CN111968115B - Method and system for detecting orthopedic consumables based on rasterization image processing method - Google Patents
Method and system for detecting orthopedic consumables based on rasterization image processing method Download PDFInfo
- Publication number
- CN111968115B CN111968115B CN202010942091.6A CN202010942091A CN111968115B CN 111968115 B CN111968115 B CN 111968115B CN 202010942091 A CN202010942091 A CN 202010942091A CN 111968115 B CN111968115 B CN 111968115B
- Authority
- CN
- China
- Prior art keywords
- image
- orthopedic
- picture
- consumable
- bone nail
- 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
- 230000000399 orthopedic effect Effects 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000003672 processing method Methods 0.000 title claims abstract description 13
- 238000001514 detection method Methods 0.000 claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 9
- 210000000988 bone and bone Anatomy 0.000 claims description 56
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 9
- 239000000463 material Substances 0.000 claims description 9
- 238000003708 edge detection Methods 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 3
- 238000003702 image correction Methods 0.000 claims description 2
- 230000011218 segmentation Effects 0.000 claims description 2
- 238000000638 solvent extraction Methods 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims description 2
- 230000008859 change Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000000474 nursing effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
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
- G06T7/001—Industrial image inspection using an image reference approach
-
- 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
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
Abstract
The invention belongs to the technical field of medical image and image processing, and relates to an orthopedic consumable detection method and system based on a rasterization image processing method. The method has no strict requirements on the quantity and quality of original data images, and the orthopedic consumable outer box and the orthopedic consumable are detected in stages by a stage detection method, so that the detection accuracy is greatly improved. The type of the orthopedic consumables outer box is detected only, the corresponding orthopedic consumables are detected according to the type of the outer box, and the accuracy is improved by 50% -60%. The method for detecting the target under the condition of only a small amount of data is provided, when the accurate marking data amount is insufficient, the method of detecting the orthopedic consumable outer box and then detecting the orthopedic consumable is adopted, and the method is superior to the single method of detecting the orthopedic consumable only. The invention can have higher accuracy under the condition of less data sets.
Description
Technical Field
The invention belongs to the technical field of medical images and image processing, relates to a system for positioning and identifying nails in an orthopedic consumable box in a medical image based on an image identification technology, and particularly relates to a method and a system for detecting orthopedic consumables based on a rasterization image processing method.
Background
Object detection is to find out the object of interest in the picture and to determine its location and category. The target detection technology is developed to date, and there are two main types of methods: traditional classical target detection methods and artificial intelligence related deep learning methods.
The traditional target detection method mainly comprises the following three steps: firstly, selecting a region, secondly, extracting features, and thirdly, classifying. The following technical problems mainly exist in the current traditional target detection technology:
in the region selection process, since the target may appear at any position of the image, and the size and aspect ratio of the target cannot be determined, a Sliding Window (Sliding Window) strategy is generally adopted to traverse the whole image. The disadvantages of this method are more pronounced: the whole image is traversed, a large number of overlapped areas are generated, so that redundant calculation is brought, and the calculation speed of subsequent feature extraction and classification is seriously influenced. Therefore, in order to accelerate the calculation efficiency, it is necessary to reduce redundant calculation while ensuring the calculation accuracy, and the prior art has no research report specially aiming at this aspect.
In feature extraction, SIFT, HOG features are generally used, but it is difficult to accurately describe an image by extracted features due to the diversity of target forms, the diversity of illumination variations, the diversity of backgrounds, and the like. Therefore, a specific feature extraction method needs to be found for the bone nail detection problem, so as to improve the accuracy of feature extraction.
Among the classifiers, SVM, Adaboost classifier, and the like are mainly used. These methods have certain robustness, but the selection of control parameters thereof has no uniform standard, so that the proper classifier parameters need to be selected for the bone nail detection problem.
Disclosure of Invention
The invention provides a novel orthopedic consumable detection method based on a rasterization image processing method aiming at the problems in the traditional target detection technology.
In order to achieve the purpose, the invention is realized by adopting the following technical scheme:
an orthopedic consumable detection method based on a rasterization image processing method comprises the following steps:
step 1: library of standard matching templates
Acquiring image data of the orthopedic consumable for training, performing operations such as image denoising and image enhancement, and improving the quality of images. And storing all image data into a folder for program operation, taking the image data as a standard matching template, and calibrating the category of each picture.
