CN110993107A - Human body five-finger image processing method and device - Google Patents
Human body five-finger image processing method and device Download PDFInfo
- Publication number
- CN110993107A CN110993107A CN201911356385.4A CN201911356385A CN110993107A CN 110993107 A CN110993107 A CN 110993107A CN 201911356385 A CN201911356385 A CN 201911356385A CN 110993107 A CN110993107 A CN 110993107A
- Authority
- CN
- China
- Prior art keywords
- finger image
- human body
- finger
- image
- hand
- 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
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a human body five-finger image processing method and device. The method comprises the following steps: determining each finger image in the human body five-finger image corresponding to the left hand and/or the right hand of the human subject according to the preset position relationship among the fingers; and determining the total human body discharge energy, the average glow intensity of each finger image or the bilateral symmetry index of the human body discharge corresponding to the human body according to each finger image in the human body five-finger image corresponding to the left hand and/or the right hand of the human body. The method processes the acquired human body five-finger image corresponding to the left hand or the right hand of the human body to obtain the detection characteristic quantity corresponding to the human body five-finger image of the human body. The image processing method and the image processing device are reasonable in design and high in processing efficiency, and the problems of low efficiency, poor consistency and the like in manual image processing in the prior art are solved.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a human body five-finger image processing method and device.
Background
The human five finger image is a color computer-processable image obtained from a camera by a computer. Specifically, a camera with a sensitive Charge Coupled Device (CCD) is disposed in front of a human body five-finger image acquisition mold (hereinafter, referred to as a mold) in a preset orientation, and the human body five-finger image is captured and acquired from a direction directly facing a finger tip by the camera.
At present, human body five-finger images of a testee are mainly read and analyzed manually, so that the workload is large, the efficiency is low, and the consistency is poor.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a human body five-finger image processing method and device, which are used for solving the problems of low efficiency, poor consistency and the like when the image is manually processed at present.
In a first aspect, as shown in fig. 1, the present invention provides a human body five-finger image processing method, including the steps of:
step S100: determining each finger image in the human body five-finger image corresponding to the left hand and/or the right hand of the human subject according to the preset position relationship among the fingers;
step S200: and determining the total human body discharge energy, the average glow intensity of each finger image or the bilateral symmetry index of the human body discharge corresponding to the human body according to each finger image in the human body five-finger image corresponding to the left hand and/or the right hand of the human body.
Further, the human body five-finger image processing method further comprises the following steps:
dividing each finger image in the human body five-finger image corresponding to the left hand and/or the right hand of the human subject into a plurality of sector images respectively, and determining the human body discharge partition energy corresponding to each sector image;
and determining the value corresponding to each attribute item in a preset attribute list corresponding to the testee according to the human body discharge subarea energy corresponding to each sector image.
Furthermore, the human body five-finger image processing method,
the preset attribute list comprises twelve attribute items which are respectively as follows: the heart meridian of hand shaoyin, the pericardium meridian of hand jueyin, the small intestine meridian of hand taiyang, the stomach meridian of foot yangming, the kidney meridian of foot shaoyin, the triple energizer meridian of hand shaoyang, the spleen meridian of foot taiyin, the liver meridian of foot jueyin, the lung meridian of hand taiyin, the gallbladder meridian of foot shaoyang, the large intestine meridian of hand yangming, and the bladder meridian of taiyang.
Furthermore, the human body five-finger image processing method,
the method for determining each finger image in the human body five-finger image corresponding to the left hand of the testee according to the preset position relationship among the fingers comprises the following steps:
determining the coordinates of the central points and the circumscribed rectangle of 5 finger images included in the human body five-finger image corresponding to the left hand of the testee;
according to the method, the coordinates of the center points of the 5 finger images are respectively matched with the left thumb image, the left index finger image, the left middle finger image, the left ring finger image and the left little finger image, and the left thumb image, the left index finger image, the left ring finger image and the left little finger image are determined according to the side length of an external rectangle corresponding to the coordinates of the center points.
Furthermore, the human body five-finger image processing method,
the method for determining each finger image in the human body five-finger image corresponding to the right hand of the human subject according to the preset position relationship among the fingers comprises the following steps:
determining the coordinates of the central point and the circumscribed rectangle of 5 finger images included in the human body five-finger image corresponding to the right hand of the human subject;
according to the method, the value of the y coordinate of the center point of a right-hand thumb image is minimum, the value of the y coordinate of the center point of a right-hand index finger image is minimum, the values of the y coordinates of the center points of the right-hand index finger image, the right-hand middle finger image, the right-hand ring finger image and the right-hand little finger image are sequentially increased, the center point coordinates of the 5 finger images are respectively matched with the right-hand thumb image, the right-hand index finger image, the right-hand middle finger image, the right-hand ring finger image and the right-hand little finger image, and the right-hand thumb image, the right-hand index finger image, the right-hand middle finger image, the right-hand ring finger image and the right-hand little finger image are determined according to the side length of an.
Furthermore, the human body five-finger image processing method,
before determining the coordinates of the center point and the circumscribed rectangle of the 5 finger images included in the human body five-finger image corresponding to the left hand or the right hand of the human subject, the method comprises the following steps:
denoising the human body five finger image corresponding to the subject according to a predetermined R channel threshold α:
when the gray value of the R channel of any pixel point in the human body five-finger image is smaller than the R channel threshold α, the gray values of R, G, B channels of the pixel point are all set to be 0;
when the gray value of the R channel of any pixel point in the human body five-finger image is not less than the R channel threshold α, the gray value of R, G, B channels of the pixel point is kept unchanged.
