CN113435377A - Medical palm vein image acquisition monitoring method and system - Google Patents
Medical palm vein image acquisition monitoring method and system Download PDFInfo
- Publication number
- CN113435377A CN113435377A CN202110761588.2A CN202110761588A CN113435377A CN 113435377 A CN113435377 A CN 113435377A CN 202110761588 A CN202110761588 A CN 202110761588A CN 113435377 A CN113435377 A CN 113435377A
- Authority
- CN
- China
- Prior art keywords
- image
- vein
- pixel
- palm
- palm vein
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 210000003462 vein Anatomy 0.000 title claims abstract description 292
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000012544 monitoring process Methods 0.000 title claims abstract description 39
- 238000012545 processing Methods 0.000 claims abstract description 55
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 238000003709 image segmentation Methods 0.000 claims abstract description 15
- 230000011218 segmentation Effects 0.000 claims abstract description 10
- 239000011159 matrix material Substances 0.000 claims description 29
- 230000007797 corrosion Effects 0.000 claims description 8
- 238000005260 corrosion Methods 0.000 claims description 8
- 230000003247 decreasing effect Effects 0.000 claims description 6
- 230000001678 irradiating effect Effects 0.000 claims description 5
- 230000009467 reduction Effects 0.000 claims description 4
- 102000001554 Hemoglobins Human genes 0.000 claims description 3
- 108010054147 Hemoglobins Proteins 0.000 claims description 3
- 210000004204 blood vessel Anatomy 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003628 erosive effect Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000284 extract Substances 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
- 238000003672 processing method Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
Landscapes
- Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Engineering & Computer Science (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention relates to the technical field of image acquisition, and discloses a medical palm vein image acquisition monitoring method, which comprises the following steps: emitting infrared light by using an LED to irradiate the palm, collecting the reflected infrared light by using an image sensor, and carrying out graying and linear stretching treatment on the collected image to obtain a palm vein image; processing the collected palm vein image by adopting a histogram equalization method to obtain an image-enhanced palm vein image; carrying out segmentation processing on the palm vein image by using a vein image segmentation algorithm based on vein curvature to obtain a vein blood vessel image; and (4) deburring and thinning the vein blood vessel image, and storing the processed vein blood vessel image into a medical database. The invention also provides a medical palm vein image acquisition monitoring system. The invention realizes the acquisition of medical vein images.
Description
Technical Field
The invention relates to the technical field of image acquisition, in particular to a medical palm vein image acquisition monitoring method and system.
Background
How to safely and efficiently identify the identity of an individual is an important problem which must be solved in the information era. The traditional identity identification method, such as an identity card, a user name and the like, has the defects that the identity card, the user name and the like are easy to lose and leak, and the like, which cannot be overcome, and the requirement of keeping the identity of the user secret in the medical field is more and more difficult to meet, and under the background, the biometric feature identification technology comes into force.
Palm vein identification is an emerging biological feature identification technology, and has many advantages, such as that palm veins belong to internal features of a body, have vitality, and are identified in a non-contact manner. As such, palm vein identification is becoming a focus of increasing attention.
The traditional vein image acquisition method extracts a small number of vein endpoints and vein intersections, and simultaneously acquires a low contrast vein image.
In view of this, how to acquire a vein image with higher quality becomes an urgent problem to be solved by those skilled in the art.
Disclosure of Invention
The invention provides a medical palm vein image acquisition monitoring method, which comprises the steps of irradiating a palm by using an LED to emit infrared light, acquiring reflected infrared light by using an image sensor to obtain a palm vein image, and processing the acquired palm vein image by adopting a histogram equalization method to obtain an image-enhanced palm vein image; and carrying out segmentation processing on the palm vein image by using a vein image segmentation algorithm based on vein curvature to obtain a vein image, simultaneously carrying out deburring and thinning processing on the vein image, and storing the processed vein image into a medical database.
In order to achieve the above object, the present invention provides a medical palm vein image acquisition monitoring method, which comprises:
emitting infrared light by using an LED to irradiate the palm, collecting the reflected infrared light by using an image sensor, and carrying out graying and linear stretching treatment on the collected image to obtain a palm vein image;
processing the collected palm vein image by adopting a histogram equalization method to obtain an image-enhanced palm vein image;
carrying out segmentation processing on the palm vein image by using a vein image segmentation algorithm based on vein curvature to obtain a vein blood vessel image;
and (4) deburring and thinning the vein blood vessel image, and storing the processed vein blood vessel image into a medical database.