Step 2: to-be-identified bone nail box classification
Inputting a bone nail box picture to be identified, carrying out category judgment by using a K neighbor algorithm, and measuring the distance between the bone nail box picture to be identified and a template picture by using the Euclidean distance in the K neighbor algorithm so as to determine the classification of the pictures. The formula used is as follows:
wherein L is the Euclidean distance between the picture and the template,
nis the number of pixels in the picture,
xiis a pixel value on a picture
yiAre the pixel values on the template.
And obtaining a K value with a better effect according to a plurality of experimental results through the calculated Euclidean distance.
And step 3: region of interest extraction
And (3) using Hough circle detection to classify the pictures, calculating the direction of the bone nail box according to the areas of the circle aggregation, dividing the areas where the bone nails are placed, and cutting the areas.
And 4, step 4: image correction
And (4) correcting the area divided in the step (3) by adopting perspective transformation, and further obtaining a standard area for placing bone nails. At the moment, the area for placing the bone nails can rotate and deform the pictures according to the horizontal and vertical arrangement of the positions of the bone nails.
And 5: image edge processing
Calculating the edge of the region of interest by using a Canny edge detection algorithm, wherein the picture is a binarization picture, and the edge characteristics of an object in the region of interest are displayed on the picture;
step 6: rasterization processing
Calculating the sum of all the same horizontal coordinate pixels of the picture in the step 5 by using a mathematical statistics method to obtain the line division of the bone nail positions; and calculating the sum of all the same column coordinate pixels to obtain column division of the bone nail positions, thereby dividing the rows and columns of the bone nail positions. This step is a core step in the overall detection method. Therefore, the accuracy of system detection is ensured. The result of the grid division directly affects the final result. Rasterization is to divide all possible positions where bone nails can be placed, and then to determine the positions.
And 7: grid bone nail placement detection
Performing convolution calculation on the grid divided in the step 6 by using the all-1 convolution kernel with the same size as the grid shape, and judging whether bone nails exist in the grid according to a calculated experiment threshold value.
And 8: grid position calibration and quantity statistics
Calibrating the position according to the grid in the step 6 and the result calculated in the step 7, calibrating the grid with the bone nails, and counting the number of the bone nails in the picture
The orthopedic consumable detection system based on the rasterization image processing method comprises the following steps:
a pre-processing module configured to: acquiring image data of the orthopedic consumable for training, performing image denoising and image enhancement operation, and improving the quality of images. The input is as follows: original images of orthopedic consumables; the output is: and (4) preprocessing the orthopedic consumable material image.
A bone staple cartridge sorting module configured to: and (4) carrying out class judgment on the bone nail box by using a K neighbor classifier, and judging which type the bone nail box belongs to. The input is as follows: preprocessing an orthopedic consumable image; the output is: a bone nail cartridge category.
A region of interest extraction module configured to: and identifying the direction of the bone nail box so as to judge which range is the place for placing the bone nails, and cutting the range. The input is as follows: preprocessing an orthopedic consumable image and a bone nail box type identification result; the output is: region of interest of an orthopedic consumable image.
An image rectification module configured to: and correcting the picture shot by the camera by adopting perspective transformation so as to obtain a standard bone nail box picture. The input is as follows: a region of interest of an orthopedic consumable image; the output is: and (4) the region of interest of the corrected standard orthopedic consumable image.
An edge detection module configured to: and performing marginalization processing on the image, and detecting all edges of the image. The input is as follows: the corrected interested area of the standard orthopedic consumable image; the output is: an edge image of the region of interest.
A statistics module configured to: and carrying out pixel point statistics on the horizontal and vertical coordinates of the edge-processed binary image. Thereby distinguishing the rows and columns of bone screws. The input is as follows: an edge image of the region of interest; the output is: and statistics of the horizontal and vertical coordinate directions.
A rasterization partitioning module configured to: and performing rasterization segmentation on the edge picture, and completely dividing the place where the bone nails can be placed. The input is as follows: the edge image of the region of interest and the statistical data of the horizontal and vertical coordinates; the output is: the rasterized image.
A rasterization detection module configured to: and performing relevant detection on the divided grids by using the target template so as to judge which grid contains the nails and give the types of the nails. Inputting the image into a rasterized image; the output is the convolution calculation data of the grid.
A rasterization statistics module configured to: and marking places with nails, and counting the number of the nails. The input is as follows: convolution calculation data of the grid; and outputting the result after the statistical calculation and the marked picture.
The detailed connection relationship of the modules is shown in the attached figure 1 of the specification.