Furthermore, the human body five-finger image processing method,
the method for determining the total human body discharge energy, the average glow intensity of each finger image or the bilateral symmetry index of the human body discharge corresponding to the human body of the human body comprises the following steps of:
accumulating the energy of the ten finger images in the human body five-finger image corresponding to the two hands of the testee to obtain the total discharge energy; wherein the energy of each finger image is the sum of the gray values of each pixel point in the single finger image;
determining the average glow intensity of each finger image according to the energy of each finger image and the number of pixel points with the gray value higher than a preset critical value in each single finger image;
determining the human body discharge bilateral symmetry index LRbalance according to the following formula:
wherein LE is the total energy of the five finger images in the human discharge image corresponding to the left hand of the human subject;
RE is the total energy of the five finger images in the human discharge image corresponding to the right hand of the subject.
Furthermore, the human body five-finger image processing method,
dividing each finger image in the human body five-finger image corresponding to the left hand and/or the right hand of the human subject into a plurality of fan-shaped images respectively, comprising the following steps:
determining the straight line of the direction of the finger tip in any finger image according to the following formula:
wherein, (centerx, centery) is the coordinate of the center point of the finger image, and theta is the included angle between the direction of the finger tip and the x axis; wherein, the right direction along the paper surface in the finger image is the positive direction of the x axis;
a rotated point coordinate (x ', y') obtained by rotating any point (x, y) on a straight line in the direction in which the finger tip is located clockwise by a preset angle β around the center point coordinate (center ) of the finger image:
a straight line connecting the coordinates of the center point of the finger image and the rotated coordinates (x ', y') of the point is a boundary straight line dividing the sector image,
the boundary straight line is intersected with the straight line in the direction of the finger tip, and a fan-shaped image with the angle of β in the finger image is obtained by enclosing, wherein the pi is more than 0 and less than β and less than 2;
and (2) determining (N-1) edge boundary lines according to the preset partition number N, and dividing any finger image into N fan-shaped images.
Further, the human body five-finger image processing method further comprises the following steps:
processing a plurality of human body five-finger images corresponding to the left hand or the right hand of the human subject acquired at a plurality of preset times to obtain values corresponding to each attribute item in a preset attribute list corresponding to the plurality of preset times, and drawing a monitoring curve with the abscissa as the time and the ordinate as the values corresponding to each attribute item.
In a second aspect, as shown in fig. 2, the present invention provides a human body five-finger image processing apparatus, comprising:
a single finger image determining module 100, configured to determine, according to a preset position relationship between fingers, each finger image in a human body five-finger image corresponding to the left hand and/or the right hand of a subject;
the magnitude determination module 200 of the human body five-finger image corresponding to the human subject is configured to determine, according to each finger image in the human body five-finger image corresponding to the left hand and/or the right hand of the human subject, a total human body discharge energy, an average glow intensity of each finger image, or a human body discharge bilateral symmetry index corresponding to the human subject.
The human body five-finger image processing method and the device provided by the invention process the acquired human body five-finger image corresponding to the left hand or the right hand of the testee to obtain each single finger image corresponding to each finger of the left hand or the right hand of the testee; dividing a single finger image into a plurality of sectors; based on the single finger image and each sector image, detection characteristic quantities corresponding to the human body five-finger image of the human body of the subject are obtained. Subsequently, the traditional Chinese medicine theory is combined, the detection characteristic quantity corresponding to the human body discharge image can be combined, and the traditional Chinese medicine doctor evaluates the human body health condition of the testee.
The image processing method and the image processing device are reasonable in design and high in processing efficiency, and the problems of low efficiency, poor consistency and the like in manual image processing in the prior art are solved.
Drawings
A more complete understanding of exemplary embodiments of the present invention may be had by reference to the following drawings in which:
FIG. 1 is a schematic flow chart of a human body five-finger image processing method according to a preferred embodiment of the present invention;
FIG. 2 is a schematic diagram of the human body five-finger image processing device according to the preferred embodiment of the invention;
FIG. 3 is a comparison diagram of a human discharge image before and after denoising;
FIG. 4 is a human discharge image corresponding to a left hand of a subject;
FIG. 5 is a five-finger image extracted from the discharge image of FIG. 4;
FIG. 6 is an image of a thumb and finger of a subject, in which the direction of the tip of the finger is shown by a straight line;
FIG. 7 is a view showing the boundary lines of the respective sectors when the thumb and finger image of a subject is divided into 8 sectors;
FIG. 8 is a schematic diagram of determining a sector image corresponding to a partition by using a triangular mask;
FIG. 9 is a schematic view of the thumb and finger image of the subject of FIG. 7 divided into 8 sector images;
FIG. 10 is a schematic diagram of twelve meridians of a human body;
fig. 11 is a graph showing the change of the heart meridian of hand shaoyin in from 9 to 17 points in time, respectively, corresponding to the human discharge images of 4 subjects;
fig. 12 is a schematic diagram of the development process of the human body five-finger image processing method according to a preferred embodiment of the invention.
