity increases, the mean value of the dataset in the S component histogram gradually decreases, so that the maturity possibility can be obtained by analyzing the S component histogram and by the data characteristics of the S component histogram.
It should be further noted that, the value range of the saturation of the pixel point in the S component is [0,1], and the saturation is divided into 100 levels at equal intervals, namely, the saturation level is 1-100; the abscissa of the S component histogram represents the saturation level, and the ordinate represents the number of pixels corresponding to a certain saturation level.
The length of the saturation range refers to the difference between the lowest saturation level and the highest saturation level in the walnut fruit image data multiplied by 1%; the total length of the saturation range is the difference between the saturation minimum level 1 and the saturation maximum level 100 multiplied by 1%.
Because the fruits are subjected to different environments, such as illumination, positions of the fruits on a tree and the like, colors with different degrees of depth can exist on one fruit, and the ripening rate is obtained through the data of the ripening possibility and the distribution condition of corresponding pixel points in the walnut fruit image.
It should be noted that, because the fruit is subjected to different environments, such as illumination, the position of the fruit on the tree, etc., there may be the possibility that different portions of the fruit may have different maturity. And (3) analyzing the S component histogram, wherein the average value of the data set in the S component histogram gradually decreases along with the increase of the fruit maturity. The more concentrated the data, the more uniform the maturity of the fruit, and the more dispersed the data, the more non-uniform the maturity of each part of the fruit. Therefore, the S histogram data are fitted into a Gaussian function, the uniformity of the fruit maturity is obtained through the kurtosis of the Gaussian function and the domain occupation ratio of the histogram data, the difference between the maturity corresponding to any pixel point and the overall maturity is obtained according to the difference between the saturation of the pixel point and the saturation mean value of all the pixel points, so that the maturity probability corresponding to each pixel point is obtained, and the higher the maturity probability is, the more mature fruits are indicated.
Specifically, the maturation probability formula of any one pixel point in the image can be expressed as:
wherein E represents the kurtosis of the Gaussian function fitted by the S component histogram, and F represents the saturation range of the S component histogramThe ratio between the length and the total length of the S-component histogram saturation range,representing the absolute value of the difference between the saturation level corresponding to the ith pixel point and the average of the saturation levels of all pixel points, H representing the total length of the saturation range of the S component histogram,/>And expressing the maturation possibility corresponding to the ith pixel point in the walnut fruit image data.
It should be noted that, the saturation range length refers to the difference between the lowest saturation level and the highest saturation level in the walnut fruit image data multiplied by 1%; the total length of the saturation range is the difference between the saturation maximum level 100 and the saturation minimum level 1 multiplied by 1%.
Wherein, because E can represent the aggregation degree of the data, when the value of E is larger, the whole ripeness degree of the fruits is unified; when the larger the value of F, the more scattered the data, the more immature parts of the fruit may be present;the uniformity of the maturity of the fruits is shown, and the higher the uniformity is, the more uniform the maturity of each part of one fruit is shown;the difference between the ripening rate of the pixel and the whole ripening rate is shown, and the larger the difference is, the larger the difference is.
In the above analysis, the S component histogram data is mainly analyzed, but there may be a very small difference between the histogram analysis and the actual image, so that the judgment of the fruit maturity is further refined by analyzing the distribution of each pixel point of the fruit image in the image. The more uniform and better the fruit maturity, the fewer and better the connected domains of the pixels with the same maturity in the fruit image, and the larger the pixel point occupation ratio with high maturity rate, the more mature the fruit, the unified degree of the fruit maturity is obtained through the number of the connected domains connected by the pixels with the same maturity probability, the degree of influence of the corresponding maturity probability on the fruit is obtained according to the occupation ratio of the connected domain area formed by the pixels with the same maturity probability, the higher the maturity probability of the pixels and the larger the pixel occupation ratio of the higher the maturity probability of the pixels are, so that the corresponding maturity rate is obtained, and the higher the maturity rate is, which indicates that the fruit is more mature.