Compared with the prior art, the invention has the advantages and positive effects that:
1. the method provided by the invention has no strict requirements on the quantity and quality of the original data image, and the orthopedic consumable outer box and the orthopedic consumable are detected in stages by a stage detection method, so that the detection accuracy is greatly improved.
2. The invention only needs to detect the type of the orthopedic consumable outer box firstly, and detects the corresponding orthopedic consumable according to the type of the outer box.
3. The invention provides a method for detecting a target under the condition of only a small amount of data, and when the accurate marking data amount is insufficient, the method for detecting the orthopedic consumable material outer box and then the orthopedic consumable material is adopted, which is superior to the single method for detecting the orthopedic consumable material.
4. The rasterization detection method provided by the invention has higher accuracy under the condition of less data sets.
Drawings
Fig. 1 is a schematic diagram of connection relationship between modules in the system.
Fig. 2 is an original image.
Fig. 3 is a circularly labeled image.
Fig. 4 is a diagram of a rough cropping area.
Fig. 5 is a graph divided in units of rows.
Fig. 6 is a perspective converted image.
Fig. 7 is a Canny edge processed image.
Fig. 8 is a left lateral statistical and a right longitudinal statistical plot.
Fig. 9 is a rasterized image.
Fig. 10 is a diagram of the final recognition result.
Fig. 11 is a bone screw box version.
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application.
Detailed Description
In order that the above objects, features and advantages of the present invention may be more clearly understood, the present invention will be further described with reference to specific embodiments. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and thus the present invention is not limited to the specific embodiments of the present disclosure.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
Interpretation of terms:
1. orthopedic consumables: the medical nursing material is a material frequently used by hospitals in the process of developing medical services, has various types and large application amount, is a material basis for developing medical and nursing work in hospitals, and has high price for part of orthopedic consumables, and the detection and utilization of the orthopedic nursing material have great practical application value.
The K nearest neighbor classification algorithm is a relatively mature method in theory and is one of the simplest machine learning algorithms. The method has the following steps: in the feature space, if most of the K nearest (i.e., nearest neighbors in the feature space) samples in the vicinity of a sample belong to a certain class, the sample also belongs to this class.
3. And (4) Hough circle transformation, which can detect a circle in the gray level image. Three points can determine a circle, and if the three points are used for making circles with all radii, a common intersection point is necessary, and the intersection point is the center of the circle with the three points as the centers. The problem is converted into a circle with the most pixels in solution.
The Canny edge detection algorithm is a multi-stage edge detection algorithm developed by John f Canny in 1986.
First step, pretreatment system
In the preprocessing module, the image is preprocessed, including rotation, gray scale change, marking and other operations, to expand the data set and make the template data set.
Secondly, carrying out class estimation by using a K nearest neighbor algorithm
In the classification module, the simplest Euclidean distance is used for measuring the distance between the picture and the template, so that the classification of the picture is determined. The formula used is as follows:
wherein the content of the first and second substances,Lis the euclidean distance between the picture and the template,
nis the number of pixels in the picture,
xiis a pixel value on a picture
yiAre the pixel values on the template.
According to the calculated Euclidean distance and multiple experimental results, the method can be used for calculating the Euclidean distanceKThe setting of 3 can achieve better results, and the type of the bone nail box to which the picture belongs can be distinguished according to the results.
Third step, region extraction
After the first step of classification, the following operation is continued after the first class of pictures are taken. In the embodiment, the picture is shot by a camera, so that the deformation of the graph is more in accordance with the perspective deformation. Only a part of the picture is used for placing nails. We first need to detect the portion of the nail that is present. The original image input is as in fig. 2.
As can be seen from fig. 2, the area of the picture where the bone pins are placed needs to be identified. First, a circle in the image is detected using a hough circle detection algorithm, as shown in fig. 3.
The part where the nails are not placed in the actual shooting process is a cover, and the round hole of the cover part can deform at the shooting angle, so that the round shape cannot be detected, and the part where the round shape is dense is detected on the picture, namely the part needing to be detected. From the area of circle detection in the picture, the area with nails can be obtained as the theoretical result, and the detected circles are more. A relatively large number of circular regions are selected. This region is the region of interest. As shown in fig. 4.
Fourth step perspective transformation
Because the arrangement of the nails in the selected area is regular, four vertexes of perspective transformation can be more accurately determined according to the circle center position of the circle. We can also find the division of each row according to the arrangement position of the circle. The uppermost circle on the figure can be found. The circle does not need to be found completely, and only a part of the circle is found. Since linear regression can be performed from several centers found, the formula is as follows.
