CN108305270B - Storage grain insect counting system and method based on mobile phone photographing - Google Patents
Storage grain insect counting system and method based on mobile phone photographing Download PDFInfo
- Publication number
- CN108305270B CN108305270B CN201810226464.2A CN201810226464A CN108305270B CN 108305270 B CN108305270 B CN 108305270B CN 201810226464 A CN201810226464 A CN 201810226464A CN 108305270 B CN108305270 B CN 108305270B
- Authority
- CN
- China
- Prior art keywords
- image
- pixel point
- pixel
- grain
- value
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration by the use of histogram techniques
-
- 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
- G06T2207/10024—Color image
-
- 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
- G06T2207/30242—Counting objects in image
Abstract
A system and a method for counting stored grain insects based on mobile phone photographing sequentially comprise the following steps: step (1): acquiring an image; step (2): carrying out color image graying on the obtained image to obtain a grayed image; and (3): carrying out image sliding window binarization processing on the grayscale image, and assigning the value of each pixel point in the image to be 0 or 255; and (4): performing image degradation on the image obtained in the step (3); and (5): and (5) counting the stored grain insects according to the image obtained in the step (4). Compared with the prior art, the method can solve the problem that the accuracy of the statistical result is reduced due to uneven image brightness, and the method for selecting the distribution interval of the grain insects by adopting histogram statistics effectively improves the accuracy of the grain insect number statistics.
Description
Technical Field
The invention belongs to the field of counting of grain insects, and particularly relates to a system and a method for counting stored grain insects based on mobile phone photographing.
Background
In the comprehensive control process of stored grain insects, the quantity of the stored grain insects is controlled within the range of damaging the stored grains, so that the serious loss of the stored grains caused by excessive quantity of the insects is avoided, unnecessary waste caused by excessive insect pest control is avoided, the pollution to the grains and the environment is aggravated, and the timely and accurate control of the stored grain insect pest information is very important.
The image processing technology is used for realizing the correct identification and number statistics of the stored grain insects, and is one of the cross research directions with vitality in the comprehensive control of the stored grain insects in recent years. In recent years, methods for counting early grain storage insect pests by using image processing appear, mainly counting according to morphological characteristics of grain insect objects, counting based on gray level image binarization of grain insects and pixel point analysis and the like, and the feasibility and effectiveness of stored grain insect information monitoring based on image processing are shown, but the methods have a certain improvement space in accuracy when counting tiny grain insects, and the problems that the cost of an image acquisition and monitoring system is high, the cost of the grain insect monitoring system is too high when a lot of points are measured in a grain depot, real-time detection cannot be realized and the like exist.
Disclosure of Invention
The invention aims to provide a system and a method for counting stored grain insects based on mobile phone photographing, which are convenient to use and good in using effect.
In order to solve the technical problems, the invention provides the following technical scheme: a grain insect counting system for storage based on mobile phone photographing comprises an image acquisition module and an image processing module;
the image acquisition module transmits acquired image information to the image processing module for processing, and the image processing module identifies and counts the grain insects.
The image acquisition module is a camera.
The system also comprises an image selection module, wherein the image acquisition module transmits the acquired image information to the image selection module, and the image selection module transmits the selected image to the image processing module for processing.
A stored grain insect counting method based on mobile phone photographing by using the system sequentially comprises the following steps:
step (1): acquiring an image;
step (2): carrying out color image graying on the obtained image to obtain a grayed image;
and (3): carrying out image sliding window binarization processing on the grayscale image, and assigning the value of each pixel point in the image to be 0 or 255;
and (4): performing image degradation on the image obtained in the step (3);
and (5): counting the stored grain insects according to the image obtained in the step (4);
the counting method comprises the following steps:
1) Searching connected domains in the image, wherein the number of the connected domains is M;
2) Calculating the number of pixel points in each connected domain, and calculating the ratio of each connected domain with the same number of pixel points in the total connected domain according to a formula (2);
Wherein the content of the first and second substances,M y is provided withyThe total number of connected domains of each pixel point;W y is provided withyThe ratio of the connected domain of each pixel point to the total connected domain;
3) Listing a histogram by taking the number of pixel points in a connected domain as an abscissa and the ratio of the connected domains with the same number of pixel points in the total connected domain as an ordinate;
4) According to normal distribution, calculating the closest interval between the distribution interval and 95.4 percent in the histogram, and taking the interval as the value range of the connected domain of the grain insects; eliminating the connected domain outside the range;
5) And finally, according to the number of the pixel points in each communication domain in the nearest interval, each pixel point is 1 stored grain insect, and the count of the stored grain insects is solved.