Specifically, the formula of the maturation rate of any one pixel point in the image can be expressed as:
in the method, in the process of the invention,expressing the maturation possibility corresponding to the ith pixel point in the walnut fruit image; />Expressing the maturity corresponding to the ith pixel point in the walnut fruit image; acquiring the maturity probability of all pixel points, and counting that the maturity probability is equal toThe number of connected domains formed by these pixels is +.>The sum of the areas of the connected domains formed by these pixels is denoted as +.>The method comprises the steps of carrying out a first treatment on the surface of the S represents the total area of the walnut fruit image.
Wherein, when the higher the ripeness probability, the ripeness of the fruit is indicated; when (when)The smaller the number of (a) indicates that the more uniform the fruit maturity, conversely,/>the larger the fruit ripening rate is, the more uniform the fruit ripening rate is; />Indicates that the maturation possibility is->The sum of the areas of the connected domains formed by the pixel points accounts for the ratio of the whole area of the walnut fruit image, the larger the ratio is, the more uniform the fruit maturity is, and the higher the influence degree of the fruit on the corresponding maturity possibility is; when maturation rate->The higher the fruit, the more ripe the fruit.
It should be noted that, according to the corresponding maturation probability of each pixel pointAnd maturation Rate->Obtaining the corresponding maturity of each pixel point, wherein the maturity possibility is->Higher, indicating that the fruit is ripe, the ripe rate +.>The higher the fruit, the more ripe the fruit. And then average the sum of the maturity of each pixel point to obtain the maturity Z of the walnut fruits, wherein the higher the maturity Z is, the higher the maturity of the walnut fruits is.
Specifically, the overall maturity of the walnut fruit image can be expressed as:
in the method, in the process of the invention,indicating the maturation possibility corresponding to the ith pixel point in the walnut fruit image,/for>The maturity corresponding to the ith pixel point in the walnut fruit image is represented, n represents the total number of pixel points in the walnut fruit image, and Z represents the overall maturity of the walnut fruit image.
Wherein, the liquid crystal display device comprises a liquid crystal display device,representing the maturity corresponding to the ith pixel point in the walnut fruit image; when the possibility of maturationThe higher the fruit, the more ripe the fruit; when maturation rate->The higher the fruit, the more ripe the fruit; the greater the maturity Z, the higher the maturity of the walnut fruit.
Step S003: and obtaining a final detection result according to the overall maturity of the walnut fruit image data and a preset threshold value.
The maturity of the walnut fruit image is obtained by the steps, and a threshold value W is set, wherein the method comprises the following stepsFor the sake of example, the present embodiment is not particularly limited, and W may be determined according to the specific implementation. The maturity of the walnut fruit image is compared with a threshold value W, and when the maturity of the walnut fruit image is larger than the threshold value W, the walnut fruit is considered to be a mature fruit, otherwise, when the maturity of the walnut fruit image is smaller than the threshold value W, the walnut fruit is considered to be immature, and the walnut fruit is required to be selected out by using a sorting device, wherein the sorting device is described by taking a mechanical arm as an example in the embodiment, the sorting device is not particularly limited in the embodiment, and the sorting device can be determined according to specific conditions.
This embodiment is completed.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (5)
1. The intelligent walnut maturity detection method based on the image data is characterized by comprising the following steps of:
collecting original image data and preprocessing to obtain a walnut fruit image;
obtaining a histogram of S component saturation of the HSV color space according to the walnut fruit image; obtaining the saturation range length of the walnut fruit image and the kurtosis of the fitted Gaussian function according to the histogram of the S component saturation of the HSV color space;
obtaining the maturation possibility of any one pixel according to the kurtosis of the Gaussian function, the saturation range length of the walnut fruit image and the difference between the saturation corresponding to any one pixel and the saturation mean value of all pixels;
obtaining the maturation rate of any pixel point according to the maturation possibility of any pixel point, the number of connected domains formed by the pixel points with the same maturation possibility, the sum of the areas of the connected domains formed by the pixel points with the same maturation possibility and the total area of the walnut fruit image;
obtaining the maturity of the walnut fruit image according to the maturity possibility of any one pixel point and the maturity rate of any one pixel point;
obtaining a detection result of the ripeness of the walnut fruits according to the ripeness degree of the walnut fruit image and a preset threshold value;
the specific acquisition method of the maturity of the walnut fruit image comprises the following steps:
the maturity formula of the walnut fruit image is as follows:
in the method, in the process of the invention,indicating the maturation possibility corresponding to the ith pixel point in the walnut fruit image,/for>The maturity corresponding to the ith pixel point in the walnut fruit image is represented, n represents the total number of pixel points in the walnut fruit image, and Z represents the overall maturity of the walnut fruit image.