Detailed Description
The exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, however, the present invention may be embodied in many different forms and is not limited to the embodiments described herein, which are provided for complete and complete disclosure of the present invention and to fully convey the scope of the present invention to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the accompanying drawings is not intended to be limiting of the invention. In the drawings, the same units/elements are denoted by the same reference numerals.
Unless otherwise defined, terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Further, it will be understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense.
Specifically, the human body five-finger image acquisition mold is provided with holes (or finger clamping groove devices) for placing a thumb, an index finger, a middle finger, a ring finger and a little finger respectively, sealing devices are arranged on the inner walls of the holes, after each finger is placed in the corresponding hole, the finger is clamped by the sealing device, and no gap exists between the finger and the sealing device. In addition, the cross-sectional shape of each hole and the mutual position relationship among the holes are used for limiting the arrangement angle and the position of each finger in the hole.
When the device is specifically implemented, a testee puts five fingers of a palm into corresponding holes of the die from the back of the die, and the CCD camera faces the fingertip direction to acquire corresponding human body five finger images. The image is obtained from the CCD camera by a computer, and then the subsequent processing can be carried out.
The human body five-finger image processing method provided by the embodiment of the invention processes the acquired human body five-finger image corresponding to the left hand or the right hand of the testee to obtain each single finger image corresponding to each finger of the left hand or the right hand of the testee; dividing a single finger image into a plurality of sectors; based on the single finger image and each sector image, detection characteristic quantities corresponding to the human body five-finger image of the human body of the subject are obtained.
Subsequently, the traditional Chinese medicine theory is combined, the detection characteristic quantity corresponding to the human body discharge image can be combined, and the traditional Chinese medicine doctor evaluates the human body health condition of the testee.
The image processing method is reasonable in design and high in processing efficiency, and solves the problems of low efficiency, poor consistency and the like in manual image processing in the prior art.
Further, the human body five-finger image processing method according to the embodiment of the present invention is configured to perform the above processing steps on a plurality of color images corresponding to the left hand or the right hand of the subject acquired at a plurality of preset times, respectively, obtain values corresponding to each attribute entry in a preset attribute list corresponding to the plurality of preset times, and draw a state curve with the abscissa as the time and the ordinate as the attribute values.
Specifically, the method of the embodiment of the present invention, in which the device for image processing is a Lenovo notebook computer (shogao E52-80), requires opencv3.3 and Visual Studio 2015 as software, includes the following steps:
1.1) obtaining the discharge image of the human body
The discharge image of the left hand and the discharge image of the right hand corresponding to the human subject are respectively obtained by utilizing the human body five-finger image obtaining die, the CCD camera and the computer.
The left-hand discharge image comprises discharge images of five fingers of the left hand;
the discharge image of the right hand includes discharge images of five fingers of the right hand.
Compared with the method for acquiring the discharge image corresponding to a single finger independently and acquiring the discharge images corresponding to five fingers simultaneously, the method is simple and convenient in operation, saves time, and can avoid measurement errors caused by different angles and forces of five fingers of a single hand in five independent measurements.
1.2) denoising and preprocessing the human body discharge image
And aiming at red noise points existing in the black background area, taking the R channel in R, G, B three channels as a denoising judgment condition, and selecting an R channel threshold value α.
When the gray value of the R channel of any pixel point in the image is smaller than the R channel threshold α, the gray values of the R, G, B three channels of the pixel point are all set to be 0, that is, the pixel point is adjusted to be black, if the gray value of the R channel of the pixel point is larger than the R channel threshold α, the pixel point is determined to be a pixel point needing to be reserved, the gray values of the R, G, B three channels of the pixel point are kept unchanged, fig. 3 shows the comparison before and after denoising for a certain discharge image, and as can be seen from fig. 3, after denoising, the finger image in the image is taken as a foreground, and the comparison with a black background is more obvious.
After denoising, the contrast between the foreground and the background meets the requirement of subsequent processing, and in order to reduce the calculation amount and improve the processing efficiency, the human body discharge image after denoising is converted into a gray scale image.
1.3) identifying the single-finger image of the five fingers from the human body discharge image
In order to facilitate the subsequent adoption of different detection characteristic quantity calculation methods aiming at different finger images, the following algorithm is designed to respectively identify the corresponding image areas of the thumb, the index finger, the middle finger, the ring finger and the little finger from the discharge image.
Fig. 4 is a discharge image of a discharge picture taken including five fingers of the left hand. Specifically, a findContours function in opencv is applied to determine the outline, center coordinates and circumscribed rectangle of each finger image.
Since each finger image appears as a closed circular ring region, the findContours function finds both the outer contour and the inner contour, as well as the outer center point corresponding to the outer contour and the inner center point corresponding to the inner contour, and the circumscribed rectangle corresponding to the outer center point of the outer contour.
Further, the outer center point and the inner center point are merged into one common center point by the following method.
For example, considering that the distance between the outer center point and the inner center point in each finger image is usually not greater than 100 pixel points, and the side length of the circumscribed rectangle is usually in the order of 1000 pixel points, any one of the outer center point and the inner center point can be used as the common center point.
For example, a center point between the outer center point and the inner center point is taken as a common center point.
And after the common central point is determined, adjusting the circumscribed rectangle corresponding to the outer central point of the outer contour into a circumscribed rectangle taking the common central point as the center, wherein the length of each side of the circumscribed rectangle of the outer contour is kept unchanged.
