CN115546543B - Human body infrared image sample processing method and storage medium - Google Patents
Human body infrared image sample processing method and storage medium Download PDFInfo
- Publication number
- CN115546543B CN115546543B CN202211204405.8A CN202211204405A CN115546543B CN 115546543 B CN115546543 B CN 115546543B CN 202211204405 A CN202211204405 A CN 202211204405A CN 115546543 B CN115546543 B CN 115546543B
- Authority
- CN
- China
- Prior art keywords
- infrared image
- human body
- samples
- human
- image sample
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
- G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Probability & Statistics with Applications (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to the field of image data processing or generating technologies, and in particular, to a method and a storage medium for processing a human infrared image sample. The method comprises the following steps: s100, acquiring a human infrared image sample set P; s200, traversing P, if P i For a normal sample, then p i Add to P'; s300, traversing P ', and grouping P' to obtain C; s400, traversing C, and clustering C by using a K-means clustering method j Clustering is carried out; s500, traversing C, if n j,k If the number of the samples is smaller than the preset number of samples, deleting c j In c) j,k Obtaining updated c j The method comprises the steps of carrying out a first treatment on the surface of the S600, traversing C and obtaining updated C j Mean value vector EF of temperature vectors corresponding to all human infrared image samples j And outputs EF j . The invention improves the accuracy of the temperature of the specific acupuncture point or region in the acquired standard human infrared image.
Description
Technical Field
The present invention relates to the field of image data processing or generating technology, and more particularly, to a human infrared image sample processing method and a storage medium.
Background
The intelligent infrared thermal imaging in-vitro detection equipment can be used for shooting human body infrared images, and the health condition of a human body can be judged based on the human body infrared images. For example, the health condition of the human body can be judged by acquiring the temperature information of the specific acupuncture point or area in the human body infrared image, specifically, the temperature of the specific acupuncture point or area in the human body infrared image to be judged can be compared with the temperature of the specific acupuncture point or area in the standard human body infrared image, and if the temperature of the specific acupuncture point or area in the human body infrared image to be judged is smaller than the temperature difference of the specific acupuncture point or area in the standard human body infrared image, the health condition of the human body is normal; if the temperature of a specific acupoint or region in the infrared image of the human body to be judged is greatly different from the temperature of the specific acupoint or region in the infrared image of the standard human body, the condition that the health condition of the human body possibly has abnormality is indicated.
The temperature of a specific acupoint or region in a standard human body infrared image is the basis for judging the health condition of a human body, and in order to improve the accuracy of judging the health condition of the human body, how to improve the accuracy of the temperature of the specific acupoint or region in the obtained standard human body infrared image is a problem to be solved.
Disclosure of Invention
The invention aims to provide an infrared image sample processing method and a storage medium, which improve the accuracy of the temperature of specific acupuncture points or areas in an obtained standard human infrared image.
According to a first aspect of the present invention, there is provided a human infrared image sample processing method, comprising the steps of:
s100, acquiring a human infrared image sample set P= { P 1 ，p 2 ，…，p i ，…，p N P, where i For the ith human body infrared image sample, the value range of i is 1 to N, and N is the number of human body infrared image samples in P.
S200, traversing P, if P i For a normal sample, then p i The initialization of append to P ', P' is Null.
S300, traversing P ', and grouping the P' according to the corresponding age, sex, region and season information to obtain C= { C 1 ，c 2 ，…，c j ，…，c M And (c), where c j For the j-th group of human infrared image sample set obtained by grouping P', the value range of j is 1 to M, and M is the number of groups included in C; m=a 1 *A 2 *A 3 *A 4 ，A 1 For the preset number of age intervals included by P', A 2 For the number of gender types included in P', A 3 For the number of zone types included in P', A 4 For the number of season types that P' includes.
S400, traversing C, and clustering C by using a K-means clustering method j Clustering to obtain c j ＝{c j,1 ，c j,2 ，…，c j,k ，…，c j,K And (c), where c j,k To pair c j Clustering to obtain a kth cluster, wherein the value range of K is 1 to K, and K is presetNumber of clusters.
S500, traversing C, if n j,k If the number of the samples is smaller than the preset number of samples, deleting c j In c) j,k Obtaining updated c j ，n j,k C is j,k Number of human infrared image samples.
