CN116797778A - Region of interest acquisition method, electronic device, and storage medium - Google Patents
Region of interest acquisition method, electronic device, and storage medium Download PDFInfo
- Publication number
- CN116797778A CN116797778A CN202310288043.3A CN202310288043A CN116797778A CN 116797778 A CN116797778 A CN 116797778A CN 202310288043 A CN202310288043 A CN 202310288043A CN 116797778 A CN116797778 A CN 116797778A
- Authority
- CN
- China
- Prior art keywords
- line
- acupoint
- acupoints
- region
- horizontal line
- 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 35
- 239000002131 composite material Substances 0.000 claims description 17
- 238000001467 acupuncture Methods 0.000 claims description 5
- 210000003414 extremity Anatomy 0.000 description 28
- 238000004458 analytical method Methods 0.000 description 7
- 230000036760 body temperature Effects 0.000 description 5
- 239000003814 drug Substances 0.000 description 5
- 210000001015 abdomen Anatomy 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 210000002414 leg Anatomy 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000000746 body region Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 210000002310 elbow joint Anatomy 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000000629 knee joint Anatomy 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 208000011580 syndromic disease Diseases 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
- 210000003857 wrist joint Anatomy 0.000 description 1
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
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a method for acquiring a region of interest, which comprises the following steps: identifying a human body contour line in the target infrared image to obtain a corresponding human body contour line pixel point set PL; identifying a region of interest in the limb and first and second characteristic acupoints CA1 and CA2 in the torso, respectively; acquiring remaining acupoints based on the identified CA1 and CA 2; the trunk is divided into a plurality of interested areas based on the obtained n set acupoints, and the boundaries of the areas positioned on two sides are human body contour lines. The invention also provides electronic equipment and a storage medium. The invention can make the acquired interested region more accurate.
Description
Technical Field
The present invention relates to the field of computer application technologies, and in particular, to a method for acquiring a region of interest, an electronic device, and a storage medium.
Background
The theory of yin-yang balance of human body channels and collaterals and acupoints is one of the core theory of traditional Chinese medicine, the infrared thermal imaging of the body surface of the human body can clearly reflect the temperature of each acupoint and the thermal order of each channel and collaterals of the human body, and the physique and syndrome features of the human body can be obtained through the analysis of the temperature of each acupoint and the thermal order of each channel and collaterals of the body surface of the human body. For example, according to the theory of traditional Chinese medicine, a human torso region is divided into a plurality of set regions, and the temperature analysis of these regions is used to detect the body function state of the human body. However, the existing region division does not include all regions within the body contour, for example, there may be unused regions between the divided regions and the body contour, as shown in fig. 1. Thus, there is a problem in that the analysis result is inaccurate.
Disclosure of Invention
Aiming at the technical problems, the invention adopts the following technical scheme:
the embodiment of the invention provides a method for acquiring a region of interest, which comprises the following steps:
the embodiment of the invention provides a method for acquiring a region of interest, which comprises the following steps:
s100, identifying human body contour lines in the target infrared image to obtain a corresponding human body contour line pixel point set PL= (PL) 1 ，PL 2 ，…，PL r ，…，PL M )，PL r R is the r pixel point in PL, the value of r is 1 to M, M is the number of pixels in PL, PL r Is (x) Lr ，y Lr )；
S200, respectively identifying m interested areas in four limbs in a target infrared image and first and second characteristic acupuncture points CA1 and CA2 in a trunk to respectively obtain m interested area pixel point sets, first and second characteristic pixel points PA1 and PA2; wherein the kth region of interest pixel point set is PROI k ＝(PROI k1 ，PROI k2 ，…，PROI kg ，…，PROI kf(k) )，PROI kg Is PROI k The g pixel point in (1) is from 1 to f (k), and f (k) PROI k The number of the pixel points in (a), and the value of k is 1 to m; CA1 and CA2 are the acupoints of n set acupoints in trunk, CA1 and CA2 are on the central axis of human body, CA2 is below CA1, and PA1 and PA2 areThe coordinates of the pixel points are (x) A1 ，y A1 ) And (x) A2 ，y A2 )；
S300, dividing a composite region surrounded by contour lines of the head and the neck into H regions of interest based on CA1 and CA2 and a set division rule, wherein the region of interest located at the outermost side of the composite region comprises the contour line of the corresponding composite region;
s400, acquiring the rest acupoints in the n set acupoints in the target infrared image based on the CA1 and CA2 obtained by recognition;
s500, dividing a trunk area surrounded by contour lines of the trunk into F interested areas based on the acquired n set acupoints, wherein the interested areas positioned at the outermost sides of the trunk area comprise corresponding trunk contour lines.
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 and executed by a processor to implement a method as described above.
The embodiment of the invention also provides an electronic device comprising a processor and the non-transitory computer readable storage medium. The invention has at least the following beneficial effects:
the method for acquiring the region of interest provided by the embodiment of the invention can extend the region of interest of the human body to the contour line of the human body at least, so that the region of interest as many as possible can be acquired, and further the analysis can be more accurate.
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 schematic diagram of a conventional torso region of interest division.
Fig. 2 is a flowchart of a method for acquiring a region of interest according to an embodiment of the present invention.
Fig. 3 is a schematic diagram illustrating the division of a region of interest in a composite region 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.
An embodiment of the present invention provides a method for acquiring a region of interest, as shown in fig. 2, where the method may include the following steps:
s100, identifying human body contour lines in the target infrared image to obtain a corresponding human body contour line pixel point set PL= (PL) 1 ，PL 2 ，…，PL r ，…，PL M )，PL r R is the r pixel point in PL, the value of r is 1 to M, M is the number of pixels in PL, PL r Is (x) Lr ，y Lr )。
In the embodiment of the invention, the x-axis of the coordinate system where the target infrared image is located is the transverse direction of the human body, the y-axis is the longitudinal direction of the human body, and the origin of coordinates can be the lower left corner of the image.
In the embodiment of the invention, the target infrared image can be acquired from the image library, and the target infrared image can also be acquired in real time through the infrared camera device.
