CN111402199B - Pear fruit stone cell phenotype detection method based on computer image processing - Google Patents
Pear fruit stone cell phenotype detection method based on computer image processing Download PDFInfo
- Publication number
- CN111402199B CN111402199B CN202010095277.2A CN202010095277A CN111402199B CN 111402199 B CN111402199 B CN 111402199B CN 202010095277 A CN202010095277 A CN 202010095277A CN 111402199 B CN111402199 B CN 111402199B
- Authority
- CN
- China
- Prior art keywords
- image
- pear
- stone
- particles
- area
- 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
- 239000004575 stone Substances 0.000 title claims abstract description 104
- 235000014443 Pyrus communis Nutrition 0.000 title claims abstract description 90
- 235000013399 edible fruits Nutrition 0.000 title claims abstract description 66
- 238000012545 processing Methods 0.000 title claims abstract description 27
- 238000001514 detection method Methods 0.000 title claims abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 28
- 238000005259 measurement Methods 0.000 claims abstract description 10
- 239000002245 particle Substances 0.000 claims description 56
- 230000011218 segmentation Effects 0.000 claims description 14
- JPYHHZQJCSQRJY-UHFFFAOYSA-N Phloroglucinol Natural products CCC=CCC=CCC=CCC=CCCCCC(=O)C1=C(O)C=C(O)C=C1O JPYHHZQJCSQRJY-UHFFFAOYSA-N 0.000 claims description 8
- QCDYQQDYXPDABM-UHFFFAOYSA-N phloroglucinol Chemical compound OC1=CC(O)=CC(O)=C1 QCDYQQDYXPDABM-UHFFFAOYSA-N 0.000 claims description 8
- 229960001553 phloroglucinol Drugs 0.000 claims description 8
- 238000005260 corrosion Methods 0.000 claims description 7
- 230000007797 corrosion Effects 0.000 claims description 7
- 238000009499 grossing Methods 0.000 claims description 7
- 230000002792 vascular Effects 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- VEXZGXHMUGYJMC-UHFFFAOYSA-N Hydrochloric acid Chemical compound Cl VEXZGXHMUGYJMC-UHFFFAOYSA-N 0.000 abstract description 16
- 238000011160 research Methods 0.000 abstract description 4
- 238000000926 separation method Methods 0.000 abstract description 4
- 238000009395 breeding Methods 0.000 abstract 1
- 230000001488 breeding effect Effects 0.000 abstract 1
- 210000004027 cell Anatomy 0.000 description 86
- 241000220324 Pyrus Species 0.000 description 68
- 230000006870 function Effects 0.000 description 8
- 229920005610 lignin Polymers 0.000 description 5
- 244000088401 Pyrus pyrifolia Species 0.000 description 3
- 235000001630 Pyrus pyrifolia var culta Nutrition 0.000 description 3
- QNBLWPGKPNANOY-UHFFFAOYSA-N benzene-1,3,5-triol;hydrochloride Chemical compound Cl.OC1=CC(O)=CC(O)=C1 QNBLWPGKPNANOY-UHFFFAOYSA-N 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 241000196324 Embryophyta Species 0.000 description 2
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 2
- 235000011572 Pyrus ussuriensis Nutrition 0.000 description 2
- 235000004789 Rosa xanthina Nutrition 0.000 description 2
- 241000220222 Rosaceae Species 0.000 description 2
- UIIMBOGNXHQVGW-UHFFFAOYSA-M Sodium bicarbonate Chemical compound [Na+].OC([O-])=O UIIMBOGNXHQVGW-UHFFFAOYSA-M 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 230000000875 corresponding effect Effects 0.000 description 2
- 230000008021 deposition Effects 0.000 description 2
- 239000012153 distilled water Substances 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000004043 dyeing Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 244000144730 Amygdalus persica Species 0.000 description 1
- 235000011446 Amygdalus persica Nutrition 0.000 description 1
- 241001292396 Cirrhitidae Species 0.000 description 1
- 229920004449 Halon® Polymers 0.000 description 1
- 241000238631 Hexapoda Species 0.000 description 1
- 101001018064 Homo sapiens Lysosomal-trafficking regulator Proteins 0.000 description 1
- 102100033472 Lysosomal-trafficking regulator Human genes 0.000 description 1
- 244000038561 Modiola caroliniana Species 0.000 description 1
- 235000010703 Modiola caroliniana Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000002421 cell wall Anatomy 0.000 description 1
- 229920002678 cellulose Polymers 0.000 description 1
- 239000001913 cellulose Substances 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- PXBRQCKWGAHEHS-UHFFFAOYSA-N dichlorodifluoromethane Chemical compound FC(F)(Cl)Cl PXBRQCKWGAHEHS-UHFFFAOYSA-N 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 235000012055 fruits and vegetables Nutrition 0.000 description 1
- 238000003711 image thresholding Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005360 mashing Methods 0.000 description 1
- 238000000399 optical microscopy Methods 0.000 description 1
- 235000021017 pears Nutrition 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004626 scanning electron microscopy Methods 0.000 description 1
- 239000013049 sediment Substances 0.000 description 1
- 229910000030 sodium bicarbonate Inorganic materials 0.000 description 1