Wherein:ais the slope of the straight line to be calculated;
bis the straight line intercept to be calculated;
Xis the abscissa of the center of the circle;
F（X）is the ordinate of the centre of a circle,
the sum of the distances from the points to the straight line is used, the used method is the same as that in the second step, and the Euclidean distance is used as an optimization target to calculate the values of a and b. So that other points can be found. The circle centers on other rows can be found through translation of the straight line. So that all detected circles are divided per row unit as shown in fig. 5.
Through the division of the rows, the position of the center of the circle can be determined. This allows the upper left (leftmost point in the first row), upper right (rightmost point in the first row), lower left (leftmost point in the fourth row), and lower right (rightmost point in the fourth row) to be found. So that the perspective transformed points are found. The acquired region is then transformed from perspective to a size of 1900 x 750. As shown in fig. 6.
Fifth step, edge detection
And performing edge extraction on the image after perspective transformation for further mathematical statistics. Canny algorithm is used for edge lifting. The resulting edge image is shown in fig. 7.
Sixth step, counting the values
And then, accumulating, calculating and superposing the numerical values on the rows and the columns respectively. The pixel characteristics in the horizontal and vertical directions can be obtained by using one-time matrix multiplication.
Wherein:xiis the pixel value on the corresponding pixel point
nCounting the number of rows or columns and counting the number of different directions, which represents the change
FIs the sum of all pixel values of a row or a column.
The pixel characteristics in the horizontal and vertical directions are obtained through the above calculation. As shown in fig. 8.
The seventh step, the grid division
The position of the circular area can be obtained through counting. Since the pixel value of the area without a circle is 0 after the image is binarized, the area of a row or a column can be distinguished according to the 0 value between the statistical values. The left graph in fig. 8 may divide rows and the right graph may divide columns. By dividing, a rasterized region may be obtained, as shown in fig. 9.
Eighth step, grid classification and calibration
By performing convolution calculation analysis on the regions rasterized in the fourth step, and then according to an empirical threshold, it can be determined which grid has nails and which regions have no nails. The formula is as follows:
wherein: x is a matrix of all pixels on a grid.
onesIs an all-one matrix with the same dimension as X
⨂ is the convolution calculation operator.
Final data from the result of the convolution. The output results are shown in fig. 10.
From a comparison of fig. 10 and 2, it can be seen that all nails have been identified, and therefore this example demonstrates that the method provided by the present invention is very accurate. The types of the bone nail boxes used in the method are shown in fig. 11, and 9 types of the bone nail boxes are used, and the detection accuracy is shown in table 1.
TABLE 1 accuracy statistics of the test
Table 1 shows the types of bone screw cartridges used in the method, but the types of bone screw cartridges are not limited thereto. The accuracy rate of judging whether the bone nail exists at the position of the bone nail in the bone nail box types. Higher accuracy is achieved in the experiment.
The above description is only a preferred embodiment of the present invention, and not intended to limit the present invention in other forms, and any person skilled in the art may apply the above modifications or changes to the equivalent embodiments with equivalent changes, without departing from the technical spirit of the present invention, and any simple modification, equivalent change and change made to the above embodiments according to the technical spirit of the present invention still belong to the protection scope of the technical spirit of the present invention.
Claims (5)
1. An orthopedic consumable detection method based on a rasterization image processing method is characterized by comprising the following steps:
step 1, obtaining pictures of all bone nail boxes, using the pictures as templates, storing the pictures in a file, and then calibrating the classification of each picture;
step 2, carrying out class judgment on the bone nail box by using a K nearest neighbor algorithm, and judging the class attribute of the bone nail box;
step 3, correcting the shot picture by using an image correction algorithm to obtain a standard bone nail box picture;
step 4, identifying the direction of the bone nail box so as to judge the range of the bone nail placement, and cutting the range;
step 5, performing marginalization processing on the cut image, and converting the edge of the image;
step 6, rasterizing the edge picture to divide all places where bone nails can be placed;
step 7, processing the grids divided in the step 6 by using two-dimensional convolution, thereby judging grids containing nails;
step 8, marking places with nails, and counting the number of the nails;
the grid processing in the step 6 uses a mathematical statistics method to calculate the sum of all the same abscissa pixels of the picture in the step 5 to obtain the line division of the bone nail position; and calculating the sum of all the same column coordinate pixels to obtain column division of the bone nail positions, thereby dividing the rows and columns of the bone nail positions.