Further, in an embodiment of the present invention, PL may be obtained based on the following steps:
s101, identifying a human body contour line in a target infrared image to obtain a corresponding human body contour line initial pixel point set PLI= (PLI) 1 ，PLI 2 ，…，PLI r ，…，PLI M )。
S102, acquiring a temperature set TCI= (TLI) corresponding to the PLI 1 ，TLI 2 ，…，TLI r ，…，TLI M )，TLI r For PLI r Corresponding temperature.
Those skilled in the art will recognize that any temperature at which each pixel is obtained from an infrared image is within the scope of the present invention.
S103, if TLI r < T0, execute S104; t0 is a preset temperature value; otherwise, S107 is performed.
In an exemplary embodiment of the present invention, T0 is a preset average human body temperature threshold, which may be an empirical value, for example, 36.5 °. Specifically, T0 may be obtained by:
t0=avg (T1, T2, …, tz, …, TG), tz being the body temperature of the z-th user, z having a value of 1 to G, G being the number of users. G users can obtain the body temperature in a random mode, and the body temperature of each user can be measured by a temperature measuring device.
In another exemplary embodiment of the present invention, t0=avg (T 1 ，t 2 ，…，t w ，…，t N ) Wherein t is w And N is the number of pixels in the area surrounded by the human body contour line identified in S101, wherein the temperature corresponds to the w-th pixel in the area surrounded by the human body contour line identified in S101. Compared with the previous embodiment, the accuracy of the T0 in this embodiment can be improved by using the body temperature of the user corresponding to the target infrared image as the reference temperature.
S104, if x LIr ＜x 0 Setting x LIr ＝x LIr +b, if x LIr ＞x 0 Setting x LIr ＝x LIr -b；x 0 Is the abscissa, x of the central axis of the human body corresponding to the target infrared image in the target infrared image LIr For TLI r The corresponding abscissa of the pixel points, b is the number of preset pixel points; s105 is performed.
In one exemplary embodiment, b is set to a value that does not affect the accuracy of acupoint recognition, e.g., b=1.
S105, if the pixel point (x LIr ，y LIr ) The corresponding temperature is less than T0, S104 is executed, i.e. the abscissa of the pixel is continuously adjusted until the corresponding temperatureGreater than T0 or equal to T0; otherwise, S106 is performed.
S106, setting r=r+1, and if r is less than or equal to M, executing S103; otherwise, the control program is exited.
The technical effects of S101 to S106 are: because the body structures of the users are different, the human body contour lines identified by the trained image identification models may have deviation, and the identified human body contour lines can be adjusted through S101-S106, so that the human body contour lines are more accurate.
S200, respectively identifying m interested areas in four limbs in a target infrared image and first and second characteristic acupuncture points CA1 and CA2 in a trunk to respectively obtain m interested area pixel point sets, first and second characteristic pixel points PA1 and PA2; wherein the kth region of interest pixel point set is PROI k ＝(PROI k1 ，PROI k2 ，…，PROI kg ，…，PROI kf(k) )，PROI kg Is PROI k The g pixel point in (1) is from 1 to f (k), and f (k) PROI k The number of the pixel points in (a), and the value of k is 1 to m; CA1 and CA2 are the acupoints of n set acupoints in trunk, CA1 and CA2 are on the central axis of human body, CA2 is below CA1, and the pixel coordinates of PA1 and PA2 are (x) A1 ，y A1 ) And (x) A2 ，y A2 )。
In the embodiment of the invention, the human body contour lines and the characteristic acupuncture points in the target infrared image can be identified through the trained image identification model. Specifically, the trained image recognition model may be obtained by inputting a sample image labeled with a human body contour line, a region of interest in an extremity, CA1 and CA2 into a neural network model for training, and the specific training mode may be the prior art. In the embodiment of the present invention, the region of interest in the limb may be a joint region such as a wrist joint, an elbow joint, a knee joint, and the like. Due to the symmetry of the limb, a classification algorithm may be used to identify the region of interest in the limb, i.e. when the region of interest in the limb is identified, whether it is a left limb or a right limb may be determined by the relationship between the abscissa of the identified region of interest and the abscissa of the feature acupoint.
In the case where n set acupoints are acupoints in the front torso region, the target infrared image is a human front image, CA1 may be an easily identifiable Tiantu acupoint, and CA2 may be an easily identifiable shenque acupoint. In the case where n set acupoints are acupoints in the back torso region, the target infrared image is a back image of a human body, CA1 may be a large vertebral acupoint that is easily identified, and CA2 may be a long strong acupoint that is easily identified.
In the embodiment of the invention, the region of interest is a region which is divided into human body regions based on analysis requirements, and can be divided based on the analysis requirements and the theory of traditional Chinese medicine.
S300, dividing a composite region surrounded by contour lines of the head and the neck into H regions of interest based on CA1 and CA2 and a set division rule, wherein the region of interest located at the outermost side of the composite region comprises the contour line of the corresponding composite region.
S400, acquiring the rest acupoints in the n set acupoints in the target infrared image based on the CA1 and CA2 obtained through recognition.
Further, S400 specifically includes:
s402, obtaining y from PL A1 Is defined by two symmetrical pixel point coordinates (x 01 ，y A1 ) And (x) 02 ，y A1 ) I.e. two points of intersection of a first line, which is a line passing through the first characteristic point and perpendicular to the central axis of the body, and the human body contour line, and acquiring the ordinate y from the PL A2 Is defined by two symmetrical pixel point coordinates (x 03 ，y A2 ) And (x) 04 ，y A2 ) Namely, two intersection points of a second straight line and a human body contour line, wherein the second straight line passes through the second characteristic acupoint and is perpendicular to the central axis of the human body; wherein x is 01 ＜x A1 ＜x 02 ，x 03 ＜x A2 ＜x 04 。
S404, acquiring (min (x) 01 ，x 03 )，y A1 ) Or (min (x) 02 ，x 04 )，y A1 ) The corresponding pixel point coordinates are used as coordinates (x A3 ，y A3 ) I.e. select the firstThe coordinate corresponding to the shortest intersection line of the intersection line and the second intersection line is taken as the coordinate of CA3, the first intersection line is the intersection line between the first straight line and the human body contour line, and the second intersection line is the intersection line between the second straight line and the human body contour line.
