CN106780347B - Early loquat bruise identification method based on OCT image processing - Google Patents
Early loquat bruise identification method based on OCT image processing Download PDFInfo
- Publication number
- CN106780347B CN106780347B CN201710071158.1A CN201710071158A CN106780347B CN 106780347 B CN106780347 B CN 106780347B CN 201710071158 A CN201710071158 A CN 201710071158A CN 106780347 B CN106780347 B CN 106780347B
- Authority
- CN
- China
- Prior art keywords
- image
- loquat
- cell
- area
- pixel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 241001092070 Eriobotrya Species 0.000 title claims abstract description 46
- 235000009008 Eriobotrya japonica Nutrition 0.000 title claims abstract description 46
- 208000034656 Contusions Diseases 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 title claims abstract description 31
- 208000034526 bruise Diseases 0.000 title claims abstract description 23
- 238000012545 processing Methods 0.000 title claims abstract description 23
- 238000001914 filtration Methods 0.000 claims abstract description 16
- 235000013399 edible fruits Nutrition 0.000 claims abstract description 11
- 230000009467 reduction Effects 0.000 claims abstract description 5
- 238000005070 sampling Methods 0.000 claims abstract description 3
- 210000004027 cell Anatomy 0.000 claims description 62
- 230000001413 cellular effect Effects 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000006073 displacement reaction Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 210000001339 epidermal cell Anatomy 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 210000002615 epidermis Anatomy 0.000 claims description 2
- 238000002179 total cell area Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 15
- 238000007920 subcutaneous administration Methods 0.000 abstract description 2
- 238000012014 optical coherence tomography Methods 0.000 description 18
- 210000001519 tissue Anatomy 0.000 description 14
- 230000007547 defect Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 4
- 238000001228 spectrum Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 238000000701 chemical imaging Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000013505 freshwater Substances 0.000 description 1
- 230000009643 growth defect Effects 0.000 description 1
- 210000003701 histiocyte Anatomy 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000013535 sea water Substances 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4023—Scaling of whole images or parts thereof, e.g. expanding or contracting based on decimating pixels or lines of pixels; based on inserting pixels or lines of pixels
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10101—Optical tomography; Optical coherence tomography [OCT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20152—Watershed segmentation
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a loquat early bruise identification method based on OCT image processing. The method comprises the steps of collecting an SD-OCT image with cell image details of loquat fruits, using a bicubic interpolation algorithm to perform down-sampling and image resolution reduction on the image, performing Gaussian fuzzy noise reduction processing, extracting a boundary line between a loquat fruit target and a background, taking the highest point of the boundary line as a reference point, deforming the boundary line into a straight line along the reference point according to the reference point, performing mean filtering on the image, performing binarization processing on the image, processing the binary image to obtain a cell area corresponding to each cell, and analyzing and calculating the cell area to obtain a bruise identification result. The method provided by the invention realizes full-automatic detection of early bruising of loquat pulp, completes subcutaneous cell identification and discrimination of bruised tissues, improves detection efficiency, and lays a technical foundation for online detection of inherent quality of loquat.
Description
Technical Field
The invention belongs to the field of automatic detection of internal quality of fruits, relates to an OCT image processing method, and particularly relates to an early loquat bruise identification method based on OCT image processing.
Background
The loquat is one of the special fruits in China, and the nondestructive rapid detection method of the internal quality in the picking, selling, transporting and storing processes is a main technical problem facing the development of the loquat industry. Loquat is very easily damaged by external force in the sale process of each industry, and the later-stage deterioration is caused. Bruising of loquat may occur in each link of picking, storage, transportation, packaging and the like, and is not easy to be noticed in early sales. The shelf life of the loquat after bruise is greatly shortened, and due to the damage of a cell structure, the organization is gradually browned, so that the satisfaction degree and the repurchase rate of a consumer are seriously influenced.
On the internal structure of the loquat in nondestructive detection, a spectrum method or hyperspectral imaging is generally used, large-scale equipment is needed to guarantee comprehensive collection of spectrum information, more detection time and cost are consumed, certain technical requirements are provided for detection personnel, the hyperspectral image hardly reflects the internal situation of the loquat, and the spectrum characteristics have certain offset along with the change of the loquat types. The spectral domain optical coherence tomography (SD-OCT) shows the internal structural morphology and distribution of substances by measuring the optical interference characteristics of the substances, the SD-OCT images are used for identification, quantitative measurement and qualitative identification of a plurality of tissues of a human body at present, and reports show that the images can clearly show the hierarchical structure of biological tissues. At present, the OCT image method is mainly applied to the fields of agriculture and breeding: observing the epidermal structure of apple, distinguishing seawater nucleated pearl from fresh water non-nucleated pearl, observing the internal cell structure of seeds, observing the growth defects of plant leaves, and the like. The method is used for loquat industry and has wide application prospect.