- 235000017557 sodium bicarbonate Nutrition 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 238000003756 stirring Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000010257 thawing Methods 0.000 description 1
- 238000004627 transmission electron microscopy Methods 0.000 description 1
- 238000005303 weighing Methods 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
Abstract
The invention discloses a pear fruit stone cell phenotype detection method based on computer image processing. The method can analyze the number of the stone cells, the size and the area of the stone cells and the area of the section of the pear fruit, and further analyze the density of the stone cells, and compared with the traditional hydrochloric acid freeze separation method and enzymolysis method, the method improves the working efficiency of the stone cell property measurement, enriches the statistical data of the stone cell property, reduces the error and the research cost of manual measurement, and has profound significance for pear germplasm assessment and breeding.
Description
Technical Field
The invention belongs to the technical field of pear germplasm resources, and particularly relates to a pear fruit stone cell phenotype detection method based on computer image processing.
Background
The fructus Pyri is Prunus persica of Rosaceae (Rosaceae)Perennial woody plants of the genus Pyrus (Pyrus L.) of the family Amygdalideae are the third biggest fruit tree species in China, and have long cultivation history and wide planting area. In 2017, the cultivation area of pears in China is 96 ten thousand hm 2 About 8.3% of the total area of the national fruits, the yield of 1653 ten thousand t, about 9.7% of the total yield of the national fruits, and the cultivation area and the yield of the national fruits are about 2/3 of the world. However, since the stone cell content of the fruit of Asian pear is higher than that of American pear, especially some traditional cultivars such as Dangshan pear, the fruit of Chinese pear has weaker competitive power in foreign markets, and the export quantity and the export price are far lower than those of Japan and other western countries. Stone cells are characteristic features in pear pulp and are also important factors influencing fruit quality, so that it is important to select varieties with low stone cell content to improve fruit varieties.
Stone cells belong to thick-wall cells, and are developed by secondary deposition of lignin, cellulose and other components on the cell wall by the thin-wall cells. The composition of stone cell lignin is consistent with that of most dicotyledonous plants, comprising a major amount of G-lignin and a minor amount of S-lignin. The lignified stone cells can be stained to mauve by phloroglucinol hydrochloride solution, and based on this method, the stone cell distribution and size can be observed, but are difficult to count. At present, the frozen hydrochloric acid separation method is the most commonly used method for measuring the content of the stone cells, but the method can not completely separate the stone cells from the pulp and has complex operation. Optical microscopy, transmission electron microscopy and scanning electron microscopy can be used to observe stone cell size and density, although these methods are accurate in measurement, they are costly, time consuming and not suitable for germplasm resource research.
Computer vision software is increasingly being used to improve traditional agriculture, and most researchers have adopted computer vision technology to detect diseases early on based on the visible phenotype to improve food quality. Computer vision is also increasingly being used for inspection and grading of fruit and vegetable quality. Compared with manual statistics, the computer vision software has more objective statistical effect and higher statistical efficiency, and can help users to better distinguish subtle phenotype differences.
A set of algorithms written using the c# language and Halcon computer vision library was used to handle the development of images and software, which the applicant named pearcrocess. The Pearprocess is suitable for measuring the number, the size, the area and the density of the stone cells, and can output a result within one minute as long as the image of the cut surface of the pear fruit dyed by the phloroglucinol is introduced, and in addition, the high correlation between the density of the stone cells and the content of the stone cells measured by a frozen hydrochloric acid separation method shows the accuracy of software. The development of the software provides a high-efficiency stone cell detection technology and abundant stone cell character phenotype statistical data, is helpful for revealing the difference of the stone cell characters of pear germplasm resources, and screens excellent variety resources and varieties so as to improve the quality of pear fruits.