Through the above processing, five common central points corresponding to the five finger images and the respective side lengths of the corresponding external rectangles can be obtained, but the finger images cannot be matched with the corresponding specific fingers.
Further, in combination with the relative position relationship of the holes in the mold, it can be determined that, in the discharge image corresponding to the left hand, the upper left foreground image area is the thumb image, and the four right foreground image areas are the index finger image area, the middle finger image area, the ring finger image area and the little finger image area in turn.
And respectively cutting the thumb image, the index finger image, the middle finger image, the ring finger image and the little finger image by using a bubbling algorithm according to the mutual position relation of the foreground images in the image.
It should be noted that, in the image corresponding to the left hand in fig. 4, the upper left corner is the origin of coordinates, and the value of the x coordinate is larger the more the right; the value of the y coordinate is larger the further down.
As can be seen from fig. 5, the x coordinate of the center point of the thumb image located at the upper left is the smallest, so that the point with the smallest x coordinate among the five common center points is found, and the thumb image is cut out by using the circumscribed rectangle.
And cutting the images of the other four fingers by taking the y coordinate of each central point as a basis. According to the mutual position relation of the fingers, the value of the y coordinate of the central point of the index finger image is minimum, the values of the y coordinates of the index finger image, the middle finger image, the ring finger image and the little finger image are sequentially increased, and the y value of the central point of the little finger image is maximum.
After each common center point is matched with the finger images, the index finger image, the middle finger image, the ring finger image and the little finger image can be respectively cut according to each side length of the external rectangle corresponding to each finger image. The five finger image extracted from the human discharge image of fig. 5 is shown in fig. 5.
1.4) calculating detection characteristic quantities such as energy
Calculating the following detection characteristic quantities respectively for each finger image area obtained by cutting:
(1) energy of area E
E＝Σu (1)
Wherein u is the gray value of each pixel point in a single finger image.
(2) Sum of area sum
The total area value sum is defined as the number of pixel points in the single finger image, wherein the gray value of the pixel points is higher than a preset critical value.
(3) Average glow intensity I
The average glow intensity I is defined as the average light intensity of a single finger image:
I＝E/sum； (2)
the average glow intensity can be used to characterize the subject's level of quantum activity.
1.5) calculating the detection characteristic quantities such as energy and the like for each sector hand image
Specifically, each individual finger presentation corresponds to a particular finger discharge image. Each finger image is then sectorized, wherein the starting straight line of the angular coordinate of each sector starts from the direction of the finger tip.
Specifically, the thumb of the right hand is taken as an example. The general direction of each finger tip can be predetermined according to the placement angle and position of each finger limited by each hole in the mold. Take the right thumb as an example, wherein the straight line in the middle of the left side of fig. 6 shows the direction in which the tip of the right thumb is located.
The following pre-processing is done for the image shown in fig. 6. Since the size of fig. 7 is small, the length and width of the image are respectively enlarged to three times the size for convenience of processing and display, and the abscissa (noted as abscissa, x; ordinate, y) of the center point in the image is also transformed accordingly.
Specifically, an image (i.e., a full black image) is generated, wherein the size of the image is 3 times that of the image to be enlarged, and the gray value of each pixel point is 0; then, the image to be enlarged is overlaid on the center position of the newly generated full black image, so as to obtain an enlarged image (i.e., an annular black image with equal width and equal length is enlarged outside the image to be enlarged). At this time, the coordinates of x and y are changed to x + the length of the original and y + the width of the original.
For the expanded discharge image, a linear equation representing the direction of the finger tip is determined according to the following formula:
wherein, (centerx, centery) is the coordinate of the central point of the image, and θ is the included angle between the direction of the finger tip and the x axis. The partitioning is then performed clockwise or counterclockwise, as viewed from the finger tip of fig. 7.
Specifically, when any point (x, y) on the linear equation indicating the direction in which the finger tip is located is rotated clockwise β around the center point coordinate (center ) of the image, the resultant rotated point coordinate (x ', y') is as follows:
wherein β is the angle between the straight line representing the direction of the finger tip and the straight line of the boundary of the target subarea, and 0 & lt β & lt 2 pi.
The rotation coordinate points obtained according to the above formula are respectively made into straight lines with the center point (center ) of the image, and the thumb-finger partition image shown in fig. 7 is obtained. For example, the thumb image is divided into eight regions.
In calculating the energy level in each partition, the energy level of each region may be calculated sequentially in a clockwise direction or a counterclockwise direction.
Specifically, a triangular mask method is used to determine the corresponding area of each sector image. The steps of the triangular mask are as follows: and (3) drawing a triangle with the gray value of 255 for each pixel point by taking the rotation points on the two pairs of boundary straight lines of each partition determined according to the formulas (3) and (4) and the central point of the image as vertexes, and drawing a black background area with the gray value of 0 outside the triangle to obtain the image for the triangular mask with the same size as the finger image. The original finger image is overlaid with the triangular mask image (shown on the left side of fig. 8) and the finger image mask, and the overlaid image is shown on the right side of fig. 8. The triangular mask method sets the gray values of other areas except the target sector image in the finger image to be zero, and only the gray values of all pixel points in the target sector image are reserved for calculating the energy of the sector image.