In an embodiment of the invention, CA3 may be a shoulder peak.
S406, obtaining the transverse length Deltax= |x A3 -x A1 ∣/W 13 And obtaining the straight-in length Δy= |y A2 -y A1 ∣/V 12 ，W 13 V is the number of transverse dimensions between CA1 and CA3 12 Is the number of straight inches between CA1 and CA 2. W (W) 13 And V 12 Can be determined based on the theory of traditional Chinese medicine.
S408, taking CA1 or CA2 as a reference acupoint, and acquiring the rest acupoints in the n set acupoints in the target infrared image based on the position relation table between the Deltax and Deltay and the n set acupoints.
In the embodiment of the invention, the position association relationship between acupoints can be determined based on the theory of traditional Chinese medicine, such as acupuncture.
Specifically, the n set acupoints may include n1 first acupoints located on the central axis of the human body and n2 second acupoints located on both sides of the central axis of the human body, and the positional relationship table between the n set acupoints includes a first acupoint positional relationship table and a second acupoint positional relationship table, wherein the ith row of the first acupoint positional relationship table includes (C1) i ，h1，P ci )，C1 i An ID of an i-th first acupoint of the n1 first acupoints, i having a value of 1 to n1, h1 having a value of 1 or 2, wherein h1=1 represents C1 i Is positioned on the upper side of the reference acupoint, and h1=2 represents C1 i Is positioned at the lower side of the reference acupoint, P ci Representing the number of straight-in-between the i-th first acupoint and the reference acupoint. The j th row of the second acupoint position relationship table includes (C2 j ，C1 je ，(h1，PX je )，(h2，PY je ))，C2 j ID, C1 for the j-th second acupoint of the n2 second acupoints je Is C2 j The value of h2 is 3 or 4, and h2=3 represents C2 j At C1 je Left side of the corresponding first acupoint, h2=4 represents C2 j At C1 je Right side of corresponding first acupoint PX je Is C2 j And C1 je The number of transverse dimensions between the h1 st sides of the corresponding first acupoints PY je Is C2 j And C1 je The number of straight dimensions between the h2 side of the corresponding first acupoint, e, is 1 to n1, and j, is 1 to n2. In the embodiment of the present invention, the ID of the acupoint may be the name of the acupoint or any other identifier capable of knowing the name of the acupoint.
In the embodiment of the present invention, the lateral dimension refers to a unit of measure between acupoints in the lateral direction of the human body, for example, acupoint a is located at the left or right of acupoint B by X lateral dimensions. The straight dimension refers to a unit of measure between points located in the longitudinal direction of the human body, for example, point a is located at X straight dimension positions above or below point B.
In the embodiment of the invention, with C2 j The first acupoint associated with C2 j The first acupoint with the shortest distance between the first acupoint and the second acupoint in the chest area is located in the chest section, and the first acupoint of the second acupoint in the abdomen area is located in the abdomen section, which can be determined based on the existing human body acupoint map.
Those skilled in the art know that n set acupoints can be obtained from the target infrared image through the first acupoint position relationship table and the second acupoint position relationship table. In practical application, when the target infrared image is a frontal image of a human body, all acupoints on the conception vessel can be acquired through the first acupoint position relation table based on the Tiantu or Shenque, and then other acupoints, namely, abdomen meridian acupoints, can be acquired according to the conception vessel and the second acupoint position relation table. When the target infrared image is a human back image, all the acupoints on the governor vessel can be acquired through the first acupoint position relation table based on the greater vertebrae or the greater vertebrae, and then other acupoints, namely the back meridian acupoints, can be acquired according to the governor vessel and the second acupoint position relation table.
In some special cases, such as the case of too thin a human body waist line, the acupoints near the human body contour line may fall outside the human body contour line during calculation, and therefore, the abscissa calculated in this case needs to be adjusted so that the calculated acupoints are located within the human body contour line.
Specifically, in S408, any second acupoint C2 is acquired j If h2=3, if (x je -P je *△x)＜x c1 The coordinates (x c1 +a，y je ) As C2 j Coordinates of the corresponding acupoints; if h2=4, if (x je +P je *△x)＞x c2 The coordinates (x c2 -a，y je ) As C2 j Coordinates of the corresponding acupoints; wherein x is je And y je Respectively C1 je The corresponding abscissa and ordinate, x of the first acupoint c1 Is the ordinate in PL is y je And the abscissa, x, of the pixel point located on the left side of the reference acupoint c2 Is the ordinate in PL is y je And the abscissa of the pixel points located on the right side of the reference acupoint, a, is a preset number of pixels, in one example, a=1.
S500, dividing a trunk area surrounded by contour lines of the trunk into F interested areas based on the obtained n set acupoints, wherein the interested area positioned at the outermost side of the trunk area comprises corresponding trunk contour lines, namely R1n_R2n_ … n_Rp_ … n_RF=null, R1n_R2_ … _Rp_ … _RF=R, rp is the p interested area in the F interested areas, and R is the area corresponding to the trunk in the target infrared image.
In the embodiment of the invention, F interested areas can be set based on actual needs. Each region may include 1 acupoint or a plurality of acupoints, and the present invention is not particularly limited as long as F regions of interest can cover the entire torso region, i.e., the boundaries of the regions of interest located on both sides of the torso are human body contours.
According to the method for acquiring the region of interest, which is provided by the embodiment of the invention, the region of interest of the trunk part can be extended to the contour line of the human body, so that the region of interest as many as possible can be acquired, and further, the analysis can be more accurate.
Further, in the embodiment of the present invention, the following steps are further included after S200:
s210, correcting m regions of interest.
In the embodiment of the invention, each of m interested areas is formed by two straight lines and two limb contour lines positioned between the two straight lines, namely, in the labeling process of a sample image, the two straight lines can be marked up and down at the positions corresponding to the interested areas of the limbs, and can be parallel lines or not, and the two straight lines can be set based on actual needs.