And (3) selecting an image range after the image is acquired in the step (1), and transmitting the image in the selected range to the step (2) for processing.
The specific method for performing image sliding window binarization processing on the grayscale image in the step (3) is as follows:
(1) Dividing the image into N basic units, wherein the size of the basic units is N multiplied by N pixel points;
(2) Calculating a threshold value of a pixel point in a basic unit according to a formula (1);
Wherein the content of the first and second substances,Xis a gray threshold value in a basic unit;x ij is as followsiGo to the firstjGray values of pixel points of the columns;
(3) Reassigning the gray value of each pixel point in the basic unit;
wherein, the first and the second end of the pipe are connected with each other,
to be second after reassignmentiGo to the firstjThe gray values of the pixel points of the columns.
The basic unit is a square matrix of 3 x 3 pixel sizes.
Step (2): the method for carrying out color image graying on the acquired image to obtain a grayed image comprises the following steps: and converting each pixel point of the color image into a numerical value of (0 to 255).
After the step (2), stretching the grayed image, wherein the stretching method comprises the following steps: let us note thatpThe gray scale value of each pixel point isH p The pixel point values of the stretched image are obtained according to equation (3):
Wherein the content of the first and second substances,H p is as followspGraying values of the pixel points;
In the counting method in step (5), the method for finding connected domains in the image in step 1) is as follows: extracting pixel regions which are adjacent to each other and have a pixel value of '255', namely, searching a pixel point with the pixel value of '255' from a first pixel point, then using the pixel point as a center to inquire whether eight pixel points of the pixel point are all '255' or not, and using the pixel point as the center to inquire whether eight pixel points of the pixel point are all '255' or not until a whole closed connected domain is found, and removing the points.
Through the technical scheme, the invention has the beneficial effects that: compared with the prior art, the method can solve the problem that the accuracy of the statistical result is reduced due to uneven image brightness, and the method for selecting the distribution interval of the stored grain insects by adopting histogram statistics effectively improves the accuracy of the grain insect number statistics.
Drawings
FIG. 1 is a schematic view of the structure of the present invention;
FIG. 2 is an original image sample 1;
FIG. 3 is an original image sample 2;
fig. 4 is an original image sample 3;
fig. 5 is a binarization image processing result using the overall average gray level as a threshold value for an original image sample 1;
fig. 6 is a binarization image processing result using the overall average gray level as a threshold value for the original image sample 2;
fig. 7 is a binarization image processing result using the overall average gray level as a threshold value for the original image sample 3;
fig. 8 is an image processing result of the sliding window binarization method applied to the original sample 1;
fig. 9 is an image processing result of the sliding window binarization method applied to the original sample 2;
fig. 10 shows the result of image processing by the sliding window binarization method for the original sample 3.
Detailed Description
A grain insect counting system for storage based on mobile phone photographing is shown in figure 1 and comprises an image acquisition module, an image selection module and an image processing module;
the image acquisition module transmits acquired image information to the image selection module, the image selection module transmits the selected image to the image processing module for processing, and the image processing module identifies and counts the grain insects.
The image acquisition module is a camera.
When the mobile phone camera shooting system is used, an image is collected through the camera, and the collected image is used for selecting a range by the image selection module, wherein the image selection module is mature in the prior art, and is widely applied to the existing mobile phone camera shooting system, and the function of the image selection module is realized if the existing mobile phone selects a certain range for shot pictures.
The invention also discloses a method for counting the stored grain insects based on mobile phone photographing by using the system, which sequentially comprises the following steps:
step (1): acquiring an image; specifically, an image is acquired through a camera.
