CN114119604A - Pathological sample distribution monitoring system - Google Patents
Pathological sample distribution monitoring system Download PDFInfo
- Publication number
- CN114119604A CN114119604A CN202111638559.3A CN202111638559A CN114119604A CN 114119604 A CN114119604 A CN 114119604A CN 202111638559 A CN202111638559 A CN 202111638559A CN 114119604 A CN114119604 A CN 114119604A
- Authority
- CN
- China
- Prior art keywords
- image
- slide
- area
- label
- slide plate
- 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.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 48
- 230000001575 pathological effect Effects 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 claims description 21
- 230000011218 segmentation Effects 0.000 claims description 12
- 230000009466 transformation Effects 0.000 claims description 9
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 7
- 230000007170 pathology Effects 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000012706 support-vector machine Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000004043 dyeing Methods 0.000 claims description 2
- 239000011521 glass Substances 0.000 description 5
- 238000003745 diagnosis Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000000750 progressive effect Effects 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
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/1408—Methods for optical code recognition the method being specifically adapted for the type of code
- G06K7/1417—2D bar codes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G06T3/02—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-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
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- 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
- G06T2207/10056—Microscopic 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
-
- 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
- G06T2207/20076—Probabilistic image processing
-
- 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
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/30004—Biomedical image processing
Abstract
The invention discloses a pathological sample distribution monitoring system. The system, comprising: the image shooting device is used for shooting the area of the slide plate and the area of the slide taking position in real time and acquiring the image of the slide plate and the image of the slide taking area; the specimen label identification module is used for identifying label information of each slide in the slide plate image; the identity recognition module is used for recognizing the identity information of the person taking the picture in the picture taking area image; and the monitoring module is used for matching the label information with the identity information to generate a distribution monitoring result. The invention can realize the real-time monitoring of the distribution operation of the pathological sample.
Description
Technical Field
The invention relates to the field of pathological sample monitoring, in particular to a pathological sample distribution monitoring system.
Background
The initial form of the pathological sample is an operation specimen, which is collected, dehydrated and embedded into a wax block after entering a pathology department, and then the wax block is sliced and stained into a slide carrying sample tissues. The glass slides are distributed to different pathologists, and the pathologists put under a microscope to observe the cell morphology in the glass slides to realize disease diagnosis.
At present, a medical institution usually adopts a manual mode to distribute pathological sample slides, for example, a distribution worker sends the slides to a diagnosis room or related personnel take the slides away from a pathology department, the distribution mode cannot realize the monitoring of the distribution process, and when the pathological sample slides are mistakenly taken or lost, the pathological sample slides cannot be traced back, the loss cannot be timely made up, and the subsequent diagnosis operation is influenced.
Disclosure of Invention
Based on this, the embodiment of the invention provides a pathological sample distribution monitoring system to realize real-time monitoring of pathological sample distribution operation.
In order to achieve the purpose, the invention provides the following scheme:
a pathological sample distribution monitoring system comprising:
the image shooting device is used for shooting the area of the slide plate and the area of the slide taking position in real time and acquiring the image of the slide plate and the image of the slide taking area;
the specimen label identification module is used for identifying label information of each slide in the slide tray image;
the identity recognition module is used for recognizing the identity information of the person taking the picture in the picture taking area image;
and the monitoring module is used for matching the label information with the identity information to generate a distribution monitoring result.
Optionally, the image capturing apparatus specifically includes:
a camera, a machine vision light source, and a camera mount; the camera and the machine vision light source are both arranged on the camera support.
Optionally, the pathological sample distribution monitoring system further includes:
and the post query module is used for calling the distribution monitoring result when errors occur in the operation link after distribution so as to realize problem tracing.
Optionally, the pathological sample distribution monitoring system further includes:
and the database platform is used for storing the distribution monitoring results at all times.
Optionally, the specimen label identification module specifically includes:
a slide plate area detection unit for detecting a slide plate area in the slide plate image based on Otsu's method;
the label contour segmentation unit is used for segmenting the label contour of each slide in the slide plate area according to a watershed algorithm to obtain a contour image;
the label area detection unit is used for extracting the directional gradient histogram characteristics of the contour image, inputting the directional gradient histogram characteristics of the contour image into a trained support vector machine classifier, determining whether the contour image contains a label area or not, and determining the contour image containing the label area as a target image;
the slide printing style determining unit is used for inputting the directional gradient histogram characteristics of the target images into a trained artificial neural network to obtain the printing style of each target image; the printing style comprises the existence of the two-dimensional code, the printing position of the information field and the printing direction of the information field; the information field comprises a slide number and a dyeing type;
and the label information identification unit is used for identifying the target image according to the printing pattern to obtain the label information of the slide corresponding to the target image.