Fig. 9 is a schematic diagram of the thumb image shown in fig. 7 after being divided into 8 regions and then triangular masking is performed.
In specific implementation, the energy of each partitioned area is calculated according to the energy formula in formula (1).
1.6) calculating the twelve meridians
On the basis that a Mandel doctor divides finger areas according to the traditional Chinese medicine theory, the embodiment of the invention adopts a twelve meridian energy calculation rule shown in Table 1. It should be understood that the entries in table 1 are simplified usages of the following attribute items, respectively: the heart meridian of hand shaoyin, the pericardium meridian of hand jueyin, the small intestine meridian of hand taiyang, the stomach meridian of foot yangming, the kidney meridian of foot shaoyin, the triple energizer meridian of hand shaoyang, the spleen meridian of foot taiyin, the liver meridian of foot jueyin, the lung meridian of hand taiyin, the gallbladder meridian of foot shaoyang, the large intestine meridian of hand yangming, and the bladder meridian of taiyang.
Specifically, as shown in fig. 10, the heart of hand shaoyin is related to the little finger; the pericardium meridian of hand jueyin is related to the middle finger; the small intestine meridian of hand taiyang is related to the small finger; the stomach meridian of foot yangming is related to the middle finger; the kidney meridian of foot shaoyin is related to the little finger and the middle finger; the triple energizer meridian of hand shaoyang is related to the ring finger and thumb; the spleen meridian of foot taiyin is related to the ring finger; the liver meridian of foot jueyin is related to the middle finger; the lung meridian of hand taiyin is related to the thumb, middle finger and little finger; the gallbladder meridian of foot shaoyang is related to the middle finger; the large intestine channel of hand yangming is related to the index finger; the bladder meridian of foot taiyang is related to the ring finger.
TABLE 1 twelve rules for calculating the energy of meridians
In specific implementation, the left thumb is divided into 8 sector partitions according to the twelve meridian energy calculation rules; the index finger at the left side is divided into 9 sector partitions; the left middle finger is divided into 7 sector partitions; the ring finger on the left side is divided into 9 sector partitions; the left little finger is divided into 6 sector partitions; the right thumb is divided into 8 sector partitions; the index finger on the right side is divided into 9 sector partitions; the right middle finger is divided into 7 sector partitions; the ring finger on the right side is divided into 9 sector partitions; the right little finger is divided into 6 sectorial subareas.
Preferably, the level of the twelve meridian energy can be determined by adopting the following criteria: 0-2 indicates very low energy; 2-4 indicates low energy; 4-6 represent energy optima; 6-8 indicates a slightly higher energy; 8-10 represent energy superelevations.
By applying the twelve-meridian energy calculation rule shown in table 1, a plurality of human body discharge image measurements are performed every half hour (4 times in a hour, namely 48 data points) on the same day for a plurality of testees, and the twelve-meridian energy values corresponding to the testees are respectively determined.
The following description takes the hand-sun-small intestine channel as an example to illustrate that the data obtained by the image processing method of the embodiment of the invention has good consistency and high processing efficiency.
Fig. 11 is a graph from 9: 30-17: 00 hand sun small intestine channel data. It can be seen that in the time period of 13:00-15:00, the energy of the small intestine channel of the hand-sun has obvious change rule, namely, the energy reaches the highest value first and then decreases.
According to the theory of traditional Chinese medicine channels and collaterals, in twelve hours of a day, 13:00-15:00, the small intestine channel of hand-Taiyang is most active. Therefore, the hand-sun small intestine meridian data obtained by the image processing method of the embodiment of the invention is better in conformity with theory, and the data obtained by the image processing method is effective, good in consistency and high in processing efficiency.
By applying the human body five-finger image processing method of the embodiment, the processing result of a large amount of test data shows that the data obtained by the image processing method is effective, good in consistency and high in processing efficiency.
1.7) constructing detection characteristic quantity corresponding to human body discharge image
According to the energy of the single finger and the energy of each partition of each finger of the two hands, the following health detection characteristic quantities corresponding to the human body discharge image are further determined so as to fully mine the information quantity contained in the data:
total human body discharge energy EE: the total human body discharge energy EE is the sum of the energy of each of the ten fingers of the two hands of the human subject.
Human body discharge bilateral symmetry index LRbalance:
wherein LE is the total energy of the five finger images in the discharge image of the left hand of the subject; RE is the total energy of the five finger images in the discharge image of the right hand of the subject.
The human discharge bilateral symmetry index LRbalance can be used for indicating the symmetry of the left brain and the right brain of the human subject. Wherein, the closer the numerical value of the bilateral symmetry index of the human body discharge is to 100%, the more ideal.
To sum up, the image processing method and apparatus of the embodiment of the present invention segment the image corresponding to each finger according to the position and mutual position relationship of each finger in the human body discharge image acquisition mold, and determine the energy index corresponding to each finger; the finger images are divided into regions, and detection characteristic quantities such as twelve channels and collaterals energy corresponding to the human body discharge image of the human body to be tested are determined according to the corresponding relation between the traditional Chinese medicine channels and collaterals and the fingers.
The embodiment of the invention provides an image processing method and device of a human body discharge image on the basis of a human body discharge principle and a traditional Chinese medicine meridian principle. The acquired discharge images of the five fingers of the left hand and the five fingers of the right hand are calculated, and detection characteristic quantities corresponding to the discharge images of the human body, such as human body discharge energy, twelve meridian energy and the like, can be obtained.