S600, traversing C and obtaining updated C j Mean value vector EF of temperature vectors corresponding to all human infrared image samples j And outputs EF j 。
Compared with the prior art, the human infrared image sample processing method and the storage medium provided by the invention have obvious beneficial effects, can achieve quite technical progress and practicality, have wide industrial utilization value, and have at least the following beneficial effects:
the invention groups the normal samples in the human infrared image sample set according to age, sex, region and season information, so that each group of normal samples corresponds to the same age, sex, region and season, on the basis, the invention clusters each group, eliminates clusters with fewer human infrared image samples in each group, and obtains updated each group, because the probability that the human infrared image sample in the clusters with fewer human infrared image samples is an abnormal sample is relatively larger, compared with the temperature of a specific acupoint or region in the human infrared image of the standard obtained directly according to all the normal human infrared image samples corresponding to the same age, sex, region and season, the invention uses each updated group as the basis for calculating the temperature of each acupoint or region of the human infrared image of the standard corresponding to each group, and can improve the accuracy of the temperature of the specific acupoint or region in the obtained standard human infrared image.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a human infrared image sample processing method according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.
According to a first aspect of the present invention, there is provided a human infrared image sample processing method, as shown in fig. 1, comprising the steps of:
s100, acquiring a human infrared image sample set P= { P 1 ，p 2 ，…，p i ，…，p N P, where i For the ith human body infrared image sample, the value range of i is 1 to N, and N is the number of human body infrared image samples in P.
According to the invention, P is a human body infrared image sample set, the human body infrared images are obtained by shooting different human bodies, the age, sex, region and the like corresponding to the human bodies possibly have differences, and the seasons for shooting the infrared images of the human bodies possibly also have differences.
It should be understood that the larger the value of N, the larger the number of samples based on the present invention, the more likely it is to reduce the interference of accidental factors on the temperature of specific acupoints or regions in the standard human infrared image, and improve EF acquired in S600 j Accuracy of (3).
S200, traversing P, if P i For a normal sample, then p i The initialization of append to P ', P' is Null.
Optionally, the invention judges p manually i Whether the sample is a normal sample or not, or judging p according to preset judging conditions i Whether it is a normal sample. Optionally, preset judgmentThe breaking condition is at least one of the following judging conditions: whether the conventional physical examination data exceeds a normal value; whether the human body infrared image accords with the infrared imaging characteristics of the infrared thermal imaging healthy person or not; whether the population meets the mild quality characteristics or not; whether the excessive diseases occur in the information acquisition table. It should be understood that the judgment result corresponding to the normal sample is: the infrared imaging characteristics of healthy people are met without exceeding normal values, the infrared imaging characteristics of healthy people are met, the mild characteristics are met, and excessive diseases are not caused.
According to the invention, if p i For abnormal samples, p will not be considered in the process of obtaining the temperature of a specific acupoint or region in the standard infrared image of human body i 。
S300, traversing P ', and grouping the P' according to the corresponding age, sex, region and season information to obtain C= { C 1 ，c 2 ，…，c j ，…，c M And (c), where c j For the j-th group of human infrared image sample set obtained by grouping P', the value range of j is 1 to M, and M is the number of groups included in C; m=a 1 *A 2 *A 3 *A 4 ，A 1 For the preset number of age intervals included by P', A 2 For the number of gender types included in P', A 3 For the number of zone types included in P', A 4 For the number of season types that P' includes.
According to the invention, the age, sex, region and season information corresponding to each human infrared image sample can be different, and the differences can influence the acquisition of the temperature of a specific acupoint or region in the standard human infrared image, so that the invention groups P' according to the corresponding age, sex, region and season information, and further analyzes the temperature of the specific acupoint or region in the standard human infrared image on the basis of the same age interval, the same sex, the same region and the same season.