Further, in the embodiment of the present invention, S210 specifically includes:
s211, for the kth region of interest, acquiring the center O of the kth region of interest k ＝(x k ，y k ) Obtaining 4 intersection points P between two parallel lines corresponding to the kth region of interest and corresponding limb contour lines Lk1 ，P Lk2 ，P Lk3 ，P Lk4 ，P Lk1 ，P Lk2 ，P Lk3 ，P Lk4 Is (x) c Lk1 ，y c Lk1 )、(x c Lk2 ，y c Lk2 )、(x c Lk3 ，y c Lk3 )、(x c Lk4 ，y c Lk4 ) Wherein if x k ＞x A1 I.e. left limb, left hand or left leg, x c Lk1 ≤x c Lk2 ＜x k ，y c Lk1 ＞y c Lk2 ＞y k ，x c Lk4 ≤x c Lk3 ＜x k ，y c Lk3 ＞y c Lk4 ＞y k The method comprises the steps of carrying out a first treatment on the surface of the If x k ＜x A1 I.e. right limb, right hand or right leg, x c Lk2 ≤x c Lk1 ＜x k ，y c Lk1 ＞y c Lk2 ＞y k ，x c Lk3 ≤x c Lk4 ＜x k ，y c Lk3 ＞y c Lk4 ＞y k 。
In an embodiment of the invention, O k Can be obtained based on the existing mode. For example, x k ＝Avg(x k1 ，x k2 ，…，x kg ，…，x kf(k) )，y k ＝Avg(y k1 ，y k2 ，…，y kg ，…，y kf(k) )，(x kg ，y kg ) Is PROI kg Is defined by the coordinates of (a).
In the embodiment of the invention, P Lk1 ，P Lk2 ，P Lk3 ，P Lk4 Can be identified by a trained image recognition model.
S212, if passing P Lk1 And P Lk2 Straight line L1 and through P of (2) Lk3 And P Lk4 Is located outside the kth region of interest, and x is obtained k1 ＝max(x 1 Lk ，x 2 Lk ，…，x u1 Lk ，…，x W1 Lk (ii) and x k2 ＝min(x 1 Lk ，x 2 Lk ，…，x u2 Lk ，…，x W2 Lk ) S213 is performed; if both L1 and L2 are located inside the kth region of interest, S214 is performed; x is x u1 Lk Is positioned at P Lk1 And P Lk2 The u1 th abscissa in the coordinates corresponding to the limb contour line between the two, W1 is the position P Lk1 And P Lk2 The number of abscissas in coordinates corresponding to the limb contour lines therebetween; x is x u2 Lk Is positioned at P Lk3 And P Lk4 The u2 th abscissa in the coordinates corresponding to the limb contour line between the two, W2 is the position P Lk3 And P Lk4 And the number of abscissas in coordinates corresponding to the limb contour lines.
In the embodiment of the invention, the position P Lk1 And P Lk2 Coordinate sum corresponding to limb contour line between the two points is positioned at P Lk3 And P Lk4 Coordinates corresponding to the limb contour lines between the two can be obtained through PROI and PL.
In the embodiment of the invention, since P is known Lk1 And P Lk2 So that the linear equation of L1 can be obtained and then will be calculated by locating at P Lk1 And P Lk2 All the ordinate of the coordinates corresponding to the limb contour line are substituted into the linear equation of L1, so that all the abscissa of L1 can be obtained, and the coordinates corresponding to all the pixel points of L1 can be obtained. Similarly, the coordinates of all the pixels on L2 can be obtained.
For any pixel point on L1, if the abscissa of the pixel point is smaller than the corresponding abscissa on the corresponding limb contour line, it indicates that L1 is located outside the corresponding limb contour line, otherwise, it is located inside the corresponding limb contour line. Similarly, for any pixel on L2, if the abscissa of the pixel is greater than the corresponding abscissa on the corresponding limb contour, it indicates that L2 is located outside the corresponding limb contour, otherwise, it is located inside the corresponding limb contour.
S213, obtain x k1 And x k2 Corresponding pixel point P k1 And P k2 And get through P k1 And P k2 The straight line L0 of the first rectangular area is a first rectangular area of a symmetry axis, the height of the first rectangular area is H0, H0 is a set height, and the unit is a pixel; s215 is performed. H0 may be an empirical value.
Those skilled in the art know that any acquisition is performed to pass P k1 And P k2 The method of the first rectangular area with the straight line L0 of the (B) as the symmetry axis belongs to the protection scope of the invention.
S214, obtaining L=min (L1, L2, L3, L4), wherein L3 is P Lk2 And P Lk3 L4 is a straight line passing through P Lk1 And P Lk4 Acquiring a second rectangular area taking L as a bottom edge, wherein the height of the second rectangular area is H0; s215 is performed.
Those skilled in the art will recognize that any method of obtaining a second rectangular region with a bottom side L falls within the scope of the present invention. For example, four vertex coordinates of the second rectangular region may be obtained based on the coordinates of the two endpoints to which L corresponds and H0, specifically, for example, if L is L1, two vertices of the second rectangular regionThe coordinates of the points may be (x) c Lk1 ，y c Lk1 )、(x c Lk2 ，y c Lk2 ) The coordinates of the other two vertices are (x) c Lk1 +H0，y c Lk1 )、(x c Lk2 +H0，y c Lk2 ) If L is L2 or L3 or L4, four vertex coordinates of the second rectangular region may be acquired in a similar manner to l=l1.
And S215, taking the rectangular region as a k region of interest after correction.
Those skilled in the art know that all pixels in a rectangular area can be obtained based on the prior art, for example, the width and height of the rectangle are obtained through four vertex coordinates of the rectangular area, then each pixel coordinate point is obtained through two nested loops, and the whole rectangular area is covered, so that all pixels in the rectangular area are obtained.
The technical effect of S210 is that the region of interest in the limb can be more accurate, and in practical application, when the temperature is analyzed, the temperature of the region of interest is more accurate.
