CN111598947A - Method and system for automatically identifying patient orientation by identifying features - Google Patents
Method and system for automatically identifying patient orientation by identifying features Download PDFInfo
- Publication number
- CN111598947A CN111598947A CN202010260772.4A CN202010260772A CN111598947A CN 111598947 A CN111598947 A CN 111598947A CN 202010260772 A CN202010260772 A CN 202010260772A CN 111598947 A CN111598947 A CN 111598947A
- Authority
- CN
- China
- Prior art keywords
- pixel
- identification
- value
- image
- filtered image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000001914 filtration Methods 0.000 claims abstract description 16
- 238000012935 Averaging Methods 0.000 claims abstract description 11
- 230000002708 enhancing effect Effects 0.000 claims abstract description 10
- 238000012216 screening Methods 0.000 claims abstract description 6
- 238000004891 communication Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 239000003550 marker Substances 0.000 abstract description 6
- 238000003384 imaging method Methods 0.000 abstract description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000002324 minimally invasive surgery 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
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- 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
- 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
- G06T7/187—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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10116—X-ray 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a method and a system for automatically identifying the direction of a patient through identification characteristics, wherein the identification is placed according to a set rule, and a CB (machine B) machine is used for obtaining a digital image of a patient X-ray with the identification; filtering the digital image to reduce noise interference to obtain a filtered image, averaging the pixel gray values of the filtered image, screening according to the average value, and enhancing the picture identification area of the filtered image; carrying out binarization processing on the filtered image, searching a connected domain according to a pixel with a pixel value of 0 on the filtered image, finding a pixel set with the largest connected domain, and recording the pixel set as an identification pixel; the identification direction is obtained by comparing the pixel characteristics in the identification pixels, and the position of the patient on the digital image map is obtained by corresponding identification. The method for analyzing the imaging structure of the special marker in the X-ray image of the patient by adopting a certain rule to place the marker solves the problem of how to automatically and quickly determine the direction of the X-ray image of the patient.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to a method and a system for automatically recognizing the orientation of a patient through identification features.
Background
At present, in the surgical navigation technology, the intraoperative two-dimensional X-ray image and the preoperative CT/MR three-dimensional image are required to be registered, and because the position and the posture of a preoperative three-dimensional image patient are known, if the position of the intraoperative two-dimensional image patient can be determined, the registration efficiency can be greatly accelerated. In the method for determining the X-ray image of the patient, the observation person needs to have certain medical image reading experience through manual observation and manual input, and the efficiency is low; through a deep learning method, the calculation amount of early training is large; the manual input method is relatively inefficient through the placement of the markers and manual observation.
The prior art related to the present application is patent document CN109925057A, which discloses a spine minimally invasive surgery navigation method and system based on augmented reality, the method includes the following steps: reconstructing a virtual three-dimensional image of the patient's spine; registering the virtual three-dimensional image with the patient space to obtain the position of a virtual focus point in the virtual three-dimensional image in the patient space; projecting the surgical path formulated in the virtual three-dimensional image into a patient space; generating a DRR image from the preoperative CT image, registering the DRR image with an intraoperative X-ray image in real time, and determining an actual focus point; controlling the robot to clamp the surgical instrument to perform an operation on the actual focus point; real operation scenes are obtained in real time in an operation, the obtained video signals are output on a 3D display, preoperative operation path planning is achieved, and focus points are accurately positioned.
Disclosure of Invention
In view of the deficiencies in the prior art, it is an object of the present invention to provide a method and system for automatically identifying patient orientation by identifying features.
According to the invention, the method for automatically identifying the orientation of the patient through the identification features comprises the following steps:
an image acquisition step: placing a mark according to a set rule, and obtaining a digital image of the X-ray of the patient with the mark through a CB (CB) machine;
an image enhancement step: filtering the digital image to reduce noise interference to obtain a filtered image, averaging the pixel gray values of the filtered image, screening according to the average value, and enhancing the picture identification area of the filtered image;
a binary processing step: carrying out binarization processing on the filtered image, searching a connected domain according to a pixel with a pixel value of 0 on the filtered image, finding a pixel set with the largest connected domain, and recording the pixel set as an identification pixel;
and (3) identifying the orientation: the identification direction is obtained by comparing the pixel characteristics in the identification pixels, and the position of the patient on the digital image map is obtained by corresponding identification.