2. The intelligent detection method of walnut maturity based on image data according to claim 1, wherein the specific acquisition method of the histogram of the S component saturation of HSV color space is as follows:
presetting a plurality of saturation levels, constructing a rectangular coordinate system by taking the saturation level as a horizontal axis and the number of pixels corresponding to the saturation level as a vertical axis, and obtaining a histogram of S component saturation of the HSV color space according to the distribution of the pixels of the walnut fruit image in the constructed rectangular coordinate system.
3. The intelligent detection method for walnut maturity based on image data according to claim 1, wherein the specific acquisition method for the maturity probability of any one pixel point is as follows:
the maturation probability formula of any one pixel point is as follows:
wherein E represents the kurtosis of the Gaussian function fitted by the S component histogram, F represents the ratio between the saturation range length in the S component histogram and the total saturation range length of the S component histogram,representing absolute value of difference between saturation level corresponding to ith pixel point and average value of saturation levels of all pixel points, and H represents S fractionTotal length of saturation range of the quantity histogram, +.>Expressing the maturation possibility corresponding to the ith pixel point in the walnut fruit image data; the saturation range length is the difference between the lowest saturation level and the highest saturation level in the walnut fruit image data multiplied by 1%; the total length of the saturation range is the difference between the saturation level maximum and the saturation level minimum multiplied by 1%.
4. The intelligent detection method for walnut maturity based on image data according to claim 1, wherein the specific acquisition method for the maturity of any one pixel point is as follows:
the formula of the maturation rate of any one pixel point is as follows:
in the method, in the process of the invention,expressing the maturation possibility corresponding to the ith pixel point in the walnut fruit image; />Expressing the maturity corresponding to the ith pixel point in the walnut fruit image; s represents the total area of the walnut fruit image;
acquiring the maturity probability of all pixel points, and counting that the maturity probability is equal toThe number of connected domains formed by Q is marked as +.>The sum of the areas of the connected domains formed by all the pixels in Q is denoted as +.>。
5. The intelligent detection method of the walnut maturity based on the image data according to claim 1, wherein the specific acquisition method of the detection result of the walnut fruit maturity is as follows:
and (3) presetting a threshold value, and comparing the maturity of the obtained walnut fruit image with the preset threshold value to judge that the walnut fruit is mature when the maturity of the walnut fruit image is greater than the preset threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310796581.3A CN116523910B (en) | 2023-07-03 | 2023-07-03 | Intelligent walnut maturity detection method based on image data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310796581.3A CN116523910B (en) | 2023-07-03 | 2023-07-03 | Intelligent walnut maturity detection method based on image data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116523910A CN116523910A (en) | 2023-08-01 |
| CN116523910B true CN116523910B (en) | 2023-09-08 |
Family
ID=87401479
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310796581.3A Active CN116523910B (en) | 2023-07-03 | 2023-07-03 | Intelligent walnut maturity detection method based on image data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116523910B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111160250A (en) * | 2019-12-30 | 2020-05-15 | 安徽易刚信息技术有限公司 | Blueberry growing period detection method and device based on artificial neural network |
| KR20210087729A (en) * | 2020-01-03 | 2021-07-13 | 재단법인대구경북과학기술원 | Method and Apparatus for Predicting of Brix and Acidity of Strawberries Using Image Data |
| CN115223164A (en) * | 2022-08-29 | 2022-10-21 | 广西壮族自治区农业科学院 | Melon maturity detection method and system based on artificial intelligence |