Further, in another embodiment of the present invention, S402 is replaced with:
s403, obtaining y from PL A1 Is defined by two symmetrical pixel point coordinates (x 01 ，y A1 ) And (x) 02 ，y A1 ) Namely, two intersection points of the first intersection line and the human body contour line; wherein x is 01 ＜x A1 ＜x 02 ，x 03 ＜x A2 ＜x 04 。
S404 is replaced with:
s405, will (x) 01 ，y A1 ) Or (x) 02 ，y A1 ) As the coordinates (x) of the reference feature point CA3 A3 ，y A3 ) Two intersections of the first intersection line and the human body contour line are regarded as coordinates of CA 3.
The technical effect of S403 and S405 is that inaccurate position of the obtained shoulder peak point caused by too thin waist line in the target infrared image can be avoided.
Further, in the embodiment of the present invention, after S200, the method further includes the following steps:
s220, if x A1 ≠x A2 Then set x A1 ＝x A2 ＝x 0 That is, if CA1 and CA2 are not on the central axis due to errors or the like, they need to be adjusted to the central axis to improve the accuracy of the acupoint recognition.
Further, in the embodiment of the present invention, the region of interest of the composite region may be divided based on actual needs, as long as the divided region of interest includes a corresponding contour line. In one exemplary embodiment, in the case that the target infrared image is a frontal image of a human body, S300 may specifically include:
s301, acquiring a first fixed point b1= (x) in the target infrared image b1 ，y b1 ) And a second fixed point b2= (x b2 ，y b2 ) As shown in fig. 3, x b1 ＝x A1 ，y b1 ＝y A1 +△V，x b2 ＝x A1 ，y b2 ＝y A1 And + [ delta ] V/2, [ delta ] V is the number of preset straight-dimension, preferably [ delta ] V is 3 preset straight-dimension, i.e., 3 cun upward of Tiantu acupoint. In the embodiment of the invention, 1 preset dimension is seventeenth of the height between Tiantu point and Shenque point, namely (y) A1 -y A2 )/17。
S302, a first horizontal line h1 and a second horizontal line h2 are respectively acquired. As shown in fig. 3, the first horizontal line is a straight line passing through the first fixing point and intersecting both ends with both side contour lines, and the second horizontal line is a straight line passing through the second fixing point and intersecting both ends with both side contour lines.
S303, a first vertical line v1 and a fourth horizontal line h4 are acquired. As shown in fig. 3, the first vertical line v1 is a straight line passing through a reference point b, which is the end point of the first horizontal line, and both ends of which intersect with the third horizontal line h3 and the overhead profile line, respectively, and the third horizontal line is a straight line passing through (x A1 ，y A1 ) And a straight line intersecting the contour lines on both sides; the fourth horizontal line is a straight line passing through the intersection of the first vertical line and the overhead profile line.
S304, respectively obtaining fifth to seventh horizontal lines intersecting with the contour line of the composite region, wherein the distance between the fifth horizontal line h5 and the fourth horizontal line h4, the distance between the fifth horizontal line h5 and the sixth horizontal line h6, the distance between the sixth horizontal line h6 and the seventh horizontal line h7 and the distance between the seventh horizontal line h7 and the first horizontal line h1 are equal, namely dividing the first vertical line into 4 parts, and respectively drawing the horizontal lines by using the average points to obtain the fifth to seventh horizontal lines.
S305, respectively obtaining a second vertical line and a third vertical line, wherein two ends of the second vertical line and the third vertical line are respectively connected with a fourth horizontal line and a first horizontal line, the distance between the second vertical line and the first vertical line is equal to the distance between the second vertical line and the corresponding endpoint of a sixth horizontal line, the distance between the third vertical line and the first vertical line is equal to the distance between the third vertical line and the corresponding endpoint of the sixth horizontal line, namely the sixth horizontal line is equally divided into 4 parts, and the second vertical line and the third vertical line are obtained by evenly dividing points on two sides to draw the vertical lines.
S306, obtaining the H regions of interest based on the first to seventh horizontal lines and the first to third vertical lines, as a grid region shown in fig. 3.
Further, in another embodiment of the present invention, in the case where the target infrared image is a back image of a human body,
s300 may be replaced with:
s310, identifying Tao Daoxue and the to-yang acupoint in the target infrared image, and dividing a composite region surrounded by the contour lines of the head and the neck into H regions of interest based on the identified Tao Daoxue and to-yang acupoint and a set division rule, wherein the region of interest located at the outermost side of the composite region comprises the contour lines of the corresponding composite region.
In this embodiment, the region of interest of the composite region is divided substantially the same as S301 to S306, except that the acupoint to which the fixed point is obtained in this embodiment is a pottery acupoint, and the preset dimension is Tao Daoxue and one tenth of the height between the acupoint and the sun acupoint.
Further, the method also comprises the following steps:
and S600, visually displaying the obtained (F+m) target infrared images of the regions of interest.
Those skilled in the art will recognize that any means of visually displaying the acquired (f+m) infrared images of the target of interest are within the scope of the present invention. Embodiments of the present invention also provide a non-transitory computer readable storage medium that may be disposed in an electronic device to store at least one instruction or at least one program for implementing one of the methods embodiments, the at least one instruction or the at least one program being loaded and executed by the processor to implement the methods provided by the embodiments described above.
Embodiments of the present invention also provide an electronic device comprising a processor and the aforementioned non-transitory computer-readable storage medium.
Embodiments of the present invention also provide a computer program product comprising program code for causing an electronic device to carry out the steps of the method according to the various exemplary embodiments of the invention as described in the specification, when said program product is run on the electronic device.
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 present disclosure is defined by the appended claims.