In order to improve the counting accuracy, after the image is acquired in the step (1), an image range needs to be selected, and the image in the selected range is transmitted to the step (2) to be processed. Specifically, the image selection range is realized through an image selection module, and the realization method is mature prior art.
Step (2): carrying out color image graying on the obtained image to obtain a grayed image;
the specific method comprises the following steps: converting each pixel point of the color image into a numerical value of (0 to 255), which is a mature prior art.
After the step (2), stretching the grayed image, wherein the stretching method comprises the following steps: let us note thatpThe gray scale value of each pixel point isH p Obtaining pixel point values of the stretched image according to formula (3):
Wherein the content of the first and second substances,H p is as followspGraying values of the pixel points;
And (3): and performing image sliding window binarization processing on the stretched gray-scale image, and assigning the value of each pixel point in the image to be 0 or 255.
The specific method for carrying out image sliding window binarization processing on the gray level image comprises the following steps:
(1) Dividing an image into N basic units, wherein the size of each basic unit is N multiplied by N pixel points; in this embodiment, the basic unit is a square matrix with 3 × 3 pixel sizes.
(2) Calculating a threshold value of a pixel point in a basic unit according to a formula (1);
Wherein the content of the first and second substances,Xis a gray threshold value in a basic unit;x ij is as followsiGo to the firstjGray values of pixel points of the columns;
(3) Carrying out reassignment on the gray value of each pixel point in the basic unit;
wherein the content of the first and second substances,
to be assigned again the firstiGo to the firstjThe gray values of the pixel points of the columns.
Through choosing for use sliding window binarization processing, avoided because of there being the process of shooing exposure not enough, the inhomogeneous phenomenon of image brightness distribution leads to grey scale distribution inhomogeneous, and then influences the selection of whole image binarization threshold value, causes binary image distortion, has great influence and the problem that exists to later stage grain worm discernment and count, the maintenance image quality that can be better.
And (4): and (4) performing image degradation on the image obtained in the step (3), wherein the image degradation is mature prior art and can be realized by adopting the prior method.
By degrading the image, the data volume of the image is reduced, and the real-time performance of detection and identification is ensured.
And (5): counting stored grain insects according to the image obtained in the step (4);
the counting method comprises the following steps:
1) Searching connected domains in the image, wherein the number of the connected domains is M; the method for searching the connected domain in the image comprises the following steps: extracting pixel regions with pixel values of '255' which are adjacent to each other, namely, searching a pixel point with the pixel value of '255' from a first pixel point, inquiring whether eight pixel points of the pixel point are all '255' or not by taking the pixel point as a center, and pushing the pixel point until a whole closed connected domain is found, and clearing the pixel points to prevent the repeated technology.
2) Calculating the number of pixel points in each connected domain, and calculating the ratio of each connected domain with the same number of pixel points in the total connected domain according to a formula (2);
Wherein the content of the first and second substances,M y to be provided withyThe total number of connected domains of each pixel point;W y to be provided withyThe ratio of the connected domain of each pixel point to the total connected domain;
3) Listing a histogram by taking the number of pixel points in a connected domain as an abscissa and the ratio of the connected domains with the same number of pixel points in the total connected domain as an ordinate;
4) According to normal distribution, calculating an interval with a distribution interval closest to 95.4% in the histogram, and taking the interval as a value range of a connected domain of the grain insects; rejecting connected domains outside the range;
5) And finally, according to the number of the pixel points in each communication domain in the nearest interval, each pixel point is 1 stored grain insect, and the count of the stored grain insects is solved.
As shown in the following table 1, the number of pixels of each connected domain of a histogram of a certain experiment approaches to normal distribution, a 95.4% numerical value of a distribution interval of the histogram of the certain experiment, which is closest to a true value, is selected as a value range of the connected domain of the grain insect, the connected domains outside the range are ignored as interference items, the connected domains 2 with the pixel numbers of 18 to 24 are taken as the closest interval, and the connected domains 1 and 3 are removed. Experimental results prove that the method reduces the influence of noise such as randomness of lens focal length for photographing by the mobile phone on the accuracy of counting results, and effectively improves the accuracy of counting the number of the system grain insects.