Disclosure of Invention
The invention aims to provide a pear fruit stone cell phenotype detection method based on computer image processing, which is characterized in that a pear fruit section image dyed by phloroglucinol hydrochloride is collected, the image is modulated into a gray value image, the image contour is segmented and extracted by using a threshold value, the number, the size and the area of stone cells are counted, the area is accumulated, the density of the stone cells is analyzed, the working efficiency of stone cell property measurement is improved, the statistical data of the stone cell property is enriched, and the error and the research cost of manual measurement are reduced.
The technical solution for realizing the purpose of the invention is as follows: a pear fruit stone cell phenotype detection method based on computer image processing comprises the following steps:
step 1, collecting a pear cut surface image dyed by phloroglucinol, reading in the image and obtaining a gray value image of the pear cut surface;
step 2, dividing the gray value image: extracting pear cut surfaces from the gray value images by adopting a global threshold segmentation algorithm, and extracting bright particles from the gray value images by adopting a dynamic threshold segmentation algorithm to obtain segmented images, wherein the bright particles correspond to the lignified stone cell particles in the pear fruits;
step 3, smoothing and denoising the segmented image to obtain a denoised image;
and 4, measuring the area of the pear section and counting the data of the pear stone cell characteristics, including the number, the size and the area of the stone cells, from the denoised image, and calculating to obtain the stone cell density.
Compared with the prior art, the technical scheme provided by the invention has the following technical effects:
1. the pear stone cell phenotype detection method based on computer image processing can analyze not only stone cell quantity, but also stone cell size, area and fruit section area, further can analyze stone cell density, enriches statistical data of stone cell characters, is beneficial to revealing differences of pear germplasm resource stone cell characters, screens excellent varieties and improves fruit quality.
2. According to the pear fruit stone cell phenotype detection method based on computer image processing, through utilizing the phloroglucinol-dyed pear fruit section picture, stone cell data can be rapidly output by selecting proper parameters, the working efficiency of stone cell property measurement is improved, the error and research cost of manual measurement are reduced, and the accuracy of software is indicated by the high correlation of stone cell density and stone cell content measured by a frozen hydrochloric acid separation method.
3. The pear fruit stone cell phenotype detection method based on computer image processing has the advantages of high efficiency, convenience, accuracy and the like, and provides a more efficient way for researching the pear germplasm resource stone cell character difference.
Drawings
Fig. 1 is a freehand slice of a pear fruit stained with phloroglucinol in example 1 of a computer image processing-based pear fruit stone cell phenotype detection method of the present invention.
FIG. 2 is a diagram showing the binarization of the pear fruit stone cell phenotype test method according to the embodiment 1. Wherein: and (A) removing peel and kernel from the cut surface picture of the pear fruit. And (B) dividing the image by the particles after the binary processing. And C, dividing the image by the denoised particles.
Fig. 3 is a gray scale image of the combination of the segmented particle image and the original image in example 1 of a pear fruit stone cell phenotype detection method based on computer image processing according to the present invention.
Fig. 4 is a pearson correlation coefficient heat map of stone cell content and software analysis stone cell data in example 1 of a pear fruit stone cell phenotype detection method based on computer image processing of the present invention.
Detailed Description
The present invention will be described in detail with reference to specific examples. From the following description and examples, one skilled in the art can ascertain the essential characteristics of this invention, and without departing from the spirit and scope thereof, can make various changes and modifications of the invention to adapt it to various usages and conditions.
A pear fruit stone cell phenotype detection method based on computer image processing comprises the following steps:
and step 1, collecting images of the pear cut surfaces dyed by phloroglucinol, reading in the images and obtaining gray value images of the pear cut surfaces. The method specifically comprises the following steps:
and (5) reading an RGB original image of the pear fruit section image by adopting imread.
And performing parameter adjustment on the RGB original image to obtain a gray value image.
Step 2, dividing the gray value image: and extracting pear cut surfaces from the gray value images by adopting a global threshold segmentation algorithm, and extracting bright particles from the gray value images by adopting a dynamic threshold segmentation algorithm to obtain segmented images, wherein the bright particles correspond to the lignified stone cell particles in the pear fruits. The method specifically comprises the following steps:
step 2-1: extracting pear fruit cut surfaces: setting a threshold value thresh, setting pixels with gray values larger than the threshold value thresh in the gray value image to be white, setting pixels smaller than or equal to the threshold value thresh to be black, and completely extracting the pear cut surface from the background to be used as a measuring area. The threshold function of the threshold value threshold is threshold, and the default parameters are 44-255.