Claims (10)
1. A method of acquiring a region of interest, the method comprising the steps of:
s100, identifying human body contour lines in the target infrared image to obtain a corresponding human body contour line pixel point set PL= (PL) 1 ，PL 2 ，…，PL r ，…，PL M )，PL r R is the r pixel point in PL, the value of r is 1 to M, M is the number of pixels in PL, PL r Is (x) Lr ，y Lr )；
S200, respectively identifying m interested areas in four limbs in a target infrared image and first and second characteristic acupuncture points CA1 and CA2 in a trunk to respectively obtain m interested area pixel point sets, first and second characteristic pixel points PA1 and PA2; wherein the kth region of interest pixel point set is PROI k ＝(PROI k1 ，PROI k2 ，…，PROI kg ，…，PROI kf(k) )，PROI kg Is PROI k The g pixel point in (1) is from 1 to f (k), and f (k) PROI k The number of the pixel points in (a), and the value of k is 1 to m; CA1 and CA2 are the acupoints of n set acupoints in trunk, CA1 and CA2 are on the central axis of human body, CA2 is below CA1, and the pixel coordinates of PA1 and PA2 are (x) A1 ，y A1 ) And (x) A2 ，y A2 )；
S300, dividing a composite region surrounded by contour lines of the head and the neck into H regions of interest based on CA1 and CA2 and a set division rule, wherein the region of interest located at the outermost side of the composite region comprises the contour line of the corresponding composite region;
s400, acquiring the rest acupoints in the n set acupoints in the target infrared image based on the CA1 and CA2 obtained by recognition;
s500, dividing a trunk area surrounded by contour lines of the trunk into F interested areas based on the acquired n set acupoints, wherein the interested areas positioned at the outermost sides of the trunk area comprise corresponding trunk contour lines.
2. The method according to claim 1, further comprising the step, after S200, of:
s210, correcting m regions of interest;
s210 specifically includes:
s211, for the kth region of interest, acquiring the center O of the kth region of interest k ＝(x k ，y k ) Acquiring a k region of interest4 points of intersection P between two straight lines and corresponding limb contour lines Lk1 ，P Lk2 ，P Lk3 ，P Lk4 ，P Lk1 ，P Lk2 ，P Lk3 ，P Lk4 Is (x) c Lk1 ，y c Lk1 )、(x c Lk2 ，y c Lk2 )、(x c Lk3 ，y c Lk3 )、(x c Lk4 ，y c Lk4 ) Wherein if x k ＞x A1 X is then c Lk1 ≤x c Lk2 ＜x k ，y c Lk1 ＞y c Lk2 ＞y k ，x c Lk4 ≤x c Lk3 ＜x k ，y c Lk3 ＞y c Lk4 ＞y k The method comprises the steps of carrying out a first treatment on the surface of the If x k ＜x A1 X is then c Lk2 ≤x c Lk1 ＜x k ，y c Lk1 ＞y c Lk2 ＞y k ，x c Lk3 ≤x c Lk4 ＜x k ，y c Lk3 ＞y c Lk4 ＞y k ；
S212, if passing P Lk1 And P Lk2 Straight line L1 and through P of (2) Lk3 And P Lk4 Is located outside the kth region of interest, and x is obtained k1 ＝max(x 1 Lk ，x 2 Lk ，…，x u1 Lk ，…，x W1 Lk (ii) and x k2 ＝min(x 1 Lk ，x 2 Lk ，…，x u2 Lk ，…，x W2 Lk ) S213 is performed; if both L1 and L2 are located inside the kth region of interest, S214 is performed; x is x u1 Lk Is positioned at P Lk1 And P Lk2 The u1 th abscissa in the coordinates corresponding to the limb contour line between the two, W1 is the position P Lk1 And P Lk2 The number of abscissas in coordinates corresponding to the limb contour lines therebetween; x is x u2 Lk Is positioned at P Lk3 And P Lk4 The u2 th abscissa in the coordinates corresponding to the limb contour line between the two, W2 is the position P Lk3 And P Lk4 The number of abscissas in coordinates corresponding to the limb contour lines therebetween;
s213, obtain x k1 And x k2 Corresponding pixel point P k1 And P k2 And get through P k1 And P k2 The straight line L0 of the first rectangular area is a first rectangular area of a symmetry axis, the height of the first rectangular area is H0, H0 is a set height, and the unit is a pixel; s215 is performed;
s214, obtaining L=min (L1, L2, L3, L4), wherein L3 is P Lk2 And P Lk3 L4 is a straight line passing through P Lk1 And P Lk4 Acquiring a second rectangular area taking L as a bottom edge, wherein the height of the second rectangular area is H0; s215 is performed;
and S215, taking the rectangular region as a k region of interest after correction.
3. The method according to claim 1, wherein S500 specifically comprises:
s402, obtaining y from PL A1 Is defined by two symmetrical pixel point coordinates (x 01 ，y A1 ) And (x) 02 ，y A1 ) And acquiring the ordinate y from PL A2 Is defined by two symmetrical pixel point coordinates (x 03 ，y A2 ) And (x) 04 ，y A2 ) The method comprises the steps of carrying out a first treatment on the surface of the Wherein x is 01 ＜x A1 ＜x 02 ，x 03 ＜x A2 ＜x 04 ；
S404, acquiring (min (x) 01 ，x 03 )，y A1 ) Or (min (x) 02 ，x 04 )，y A1 ) The corresponding pixel point coordinates are used as coordinates (x A3 ，y A3 )；
S406, obtaining the transverse length Deltax= |x A3 -x A1 ∣/W 13 And obtaining the straight-in length Δy= |y A2 -y A1 ∣/V 12 ，W 13 V is the number of transverse dimensions between CA1 and CA3 12 CA1 and CNumber of straight inches between A2;
s408, taking CA1 or CA2 as a reference acupoint, and acquiring the rest acupoints in the n set acupoints in the target infrared image based on the position relation table between the Deltax and Deltay and the n set acupoints.
4. A method according to claim 3, wherein S402 is replaced by:
s403, obtaining y from PL A1 Is defined by two symmetrical pixel point coordinates (x 01 ，y A1 ) And (x) 02 ，y A1 ) The method comprises the steps of carrying out a first treatment on the surface of the Wherein x is 01 ＜x A1 ＜x 02 ，x 03 ＜x A2 ＜x 04 ；
S404 is replaced with:
s405, will (x) 01 ，y A1 ) Or (x) 02 ，y A1 ) As the coordinates (x) of the reference feature point CA3 A3 ，y A3 ) The method comprises the steps of carrying out a first treatment on the surface of the CA3 is one of n set acupoints.