Subsequently, the traditional Chinese medicine theory is combined, the detection characteristic quantity corresponding to the human body discharge image can be combined, and the traditional Chinese medicine doctor evaluates the human body health condition of the testee.
The advantages of the embodiment of the invention are mainly reflected in the following aspects:
1) the human body discharge image acquired by five fingers at the same time is analyzed, so that the operation is simple, the consumed time is less, and errors caused by different angles or forces can be reduced;
2) subsequently, by combining the theory of traditional Chinese medicine, the detection characteristic quantity corresponding to the human body discharge image obtained by the embodiment can be combined, and the traditional Chinese medicine doctor evaluates the human body health condition of the testee.
Fig. 12 shows the implementation steps of the human body five-finger image processing method according to the embodiment of the invention.
The following are some definitions of terms.
The health detection method based on the human body discharge image is characterized in that the discharge image is formed according to the human body energy, and the indexes of the human body energy, the bilateral symmetry, the twelve meridian energies and the like can be deduced by combining the traditional Chinese medicine theory with the computer technologies such as image processing, data analysis and the like. At present, the popular human health detection method in China can be roughly divided into substance detection and information detection, wherein the substance detection comprises biological indexes such as blood pressure, blood sugar, heart rate and the like; the information detection comprises indexes of human body pressure, emotion, sleep quality and the like, and a detection method based on human body energy is not widely applied to China at present.
The formation of human discharge images originated at the end of the 19 th century, and 1500 "electric photographs" of human fingers, plant leaves, grains, etc. were taken by one of the Russian scientists Jacob Narkevich-Yodko who developed their own original techniques. In the beginning of the 20 th century, the former soviet electrical engineer, semeon kirian and his wife Valentina, observed a patient who received high frequency generator therapy at a hospital in clanshinat, and invented kirian photography, which could photograph different emotional states of a person to produce different halos. With a subsequent series of studies, in 1995, professor Korotkov invented the first GDV camera, which could be shown directly on a computer screen. Its basic principle is still the kirian effect, with an overall assessment of human health by measuring the energy of each finger separately.
Human body five-finger discharge image: is an image for visualizing the energy flow of human body, namely 'qi'. The principle of the discharge image formation of the human body is that excited photons and electrons are radiated when an object is placed in an electromagnetic field and subjected to a simple electrical pulse. This process is known as "photon-electron" radiation. The radiated particles are accelerated in the electromagnetic field, and an electron avalanche (electronic avalanche) is formed on the surface of the insulator, and this process is called "slipping gas discharge". The discharge causes excitation of molecules in the surrounding gas. The voltage-pulse excited photoelectric radiation is amplified by a gas discharge. The light generated in this process is recorded by a camera with a sensitive charge coupled device (charged coupled device) and converted into a colored computer or biological image.
Image energy partitioning: the human body energy discharge image obtained from the equipment is partitioned by using a basic algorithm of image segmentation according to the traditional Chinese medicine finger partition principle, and the energy value of each region is calculated.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
The invention has been described above by reference to a few embodiments. However, other embodiments of the invention than the one disclosed above are equally possible within the scope of the invention, as would be apparent to a person skilled in the art from the appended patent claims.
Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise herein. All references to "a// the [ device, component, etc ]" are to be interpreted openly as at least one instance of a device, component, etc., unless explicitly stated otherwise. The steps of any method disclosed herein do not have to be performed in the exact order disclosed, unless explicitly stated.
Claims (10)
1. A human body five-finger image processing method is characterized by comprising the following steps:
determining each finger image in the human body five-finger image corresponding to the left hand and/or the right hand of the human subject according to the preset position relationship among the fingers;
and determining the total human body discharge energy, the average glow intensity of each finger image or the bilateral symmetry index of the human body discharge corresponding to the human body according to each finger image in the human body five-finger image corresponding to the left hand and/or the right hand of the human body.
2. The human body five-finger image processing method according to claim 1, further comprising:
dividing each finger image in the human body five-finger image corresponding to the left hand and/or the right hand of the human subject into a plurality of sector images respectively, and determining the human body discharge partition energy corresponding to each sector image;
and determining the value corresponding to each attribute item in a preset attribute list corresponding to the testee according to the human body discharge subarea energy corresponding to each sector image.
3. The human body five-finger image processing method according to claim 2,
the preset attribute list comprises twelve attribute items which are respectively as follows: the heart meridian of hand shaoyin, the pericardium meridian of hand jueyin, the small intestine meridian of hand taiyang, the stomach meridian of foot yangming, the kidney meridian of foot shaoyin, the triple energizer meridian of hand shaoyang, the spleen meridian of foot taiyin, the liver meridian of foot jueyin, the lung meridian of hand taiyin, the gallbladder meridian of foot shaoyang, the large intestine meridian of hand yangming, and the bladder meridian of taiyang.
4. The human body five-finger image processing method according to claim 1,
the method for determining each finger image in the human body five-finger image corresponding to the left hand of the testee according to the preset position relationship among the fingers comprises the following steps:
determining the coordinates of the central points and the circumscribed rectangle of 5 finger images included in the human body five-finger image corresponding to the left hand of the testee;
according to the method, the coordinates of the center points of the 5 finger images are respectively matched with the left thumb image, the left index finger image, the left middle finger image, the left ring finger image and the left little finger image, and the left thumb image, the left index finger image, the left ring finger image and the left little finger image are determined according to the side length of an external rectangle corresponding to the coordinates of the center points.