And removing pear peel from the measurement area by adopting a corrosion method to obtain a pulp part without scratches and worm holes, wherein the corrosion method is an image processing algorithm, and the function of the corrosion method is an error_circle with a default radius of 70.
Step 2-2: extraction of bright particles: and (3) utilizing dynamic threshold segmentation, setting a threshold function as threshold, setting a threshold parameter as 0-120, and extracting bright particles in a measurement area.
And step 3, smoothing and denoising the segmented image to obtain a denoised image. The method specifically comprises the following steps:
step 3-1: and setting the gray value of each pixel point in the image to be the average value of the gray values of all the pixel points in a neighborhood window taking the point as the center by adopting an average filtering algorithm, realizing average smoothing by adopting a function mean_image, eliminating punctiform noise in the image, and setting mask=10 and mask=10.
Step 3-2: and further extracting unobvious particles from the smoothed image by adopting a dynamic threshold segmentation operator, wherein the unobvious particles correspond to the lignified stone cell particles in the pear fruit, and the unobvious particles and the bright particles correspond to the stone cells with different lignification degrees and sizes respectively. Different degrees and sizes of the lignification of the stone cell clusters, different colors of particles in the corresponding images,
step 3-3: the round structure with the radius of 3.5 is adopted to carry out open operation, a tubular vascular bundle is removed, the function opening_circle is adopted to remove burrs of all extracted particles, including bright particles and unobvious particles, and holes in fruit particles are filled.
And 4, measuring the area of the pear section and counting the data of the pear stone cell characteristics, including the number, the size and the area of the stone cells, from the denoised image, and calculating to obtain the stone cell density. The method comprises the following specific steps:
step 4-1: searching and drawing the outline of the pear fruit section image, and measuring the pear fruit section area;
step 4-2: counting the number of particles and the area of the particles in the image, and obtaining the number of the stone cells and the area of each stone cell;
step 4-3: and accumulating the area of each particle to obtain the total area of the stone cells, and calculating the ratio of the total area to the area of the pear section.
Example 1
A pear fruit stone cell phenotype detection method based on computer image processing specifically comprises the following steps:
1) And (3) image acquisition: and acquiring images of the pear cut surfaces dyed by phloroglucinol, reading in the images and acquiring gray value images of the pear cut surfaces.
The pear fruit in mature period is collected from Nanjing university of agriculture in the Jiangpu test base and national Chinese pear germplasm resource nursery. Slicing pear pulp by hand and dyeing with phloroglucinol-hydrochloric acid, wherein the method comprises the following specific steps:
1. first, the mixture was treated with 30% hydrochloric acid solution (V/V) for 1 minute;
2. 10% phloroglucinol was dissolved in 80% ethanol (W/V);
3. dropping the mixture onto the slices which are treated by hydrochloric acid, and dyeing for 7 minutes;
4. finally, a sufficient amount of 0.4M sodium bicarbonate solution was added dropwise to terminate the reaction.
The camera uses Canon D80, and is matched with the camera turning frame to take pictures, the camera is fixed on the turning frame, and the pear fruit slices are kept at the same level. Each shot keeps the focus consistent. The acquired picture is shown in fig. 1.
2) Image processing: dividing the gray value image: and extracting pear cut surfaces from the gray value images by adopting a global threshold segmentation algorithm, and extracting bright particles from the gray value images by adopting a dynamic threshold segmentation algorithm to obtain segmented images, wherein the bright particles correspond to the lignified stone cell particles in the pear fruits. And carrying out smoothing and denoising treatment on the segmented image to obtain a denoised image.
Model development is based on C# language and a halon computer vision library, and is used for compiling link execution codes through Xcode and processing images, and mainly comprises the following steps:
1. the acquired phloroglucinol-dyed pear slice image is colorful, and because the image data volume with RGB information is large and is inconvenient to calculate, and the RGB values are not useful for extracting fruit points from the image, the image is required to be read in and then gray value processing is carried out to obtain a gray value image.