TABLE 1 histogram statistics of connected components tested in a given experiment
| Connected domain types | Number of occupied pixel points | Number of similar connected domains | Specific gravity (/ number of connected domains) |
| Connected domain 1 | Less than 18 | 6 | 5.08% |
| Connected domain 2 | 18-24 | 110 | 94．23% |
| Connected domain 3 | Greater than 24 | 2 | 1.69% |
And (3) effect analysis:
three samples of original images containing different intensities and densities were selected as shown in fig. 2, 3 and 4. The results of the binarized image processing using the whole average gradation as the threshold are shown in fig. 5, 6 and 7, respectively. The results of image processing using the sliding window binarization method proposed herein are shown in fig. 8, 9 and 10, respectively.
The results of fig. 2 to 10 show that the contrast between the grain insect and the background is more obvious after the image processing by the sliding window binarization method. The experimental results are consistent with theoretical analysis.
In the aspect of counting the number of the grain insects: the results of comparing the statistical accuracy of the histogram statistical method and the conventional connected component algorithm are shown in table 2, using fig. 10 as the test sample.
TABLE 3 statistical accuracy of the number of grain insects by different methods
| Statistical method | Number of grain insects | Accuracy (actual number of grain insects 60) |
| Connected domain statistical method with fixed threshold value | 72 | 80% |
| Histogram statistical method | 57 | 95% |
As can be seen from the data results shown in Table 3, the histogram statistical algorithm provided by the invention effectively improves the accuracy of the grain insect statistics.
Compared with the prior art, the method can solve the problem that the accuracy of the statistical result is reduced due to uneven image brightness, and the method for selecting the distribution interval of the stored grain insects by adopting histogram statistics effectively improves the accuracy of the grain insect number statistics.
Claims (7)
1. A grain insect storage counting method based on mobile phone photographing is characterized in that: the method comprises the following steps in sequence:
step (1): acquiring an image;
step (2): carrying out color image graying on the obtained image to obtain a grayed image;
after the step (2), stretching the grayscale image, wherein the stretching method comprises the following steps: recording the gray scale value of the p-th pixel point as HpPixel point values of the stretched image are obtained according to the following formula:
H′p＝Hp×α
wherein HpThe gray scale value of the p-th pixel point is obtained;
H′pthe pixel point value of the p-th pixel point after the image is stretched;
alpha is a set value;
and (3): carrying out image sliding window binarization processing on the grayscale image, and assigning the value of each pixel point in the image to be 0 or 255;
the specific method for performing image sliding window binarization processing on the grayscale image in the step (3) is as follows:
(1) Dividing the image into N basic units, wherein the size of the basic units is N multiplied by N pixel points;
(2) Calculating a threshold value of a pixel point in a basic unit according to the following formula;
wherein X is a gray threshold value in a basic unit; x is the number ofijThe gray value of the pixel point of the ith row and the jth column is obtained;
(3) Carrying out reassignment on the gray value of each pixel point in the basic unit;
X′ij＝0 xij＜X
X′ij＝255 xij≥X
wherein, X'ijThe gray value of the pixel point of the ith row and the jth column after the reassignment is carried out;
and (4): performing image degradation on the image obtained in the step (3);
and (5): counting stored grain insects according to the image obtained in the step (4);
the counting method comprises the following steps:
1) Searching connected domains in the image, wherein the number of the connected domains is M;
2) Calculating the number of pixel points in each connected domain, and calculating the ratio of each connected domain with the same number of pixel points in the total connected domain according to the following formula;
wherein M isyThe total number of connected domains with y pixel points; w is a group ofyThe ratio of the connected domain with y pixel points to the total connected domain is calculated;
3) Listing a histogram by taking the number of pixel points in a connected domain as an abscissa and the ratio of the connected domains with the same number of pixel points in the total connected domain as an ordinate;
4) According to normal distribution, calculating an interval with a distribution interval closest to 95.4% in the histogram, and taking the interval as a value range of a connected domain of the grain insects; eliminating the connected domain outside the range;
5) According to the number of pixel points in each communication domain in the nearest interval, each pixel point is 1 stored grain insect, and finally the count of the stored grain insects is calculated;
the storage grain insect counting method is realized based on the following storage grain insect technology system, wherein the system comprises an image acquisition module and an image processing module;
the image acquisition module transmits acquired image information to the image processing module for processing, and the image processing module identifies and counts the grain insects.