| CN115994921A (en) * | 2022-12-09 | 2023-04-21 | 大连大学 | Mature cherry fruit image segmentation method integrating HSV model and improving Otsu algorithm |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10304179B2 (en) * | 2016-07-05 | 2019-05-28 | Sharp Kabushiki Kaisha | Maturity determination device and maturity determination method |
| CN106210446B (en) * | 2016-07-18 | 2019-08-30 | 北京小米移动软件有限公司 | Saturation degree Enhancement Method and device |
| CN114169618B (en) * | 2021-12-11 | 2022-08-09 | 广东工业大学 | Kiwi fruit maturity nondestructive identification prediction method based on machine vision learning |
-
2023
- 2023-07-03 CN CN202310796581.3A patent/CN116523910B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111160250A (en) * | 2019-12-30 | 2020-05-15 | 安徽易刚信息技术有限公司 | Blueberry growing period detection method and device based on artificial neural network |
| KR20210087729A (en) * | 2020-01-03 | 2021-07-13 | 재단법인대구경북과학기술원 | Method and Apparatus for Predicting of Brix and Acidity of Strawberries Using Image Data |
| CN115223164A (en) * | 2022-08-29 | 2022-10-21 | 广西壮族自治区农业科学院 | Melon maturity detection method and system based on artificial intelligence |
| CN115994921A (en) * | 2022-12-09 | 2023-04-21 | 大连大学 | Mature cherry fruit image segmentation method integrating HSV model and improving Otsu algorithm |
Non-Patent Citations (1)
| Title |
|---|
| CLASSIFICATION OF MATURITY LEVELS IN ARECA FRUIT BASED ON HSV IMAGE USING THE KNN METHOD;Frencis Matheos Sarimole 等;Journal of Applied Engineering and Technological Science;64-73 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116523910A (en) | 2023-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109308697B (en) | Leaf disease identification method based on machine learning algorithm | |
| CN109447945B (en) | Quick counting method for basic wheat seedlings based on machine vision and graphic processing | |
| CN110120042B (en) | Crop image pest and disease damage area extraction method based on SLIC super-pixel and automatic threshold segmentation | |
| CN109255757B (en) | Method for segmenting fruit stem region of grape bunch naturally placed by machine vision | |
| Sunny et al. | An efficient citrus canker detection method based on contrast limited adaptive histogram equalization enhancement | |
| Masood et al. | Plants disease segmentation using image processing | |
| CN105095907B (en) | A kind of heterogeneous fibre identification method of cotton based on RBF neural | |
| CN115018844A (en) | Plastic film quality evaluation method based on artificial intelligence | |
| Ji et al. | In-field automatic detection of maize tassels using computer vision | |
| CN109871900A (en) | The recognition positioning method of apple under a kind of complex background based on image procossing | |
| CN113298777A (en) | Cotton leaf blight detection method and system based on color features and super-pixel clustering | |
| CN115861721B (en) | Livestock and poultry breeding spraying equipment state identification method based on image data | |
| CN111784764A (en) | Tea tender shoot identification and positioning algorithm | |
| CN116958572A (en) | Leaf disease and pest area analysis method in fruit tree breeding | |
| Bhardwaj et al. | Automated optical disc segmentation and blood vessel extraction for fundus images using ophthalmic image processing | |
| CN116523910B (en) | Intelligent walnut maturity detection method based on image data | |
| Wang et al. | A fast image segmentation algorithm for detection of pseudo-foreign fibers in lint cotton | |
| Taujuddin et al. | Detection of plant disease on leaves using blobs detection and statistical analysis | |
| CN116797622A (en) | Corn tassel image double-threshold segmentation method based on multi-feature index | |
| CN115601690A (en) | Edible fungus environment detection method based on intelligent agriculture | |
| CN110458042B (en) | Method for detecting number of probes in fluorescent CTC | |
| CN115330721A (en) | Banana fruit comb plumpness detection method and system based on shape and color information | |
| Di et al. | The research on the feature extraction of sunflower leaf rust characteristics based on color and texture feature | |
| CN113239837A (en) | Machine learning-based green tomato identification method in natural environment | |
| CN112785589A (en) | Method for acquiring digital medical abnormal image through cloud network |
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 |