2. Pixels with gray values larger than thresh (threshold value) are set to be white, pixels with gray values smaller than or equal to thresh are set to be black, a threshold function is set to be threshold, and therefore the whole pear is completely extracted from the background, after pear peel is removed through a corrosion method, a measured area is a pulp portion without scratches and insect holes, and a separated gray value image is shown in fig. 2A.
3. Because there is a certain difference between gray values of pear pulp and stone cells, the parameters are set to 0-120 by using dynamic threshold segmentation, and bright particles are extracted, and the extraction result is shown in fig. 2B.
4. In order to improve the accuracy of data statistics, the extracted particles are subjected to denoising treatment. Noise in an image is mainly divided into two types: one is noise generated due to uneven image gray values during image thresholding, a mean value filtering algorithm is adopted to set the gray value of each pixel point as the average value of all pixel gray values in a neighborhood window with the point as the center, mean smoothing is realized by defining a function mean_image, point-like noise in an image is eliminated, the mask width is 10, and the mask height is 10; the second is noise generated by vascular bundle cells contained in pear pulp, deposition of lignin contained in the vascular bundle cells is dyed into red by phloroglucinol, punctiform or tubular distribution is shown in a pear fruit section, a circular structure with the radius of 3.5 is used for carrying out open operation, tubular vascular bundles are removed, meanwhile, a function open_circle is used for removing burrs of extracted particles, holes in fruit particles are filled, the integrity noise point removal of the particles and the integrity improvement of the particles are improved, and the accuracy of stone cell number and area statistics is improved. The effect of noise removal is shown in fig. 2C.
Noise elimination and particle integrity improvement increase the accuracy of the number and area statistics of the stone cells.
3) Image and data output: and measuring the area of the pear section and counting the data of the pear stone cell characteristics, including the number, the size and the area of the stone cells, from the denoised image, and calculating to obtain the stone cell density.
According to the denoised image, the stone cell character of the pear fruit is counted, and the method mainly comprises the following steps:
1. searching and drawing an image outline, and measuring the pear fruit section area according to the size value corresponding to the standard pixel;
2. counting the number of particles in the image and the area of each particle;
3. and calculating the total area of the particles by accumulating the areas of the particles, and calculating the proportion of the particles by using the total area of the particles and the area of the pear fruit section.
And storing the found outline picture, combining the segmented particle image with the original image, and combining the gray level image as shown in fig. 3. The number, area and proportion of output points in the txt file, and the area of each point.
4) And (3) verifying the reliability of the stone cell property data: and (3) carrying out correlation analysis on the data output by the Pearprocess and the content of the stone cells measured by using a frozen hydrochloric acid method, and manufacturing a pearson correlation coefficient heat map.
Taking edible fruit part, sampling 100g by quartering, and standing in a low temperature refrigerator at-20deg.C overnight. Taking out the sample, thawing, adding 100ml of distilled water, mashing for 2 minutes in a homogenizer, pouring the homogenate into a 500ml beaker, adding a proper amount of distilled water to dilute the homogenate, standing at room temperature for a while after stirring to enable stone cells to sink, pouring out floating matters, resuspending the sediment with 0.5mol/L hydrochloric acid solution, standing for a while, discarding the upper floating matters, repeating for 3-4 times, separating to obtain pure stone cells, drying the washed stone cells in an oven until the weight is constant after the water is absorbed by filter paper, and weighing to obtain the stone cell content in 100g pulp.
In the embodiment, 54 pear fruits are selected to measure the content of the stone cells by using the method, 10 fruits are selected for each variety, the average value is obtained by repeating three times, and the obtained data and the data output by the Pearprocess are subjected to correlation analysis to find that the content of the stone cells is positively correlated with the number, the size, the area and the density of the stone cells, wherein the correlation between the content of the stone cells and the density of the stone cells is the highest, and the correlation coefficient is as high as 0.603; the correlation between the stone cell content and the stone cell area is inferior, and the correlation coefficient reaches 0.464; the correlation of the stone cell content with the number and size of stone cells was low, and the correlation coefficients were 0.326 and 0.255, respectively (fig. 4).
While only a few embodiments of the present invention have been described, it should be noted that modifications could be made by those skilled in the art without departing from the principles of the present invention, which modifications are to be regarded as being within the scope of the invention.