2. The method for detecting orthopedic consumables based on the rasterized image processing method according to claim 1, characterized in that the formula adopted in step 2 is as follows:
wherein the content of the first and second substances,Lis the euclidean distance between the picture and the template,
nis the number of pixels in the picture,
xiis the value of a pixel on the picture,
yiare the pixel values on the template.
3. The method for detecting the orthopedic consumables based on the rasterized image processing method according to claim 1, wherein Hough circle detection is used in the step 4, and the direction of the bone nail box is calculated according to the area where circles are gathered.
4. The method for detecting orthopedic consumables based on the rasterized image processing method according to claim 1, wherein a Canny edge detection algorithm is used in step 5 to calculate the edge of the region of interest, the picture is a binarized picture, and the edge characteristics of the object in the region are displayed on the picture.
5. The orthopedic consumable detection system for realizing the rasterized image processing method according to claim 1, comprising
A pre-processing module configured to: acquiring image data of orthopedic consumables for training, and performing image denoising and image enhancement operations to improve the quality of images;
a bone staple cartridge sorting module configured to: judging the type of the bone nail box by using a K nearest neighbor classifier, and outputting the type of the bone nail box;
a region of interest extraction module configured to: identifying the direction of the bone nail box so as to judge the range for placing the bone nails, cutting the range and outputting the interested region of the orthopedic consumable image;
an image rectification module configured to: inputting the interested region of the orthopedic consumable image, correcting the picture shot by the camera by adopting perspective transformation to obtain a standard bone nail box picture, and outputting the corrected interested region of the standard orthopedic consumable image;
an edge detection module configured to: performing marginalization processing on the region-of-interest image of the corrected standard orthopedic consumable material image, detecting the edge of the image, and outputting an edge image of the region-of-interest;
a statistics module configured to: carrying out pixel point statistics on horizontal and vertical coordinates on the edge image of the region of interest, and outputting statistical data in the horizontal and vertical coordinate direction;
a rasterization partitioning module configured to: performing rasterization segmentation on the edge image of the region of interest, completely dividing the places where bone nails can be placed, and outputting a rasterized image;
a rasterization detection module configured to: detecting the grids of the rasterized image by using the target template, judging the grids containing the nails, giving the types of the nails, and outputting convolution calculation data of the grids;
a rasterization statistics module configured to: and marking places with nails, and counting the number of the nails.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010942091.6A CN111968115B (en) | 2020-09-09 | 2020-09-09 | Method and system for detecting orthopedic consumables based on rasterization image processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010942091.6A CN111968115B (en) | 2020-09-09 | 2020-09-09 | Method and system for detecting orthopedic consumables based on rasterization image processing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111968115A CN111968115A (en) | 2020-11-20 |
| CN111968115B true CN111968115B (en) | 2021-05-04 |
Family
ID=73392720
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010942091.6A Active CN111968115B (en) | 2020-09-09 | 2020-09-09 | Method and system for detecting orthopedic consumables based on rasterization image processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111968115B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113642406B (en) * | 2021-07-14 | 2023-01-31 | 广州市玄武无线科技股份有限公司 | System, method, device, equipment and storage medium for counting densely-suspended paper sheets |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010057081A1 (en) * | 2008-11-14 | 2010-05-20 | The Scripps Research Institute | Image analysis platform for identifying artifacts in samples and laboratory consumables |
| CN108171269A (en) * | 2018-01-04 | 2018-06-15 | 吴勤旻 | A kind of medical instrument pattern recognition device |
| CN108304845A (en) * | 2018-01-16 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Image processing method, device and storage medium |
| CN110264405A (en) * | 2019-06-17 | 2019-09-20 | 深圳飞马机器人科技有限公司 | Image processing method, device, server and storage medium based on interpolation algorithm |
| CN110276379A (en) * | 2019-05-21 | 2019-09-24 | 方佳欣 | A kind of the condition of a disaster information rapid extracting method based on video image analysis |
| CN110782005A (en) * | 2019-09-27 | 2020-02-11 | 山东大学 | Image annotation method and system for tracking based on weak annotation data |