In industrial application, the OCT image of the loquat has small contrast and unobvious characteristics, and the early bruise condition can not be basically distinguished by adopting manual discrimination. In the application process of the loquat OCT image, an image processing algorithm is not systematically reported, various researches are still in a starting stage, and a method capable of identifying early-stage bruises of the loquat is absent in the prior art.
Disclosure of Invention
Aiming at the problems in the background art, the invention aims to provide the loquat early bruise identification method based on OCT image processing, which can automatically identify the bruise defect of the loquat in the OCT image, evaluate the morphological parameters of the histiocyte, improve the detection efficiency, and lay the technical foundation for online detection of the loquat in cooperation with the appearance detection methods such as imaging.
The technical scheme adopted by the invention comprises the following steps:
1) the method comprises the following steps of collecting an SD-OCT image with cell details of loquat fruits, wherein the image definition of the SD-OCT image is up to the level that naked eyes can clearly distinguish cells of loquat epidermis and loquat pulp;
2) using a bicubic interpolation algorithm to perform down-sampling on the image and reduce the resolution of the image;
3) performing Gaussian blur noise reduction treatment on the SD-OCT image obtained in the step 2);
4) extracting a boundary between the loquat fruit target and the background;
5) taking the highest point of the boundary line as a reference point, calculating the longitudinal coordinate difference between the boundary line and the reference point as a displacement amount, and performing vertical displacement on each column of the boundary line except the column where the reference point is located to deform the boundary line into a straight line along the reference point; deleting the pixels shifted out of the image area, and directly filling zero in the new area shifted into the image;
6) taking a 3 x 3 template, and carrying out mean filtering on the image;
7) setting a threshold value, and carrying out binarization processing on the image to obtain a binary image, wherein pixels in the binary image are zero pixels or non-zero pixels;
8) and processing the binary image to obtain cell areas corresponding to the cells, and analyzing and calculating the cell areas to obtain the result of bruise identification.
The step 8) is specifically as follows:
8.1) for each pixel of the binary image, the shortest distance of the pixel is calculated: if the located pixel is a zero pixel, the shortest distance is the distance between the located pixel and the nearest non-zero pixel; if the pixel is a non-zero pixel, the shortest distance is zero;
8.2) segmenting the image according to different cells by using a watershed algorithm and the shortest distance in the step 8.1) to obtain each segmented cell area;
8.3) screening in each divided cell area, removing the cell area of the epidermal cells and reserving the cell area of the pulp cells; specifically, the remaining image area is selected and reserved starting to be selected at a distance downwards from the line where the reference point is located.
8.4) calculating the Ferrett diameter and the equivalent diameter of each cell area, and reserving the cell areas of which the Ferrett diameter meets the Ferrett diameter lower limit threshold value which is not less than R1 which is not less than the Ferrett diameter upper limit threshold value and the maximum equivalent diameter is less than the equivalent diameter threshold value;
8.5) calculating the total area surface area, the average area, the average Feret diameter, the average equivalent circle diameter and the number of cells per unit area from all the cell areas obtained in step 8.4): total area surface area: defined as the sum of the areas of all cellular regions; average area is total cell area surface area/number of cell areas; average feret diameter-the sum of the feret diameters of all cellular regions/number of cellular regions; the average equivalent circle diameter is the sum of equivalent circle diameters of all cell areas/number of cell areas; the number of cells per unit area is the number of cell regions/area occupied by the OCT image;
8.6) setting a standard sample set of normal and bruised loquats, respectively calculating the total area surface area, the average area, the average Feret diameter, the average equivalent circle diameter and the cell number threshold value of unit area of the standard sample, and judging and obtaining the result of bruising identification through clustering analysis.