It should be appreciated that if P' includes a preset number of age intervals of A 1 P' includes a number of gender types A 2 Number of zone types A included in P 3 P' includes a number of season types A 4 Then, according to the dividing standard of dividing human infrared images of different age ranges, different sexes, different regions and different seasons into different groups, dividing P' to obtain the group number M=A 1 *A 2 *A 3 *A 4 。
As a specific embodiment, the preset age interval is: 0-6 years old (pre-school), 7-12 years old (primary school), 13-15 years old (junior middle school), 16-18 years old (senior middle school), 19-35 years old, 36-45 years old, 46-55 years old, 56-65 years old, 66-75 years old, 76-85 years old and 86-100 years old; gender categories are male and female; the region types are the south and the north; the season types are spring, summer, autumn and winter. It is known to those skilled in the art that any division criteria are used in the prior art to divide age, gender, region and season information, which falls within the scope of the present invention.
S400, traversing C, and clustering C by using a K-means clustering method j Clustering to obtain c j ＝{c j,1 ，c j,2 ，…，c j,k ，…，c j,K And (c), where c j,k To pair c j And clustering to obtain a kth cluster, wherein the value range of K is 1 to K, and K is the preset cluster number.
The invention utilizes the K-means clustering method to perform c j Clustering is performed, including:
s410, from c j And randomly selecting K human infrared image samples as centroids.
S420 for c j The method comprises the steps of obtaining the distance between each human body infrared image sample and each centroid, and dividing the distance into a set of centroids closest to the human body infrared image sample; wherein c j B1 th human body infrared image sample p j,b1 With the kth centroid p j,k Distance of dj b1,k ，dj b1,k And sim (F) j,b1 ，F j,k ) In negative correlation, the value range of b1 is 1 to Z j ，Z j C is j The number of the infrared image samples of the middle human body is sim () which is the similarity, F j,b1 Is p j,b1 Corresponding temperature vector, F j,b1 ＝(T b1,1 ，T b1,2 ，...，T b1,q ，...，T b1,Q )，T b1,q Is p j,b1 The temperature corresponding to the q-th acupoint or region F j,k Is p j,k Corresponding temperature vector, F j,k ＝(T k,1 ，T k,2 ，...，T k,q ，...，T k,Q )，T k,q Is p j,k The corresponding temperature of the Q-th acupoint or region, the value range of Q is 1 to Q, and Q is the preset acupoint and region number.
According to the invention, the temperature vector is constructed based on the temperature of the acupoints and/or the temperature of the region of the human body. Alternatively, the temperature of the acupoints of the whole body/part of the human body is used to construct a temperature vector, or the temperature of the region of the whole body/part of the human body is used to construct a temperature vector, or the temperature of the acupoints of the whole body/part of the human body and the temperature of the region of the whole body/part are used to construct a temperature vector. Those skilled in the art will appreciate that constructing temperature vectors using the temperature of any acupoint and the temperature of the region in the prior art falls within the scope of the present invention.
Optionally, sim (F j,b1 ，F j,k ). Those skilled in the art will appreciate that any similarity calculation method used in the prior art to calculate the similarity between two vectors falls within the scope of the present invention.
Alternatively, dj b1,k ＝1/(1+sim(F j,b1 ，F j,k )). Those skilled in the art will appreciate that any expression used in the prior art to characterize a negative correlation between two parameters falls within the scope of the present invention.
S430, c j After each human infrared image sample is divided, the mass centers of K sets are obtained again.
According to the invention, the center of mass of the re-acquired set is the human infrared image sample corresponding to the temperature vector with the maximum similarity with a in the set, and a is the average vector of the temperature vectors corresponding to the human infrared image sample in the set.
S440, repeating the steps S420-S430 until the obtained mass center is not changed any more or the repeated times reach the set times, and ending the clustering.
Thus, pair c can be obtained j And carrying out K clustered clusters.
S500, traversing C, if n j,k If the number of the samples is smaller than the preset number of samples, deleting c j In c) j,k Obtaining updated c j ，n j,k C is j,k Number of human infrared image samples.
According to the invention, if n j,k Less than the preset sample number, judge c j,k If the human body infrared image sample is an abnormal sample, c will not be considered in the process of acquiring the temperature of the specific acupoint or region in the standard human body infrared image j,k An infrared image sample of a human body.