Optionally, the identity module specifically includes:
and the face recognition unit is used for recognizing the face image in the picture taking area image and determining the face image as the identity information of the picture taking person.
Optionally, the slide tray area detecting unit specifically includes:
the zooming subunit is used for carrying out zooming operation on the slide plate image to obtain a slide plate image with a set size;
the preprocessing subunit is used for carrying out gray level conversion processing and filtering processing on the slide tray image with the set size to obtain a processed image;
a segmentation subunit, configured to perform threshold segmentation on the processed image by using the Otsu method, and search for a contour to obtain an initial region;
and the affine transformation subunit is used for carrying out affine transformation on the initial region to obtain the region of the slide plate.
Optionally, the image capturing apparatus further includes:
the base is used for placing the camera support.
Compared with the prior art, the invention has the beneficial effects that:
the embodiment of the invention provides a pathological sample distribution monitoring system, which adopts an image shooting device to monitor a slide plate area and a slide taking position area in real time, can acquire slide plate images containing batch slides and slide taking area images corresponding to the slide plate images, can determine label information of the taken slides and identity information of a person taking the slides in real time through a specimen label identification module and an identity identification module, and realizes real-time monitoring of pathological sample distribution operation.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
Fig. 1 is a block diagram of a pathological sample distribution monitoring system provided in an embodiment of the present invention;
FIG. 2 is a flow chart of a pathology sample distribution monitoring method according to an embodiment of the present invention;
FIG. 3 is a flow chart of the determination of the slide tray area provided by the embodiment of the present invention;
FIG. 4 is a flow chart of determining a target image according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a print pattern recognition provided by an embodiment of the present invention;
fig. 6 is a schematic diagram illustrating identification of tag information according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Fig. 1 is a block diagram of a pathological sample distribution monitoring system according to an embodiment of the present invention.
Referring to fig. 1, the pathological sample distribution monitoring system of the present embodiment includes:
and the image shooting device is used for shooting the area of the slide plate and the area of the slide taking position in real time and acquiring the image of the slide plate and the image of the slide taking area.
And the specimen label identification module is used for identifying the label information of each slide in the slide tray image.
And the identity identification module is used for identifying the identity information of the person taking the picture in the picture taking area image.
And the monitoring module is used for matching the label information with the identity information to generate a distribution monitoring result, so that when an operator in the area of the slide taking position places the slide plate with the slide in the area of the shooting slide plate, and directly takes away the whole slide plate after shooting and identifying, the operator can determine when and who take away the slide according to the monitored label information and identity information (distribution monitoring result) so as to trace back.
In one example, the image capturing apparatus specifically includes:
a camera, a machine vision light source, and a camera mount; the camera and the machine vision light source are both arranged on the camera support. In practical applications, the camera may be a high resolution camera.
In one example, the pathology sample distribution monitoring system, further comprising:
and the post query module is used for calling the distribution monitoring result when errors occur in the operation link after distribution so as to realize problem tracing.
In one example, the pathology sample distribution monitoring system, further comprising: and the database platform is used for storing the distribution monitoring results at all times.
In one example, the specimen label identification module specifically includes:
a slide plate area detection unit for detecting a slide plate area in the slide plate image based on Otsu's method.
And the label contour segmentation unit is used for segmenting the label contour of each slide in the slide tray area according to a watershed algorithm to obtain a contour image. Specifically, labels and background position mark points are set in advance according to the characteristics of the slide plate, the mark points are set in advance, the watershed algorithm is adopted to segment the area of the slide plate to obtain a label profile, and a profile image is extracted from the area of the slide plate by the label profile.
And the label area detection unit is used for extracting the directional gradient histogram characteristics of the contour image, inputting the directional gradient histogram characteristics of the contour image into a trained support vector machine classifier, determining whether the contour image contains a label area, determining the contour image containing the label area as a target image, and filtering the contour image (non-label area) without the label area.
And the slide printing style determining unit is used for inputting the directional gradient histogram characteristics of the target images into the trained artificial neural network to obtain the printing style of each target image. The printing style is determined by different printers, and the different styles are represented by whether the two-dimensional code, the printing position of the information field, the printing direction of the information field and the like are contained, so that the printing style of the embodiment comprises the existence of the two-dimensional code, the printing position of the information field and the printing direction of the information field; the information field includes a slide number and a stain type.