Preferably, the image enhancement step comprises:
a median filtering step: filtering the digital image map by using a median filter to obtain a filtered image;
a normalization step: and averaging the gray value of the picture pixel of the filtered image, setting the gray value larger than the average value as 1, normalizing the gray value smaller than the average value between 0 and the average value, and enhancing the picture identification area of the filtered image.
Preferably, the binary processing step includes:
a threshold value sorting step: setting a threshold value, carrying out binarization processing on the filtered image through the threshold value, if the pixel value in the filtered image is lower than the threshold value, setting the pixel value to be 0, otherwise, setting the pixel value to be 1;
a pixel communication step: and searching a connected domain for the pixel with the pixel value of 0 in the filtered image until all the pixels with the pixel value of 0 are found, and taking the pixel set with the maximum connected domain as an identification pixel.
Preferably, the step of identifying the orientation comprises:
setting a limit step: determining the maximum and minimum value of the identification pixel on the X axis, recording the maximum and minimum value as the maximum and minimum value of the X axis, determining the maximum and minimum value of the identification pixel on the Y axis, and recording the maximum and minimum value as the maximum and minimum value of the Y axis;
a region segmentation step: constructing a bounding box by using the maximum and minimum values of the X axis and the maximum and minimum values of the Y axis, and dividing the bounding box into 4 regions by using a central line;
and a region comparison step: and comparing the region characteristics of the 4 regions to obtain the identification azimuth.
Preferably, the mark comprises a circular ring part and an opening part, the circular ring part is consistent with the head direction of the patient, and the opening part is consistent with the right hand direction of the patient.
According to the invention, a system for automatically identifying the orientation of a patient by identifying features is provided, comprising:
an image acquisition module: placing a mark according to a set rule, and obtaining a digital image of the X-ray of the patient with the mark through a CB (CB) machine;
an image enhancement module: filtering the digital image to reduce noise interference to obtain a filtered image, averaging the pixel gray values of the filtered image, screening according to the average value, and enhancing the picture identification area of the filtered image;
a binary processing module: carrying out binarization processing on the filtered image, searching a connected domain according to a pixel with a pixel value of 0 on the filtered image, finding a pixel set with the largest connected domain, and recording the pixel set as an identification pixel;
an orientation identification module: the identification direction is obtained by comparing the pixel characteristics in the identification pixels, and the position of the patient on the digital image map is obtained by corresponding identification.
Preferably, the image enhancement module comprises:
a median filtering module: filtering the digital image map by using a median filter to obtain a filtered image;
a normalization module: and averaging the gray value of the picture pixel of the filtered image, setting the gray value larger than the average value as 1, normalizing the gray value smaller than the average value between 0 and the average value, and enhancing the picture identification area of the filtered image.
Preferably, the binary processing module includes:
a threshold sorting module: setting a threshold value, carrying out binarization processing on the filtered image through the threshold value, if the pixel value in the filtered image is lower than the threshold value, setting the pixel value to be 0, otherwise, setting the pixel value to be 1;
a pixel communication module: and searching a connected domain for the pixel with the pixel value of 0 in the filtered image until all the pixels with the pixel value of 0 are found, and taking the pixel set with the maximum connected domain as an identification pixel.
Preferably, the identifying the orientation module comprises:
a limit setting module: determining the maximum and minimum value of the identification pixel on the X axis, recording the maximum and minimum value as the maximum and minimum value of the X axis, determining the maximum and minimum value of the identification pixel on the Y axis, and recording the maximum and minimum value as the maximum and minimum value of the Y axis;
a region segmentation module: constructing a bounding box by using the maximum and minimum values of the X axis and the maximum and minimum values of the Y axis, and dividing the bounding box into 4 regions by using a central line;
a region comparison module: and comparing the region characteristics of the 4 regions to obtain the identification azimuth.