Preferably, if n j,k If the number of the samples is greater than or equal to the preset number of samples, EF is determined j,k Add to EF' j And outputs EF' j ；EF’ j Is initialized to Null, EF j,k C is j,k The average value vector of the temperature vectors corresponding to the human infrared image samples. EF 'of the invention' j Is composed of average value vectors of temperature vectors corresponding to each cluster with the number of human infrared image samples in the cluster being more than or equal to the preset number of samples, EF' j Each vector of the array corresponds to a cluster, EF 'with the number of human infrared image samples in the cluster being more than or equal to the preset number of samples' j Can be used to characterize the temperature vector of the corresponding cluster, thus, the present invention outputs EF' j Can judge the corresponding age as A 1,j Sex is A 2,j The region is A 3,j And season A 4,j Whether the human infrared image of (a) provides more reference basis normally, wherein A is 1,j C is j Age of corresponding, A 2,j C is j Corresponding gender, A 3,j C is j Corresponding region A 4,j C is j Corresponding seasons.
It should be appreciated that the grouping of P' in S300 may be a relatively broad group, e.g., if the grouping is performed in the south and north according to the geographic type, in the case of consistency of age, gender and season information, then the region corresponding to the infrared image of the human bodyOnly the north and south distinction will be made; however, the corresponding regions of different human infrared images also belonging to north or south may also have larger differences, and the differences corresponding to these regions may also lead to different health condition judgment standards, so the invention will c j Clustering, wherein the average value vector of the temperature vector of each cluster can be used for reflecting the characteristics of the temperature vector of the cluster, and a later user can refer to EF' j The average value vector of the temperature vectors corresponding to each cluster in the image is used for more accurately judging the human infrared image to be judged.
In the present invention, the average vector of the plurality of temperature vectors is a vector formed by the average values of the elements corresponding to the temperature vectors. For example, the first temperature vector is [ T ] 1,1 ，T 1,2 ，…，T 1,747 ]The second temperature vector is [ T ] 2,1 ，T 2,2 ，…，T 2,747 ]The third temperature vector is [ T ] 3,1 ，T 3,2 ，…，T 3,747 ]Then the average vector of these three temperature vectors is: [ (T) 1,1 +T 2,1 +T 3,1 )/3，(T 1,2 +T 2,2 +T 3,2 )/3，…，(T 1,747 +T 2,747 +T 3,747 )/3]。
Optionally, the preset number of samples is N 'that is a multiple of the set ratio, for example 0.1% ×n'; or the preset number of samples is a fixed value.
S600, traversing C and obtaining updated C j Mean value vector EF of temperature vectors corresponding to all human infrared image samples j And outputs EF j 。
According to the invention, EF j For updated c j The average value vector of the temperature vectors corresponding to the human infrared image samples is updated by the updated c j The middle human body infrared images are all that the age of the normal human body health condition is A 1,j Sex is A 2,j The region is A 3,j And season A 4,j Is capable of inputting EF j As age A 1,j Sex is A 2,j The region is A 3,j And season A 4,j Is a standard human infrared image of (2)A corresponding temperature vector.
It should be understood that the temperature vector is composed of temperatures of multiple acupoints and/or regions, and is based on EF j When the infrared image of the human body to be judged is judged, the temperature of the acupuncture point and/or the region in the infrared image of the human body to be judged can be compared with the temperature of the corresponding acupuncture point and/or region in the standard infrared image of the human body.
Embodiments of the present invention also provide a non-transitory computer readable storage medium having stored therein at least one instruction or at least one program loaded by a processor and performing the method of the embodiments of the present invention.
While certain specific embodiments of the invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the invention. Those skilled in the art will also appreciate that many modifications may be made to the embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.