And the label information identification unit is used for identifying the target image according to the printing pattern to obtain the label information of the slide corresponding to the target image. The specific identification process is as follows: judging whether the printing direction of the label in the target image and the target image have the two-dimensional code, if so, decoding the two-dimensional code, and after the decoding is successful, performing character (OCR) recognition on the label according to the printing position of the information field and the printing direction of the information field to obtain a two-dimensional code recognition result and a character recognition result; if not, character (OCR) recognition is directly carried out on the label according to the printing position of the information field and the printing direction of the information field, and a character recognition result is obtained. The label information comprises a two-dimensional code recognition result and/or a character recognition result.
In one example, the identity module specifically includes:
and the face recognition unit is used for recognizing the face image in the picture taking area image and determining the face image as the identity information of the picture taking person.
In one example, the slide tray area detecting unit specifically includes:
the zooming subunit is used for carrying out zooming operation on the slide plate image to obtain a slide plate image with a set size;
the preprocessing subunit is used for carrying out gray level conversion processing and filtering processing on the slide tray image with the set size to obtain a processed image;
a segmentation subunit, configured to perform threshold segmentation on the processed image by using the Otsu method, and search for a contour to obtain an initial region;
and the affine transformation subunit is used for carrying out affine transformation on the initial region to obtain the region of the slide plate.
In one example, the image capturing apparatus further includes: the base is used for placing the camera support.
In practical application, referring to fig. 2, a specific flow of the distribution monitoring method for the pathological sample distribution monitoring system is as follows:
the method comprises the following steps: the slide plate is photographed with a high resolution camera and an image of the slide plate is acquired.
Step two: the area outline (initial area) of the slide plate is obtained, and the area of the slide plate is obtained through affine transformation, and the specific process is shown in fig. 3. Referring to fig. 3, the process includes:
(1) zooming the image, and unifying the image preprocessing size;
(2) carrying out gray level transformation and filtering on the image;
(3) performing threshold segmentation on the image by using the Otsu method, and searching the outline to obtain an initial region;
(4) and carrying out affine transformation on the initial area to obtain a slide disc area.
Step three: and detecting the position of the slide label by adopting a region segmentation algorithm to obtain a target image, wherein the specific process is shown in fig. 4. Referring to fig. 4, the process includes:
(1) setting a label and a background position Mark point (Mark point) in advance according to the characteristics of the slide plate;
(2) carrying out watershed algorithm operation on the region of the slide plate panel obtained in the step two by adopting a mark point set in advance, and obtaining a label contour after segmentation;
(3) extracting a contour image from a glass slide plate area by using a label contour, extracting directional gradient histogram (Hog) characteristics from the contour image, classifying the contour image by using a trained support vector machine (Svm) classifier, determining whether the contour image contains a glass slide label (label area) or not, determining the contour image containing the glass slide label as a target image, and filtering out a non-label area.
Step four: the slide print pattern is identified by adopting a characteristic extraction and machine learning mode, and the specific process is shown in figure 5. Referring to fig. 5, the process includes:
(1) collecting data of a batch of slide label patterns used on site in advance, carrying out Hog feature extraction on all the data, designing an Artificial Neural Network (ANN), and training the ANN to obtain a label pattern classification model.
(2) And inputting the feature data of the Hog feature of the target image obtained in the step three into the trained ANN for recognition to obtain a corresponding printing style.
Step five: according to the slide printing style, the identification and extraction of the slide label information are carried out, and the specific process is shown in fig. 6. Referring to fig. 6, the process includes:
(1) and determining the printing direction of the label and the type of the two-dimensional code according to the printing style obtained in the step four and the attribute characteristics of the label set in advance.
(2) The label is rotated.
(3) And detecting and identifying the two-dimensional code.
(4) Character (OCR) recognition is performed.
The pathological sample distribution monitoring system of the embodiment realizes real-time monitoring of pathological sample distribution operation, and when the pathological sample slide is mistakenly taken or lost, the pathological sample slide can be traced back according to the distribution monitoring result, so that loss is compensated in time, and subsequent diagnosis operation is prevented from being influenced.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (8)
1. A pathology sample distribution monitoring system, comprising:
the image shooting device is used for shooting the area of the slide plate and the area of the slide taking position in real time and acquiring the image of the slide plate and the image of the slide taking area;
the specimen label identification module is used for identifying label information of each slide in the slide tray image;
the identity recognition module is used for recognizing the identity information of the person taking the picture in the picture taking area image;
and the monitoring module is used for matching the label information with the identity information to generate a distribution monitoring result.
2. The pathological sample distribution monitoring system according to claim 1, wherein the image capturing device specifically comprises:
a camera, a machine vision light source, and a camera mount;
the camera and the machine vision light source are both arranged on the camera support.
3. The pathological sample distribution monitoring system of claim 1, further comprising:
and the post query module is used for calling the distribution monitoring result when errors occur in the operation link after distribution so as to realize problem tracing.