Claims (6)
1. The pear fruit stone cell phenotype detection method based on computer image processing is characterized by comprising the following steps of:
step 1, collecting a pear cut surface image dyed by phloroglucinol, reading in the image and obtaining a gray value image of the pear cut surface;
step 2, dividing the gray value image: extracting pear cut surfaces from the gray value images by adopting a global threshold segmentation algorithm, and extracting bright particles from the gray value images by adopting a dynamic threshold segmentation algorithm to obtain segmented images, wherein the bright particles correspond to the lignified stone cell particles in the pear fruits;
step 3, smoothing and denoising the segmented image to obtain a denoised image; the method specifically comprises the following steps:
step 3-1: setting the gray value of each pixel point in an image to be the average value of the gray values of all the pixel points in a neighborhood window taking the point as the center by adopting an average value filtering algorithm, realizing average value smoothing by adopting a function mean_image, eliminating punctiform noise in the image, and setting mask=10 and mask=10;
step 3-2: further extracting unobvious particles from the smoothed image by adopting a dynamic threshold segmentation operator, wherein the unobvious particles correspond to the lignified stone cell particles in the pear fruit, and the unobvious particles and the bright particles correspond to the stone cells with different lignification degrees and sizes respectively;
step 3-3: performing open operation by adopting a circular structure with the radius of 3.5, removing a tubular vascular bundle, removing burrs of all extracted particles by adopting a function opening_circle, and filling holes in fruit particles;
and 4, measuring the area of the pear section and counting the data of the pear stone cell characteristics, including the number, the size and the area of the stone cells, from the denoised image, and calculating to obtain the stone cell density.
2. The method for detecting the phenotype of pear fruit stone cells based on computer image processing according to claim 1, wherein the step 1 of obtaining the gray value image of the cut surface of the pear fruit specifically comprises the following steps:
an image read is adopted to read in an RGB original image of the pear fruit section image;
and performing parameter adjustment on the RGB original image to obtain a gray value image.
3. The method for detecting the phenotype of pear fruit stone cells based on computer image processing according to claim 1, wherein the segmentation processing in the step 2 specifically comprises the following steps:
step 2-1: extracting pear fruit cut surfaces: setting a threshold value thresh, setting pixels with gray values larger than the threshold value thresh in the gray value image to be white, setting pixels smaller than or equal to the threshold value thresh to be black, and completely extracting a pear cut surface from the background to be used as a measuring area;
step 2-2: extraction of bright particles: and (3) utilizing dynamic threshold segmentation, setting a threshold function as threshold and setting parameters as 0-120, and extracting bright particles in a measurement area.
4. A method for detecting a phenotype of pear fruit stone cells based on computer image processing according to claim 3, wherein the threshold function of the threshold value threshold is threshold, and the default parameters are 44-255.
5. A method for detecting the phenotype of pear fruit stone cells based on computer image processing according to claim 3, wherein the pear fruit peel is removed from the measuring area in the step 2-1 by adopting a corrosion method to obtain a pulp part without scratches and worm holes, wherein the corrosion method is an image processing algorithm, and the function of the corrosion method is an error_circle, and the default radius is 70.
6. The method for detecting the phenotype of pear fruit stone cells based on computer image processing according to claim 1, wherein the specific steps of the step 4 are as follows:
step 4-1: searching and drawing the outline of the pear fruit section image, and measuring the pear fruit section area;
step 4-2: counting the number of particles and the area of the particles in the image, and obtaining the number of the stone cells and the area of each stone cell;
step 4-3: and accumulating the area of each particle to obtain the total area of the stone cells, and calculating the ratio of the total area to the area of the pear section.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010095277.2A CN111402199B (en) | 2020-02-08 | 2020-02-08 | Pear fruit stone cell phenotype detection method based on computer image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010095277.2A CN111402199B (en) | 2020-02-08 | 2020-02-08 | Pear fruit stone cell phenotype detection method based on computer image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111402199A CN111402199A (en) | 2020-07-10 |
| CN111402199B true CN111402199B (en) | 2024-01-12 |
Family
ID=71432676