The step 4) is specifically as follows:
4.1) setting a filtering template to be [ -1, 1], and carrying out first filtering on the OCT image;
4.2) setting a filtering template as [ 1-1 ], and carrying out secondary filtering on the OCT image;
4.3) carrying out normalization processing on the filtered image;
4.4) carrying out binarization transformation on the image: setting a threshold, setting pixels of the image which are larger than or equal to the threshold as 1, and setting pixels of the image which are smaller than the threshold as 0;
4.5) carrying out closed operation on the image;
4.6) carrying out opening operation on the image;
4.7) for each column of pixel points in the binarized image, searching the column from top to bottom to present the pixel point with the first gray value of 1 and recording the pixel point as a boundary between the target and the background.
The step 7) is specifically as follows: setting a segmentation limit, setting pixels which are greater than or equal to 0 and less than or equal to the segmentation limit in the image as 1, and setting pixels which are greater than the segmentation limit in the image as 0.
The invention adopts a multi-time template matching filtering mode to process images, and aims to extract the image of the loquat large cell from the change of the OCT image gray scale, calculate various section characteristics of the cell at the later stage and judge the existence of bruise from characteristic parameters. In the previous patent, the main purpose of the earlier stage of the image is to extract and calculate the optical characteristic parameters of local tissues, and then judge the bruise by using the optical parameters.
The invention has the beneficial effects that:
the invention uses OCT image to detect the internal bruise defect of loquat fruit, has the advantages of no damage, rapidness and low cost, and greatly improves the efficiency and accuracy of bruise discrimination.
The method adopts the cell structure parameters as evaluation means, has universality for the bruised tissues with different shapes, sizes, thicknesses, production areas and growth environments, can automatically mark the positions of defective cells, and has better positioning precision compared with other methods.
The invention adopts the cell particle parameters as an evaluation means, combines the image after the flattening transformation, and has certain robustness of the detection effect.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
FIG. 2 is an OCT image of a typical loquat sample in which (a) the sample is normal and free of defects and (b) the sample has a bruise defect in its flesh tissue.
FIG. 3 is an original image of an image processing process according to an embodiment of the present invention.
FIG. 4 is an image of a straight line boundary obtained after flattening according to an embodiment of the present invention.
FIG. 5 is an image of all cellular regions after segmentation in accordance with an embodiment of the present invention.
FIG. 6 is an image of the region of cells retained after screening according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the invention and the implementation process thereof are as follows:
1) using a TELSTO 1300V2 model SD-OCT imager produced by Thorlabs company to collect 40 SD-OCT image samples of loquat fruits, wherein 20 SD-OCT image samples contain bruise defects with different degrees, and 20 SD-OCT image samples are normal samples; FIG. 2 is an OCT image of 2 typical loquat samples (a) normal defect-free samples and (b) bruise defect in pulp tissue of the samples. The figure shows that normal defect-free tissue structures are dense and compact, while tissue with bruises presents sparse tissue with less density. The bruising condition cannot be judged only by naked eyes.
2) The original image as shown in fig. 4 is input, down-sampled using a bicubic interpolation algorithm, and the original image resolution (1625 × 1024) is reduced to 1/3. The purpose of downsampling is to facilitate fast processing of the image.
3) And then, carrying out Gaussian blur noise reduction treatment on the SD-OCT image, and removing shot noise.
4) Extracting a boundary between the loquat fruit target and the background;
4.1) setting the template to [ -1, 1], and carrying out first filtering on the OCT image;
4.2) setting the template as [ 1-1 ], and carrying out secondary filtering on the OCT image;
and performing secondary filtering operation to extract the vertical mutation part of the flattened image.
4.3) carrying out maximum and minimum normalization processing on the filtered image;
4.4) carrying out binarization transformation on the image: setting a threshold to be 1.2, setting pixels of the image larger than or equal to the threshold to be 1, and setting pixels of the image smaller than the threshold to be 0;
4.5) taking 3 × 3 square areas, and performing closed operation on the image;
4.6) taking 3 × 3 square areas and carrying out open operation on the image.
The region is closed and opened, and the background and the target are distinguished.
4.7) for each column of pixel points in the binarized image, searching the column from top to bottom to present the pixel point with the first gray value of 1 and recording the pixel point as a boundary between the target and the background.
5) Taking the highest point of the boundary line and taking the highest point as a reference point; calculating the longitudinal coordinate difference between the boundary line and the reference point, and taking the longitudinal coordinate difference as a displacement amount to perform vertical displacement on each column of the boundary line except the column where the reference point is located, so that the boundary line becomes a straight line passing through the reference point; deleting the pixels shifted out of the image area, and directly filling zero in the new area shifted into the image; after the flattening transformation, it is shown in fig. 4.