Preferably, the mark comprises a circular ring part and an opening part, the circular ring part is consistent with the head direction of the patient, and the opening part is consistent with the right hand direction of the patient.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention effectively simplifies the shooting steps of the X-ray images of the patient, improves the shooting efficiency, and does not need an observer to have rich medical image reading experience;
2. the invention automatically identifies the image posture of the patient by placing the marker according to a certain rule without means such as deep learning model and early training, reduces the difficulty degree of posture identification implementation and is convenient for popularization and application.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a schematic flow chart of the present invention;
figure 2 is a schematic representation of the placement of the marker of the present invention.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that it would be obvious to those skilled in the art that various changes and modifications can be made without departing from the spirit of the invention. All falling within the scope of the present invention.
According to the invention, when a patient shoots an X-ray image in the CB machine, the image posture of the patient is automatically identified through the markers which are placed according to a certain rule. The method for analyzing the imaging structure of the special marker in the X-ray image of the patient by adopting a certain rule to place the marker solves the problem of how to automatically and quickly determine the direction of the X-ray image of the patient.
As shown in fig. 1, the present invention is implemented by the following steps:
an image acquisition step: placing a mark according to a set rule, and obtaining a digital image of the X-ray of the patient with the mark through a CB (CB) machine;
an image enhancement step: filtering the digital image to reduce noise interference to obtain a filtered image, averaging the pixel gray values of the filtered image, screening according to the average value, and enhancing the picture identification area of the filtered image;
a binary processing step: carrying out binarization processing on the filtered image, searching a connected domain according to a pixel with a pixel value of 0 on the filtered image, finding a pixel set with the largest connected domain, and recording the pixel set as an identification pixel;
and (3) identifying the orientation: the identification direction is obtained by comparing the pixel characteristics in the identification pixels, and the position of the patient on the digital image map is obtained by corresponding identification.
Specifically, firstly, a certain rule is set for placing the mark, as shown in fig. 2, the mark is in a shape of letter K, a K ring is consistent with the head of the patient, and the opening direction is consistent with the right hand of the patient; obtaining a digital image of X-ray of a patient with a K mark through a CB machine;
after a digital image is obtained, filtering the image by using a median filter to reduce noise interference, specifically, performing convolution on the whole image by using a 3 x 3 window, sequencing 3 x 3 pixel values in total in the convolution process, and selecting a middle value as an output pixel value after sequencing; averaging the gray values of the pixels of the picture, setting the gray value larger than the average value as 1, and normalizing the gray value smaller than the average value from 0 to the average value to enhance the identification area of the picture;
secondly, because the density of the material of the K-shaped ring is high and the color of the K-shaped ring on the image is dark, the image of the filtering image is subjected to binarization processing by using a threshold value of 0.8, the value lower than the threshold value is set to be 0, and the rest is 1; and searching the connected domain through the pixel with the pixel value of 0 on the picture until all the pixels with the pixel value of 0 are searched. Finding out the pixel set with the largest connected domain, namely the pixel set is the identification pixel;
finally, comparing the pixel characteristics with the maximum connected domain to obtain the identification direction, and obtaining the orientation of the patient on the image through the corresponding identification; specifically, the maximum and minimum values of the X axis and the maximum and minimum values of the Y axis under the maximum connected domain are found out; constructing a bounding box by using the X-axis maximum and minimum values and the Y-axis maximum and minimum values, and dividing the bounding box into 4 regions by using a central line; and comparing the characteristics of the regions, counting the sum of the identification pixels of each region, and counting the smallest region, namely the upper right corner of the K graph, thereby judging the specific orientation of the patient.
Those skilled in the art will appreciate that, in addition to implementing the systems, apparatus, and various modules thereof provided by the present invention in purely computer readable program code, the same procedures can be implemented entirely by logically programming method steps such that the systems, apparatus, and various modules thereof are provided in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Therefore, the system, the device and the modules thereof provided by the present invention can be considered as a hardware component, and the modules included in the system, the device and the modules thereof for implementing various programs can also be considered as structures in the hardware component; modules for performing various functions may also be considered to be both software programs for performing the methods and structures within hardware components.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes or modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention. The embodiments and features of the embodiments of the present application may be combined with each other arbitrarily without conflict.