Claims (8)
1. The human body infrared image sample processing method is characterized by comprising the following steps of:
s100, acquiring a human infrared image sample set P= { P 1 ，p 2 ，…，p i ，…，p N P, where i For the ith human body infrared image sample, the value range of i is 1 to N, and N is the number of human body infrared image samples in P;
s200, traversing P, if P i For a normal sample, then p i The initialization added to P ', P' is Null; the normal sample is a human body infrared image sample of a human body with normal physical examination data not exceeding a normal value, a human body infrared image sample conforming to infrared imaging characteristics of an infrared thermal imaging healthy human, a human body infrared image sample conforming to a human body with mild characteristic crowd or a human body infrared image sample of a human body without excessive diseases in an information acquisition table;
S300, traversing P ', and grouping P' according to the corresponding age, sex, region and season information to obtain C= { C 1 ，c 2 ，…，c j ，…，c M And (c), where c j For the j-th group of human infrared image sample set obtained by grouping P', the value range of j is 1 to M, and M is the number of groups included in C; m=a 1 *A 2 *A 3 *A 4 ，A 1 For the preset number of age intervals included by P', A 2 For the number of gender types included in P', A 3 For the number of zone types included in P', A 4 Number of season types included for P';
s400, traversing C, and clustering C by using a K-means clustering method j Clustering to obtain c j ＝{c j,1 ，c j,2 ，…，c j,k ，…，c j,K And (c), where c j,k To pair c j Clustering to obtain kth clusters, wherein the value range of K is 1 to K, and K is the preset number of clusters;
s500, traversing C, if n j,k If the number of the samples is smaller than the preset number of samples, deleting c j In c) j,k Obtaining updated c j ，n j,k C is j,k The number of the middle human body infrared image samples;
s600, traversing C and obtaining updated C j Mean value vector EF of temperature vectors corresponding to all human infrared image samples j And outputs EF j ；
In the S400, c is clustered by using a K-means clustering method j Clustering is performed, including:
s410, from c j Randomly selecting K human infrared image samples as centroids;
s420 for c j The method comprises the steps of obtaining the distance between each human body infrared image sample and each centroid, and dividing the distance into a set of centroids closest to the human body infrared image sample; wherein c j B1 th human body infrared image sample p j,b1 With the kth centroid p j,k Distance of dj b1,k ，dj b1,k And sim (F) j,b1 ，F j,k ) In negative correlation, the value range of b1 is 1 toZ j ，Z j C is j The number of the infrared image samples of the middle human body is sim () which is the similarity, F j,b1 Is p j,b1 Corresponding temperature vector, F j,b1 ＝(T b1,1 ，T b1,2 ，...，T b1,q ，...，T b1,Q )，T b1,q Is p j,b1 The temperature corresponding to the q-th acupoint or region F j,k Is p j,k Corresponding temperature vector, F j,k ＝(T k,1 ，T k,2 ，...，T k,q ，...，T k,Q )，T k,q Is p j,k The temperature corresponding to the Q-th acupoint or region, the value range of Q is 1 to Q, and Q is the number of preset acupoints and regions;
s430, c j After each human body infrared image sample is divided, re-acquiring the mass centers of K sets;
s440, repeating the steps S420-S430 until the obtained mass center is not changed any more or the repeated times reach the set times, and ending the clustering.
2. The method according to claim 1, wherein in S500, if n j,k If the number of the samples is greater than or equal to the preset number of samples, EF is determined j,k Add to EF' j And outputs EF' j ；EF’ j Is initialized to Null, EF j,k C is j,k The average value vector of the temperature vectors corresponding to the human infrared image samples.
3. The method according to claim 1, wherein in S200, p is determined manually or by a predetermined determination condition i Whether it is a normal sample.
4. The method of claim 1, wherein the predetermined age interval is: 0-6 years old, 7-12 years old, 13-15 years old, 16-18 years old, 19-35 years old, 36-45 years old, 46-55 years old, 56-65 years old, 66-75 years old, 76-85 years old and 86-100 years old; the gender categories are male and female; the region types are the south and the north; the season types are spring, summer, autumn and winter.
5. The method according to claim 1, wherein in S420, sim (F) is obtained using a cosine similarity algorithm j,b1 ，F j,k )。
6. The method of claim 1, wherein in S420, dj b1,k ＝1/(1+sim(F j,b1 ，F j,k ))。
7. The method according to claim 1, wherein in S500, the preset number of samples is 0.1% ×n ', N ' is the number of human infrared image samples in P '.