4. The pathological sample distribution monitoring system of claim 1, further comprising:
and the database platform is used for storing the distribution monitoring results at all times.
5. The pathological sample distribution monitoring system according to claim 1, wherein the specimen label identification module specifically comprises:
a slide plate area detection unit for detecting a slide plate area in the slide plate image based on Otsu's method;
the label contour segmentation unit is used for segmenting the label contour of each slide in the slide plate area according to a watershed algorithm to obtain a contour image;
the label area detection unit is used for extracting the directional gradient histogram characteristics of the contour image, inputting the directional gradient histogram characteristics of the contour image into a trained support vector machine classifier, determining whether the contour image contains a label area or not, and determining the contour image containing the label area as a target image;
the slide printing style determining unit is used for inputting the directional gradient histogram characteristics of the target images into a trained artificial neural network to obtain the printing style of each target image; the printing style comprises the existence of the two-dimensional code, the printing position of the information field and the printing direction of the information field; the information field comprises a slide number and a dyeing type;
and the label information identification unit is used for identifying the target image according to the printing pattern to obtain the label information of the slide corresponding to the target image.
6. The pathological sample distribution monitoring system according to claim 1, wherein the identification module specifically comprises:
and the face recognition unit is used for recognizing the face image in the picture taking area image and determining the face image as the identity information of the picture taking person.
7. The pathology sample distribution monitoring system of claim 5, wherein the slide tray area detection unit comprises:
the zooming subunit is used for carrying out zooming operation on the slide plate image to obtain a slide plate image with a set size;
the preprocessing subunit is used for carrying out gray level conversion processing and filtering processing on the slide tray image with the set size to obtain a processed image;
a segmentation subunit, configured to perform threshold segmentation on the processed image by using the Otsu method, and search for a contour to obtain an initial region;
and the affine transformation subunit is used for carrying out affine transformation on the initial region to obtain the region of the slide plate.
8. The pathological sample distribution monitoring system according to claim 2, wherein said image capturing device further comprises:
the base is used for placing the camera support.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111638559.3A CN114119604A (en) | 2021-12-29 | 2021-12-29 | Pathological sample distribution monitoring system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111638559.3A CN114119604A (en) | 2021-12-29 | 2021-12-29 | Pathological sample distribution monitoring system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114119604A true CN114119604A (en) | 2022-03-01 |
Family
ID=80363248
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111638559.3A Pending CN114119604A (en) | 2021-12-29 | 2021-12-29 | Pathological sample distribution monitoring system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114119604A (en) |
-
2021
- 2021-12-29 CN CN202111638559.3A patent/CN114119604A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021047232A1 (en) | Interaction behavior recognition method, apparatus, computer device, and storage medium | |
CN108520226B (en) | Pedestrian re-identification method based on body decomposition and significance detection | |
US7715596B2 (en) | Method for controlling photographs of people | |
Guo et al. | Automatic identification of individual primates with deep learning techniques | |
CN110245657B (en) | Pathological image similarity detection method and detection device | |
CN106803248B (en) | Fuzzy license plate image blur evaluation method | |
CN106203237A (en) | The recognition methods of container-trailer numbering and device | |
CN106874901B (en) | Driving license identification method and device | |
CN106650623A (en) | Face detection-based method for verifying personnel and identity document for exit and entry | |
US11488401B2 (en) | Prostate cancer tissue image classification with deep learning | |
CN109376717A (en) | Personal identification method, device, electronic equipment and the storage medium of face comparison | |
CN109409250A (en) | A kind of across the video camera pedestrian of no overlap ken recognition methods again based on deep learning | |
CN110569856A (en) | sample labeling method and device, and damage category identification method and device | |
CN111161295A (en) | Background stripping method for dish image | |
CN115298692A (en) | Automatic candidate sperm identification | |
CN114445879A (en) | High-precision face recognition method and face recognition equipment | |
CN108805181B (en) | Image classification device and method based on multi-classification model | |
CN112381840A (en) | Method and system for marking vehicle appearance parts in loss assessment video | |
CN114119604A (en) | Pathological sample distribution monitoring system | |
CN113627255A (en) | Mouse behavior quantitative analysis method, device, equipment and readable storage medium | |
CN114663803A (en) | Logistics center hanging clothing classification method and device based on video streaming | |
Bindhu et al. | Analytical study on digital image processing applications | |
CN111583275A (en) | Method, system, device and storage medium for identifying pathological number of section | |
Nugroho et al. | Performance of Convolutional Neural Network in Detecting Plasmodium Parasites | |
CN111723612A (en) | Face recognition and face recognition network training method and device, and storage medium |
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 |