2. The grain insect warehousing counting method based on mobile phone photographing as claimed in claim 1, wherein the grain insect warehousing counting method comprises the following steps: the image acquisition module is a camera.
3. The grain insect warehousing counting method based on mobile phone photographing as claimed in claim 2, characterized in that: the system also comprises an image selection module, wherein the image acquisition module transmits the acquired image information to the image selection module, and the image selection module transmits the selected image to the image processing module for processing.
4. The grain insect warehousing counting method based on mobile phone photographing as claimed in claim 1, wherein the grain insect warehousing counting method comprises the following steps: and (3) selecting an image range after the image is acquired in the step (1), and transmitting the image in the selected range to the step (2) for processing.
5. The warehousing grain insect counting method based on mobile phone photographing as claimed in claim 1, characterized in that: the basic unit is a square matrix of 3 x 3 pixel sizes.
6. The warehousing grain insect counting method based on mobile phone photographing as claimed in claim 1, characterized in that: step (2): the method for carrying out color image graying on the acquired image to obtain a grayed image comprises the following steps: and converting each pixel point of the color image into a numerical value of 0-255.
7. The grain insect warehousing counting method based on mobile phone photographing as claimed in claim 1, wherein the grain insect warehousing counting method comprises the following steps:
in the counting method in step (5), the method for finding connected domains in the image in step 1) is as follows: extracting pixel regions which are adjacent to each other and have a pixel value of '255', namely, searching a pixel point with the pixel value of '255' from a first pixel point, then using the pixel point as a center to inquire whether eight pixel points of the pixel point are all '255' or not, and using the pixel point as the center to inquire whether eight pixel points of the pixel point are all '255' or not until a whole closed connected domain is found, and removing the points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810226464.2A CN108305270B (en) | 2018-03-19 | 2018-03-19 | Storage grain insect counting system and method based on mobile phone photographing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810226464.2A CN108305270B (en) | 2018-03-19 | 2018-03-19 | Storage grain insect counting system and method based on mobile phone photographing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108305270A CN108305270A (en) | 2018-07-20 |
| CN108305270B true CN108305270B (en) | 2022-11-01 |
Family
ID=62850297
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810226464.2A Active CN108305270B (en) | 2018-03-19 | 2018-03-19 | Storage grain insect counting system and method based on mobile phone photographing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108305270B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109272103A (en) * | 2018-08-01 | 2019-01-25 | 河南工业大学 | The method that a kind of pair of number of pest carries out express statistic |
| CN109872301B (en) * | 2018-12-26 | 2022-07-15 | 浙江清华长三角研究院 | Color image preprocessing method for rice pest and disease identification and counting |
| CN111507959A (en) * | 2020-04-15 | 2020-08-07 | 江苏科恒环境科技有限公司 | Mushroom head quantity statistical system based on image recognition |
| CN111639572A (en) * | 2020-05-22 | 2020-09-08 | 上海交通大学 | Method for estimating efficient flower volume of vine month season |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101976350A (en) * | 2010-10-20 | 2011-02-16 | 中国农业大学 | Grain storage pest detection and identification method based on video analytics and system thereof |
| CN106815819A (en) * | 2017-01-24 | 2017-06-09 | 河南工业大学 | Many strategy grain worm visible detection methods |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7864365B2 (en) * | 2006-06-15 | 2011-01-04 | Sharp Laboratories Of America, Inc. | Methods and systems for segmenting a digital image into regions |
| CN100512374C (en) * | 2007-12-05 | 2009-07-08 | 北京航空航天大学 | A method for image edge detection based on threshold sectioning |
| CN103246872B (en) * | 2013-04-28 | 2016-02-10 | 北京农业智能装备技术研究中心 | A kind of wide spectrum insect pest situation automatic telemetry method based on computer vision technique |