Claims (10)
1. A method for automatically identifying patient orientation by identifying features, comprising:
an image acquisition step: placing a mark according to a set rule, and obtaining a digital image of the X-ray of the patient with the mark through a CB (CB) machine;
an image enhancement step: filtering the digital image to reduce noise interference to obtain a filtered image, averaging the pixel gray values of the filtered image, screening according to the average value, and enhancing the picture identification area of the filtered image;
a binary processing step: carrying out binarization processing on the filtered image, searching a connected domain according to a pixel with a pixel value of 0 on the filtered image, finding a pixel set with the largest connected domain, and recording the pixel set as an identification pixel;
and (3) identifying the orientation: the identification direction is obtained by comparing the pixel characteristics in the identification pixels, and the position of the patient on the digital image map is obtained by corresponding identification.
2. The method of claim 1, wherein the image enhancement step comprises:
a median filtering step: filtering the digital image map by using a median filter to obtain a filtered image;
a normalization step: and averaging the gray value of the picture pixel of the filtered image, setting the gray value larger than the average value as 1, normalizing the gray value smaller than the average value between 0 and the average value, and enhancing the picture identification area of the filtered image.
3. The method of automatically identifying patient orientation by identification feature of claim 1 wherein said binary processing step comprises:
a threshold value sorting step: setting a threshold value, carrying out binarization processing on the filtered image through the threshold value, if the pixel value in the filtered image is lower than the threshold value, setting the pixel value to be 0, otherwise, setting the pixel value to be 1;
a pixel communication step: and searching a connected domain for the pixel with the pixel value of 0 in the filtered image until all the pixels with the pixel value of 0 are found, and taking the pixel set with the maximum connected domain as an identification pixel.
4. The method of automatically identifying a patient's orientation by identifying features of claim 1 wherein the identifying an orientation step comprises:
setting a limit step: determining the maximum and minimum value of the identification pixel on the X axis, recording the maximum and minimum value as the maximum and minimum value of the X axis, determining the maximum and minimum value of the identification pixel on the Y axis, and recording the maximum and minimum value as the maximum and minimum value of the Y axis;
a region segmentation step: constructing a bounding box by using the maximum and minimum values of the X axis and the maximum and minimum values of the Y axis, and dividing the bounding box into 4 regions by using a central line;
and a region comparison step: and comparing the region characteristics of the 4 regions to obtain the identification azimuth.
5. The method of claim 1, wherein the indicator comprises a circular portion and an opening, the circular portion is aligned with the head of the patient, and the opening is aligned with the right hand of the patient.
6. A system for automatically identifying the orientation of a patient by identifying features, comprising:
an image acquisition module: placing a mark according to a set rule, and obtaining a digital image of the X-ray of the patient with the mark through a CB (CB) machine;
an image enhancement module: filtering the digital image to reduce noise interference to obtain a filtered image, averaging the pixel gray values of the filtered image, screening according to the average value, and enhancing the picture identification area of the filtered image;
a binary processing module: carrying out binarization processing on the filtered image, searching a connected domain according to a pixel with a pixel value of 0 on the filtered image, finding a pixel set with the largest connected domain, and recording the pixel set as an identification pixel;
an orientation identification module: the identification direction is obtained by comparing the pixel characteristics in the identification pixels, and the position of the patient on the digital image map is obtained by corresponding identification.
7. The system of claim 6, wherein the image enhancement module comprises:
a median filtering module: filtering the digital image map by using a median filter to obtain a filtered image;
a normalization module: and averaging the gray value of the picture pixel of the filtered image, setting the gray value larger than the average value as 1, normalizing the gray value smaller than the average value between 0 and the average value, and enhancing the picture identification area of the filtered image.
8. The system of claim 6, wherein the binary processing module comprises:
a threshold sorting module: setting a threshold value, carrying out binarization processing on the filtered image through the threshold value, if the pixel value in the filtered image is lower than the threshold value, setting the pixel value to be 0, otherwise, setting the pixel value to be 1;
a pixel communication module: and searching a connected domain for the pixel with the pixel value of 0 in the filtered image until all the pixels with the pixel value of 0 are found, and taking the pixel set with the maximum connected domain as an identification pixel.
9. The system of claim 6, wherein the identify orientation module comprises:
a limit setting module: determining the maximum and minimum value of the identification pixel on the X axis, recording the maximum and minimum value as the maximum and minimum value of the X axis, determining the maximum and minimum value of the identification pixel on the Y axis, and recording the maximum and minimum value as the maximum and minimum value of the Y axis;
a region segmentation module: constructing a bounding box by using the maximum and minimum values of the X axis and the maximum and minimum values of the Y axis, and dividing the bounding box into 4 regions by using a central line;
a region comparison module: and comparing the region characteristics of the 4 regions to obtain the identification azimuth.