5. The human body five-finger image processing method according to claim 1,
the method for determining each finger image in the human body five-finger image corresponding to the right hand of the human subject according to the preset position relationship among the fingers comprises the following steps:
determining the coordinates of the central point and the circumscribed rectangle of 5 finger images included in the human body five-finger image corresponding to the right hand of the human subject;
according to the method, the value of the y coordinate of the center point of a right-hand thumb image is minimum, the value of the y coordinate of the center point of a right-hand index finger image is minimum, the values of the y coordinates of the center points of the right-hand index finger image, the right-hand middle finger image, the right-hand ring finger image and the right-hand little finger image are sequentially increased, the center point coordinates of the 5 finger images are respectively matched with the right-hand thumb image, the right-hand index finger image, the right-hand middle finger image, the right-hand ring finger image and the right-hand little finger image, and the right-hand thumb image, the right-hand index finger image, the right-hand middle finger image, the right-hand ring finger image and the right-hand little finger image are determined according to the side length of an.
6. The human body five-finger image processing method according to any one of claims 4 or 5,
before determining the coordinates of the center point and the circumscribed rectangle of the 5 finger images included in the human body five-finger image corresponding to the left hand or the right hand of the human subject, the method comprises the following steps:
denoising the human body five finger image corresponding to the subject according to a predetermined R channel threshold α:
when the gray value of the R channel of any pixel point in the human body five-finger image is smaller than the R channel threshold α, the gray values of R, G, B channels of the pixel point are all set to be 0;
when the gray value of the R channel of any pixel point in the human body five-finger image is not less than the R channel threshold α, the gray value of R, G, B channels of the pixel point is kept unchanged.
7. The human body five-finger image processing method according to claim 1,
the method for determining the total human body discharge energy, the average glow intensity of each finger image or the bilateral symmetry index of the human body discharge corresponding to the human body of the human body comprises the following steps of:
accumulating the energy of the ten finger images in the human body five-finger image corresponding to the two hands of the testee to obtain the total discharge energy; wherein the energy of each finger image is the sum of the gray values of each pixel point in the single finger image;
determining the average glow intensity of each finger image according to the energy of each finger image and the number of pixel points with the gray value higher than a preset critical value in each single finger image;
determining the human body discharge bilateral symmetry index LRbalance according to the following formula:
wherein LE is the total energy of the five finger images in the human discharge image corresponding to the left hand of the human subject;
RE is the total energy of the five finger images in the human discharge image corresponding to the right hand of the subject.
8. The human body five-finger image processing method according to claim 2,
dividing each finger image in the human body five-finger image corresponding to the left hand and/or the right hand of the human subject into a plurality of fan-shaped images respectively, comprising the following steps:
determining the straight line of the direction of the finger tip in any finger image according to the following formula:
wherein, (centerx, centery) is the coordinate of the center point of the finger image, and theta is the included angle between the direction of the finger tip and the x axis; wherein, the right direction along the paper surface in the finger image is the positive direction of the x axis;
a rotated point coordinate (x ', y') obtained by rotating any point (x, y) on a straight line in the direction in which the finger tip is located clockwise by a preset angle β around the center point coordinate (center ) of the finger image:
a straight line connecting the coordinates of the center point of the finger image and the rotated coordinates (x ', y') of the point is a boundary straight line dividing the sector image,
the boundary straight line is intersected with the straight line in the direction of the finger tip, and a fan-shaped image with the angle of β in the finger image is obtained by enclosing, wherein the pi is more than 0 and less than β and less than 2;
and (2) determining (N-1) edge boundary lines according to the preset partition number N, and dividing any finger image into N fan-shaped images.
9. The human body five-finger image processing method according to claim 2, further comprising:
processing a plurality of human body five-finger images corresponding to the left hand or the right hand of the human subject acquired at a plurality of preset times to obtain values corresponding to each attribute item in a preset attribute list corresponding to the plurality of preset times, and drawing a monitoring curve with the abscissa as the time and the ordinate as the values corresponding to each attribute item.