| CN111080700A (en) * | 2019-12-11 | 2020-04-28 | 中国科学院自动化研究所 | Medical instrument image detection method and device |
| CN210864770U (en) * | 2019-11-08 | 2020-06-26 | 天津一瑞生物科技股份有限公司 | Medical setting consumable detection system based on image recognition technology |
| CN111435073A (en) * | 2019-12-06 | 2020-07-21 | 上海建工集团股份有限公司 | Method and device for rapidly extracting deformation data of geotechnical engineering inclination measuring bar |
| CN111626276A (en) * | 2020-07-30 | 2020-09-04 | 之江实验室 | Two-stage neural network-based work shoe wearing detection method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110232406B (en) * | 2019-05-28 | 2021-07-06 | 厦门大学 | Liquid crystal panel CF image identification method based on statistical learning |
-
2020
- 2020-09-09 CN CN202010942091.6A patent/CN111968115B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010057081A1 (en) * | 2008-11-14 | 2010-05-20 | The Scripps Research Institute | Image analysis platform for identifying artifacts in samples and laboratory consumables |
| CN108171269A (en) * | 2018-01-04 | 2018-06-15 | 吴勤旻 | A kind of medical instrument pattern recognition device |
| CN108304845A (en) * | 2018-01-16 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Image processing method, device and storage medium |
| CN110276379A (en) * | 2019-05-21 | 2019-09-24 | 方佳欣 | A kind of the condition of a disaster information rapid extracting method based on video image analysis |
| CN110264405A (en) * | 2019-06-17 | 2019-09-20 | 深圳飞马机器人科技有限公司 | Image processing method, device, server and storage medium based on interpolation algorithm |
| CN110782005A (en) * | 2019-09-27 | 2020-02-11 | 山东大学 | Image annotation method and system for tracking based on weak annotation data |
| CN210864770U (en) * | 2019-11-08 | 2020-06-26 | 天津一瑞生物科技股份有限公司 | Medical setting consumable detection system based on image recognition technology |
| CN111435073A (en) * | 2019-12-06 | 2020-07-21 | 上海建工集团股份有限公司 | Method and device for rapidly extracting deformation data of geotechnical engineering inclination measuring bar |
| CN111080700A (en) * | 2019-12-11 | 2020-04-28 | 中国科学院自动化研究所 | Medical instrument image detection method and device |
| CN111626276A (en) * | 2020-07-30 | 2020-09-04 | 之江实验室 | Two-stage neural network-based work shoe wearing detection method and device |
Non-Patent Citations (2)
| Title |
|---|
| Evolution of imaging in surgical fracture management;Christian von Rüden et al.;《Injury》;20200531;第S51-S56页 * |
| 关于精细化管理在降低医用耗材占比作用的研究与探讨;宋尚玲 等;《医院数字化管理》;20181231;第33卷(第2期);第168-170页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111968115A (en) | 2020-11-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110826416B (en) | Bathroom ceramic surface defect detection method and device based on deep learning | |
| CN111062915B (en) | Real-time steel pipe defect detection method based on improved YOLOv3 model | |
| CN107230203B (en) | Casting defect identification method based on human eye visual attention mechanism | |
| US20100266175A1 (en) | Image and data segmentation | |
| US20110158535A1 (en) | Image processing apparatus and image processing method | |
| CN113724231B (en) | Industrial defect detection method based on semantic segmentation and target detection fusion model | |
| CN110021028B (en) | Automatic clothing making method based on clothing style drawing | |
| CN110490913B (en) | Image matching method based on feature description operator of corner and single line segment grouping | |
| CN104850822B (en) | Leaf identification method under simple background based on multi-feature fusion | |
| CN106611416B (en) | Method and device for segmenting lung in medical image | |
| CN109947273B (en) | Point reading positioning method and device | |
| CN115457565A (en) | OCR character recognition method, electronic equipment and storage medium | |
| CN111178190A (en) | Target detection method and device based on depth image and storage medium | |
| CN112580647A (en) | Stacked object oriented identification method and system | |
| CN110449658A (en) | Plate sawing sheet method and device | |
| CN108961262B (en) | Bar code positioning method in complex scene | |
| CN110826408A (en) | Face recognition method by regional feature extraction | |
| CN116342525A (en) | SOP chip pin defect detection method and system based on Lenet-5 model | |
| Kulshreshtha et al. | Content-based mammogram retrieval using k-means clustering and local binary pattern | |
| CN111968115B (en) | Method and system for detecting orthopedic consumables based on rasterization image processing method | |
| CN111368573A (en) | Positioning method based on geometric feature constraint | |
| CN111178405A (en) | Similar object identification method fusing multiple neural networks | |
| CN105761237B (en) | Chip x-ray image Hierarchical Segmentation based on mean shift | |
| CN108985294B (en) | Method, device and equipment for positioning tire mold picture and storage medium | |
| CN115457559B (en) | Method, device and equipment for intelligently correcting texts and license pictures |
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 |