10. The system of claim 6, wherein the indicator comprises a circular portion that is aligned with the head of the patient and an open portion that is aligned with the right hand of the patient.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010260772.4A CN111598947B (en) | 2020-04-03 | 2020-04-03 | Method and system for automatically identifying patient position by identification features |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010260772.4A CN111598947B (en) | 2020-04-03 | 2020-04-03 | Method and system for automatically identifying patient position by identification features |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111598947A true CN111598947A (en) | 2020-08-28 |
CN111598947B CN111598947B (en) | 2024-02-20 |
Family
ID=72192019
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010260772.4A Active CN111598947B (en) | 2020-04-03 | 2020-04-03 | Method and system for automatically identifying patient position by identification features |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111598947B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019000653A1 (en) * | 2017-06-30 | 2019-01-03 | 清华大学深圳研究生院 | Image target identification method and apparatus |
WO2019062631A1 (en) * | 2017-09-30 | 2019-04-04 | 阿里巴巴集团控股有限公司 | Local dynamic image generation method and device |
CN110688871A (en) * | 2019-09-19 | 2020-01-14 | 浙江工业大学 | Edge detection method based on bar code identification |
-
2020
- 2020-04-03 CN CN202010260772.4A patent/CN111598947B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019000653A1 (en) * | 2017-06-30 | 2019-01-03 | 清华大学深圳研究生院 | Image target identification method and apparatus |
WO2019062631A1 (en) * | 2017-09-30 | 2019-04-04 | 阿里巴巴集团控股有限公司 | Local dynamic image generation method and device |
CN110688871A (en) * | 2019-09-19 | 2020-01-14 | 浙江工业大学 | Edge detection method based on bar code identification |
Non-Patent Citations (1)
Title |
---|
袁杰;朱斐;: "基于中值滤波和梯度锐化的边缘检测" * |
Also Published As
Publication number | Publication date |
---|---|
CN111598947B (en) | 2024-02-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3509013A1 (en) | Identification of a predefined object in a set of images from a medical image scanner during a surgical procedure | |
US8929602B2 (en) | Component based correspondence matching for reconstructing cables | |
US7970212B2 (en) | Method for automatic detection and classification of objects and patterns in low resolution environments | |
CN106228548B (en) | A kind of detection method and device of screen slight crack | |
CN106898044B (en) | Organ splitting and operating method and system based on medical images and by utilizing VR technology | |
CN110223279B (en) | Image processing method and device and electronic equipment | |
US20110150279A1 (en) | Image processing apparatus, processing method therefor, and non-transitory computer-readable storage medium | |
CN110796659B (en) | Target detection result identification method, device, equipment and storage medium | |
CN114022554B (en) | Massage robot acupoint detection and positioning method based on YOLO | |
TWI684994B (en) | Spline image registration method | |
CN113223004A (en) | Liver image segmentation method based on deep learning | |
CN114972646B (en) | Method and system for extracting and modifying independent ground objects of live-action three-dimensional model | |
CN111161295A (en) | Background stripping method for dish image | |
CN114119695A (en) | Image annotation method and device and electronic equipment | |
CN109919128A (en) | Acquisition methods, device and the electronic equipment of control instruction | |
CN107145820B (en) | Binocular positioning method based on HOG characteristics and FAST algorithm | |
CN110647889B (en) | Medical image recognition method, medical image recognition apparatus, terminal device, and medium | |
CN112861588B (en) | Living body detection method and device | |
CN111598947B (en) | Method and system for automatically identifying patient position by identification features | |
CN112634266B (en) | Semi-automatic labeling method, medium, equipment and device for laryngoscope image | |
CN106097362B (en) | The automatic of artificial circular mark detects and localization method in a kind of x-ray image | |
CN114972881A (en) | Image segmentation data labeling method and device | |
CN114926635A (en) | Method for segmenting target in multi-focus image combined with deep learning method | |
CN113610071A (en) | Face living body detection method and device, electronic equipment and storage medium | |
CN115223034A (en) | Automatic hole selection method and device for cryoelectron microscope |
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 |