10. A human body five-finger image processing device is characterized by comprising:
the single finger image determining module is used for determining each finger image in the human body five-finger image corresponding to the left hand and/or the right hand of the testee according to the preset position relation among the fingers;
and the magnitude determination module of the human body five-finger image corresponding to the tested person is used for determining the total human body discharge energy, the average glow intensity of each finger image or the bilateral symmetry index of human body discharge corresponding to the tested person according to each finger image in the human body five-finger image corresponding to the left hand and/or the right hand of the tested person.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911356385.4A CN110993107B (en) | 2019-12-25 | 2019-12-25 | Human body five-finger image processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911356385.4A CN110993107B (en) | 2019-12-25 | 2019-12-25 | Human body five-finger image processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110993107A true CN110993107A (en) | 2020-04-10 |
| CN110993107B CN110993107B (en) | 2023-06-09 |
Family
ID=70076509
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911356385.4A Active CN110993107B (en) | 2019-12-25 | 2019-12-25 | Human body five-finger image processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110993107B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112614095A (en) * | 2020-12-15 | 2021-04-06 | 新绎健康科技有限公司 | Method and system for analyzing liver meridian energy based on image processing |
| CN113823407A (en) * | 2021-08-09 | 2021-12-21 | 新绎健康科技有限公司 | Physique prediction method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1286124A (en) * | 1999-08-31 | 2001-03-07 | 马传忠 | Human energy movement equipment |
| CN101577033A (en) * | 2009-05-26 | 2009-11-11 | 官洪运 | Multiband infrared image-type fire detecting system and fire alarm system thereof |
| CN101632089A (en) * | 2005-09-01 | 2010-01-20 | 光谱辨识公司 | Biometric sensor |
| CN104598884A (en) * | 2015-01-20 | 2015-05-06 | 深圳市维亿魄科技有限公司 | Human body finger vein recognition device |
| US20160166054A1 (en) * | 2011-05-16 | 2016-06-16 | Emanuele Antonio SALTALAMACCHIA | Multifunctional and Removable Electronic Light Emitting Grip Sleeve for a Paintbrush |
| US20180197643A1 (en) * | 2016-10-26 | 2018-07-12 | Industrial Heat, Llc | Monitoring and Controlling Exothermic Reactions Using Photon Detection Devices |
| CN109829368A (en) * | 2018-12-24 | 2019-05-31 | 平安科技（深圳）有限公司 | Recognition methods, device, computer equipment and the storage medium of palm feature |
-
2019
- 2019-12-25 CN CN201911356385.4A patent/CN110993107B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1286124A (en) * | 1999-08-31 | 2001-03-07 | 马传忠 | Human energy movement equipment |
| CN101632089A (en) * | 2005-09-01 | 2010-01-20 | 光谱辨识公司 | Biometric sensor |
| CN101577033A (en) * | 2009-05-26 | 2009-11-11 | 官洪运 | Multiband infrared image-type fire detecting system and fire alarm system thereof |
| US20160166054A1 (en) * | 2011-05-16 | 2016-06-16 | Emanuele Antonio SALTALAMACCHIA | Multifunctional and Removable Electronic Light Emitting Grip Sleeve for a Paintbrush |
| CN104598884A (en) * | 2015-01-20 | 2015-05-06 | 深圳市维亿魄科技有限公司 | Human body finger vein recognition device |
| US20180197643A1 (en) * | 2016-10-26 | 2018-07-12 | Industrial Heat, Llc | Monitoring and Controlling Exothermic Reactions Using Photon Detection Devices |
| CN109829368A (en) * | 2018-12-24 | 2019-05-31 | 平安科技（深圳）有限公司 | Recognition methods, device, computer equipment and the storage medium of palm feature |
Non-Patent Citations (2)
| Title |
|---|
| JINFENG YANG ETC.: "A method of multispectral finger-vein image fusion" * |
| 任丽晔等: "人体表面肌电信号的时频域特征提取研究" * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112614095A (en) * | 2020-12-15 | 2021-04-06 | 新绎健康科技有限公司 | Method and system for analyzing liver meridian energy based on image processing |
| CN113823407A (en) * | 2021-08-09 | 2021-12-21 | 新绎健康科技有限公司 | Physique prediction method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110993107B (en) | 2023-06-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11298018B2 (en) | Calculating conjunctival redness | |
| Cascinelli et al. | A possible new tool for clinical diagnosis of melanoma: the computer | |
| Kang et al. | Novel modified fuzzy c-means algorithm with applications | |
| Hall et al. | Computer screening for early detection of melanoma—is there a future? | |
| CN110993107B (en) | Human body five-finger image processing method and device | |
| US10076262B2 (en) | Localized physiologic status from luminosity around fingertip or toe | |
| Zhang et al. | Computerized facial diagnosis using both color and texture features | |
| JP2011118671A (en) | Apparatus, method and system for processing image, skin evaluation method | |
| Fernandes et al. | Early skin cancer detection using computer aided diagnosis techniques | |
| Abbes et al. | High-level features for automatic skin lesions neural network based classification | |
| Vocaturo et al. | On discovering relevant features for tongue colored image analysis | |
| CN112669959A (en) | Vitiligo state of illness automatic assessment method based on image | |
| Cheung et al. | Real-time, time–frequency mapping of event-related cortical activation | |
| CN117012344B (en) | Image analysis method for 4CMOS camera acquisition | |
| Haider et al. | Computer-assisted image processing technique for tracking wound progress | |
| CN113570724B (en) | Grid sphere corner-protection parameterization method based on inverse sphere projection and application thereof | |
| Lin | Complexion classification based on convolutional neural network | |
| KR20230069953A (en) | Skin surface analysis device and skin surface analysis method | |
| Lin et al. | Automatic sublingual vein feature extraction system | |
| CN112614095B (en) | Method and system for analyzing liver meridian energy based on image processing | |
| Azevedo-Marques et al. | Segmentation of dermatological ulcers using clustering of color components | |
| Yan et al. | Automated detection of laryngeal carcinoma in laryngoscopic images from a multicenter database using a convolutional neural network | |
| Lynn et al. | Segmentation of skin lesion towards melanoma skin cancer classification | |
| Jiang et al. | One Intelligent Facial Blackheads Identification Method Based on Computer Vision Technology | |
| RAVINDRAN et al. | GASTRIC CANCER DETECTION USING ISLIC AND SRM MODEL. |
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 |