6) And 3-by-3 templates are taken, and the image is subjected to mean filtering, so that the smoothness of the image is improved.
7) A division limit is set to 80, binarization processing is performed on the image, pixels which are greater than or equal to 0 and less than or equal to the division limit in the image are set to be 1, and pixels which are greater than the division limit in the image are set to be 0.
8) For each pixel of the binary image, the shortest distance of the pixel is calculated. For a pixel that is originally 0, its shortest distance is defined as the distance to the 1 pixel that is closest to it. For example, the distance between a zero pixel adjacent to a pass edge and the nearest non-zero pixel is 1, and the distance between a zero pixel adjacent to a pass corner and the nearest non-zero pixel is √ 2. For a pixel which is itself 1, the shortest distance is 0.
9) Dividing the image according to different cells by using a watershed algorithm to obtain each divided cell region, as shown in fig. 5;
10) screening in each divided cell area, removing the cell area of epidermal cells, and reserving the cell area of pulp cells; in this embodiment, an area image within a range of 0.07mm to 1mm is cut down based on a straight line boundary where the reference point is located, and the remaining image is as shown in fig. 6.
11) Calculating the Ferrett diameter and the equivalent diameter of each area in the area image in the step 10), and selecting the area with the Ferrett diameter of 30-100 μm and the maximum equivalent diameter of less than 150 μm.
12) From all the obtained cell regions, the total region surface area, the average region area, the average Feret diameter, the average equivalent circle diameter, and the number of cells per unit area were calculated.
13) And (4) setting a standard sample set of normal loquat and bruised loquat, respectively calculating the total area surface area, the average Feret diameter, the average equivalent circle diameter and the cell number threshold value of a unit area of the standard sample, and judging the bruised result through cluster analysis. The specific implementation adopts a KNN clustering analysis method to carry out analysis and judgment.
In this embodiment, 10 samples of normal and bruised samples are randomly selected, 20 samples are counted as standard samples, the remaining 20 samples are classified and identified, statistical values of various parameters are given in table 1, and experimental results show that the recognition rate of the bruised samples and the normal samples in the 20 samples reaches 100%.
TABLE 1 tissue structure parameters of large cells (95% confidence intervals)
Parameter(s) | Unit of | Normal tissue | Bruising tissue |
Total area of area | Mm2 | 2.08±1.20 | 1.45±0.07 |
Average area of area | Mm2 | 0.0042±0.0002 | 0.0043±0.0001 |
Average Feret diameter | μm | 58.63±1.05 | 59.15±0.85 |
Mean equivalent circle diameter | μm | 40.42±0.73 | 40.62±0.61 |
Number of cells per unit area | - | 491.70±25.54 | 340.15±12.34 |
The method can be used for realizing the full-automatic detection of the early bruise of the loquat pulp, completing the subcutaneous cell identification and discrimination of the bruised tissue, obtaining stronger detection reliability by detecting the bruised tissue of the loquats of different production places and varieties, and improving the detection efficiency.
In the embodiment of the present invention, it can be further understood by those skilled in the art that all or part of the steps in the method for implementing the above embodiment may be implemented by instructing the relevant hardware through a program, where the program may be stored in a computer-readable storage medium, where the storage medium includes a ROM/RAM, a magnetic disk, an optical disk, and the like.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (4)
1. An early loquat bruise identification method based on OCT image processing is characterized in that: the method comprises the following steps:
1) collecting an SD-OCT image with cell image details of the loquat fruits;
2) using a bicubic interpolation algorithm to perform down-sampling on the image and reduce the resolution of the image;
3) performing Gaussian blur noise reduction treatment on the SD-OCT image obtained in the step 2);
4) extracting a boundary between the loquat fruit target and the background;
5) taking the highest point of the boundary line as a reference point, calculating the longitudinal coordinate difference between the boundary line and the reference point as a displacement amount, and performing vertical displacement on each column of the boundary line except the column where the reference point is located to deform the boundary line into a straight line along the reference point;
6) taking a 3 x 3 template, and carrying out mean filtering on the image;
7) setting a threshold value, and carrying out binarization processing on the image to obtain a binary image;