5. The method according to claim 3, wherein the n set points include n1 first points located on the central axis of the human body and n2 second points located on both sides of the central axis of the human body, and the positional relationship table between the n set points includes a first point positional relationship table and a second point positional relationship table, wherein an i-th row of the first point positional relationship table includes (C1) i ，h1，P ci )，C1 i An ID of an i-th first acupoint of the n1 first acupoints, i having a value of 1 to n1, h1 having a value of 1 or 2, wherein h1=1 represents C1 i Is positioned on the upper side of the reference acupoint, and h1=2 represents C1 i Is positioned at the lower side of the reference acupoint, P ci Representing the number of straight-in-between the ith first acupoint and the reference acupoint; the j th row of the second acupoint position relationship table includes (C2 j ，C1 je ，(h1，PX je )，(h2，PY je ))，C2 j ID, C1 for the j-th second acupoint of the n2 second acupoints je Is C2 j The ID of the first acupoint is associated, the value of h2 is 3 or 4, and h2=3 tableC2 of the illustration j At C1 je Left side of the corresponding first acupoint, h2=4 represents C2 j At C1 je Right side of corresponding first acupoint PX je Is C2 j And C1 je The number of transverse dimensions between the h1 st sides of the corresponding first acupoints PY je Is C2 j And C1 je The number of straight dimensions between the h2 side of the corresponding first acupoint, e, is 1 to n1, and j, is 1 to n2.
6. The method of claim 5, wherein in S408, any second acupoint C2 is acquired j If h2=3, if (x je -P je *△x)＜x c1 The coordinates (x c1 +a，y je ) As C2 j Coordinates of the corresponding acupoints; if h2=4, if (x je +P je *△x)＞x c2 The coordinates (x c2 -a，y je ) As C2 j Coordinates of the corresponding acupoints; wherein x is je And y je Respectively C1 je The corresponding abscissa and ordinate, x of the first acupoint c1 Is the ordinate in PL is y je And the abscissa, x, of the pixel point located on the left side of the reference acupoint c2 Is the ordinate in PL is y je And the abscissa of the pixel points positioned on the right side of the reference acupoint, a is the preset pixel point number.
7. The method of claim 1, wherein PL is obtained based on the steps of:
s101, identifying a human body contour line in a target infrared image to obtain a corresponding human body contour line initial pixel point set PLI= (PLI) 1 ，PLI 2 ，…，PLI r ，…，PLI M )；
S102, acquiring a temperature set TCI= (TLI) corresponding to the PLI 1 ，TLI 2 ，…，TLI r ，…，TLI M )，TLI r For PLI r A corresponding temperature;
s103, if TLI r < T0, execute S104; t0 is a preset temperature value; otherwise, executing S106;
s104, if x LIr ＜x 0 Setting x LIr ＝x LIr +b, if x LIr ＞x 0 Setting x LIr ＝x LIr -b；x 0 X is the abscissa of the central axis LIr For TLI r The corresponding abscissa of the pixel points, b is the number of preset pixel points; s105 is performed;
s105, if the pixel point (x LIr ，y LIr ) The corresponding temperature is less than T0, S104 is executed; otherwise, executing S106;
s106, setting r=r+1, and if r is less than or equal to M, executing S103; otherwise, the control program is exited.
8. The method of claim 1, wherein the target infrared image is a frontal image of a human body; s300 specifically includes:
s301, acquiring a first fixed point b1= (x) in the target infrared image b1 ，y b1 ) And a second fixed point b2= (x b2 ，y b2 )，x b1 ＝x A1 ，y b1 ＝y A1 +△V，x b2 ＝x A1 ，y b2 ＝y A1 The number of the plus delta V/2, delta V is the number of preset straight inches; wherein 1 preset straight dimension= (y) A1 -y A2 )/17；
S302, respectively obtaining a first horizontal line and a second horizontal line, wherein the first horizontal line is a straight line passing through a first fixed point and two ends of the first horizontal line are intersected with the profile lines on two sides, and the second horizontal line is a straight line passing through a second fixed point and two ends of the second horizontal line are intersected with the profile lines on two sides;
s303, obtaining a first vertical line and a fourth horizontal line, wherein the first vertical line is a straight line passing through a reference point, and two ends of the straight line respectively intersect with a third horizontal line and a top-of-head contour line, the reference point is the end point of the first horizontal line, and the third horizontal line is a straight line passing through (x A1 ，y A1 ) And a straight line intersecting the contour lines on both sides; the fourth horizontal line is a straight line passing through the intersection point of the first vertical line and the overhead profile line;
s304, respectively acquiring fifth to seventh horizontal lines intersecting with the contour line of the composite region, wherein the distance between the fifth horizontal line and the fourth horizontal line, the distance between the fifth horizontal line and the sixth horizontal line, the distance between the sixth horizontal line and the seventh horizontal line and the distance between the seventh horizontal line and the first horizontal line are equal;
s305, respectively acquiring a second vertical line and a third vertical line, wherein two ends of the second vertical line and the third vertical line are respectively connected with a fourth horizontal line and a first horizontal line, the distance between the second vertical line and the first vertical line is equal to the distance between the second vertical line and the corresponding endpoint of a sixth horizontal line, and the distance between the third vertical line and the first vertical line is equal to the distance between the third vertical line and the corresponding endpoint of the sixth horizontal line;
s306, obtaining the H regions of interest based on the first to seventh horizontal lines and the first to third vertical lines.
9. 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 1-8.