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010095277.2A Active CN111402199B (en) | 2020-02-08 | 2020-02-08 | Pear fruit stone cell phenotype detection method based on computer image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111402199B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11687862B2 (en) | 2021-03-10 | 2023-06-27 | Zhejiang University | Method for guiding sales strategy of loquat fruits by evaluating and predicting quality of loquat fruits |
| CN113049588B (en) * | 2021-03-10 | 2021-12-28 | 浙江大学 | Loquat fruit quality evaluation and prediction method for guiding loquat sales strategy |
| CN113030088B (en) * | 2021-03-10 | 2022-03-15 | 浙江大学 | Cell rapid statistical evaluation method for solid lignification degree of loquat fruit |
| CN113109118A (en) * | 2021-05-13 | 2021-07-13 | 湖北省农业科学院果树茶叶研究所 | Visual semi-quantitative rapid evaluation method for pomelo cells |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS55102379A (en) * | 1976-06-14 | 1980-08-05 | Akiyoshi Yamane | Separation of stone cell from pulp-containing fruit juice in preparation of nectar containing pear flesh |
| KR20140147966A (en) * | 2013-06-20 | 2014-12-31 | 전라남도 | Cosmetic composition including stone cell of pear fruit |
| CN105004690A (en) * | 2015-07-30 | 2015-10-28 | 合肥工业大学 | Rapid and nondestructive testing method of sclereid content in pear pulp based on multi-spectral imaging technology |
| CN110118735A (en) * | 2018-02-06 | 2019-08-13 | 中国农业机械化科学研究院 | A kind of high light spectrum image-forming detection method and device detecting bergamot pear male and female |
-
2020
- 2020-02-08 CN CN202010095277.2A patent/CN111402199B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS55102379A (en) * | 1976-06-14 | 1980-08-05 | Akiyoshi Yamane | Separation of stone cell from pulp-containing fruit juice in preparation of nectar containing pear flesh |
| KR20140147966A (en) * | 2013-06-20 | 2014-12-31 | 전라남도 | Cosmetic composition including stone cell of pear fruit |
| CN105004690A (en) * | 2015-07-30 | 2015-10-28 | 合肥工业大学 | Rapid and nondestructive testing method of sclereid content in pear pulp based on multi-spectral imaging technology |
| CN110118735A (en) * | 2018-02-06 | 2019-08-13 | 中国农业机械化科学研究院 | A kind of high light spectrum image-forming detection method and device detecting bergamot pear male and female |
Non-Patent Citations (1)
| Title |
|---|
| 刘国庆等."基于优势背景色的细胞图像综合分割方法".《计算机工程与设计》.2011,第32卷(第6期),第2080-2082页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111402199A (en) | 2020-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111402199B (en) | Pear fruit stone cell phenotype detection method based on computer image processing | |
| Tong et al. | Machine vision techniques for the evaluation of seedling quality based on leaf area | |
| CN109447945B (en) | Quick counting method for basic wheat seedlings based on machine vision and graphic processing | |
| CN101085442B (en) | Method for treating and classifying orange image based on RGB composite model | |
| CN101944231A (en) | Method for extracting wheatear morphological parameters | |
| Liu et al. | A vision-based robust grape berry counting algorithm for fast calibration-free bunch weight estimation in the field | |
| CN102147402A (en) | Machine vision technology based method for rapidly detecting egg freshness | |
| Heckwolf et al. | Image analysis of anatomical traits in stalk transections of maize and other grasses | |
| CN103065149A (en) | Netted melon fruit phenotype extraction and quantization method | |
| Richner et al. | Root image analysis and interpretation | |
| CN109100323A (en) | A kind of transmitted spectrum harmless quantitative evaluation method of apple water core | |
| Marcon et al. | Estimation of total leaf area in perennial plants using image analysis | |
| CN103632157A (en) | A method for counting seeds of a wheatear portion per wheat | |
| CN103528967A (en) | Hyperspectral image based overripe Lonicera edulis fruit identification method | |
| Xue et al. | Pearprocess: A new phenotypic tool for stone cell trait evaluation in pear fruit | |
| Ye et al. | Cucumber appearance quality detection under complex background based on image processing | |
| CN113267458A (en) | Method for establishing quantitative prediction model of soluble protein content of sweet potatoes | |
| Zhang et al. | Quantitative extraction and analysis of pear fruit spot phenotypes based on image recognition | |
| CN110929787A (en) | Apple objective grading system based on images | |
| Guangrong | Detection of chalk degree of rice based on image processing | |
| Zhao et al. | A backlight and deep learning based method for calculating the number of seeds per silique | |
| CN1789978A (en) | Non-destructive detection method for quickly detecting inner quality of apple | |
| Behtari et al. | Predicting germination of Medicago sativa and Onobrychis viciifolia seeds by using image analysis | |
| CN113177911A (en) | Method for nondestructive evaluation of ozone sensitivity of plants by leaves | |
| Zhao et al. | Grading system of tomato grafting machine based on machine vision |
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 |