8) processing the binary image to obtain cell areas corresponding to all cells, and analyzing and calculating the cell areas to obtain a bruise identification result; the step 8) is specifically as follows:
8.1) for each pixel of the binary image, the shortest distance of the pixel is calculated: if the located pixel is a zero pixel, the shortest distance is the distance between the located pixel and the nearest non-zero pixel; if the pixel is a non-zero pixel, the shortest distance is zero;
8.2) segmenting the image according to different cells by using a watershed algorithm and the shortest distance in the step 8.1) to obtain each segmented cell area;
8.3) screening in each divided cell area, removing the cell area of the epidermal cells and reserving the cell area of the pulp cells;
8.4) calculating the Ferrett diameter and the equivalent diameter of each cell area, and reserving the cell areas of which the Ferrett diameter meets the Ferrett diameter lower limit threshold value which is not less than R1 which is not less than the Ferrett diameter upper limit threshold value and the maximum equivalent diameter is less than the equivalent diameter threshold value;
8.5) calculating the total area surface area, the average area, the average Feret diameter, the average equivalent circle diameter and the number of cells per unit area from all the cell areas obtained in step 8.4):
total area surface area: defined as the sum of the areas of all cellular regions;
average area is total cell area surface area/number of cell areas;
average feret diameter-the sum of the feret diameters of all cellular regions/number of cellular regions;
the average equivalent circle diameter is the sum of equivalent circle diameters of all cell areas/number of cell areas;
the number of cells per unit area is the number of cell regions/area occupied by the OCT image;
8.6) setting a standard sample set of normal and bruised loquats, respectively calculating the total area surface area, the average area, the average Feret diameter, the average equivalent circle diameter and the cell number threshold value of unit area of the standard sample, and judging and obtaining the result of bruising identification through clustering analysis.
2. The method for identifying early loquat bruise based on OCT image processing as claimed in claim 1, wherein the method comprises: the image definition of the SD-OCT image reaches the level that the naked eye can clearly distinguish the cells of the loquat epidermis and pulp.
3. The method for identifying early loquat bruise based on OCT image processing as claimed in claim 1, wherein the method comprises: the step 4) is specifically as follows:
4.1) setting a filtering template to be [ -1, 1], and carrying out first filtering on the OCT image;
4.2) setting a filtering template as [ 1-1 ], and carrying out secondary filtering on the OCT image;
4.3) carrying out normalization processing on the filtered image;
4.4) carrying out binarization transformation on the image: setting a threshold, setting pixels of the image which are larger than or equal to the threshold as 1, and setting pixels of the image which are smaller than the threshold as 0;
4.5) carrying out closed operation on the image;
4.6) carrying out opening operation on the image;
4.7) searching each column of pixel points in the binarized image from top to bottom to present the pixel point with the first gray value of 1 and recording the pixel point as a boundary between the target and the background;
4. the method for identifying early loquat bruise based on OCT image processing as claimed in claim 1, wherein the method comprises: the step 7) is specifically as follows: setting a segmentation limit, setting pixels which are greater than or equal to 0 and less than or equal to the segmentation limit in the image as 1, and setting pixels which are greater than the segmentation limit in the image as 0.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710071158.1A CN106780347B (en) | 2017-02-09 | 2017-02-09 | Early loquat bruise identification method based on OCT image processing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710071158.1A CN106780347B (en) | 2017-02-09 | 2017-02-09 | Early loquat bruise identification method based on OCT image processing |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106780347A CN106780347A (en) | 2017-05-31 |
CN106780347B true CN106780347B (en) | 2020-03-03 |
Family
ID=58955646
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710071158.1A Active CN106780347B (en) | 2017-02-09 | 2017-02-09 | Early loquat bruise identification method based on OCT image processing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106780347B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107527365A (en) * | 2017-08-18 | 2017-12-29 | 郑州云海信息技术有限公司 | A kind of method and device of dynamic calculation class circle object morphology diameter |
CN108776967A (en) * | 2018-06-12 | 2018-11-09 | 塔里木大学 | A kind of bergamot pear bruise discrimination method |
CN110264472B (en) * | 2019-05-29 | 2021-05-04 | 浙江科技学院 | SD-OCT-based fruit hypodermal cell nondestructive imaging method |