8. A non-transitory computer readable storage medium having stored therein at least one instruction or at least one program, wherein the at least one instruction or the at least one program is loaded and executed by a processor to implement the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211204405.8A CN115546543B (en) | 2022-09-29 | 2022-09-29 | Human body infrared image sample processing method and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211204405.8A CN115546543B (en) | 2022-09-29 | 2022-09-29 | Human body infrared image sample processing method and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115546543A CN115546543A (en) | 2022-12-30 |
| CN115546543B true CN115546543B (en) | 2023-07-28 |
Family
ID=84732526
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211204405.8A Active CN115546543B (en) | 2022-09-29 | 2022-09-29 | Human body infrared image sample processing method and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115546543B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117462086B (en) * | 2023-10-30 | 2024-07-26 | 北京鹰之眼智能健康科技有限公司 | Infrared image processing system, electronic device, and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111242946A (en) * | 2020-03-03 | 2020-06-05 | 广州紫川电子科技有限公司 | Human body temperature anomaly detection method and device based on infrared thermal imaging |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110084267B (en) * | 2019-03-12 | 2023-05-26 | 北京旷视科技有限公司 | Portrait clustering method, device, electronic equipment and readable storage medium |
| CN111537083A (en) * | 2020-06-22 | 2020-08-14 | 益逻触控系统公司 | Method and apparatus for measuring body temperature of a person |
| CN112446325A (en) * | 2020-11-26 | 2021-03-05 | 厦门理工学院 | 2D-3D non-contact human body measurement method for old people |
| CN114724172A (en) * | 2022-02-11 | 2022-07-08 | 深圳市创索佳电子有限公司 | Infrared imaging human body posture recognition method and device |
| CN114582489A (en) * | 2022-02-21 | 2022-06-03 | 北京中医药大学 | Infrared thermal image auxiliary acupoint selection system for acupuncture treatment of knee osteoarthritis |
-
2022
- 2022-09-29 CN CN202211204405.8A patent/CN115546543B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111242946A (en) * | 2020-03-03 | 2020-06-05 | 广州紫川电子科技有限公司 | Human body temperature anomaly detection method and device based on infrared thermal imaging |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115546543A (en) | 2022-12-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Schaltenbrand et al. | Sleep stage scoring using the neural network model: comparison between visual and automatic analysis in normal subjects and patients | |
| Nakajima et al. | Footprint-based personal recognition | |
| CN111161879B (en) | Disease prediction system based on big data | |
| CN108763590B (en) | Data clustering method based on double-variant weighted kernel FCM algorithm | |
| CN115546543B (en) | Human body infrared image sample processing method and storage medium | |
| Albergante et al. | Estimating the effective dimension of large biological datasets using Fisher separability analysis | |
| CN110364259B (en) | Method, system, medium and electronic device for predicting altitude disease | |
| CN108920893A (en) | A kind of cranio-maxillofacial bone and soft tissue form prediction method based on artificial intelligence | |
| CN104866713B (en) | Locally differentiate the Kawasaki disease and fever diagnostic system of subspace insertion based on increment | |
| CN112233742B (en) | Medical record document classification system, equipment and storage medium based on clustering | |
| CN116386853A (en) | Intelligent medical-oriented deep separable convolution dual-aggregation federal learning method | |
| CN108596228B (en) | Brain function magnetic resonance image classification method based on unsupervised fuzzy system | |
| Akmalia et al. | Skin diseases classification using local binary pattern and convolutional neural network | |
| Karaca et al. | Clustering multiple sclerosis subgroups with multifractal methods and self-organizing map algorithm | |
| CN117953973B (en) | Specific biological sequence prediction method and system based on sequence homology | |
| CN116680655A (en) | Clustering integration method for pathological signals of cervical spondylosis | |
| CN105894493A (en) | FMRI data feature selection method based on stability selection | |
| CN110334748A (en) | The cancer subtypes classification method of multiple groups data integration is carried out based on D-S evidence theory | |
| Zhang et al. | Blood vessel segmentation in fundus images based on improved loss function | |
| Lu et al. | Data enhancement and deep learning for bone age assessment using the standards of skeletal maturity of hand and wrist for chinese | |
| Hernández-Contreras et al. | Measuring changes in the plantar temperature distribution in diabetic patients | |
| CN111369490B (en) | Method for extracting bone X-ray image characteristics to judge osteoporosis | |
| CN117195027A (en) | Cluster weighted clustering integration method based on member selection | |
| Rulaningtyas et al. | Histopathology grading identification of breast cancer based on texture classification using GLCM and neural network method | |
| CN114693646B (en) | Corneal endothelial cell active factor analysis method based on deep learning |
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 |