10. An electronic device comprising a processor and the non-transitory computer readable storage medium of claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310288043.3A CN116797778B (en) | 2023-03-23 | 2023-03-23 | Region of interest acquisition method, electronic device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310288043.3A CN116797778B (en) | 2023-03-23 | 2023-03-23 | Region of interest acquisition method, electronic device, and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116797778A true CN116797778A (en) | 2023-09-22 |
| CN116797778B CN116797778B (en) | 2024-03-22 |
Family
ID=88039304
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310288043.3A Active CN116797778B (en) | 2023-03-23 | 2023-03-23 | Region of interest acquisition method, electronic device, and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116797778B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090020347A (en) * | 2007-08-23 | 2009-02-26 | (주)메쉬 | Infrared thermography detection method |
| CN108334879A (en) * | 2018-02-11 | 2018-07-27 | 深圳市朗驰欣创科技股份有限公司 | A kind of method for extracting region, system and terminal device |
| US20210295517A1 (en) * | 2020-03-17 | 2021-09-23 | Seek Thermal, Inc. | Cost effective, mass producible system for rapid detection of fever conditions based on thermal imaging |
| CN115393578A (en) * | 2022-10-13 | 2022-11-25 | 北京鹰之眼智能健康科技有限公司 | Composite region data processing system for acquiring metabolic state |
| CN115497123A (en) * | 2022-10-21 | 2022-12-20 | 北京鹰之眼智能健康科技有限公司 | Method for acquiring state parameters of region of interest |
| CN115588099A (en) * | 2022-11-02 | 2023-01-10 | 北京鹰之眼智能健康科技有限公司 | Region-of-interest display method, electronic device and storage medium |
| CN115690400A (en) * | 2022-11-02 | 2023-02-03 | 北京鹰之眼智能健康科技有限公司 | Infrared image display method |
| CN115761212A (en) * | 2022-11-02 | 2023-03-07 | 北京鹰之眼智能健康科技有限公司 | Human body state early warning system based on infrared image |
| CN115778333A (en) * | 2022-11-10 | 2023-03-14 | 北京悬丝医疗科技有限公司 | Method and device for visually positioning cun, guan and chi pulse acupuncture points |
-
2023
- 2023-03-23 CN CN202310288043.3A patent/CN116797778B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090020347A (en) * | 2007-08-23 | 2009-02-26 | (주)메쉬 | Infrared thermography detection method |
| CN108334879A (en) * | 2018-02-11 | 2018-07-27 | 深圳市朗驰欣创科技股份有限公司 | A kind of method for extracting region, system and terminal device |
| US20210295517A1 (en) * | 2020-03-17 | 2021-09-23 | Seek Thermal, Inc. | Cost effective, mass producible system for rapid detection of fever conditions based on thermal imaging |
| CN115393578A (en) * | 2022-10-13 | 2022-11-25 | 北京鹰之眼智能健康科技有限公司 | Composite region data processing system for acquiring metabolic state |
| CN115497123A (en) * | 2022-10-21 | 2022-12-20 | 北京鹰之眼智能健康科技有限公司 | Method for acquiring state parameters of region of interest |
| CN115588099A (en) * | 2022-11-02 | 2023-01-10 | 北京鹰之眼智能健康科技有限公司 | Region-of-interest display method, electronic device and storage medium |
| CN115690400A (en) * | 2022-11-02 | 2023-02-03 | 北京鹰之眼智能健康科技有限公司 | Infrared image display method |
| CN115761212A (en) * | 2022-11-02 | 2023-03-07 | 北京鹰之眼智能健康科技有限公司 | Human body state early warning system based on infrared image |
| CN115778333A (en) * | 2022-11-10 | 2023-03-14 | 北京悬丝医疗科技有限公司 | Method and device for visually positioning cun, guan and chi pulse acupuncture points |
Non-Patent Citations (3)
| Title |
|---|
| 云廷进;郭永彩;高潮;: "基于图像局部区域梯度特征描述的红外人体识别算法", 光学技术, no. 03, 15 May 2008 (2008-05-15) * |
| 李明睿;张弛;丁宁: "基于特征点的人体红外图像自动分割技术", 北京生物医学工程, no. 06, 15 December 2017 (2017-12-15) * |
| 闫勇刚;邓小玲;马祥;欧阳健飞;: "人体皮肤彩色视频误差分析及一致性提高", 红外与激光工程, no. 1, 25 May 2016 (2016-05-25) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116797778B (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109758355B (en) | Two-dimensional image processing and three-dimensional positioning method based on human acupuncture points | |
| US11576578B2 (en) | Systems and methods for scanning a patient in an imaging system | |
| CN116469519B (en) | Human body acupoint obtaining method based on infrared image | |
| CN107123137B (en) | Medical image processing method and equipment | |
| US7848547B2 (en) | Apparatus for detecting feature point and method of detecting feature point | |
| US9727986B2 (en) | Unified coordinate system for multiple CT scans of patient lungs | |
| Niethammer et al. | Geometric metamorphosis | |
| CN108245788B (en) | Binocular distance measuring device and method and accelerator radiotherapy system comprising same | |
| CN105395196B (en) | Positioning device and method of EEG the or MEG electrodes in brain MR images | |
| US20220207771A1 (en) | Heart Position Estimation | |
| CN106934810B (en) | A kind of spine correcting device | |
| CN108109170A (en) | Medical image scan method and medical imaging device | |
| US20230410346A1 (en) | Object keypoint detection | |
| GB2602163A (en) | System for determining body measurements from images | |
| CN114529502A (en) | Method and system for depth-based learning for automated subject anatomy and orientation identification | |
| CN116797778B (en) | Region of interest acquisition method, electronic device, and storage medium | |
| CN116407093B (en) | Automatic acquisition system for infrared image temperature | |
| CN111462018A (en) | Method for rectifying image in image, computer device and storage medium | |
| CN108564586A (en) | A kind of body curve's measurement method and system based on deep learning | |
| CN112396600A (en) | Lower nerve paralysis detection system under desensitization state based on thermal imaging and depth map | |
| Xia et al. | Subpixel-based accurate and fast dynamic tumor image recognition | |
| CN116313057B (en) | Abnormal region detection system based on infrared image | |
| JP2017012341A (en) | Image processing method and apparatus, and program | |
| JP2002109550A (en) | Cardiothoracic contour detection method and cardiothoracic ratio calculation method | |
| US10719962B2 (en) | Magnetic field distortion calculation apparatus, method, and program |
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 |