CN111624659B (en) * | 2020-06-05 | 2022-07-01 | 中油奥博(成都)科技有限公司 | Time-varying band-pass filtering method and device for seismic data |
CN111932499B (en) * | 2020-07-10 | 2023-12-22 | 深圳市瑞沃德生命科技有限公司 | Cell diameter calculation method, device and system |
CN113409302B (en) * | 2021-07-13 | 2023-07-07 | 浙江科技学院 | OCT image-based corn kernel early mildew identification method |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101059452A (en) * | 2007-05-29 | 2007-10-24 | 浙江大学 | Fruit quality damage-free detection method and system based on multiple spectral imaging technique |
CN105787924A (en) * | 2016-02-01 | 2016-07-20 | 首都医科大学 | Method for measuring diameter of maximum choroid blood vessel based on image segmentation |
CN105891229A (en) * | 2014-09-05 | 2016-08-24 | 熊菊莲 | Method for determining characteristic wavelength for spectral image analysis and detection of surfaces of fruits |
CN106023158A (en) * | 2016-05-10 | 2016-10-12 | 浙江科技学院 | SD-OCT-image-based nacre layer defect identification method for fresh water non-nucleated pearl |
CN106332713A (en) * | 2016-08-16 | 2017-01-18 | 浙江科技学院 | Method for identifying early-phase bruise of loquat through SD-OCT image |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9737205B2 (en) * | 2013-07-31 | 2017-08-22 | The Board Of Trustees Of The Leland Stanford Junior University | Method and system for evaluating progression of age-related macular degeneration |
-
2017
- 2017-02-09 CN CN201710071158.1A patent/CN106780347B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101059452A (en) * | 2007-05-29 | 2007-10-24 | 浙江大学 | Fruit quality damage-free detection method and system based on multiple spectral imaging technique |
CN105891229A (en) * | 2014-09-05 | 2016-08-24 | 熊菊莲 | Method for determining characteristic wavelength for spectral image analysis and detection of surfaces of fruits |
CN105787924A (en) * | 2016-02-01 | 2016-07-20 | 首都医科大学 | Method for measuring diameter of maximum choroid blood vessel based on image segmentation |
CN106023158A (en) * | 2016-05-10 | 2016-10-12 | 浙江科技学院 | SD-OCT-image-based nacre layer defect identification method for fresh water non-nucleated pearl |
CN106332713A (en) * | 2016-08-16 | 2017-01-18 | 浙江科技学院 | Method for identifying early-phase bruise of loquat through SD-OCT image |
Also Published As
Publication number | Publication date |
---|---|
CN106780347A (en) | 2017-05-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106780347B (en) | Early loquat bruise identification method based on OCT image processing | |
CN114549522B (en) | Textile quality detection method based on target detection | |
CN106780460B (en) | A kind of Lung neoplasm automatic checkout system for chest CT images | |
CN109978822B (en) | Banana maturity judging modeling method and judging method based on machine vision | |
CN109255757B (en) | Method for segmenting fruit stem region of grape bunch naturally placed by machine vision | |
CN102682305B (en) | Automatic screening system and automatic screening method using thin-prep cytology test | |
Pandey et al. | Image processing and machine learning for automated fruit grading system: A technical review | |
Pujari et al. | Grading and classification of anthracnose fungal disease of fruits based on statistical texture features | |
CN114419025A (en) | Fiberboard quality evaluation method based on image processing | |
CN106023158B (en) | The fresh water pipless pearl pearly layer defect identification method of SD-OCT images | |
CN114723704B (en) | Textile quality evaluation method based on image processing | |
CN110082298B (en) | Hyperspectral image-based wheat variety gibberellic disease comprehensive resistance identification method | |
CN115018838B (en) | Method for identifying pitting defects on surface of oxidized steel pipe material | |
CN101510262A (en) | Automatic measurement method for separated-out particles in steel and morphology classification method thereof | |
CN103394472B (en) | A kind of greening potato based on machine vision detects stage division | |
AU2020103215A4 (en) | Efficient fungi disease detection and grading for leafy vegetables using optimized image processing techniques | |
CN109239073A (en) | A kind of detection method of surface flaw for body of a motor car | |
CN112464942A (en) | Computer vision-based overlapped tobacco leaf intelligent grading method | |
CN112288760B (en) | Adherent cell image screening method and system and cell image analysis method | |
CN109584253A (en) | Oil liquid abrasive grain image partition method | |
Kumari et al. | Performance analysis of support vector machine in defective and non defective mangoes classification | |
Yro et al. | Cocoa beans fermentation degree assessment for quality control using machine vision and multiclass svm classifier | |
Qiaohua et al. | Grape size detection and online gradation based on machine vision | |
CN106780427A (en) | A kind of bergamot pear bruise discrimination method based on OCT image | |
Devi et al. | Machine vision applications to locate fruits, detect defects and remove noise: a review |
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 |