| CN104700417A (en) * | 2015-01-19 | 2015-06-10 | 湖南大学 | Computer image based automatic identification method of timber knot flaws |
| CN104796591A (en) * | 2015-05-04 | 2015-07-22 | 武向文 | Pest amount collecting and processing system and method |
| CN104866897A (en) * | 2015-06-12 | 2015-08-26 | 合肥市徽腾网络科技有限公司 | Aphid situation investigation method and device |
| CN105374015A (en) * | 2015-10-27 | 2016-03-02 | 湖北工业大学 | Binary method for low-quality document image based on local contract and estimation of stroke width |
| CN107545557A (en) * | 2016-06-23 | 2018-01-05 | 爱威科技股份有限公司 | Egg detecting method and device in excrement image |
| CN106447020B (en) * | 2016-09-13 | 2018-11-23 | 上海海事大学 | A kind of intelligence method for counting colonies |
| CN106483129B (en) * | 2016-09-23 | 2019-06-21 | 电子科技大学 | A method of the leukorrhea trichomonad based on motion estimate detects automatically |
| CN107644200A (en) * | 2017-08-30 | 2018-01-30 | 中国农业大学 | Pest and disease damage gradient of infection detection method and system based on Android system |
| CN107730470A (en) * | 2017-10-18 | 2018-02-23 | 四川理工学院 | A kind of multiple dimensioned improvement Retinex image enchancing methods blocked with histogram of explicit expression |
-
2018
- 2018-03-19 CN CN201810226464.2A patent/CN108305270B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101976350A (en) * | 2010-10-20 | 2011-02-16 | 中国农业大学 | Grain storage pest detection and identification method based on video analytics and system thereof |
| CN106815819A (en) * | 2017-01-24 | 2017-06-09 | 河南工业大学 | Many strategy grain worm visible detection methods |
Non-Patent Citations (1)
| Title |
|---|
| Research on the Rice Counting Method Based on Connected Component Labeling;Huang Jing 等;《2014 Sixth International Conference on Measuring Technology and Mechatronics Automation》;20140421;第552-555页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108305270A (en) | 2018-07-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108305270B (en) | Storage grain insect counting system and method based on mobile phone photographing | |
| WO2020224458A1 (en) | Method for detecting corona discharge employing image processing | |
| CN109325550B (en) | No-reference image quality evaluation method based on image entropy | |
| CN111915572B (en) | Adaptive gear pitting quantitative detection system and method based on deep learning | |
| CN109903282B (en) | Cell counting method, system, device and storage medium | |
| CN107038416B (en) | Pedestrian detection method based on binary image improved HOG characteristics | |
| CN107330403B (en) | Yak counting method based on video data | |
| CN108765406A (en) | A kind of snow mountain detection method based on infrared remote sensing image | |
| CN114169381A (en) | Image annotation method and device, terminal equipment and storage medium | |
| CN110751667B (en) | Method for detecting infrared dim and small targets under complex background based on human visual system | |
| CN111353968B (en) | Infrared image quality evaluation method based on blind pixel detection and analysis | |
| CN109919843B (en) | Skin image texture evaluation method and system based on adaptive quartering method | |
| CN106156728B (en) | HYPERSPECTRAL IMAGERY dimension reduction method and system based on spectral space decomposition and noise contribution analysis | |
| CN111027564A (en) | Low-illumination imaging license plate recognition method and device based on deep learning integration | |
| Kapoor et al. | Capturing banding in images: Database construction and objective assessment | |
| CN108230334B (en) | High-concentration wind-blown sand image segmentation method based on gray threshold | |
| CN115190311B (en) | Security monitoring video compression storage method | |
| Dannemiller et al. | A new method for the segmentation of algae images using retinex and support vector machine | |
| CN203970354U (en) | A kind of Tongue analytical system based on mobile terminal | |
| CN114550069B (en) | Piglet nipple counting method based on deep learning | |
| CN116311543A (en) | Handwriting analysis method and system based on image recognition technology | |
| CN107341456B (en) | Weather sunny and cloudy classification method based on single outdoor color image | |
| CN116203001A (en) | Aflatoxin B1 nondestructive testing method and device | |
| CN112668405B (en) | Method for accurately extracting quantity of soil bacteria | |
| CN107623841A (en) | A kind of good vehicle-mounted monitoring system of monitoring effect |
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 |