Optionally, the illuminating the palm with the infrared light emitted by the LED, and collecting the reflected infrared light by the image sensor, includes:
irradiating the palm with infrared light emitted by the LED, wherein in one specific embodiment of the invention, the wavelength of the emitted infrared light is 780 nm;
the infrared light penetrates through tissues and enters blood vessels, hemoglobin in the vein blood vessels absorbs the near infrared light, other palm tissues reflect the near infrared light, the reflected light returns to the image sensor, and the image sensor collects the reflected light to obtain a palm vein image with a bright background and a dark target.
Optionally, the graying and linear stretching processing of the acquired image includes:
1) solving the maximum value of three components of each pixel in the collected palm vein image, and setting the maximum value as the gray value of the pixel point to obtain the gray image of the palm vein image, wherein the formula of the graying treatment is as follows:
G(i,j)=max{R(i,j),G(i,j),B(i,j)}
wherein:
(i, j) is a pixel point in the palm vein image;
r (i, j), G (i, j) and B (i, j) are respectively the values of the pixel point (i, j) in R, G, B three color channels;
g (i, j) is the gray value of the pixel point (i, j);
2) for the gray-scale image, the gray scale of the image is linearly stretched by utilizing a piecewise linear transformation mode, and the formula is as follows:
wherein:
f (x, y) is a gray value of the gray image;
MAXf(x,y),MINf(x,y)respectively the maximum and minimum grey values of the grey map.
Optionally, the processing the collected palm vein image by using a histogram equalization method includes:
1) dividing the palm vein image into M continuous and non-overlapping subregions;
2) calculating a gray level histogram of each subregion;
3) calculate the average number of pixels per sub-region:
wherein:
m represents the total number of pixels in the sub-region;
l represents the number of gray levels of the sub-region;
set the enhancement threshold toMaking the gray level histogram of the subarea larger thanTruncating the pixel number, adding the truncated pixel number, and averagely distributing the pixel number to each gray level;
4) calculating the probability of the occurrence of each gray level pixel in each sub-region gray level histogram after distribution:
wherein:
i represents a gray level, and L gray levels are total;
nirepresenting the number of pixels with the gray level i in the sub-area;
m represents the total number of pixels in the sub-region;
Pia probability of occurrence of a pixel representing a gray level i in the sub-region;
5) performing histogram equalization processing on each subarea:
wherein:
Pja probability of occurrence of a pixel representing a gray level j in the sub-region;
i' represents the gray level after histogram equalization processing;
obtaining a balanced subregion image;
6) and combining the equalized subarea images to obtain an image-enhanced palm vein image.
Optionally, the performing, by using a vein image segmentation algorithm based on vein curvature, a segmentation process on the palm vein image includes:
1) calculating the curvature k of the palm vein image at different direction angles thetaθ:
d′θ=d′xcosθ+d′ycosθ
Wherein:
(x, y) represents coordinates of the palm vein image;
d′θa first directional derivative representing a palm vein image;
d″θrepresenting the second directional derivative of the palm vein image;
in one embodiment of the present invention, the selected directional angle is 45 °;
2) detecting kθThe detected local maximum point is taken as Q ═ Q1,q2,…,qnN is the number of detected local maximum points; for detected local maximum points qiIn the neighborhood of (2), counting the number N (q) of continuous pixels with curvature value larger than 0i) And calculating the score of the local maximum point:
S(qi)=k(qi)*N(qi)
wherein:
k(qi) Denotes qiA curvature value of;
storing the scores of all local maximum points in a matrix F;
3) in the matrix F, respectively finding a pixel point (x, y), two pixel points adjacent to the left side of the pixel point and two pixel points adjacent to the right side of the pixel point; if the value of the pixel point (x, y) is smaller than or larger than the values of the two adjacent 4 pixel points, increasing or decreasing the value of the pixel point (x, y), and horizontally connecting the 5 pixel points, wherein the formula for increasing or decreasing the value of the pixel point (x, y) is as follows:
G(x,y)=min{max(F(x+1),y),F(x+2,y)),max(F(x-1),y),F(x-2,y))}
wherein:
g (x, y) is the pixel value of the pixel (x, y) after enhancement or reduction;
processing all pixel values to obtain a vein blood vessel image based on curvature;
4) and carrying out binarization processing on the vein image based on the curvature, selecting a threshold value T, marking pixel points smaller than the threshold value T in the vein image based on the curvature as a background, and marking the rest pixel points as veins to obtain the vein image.
Optionally, the deburring and thinning processing on the vein blood vessel image includes:
1) carrying out corrosion treatment on the vein blood vessel image pixel matrix:
wherein:
a represents a vein blood vessel image pixel matrix;
(x, y) represents image pixels;
b represents the erosion matrix, which in one embodiment of the invention is:
b is sequentially moved on A, when the image element (x, y) of A is translated, if the image element (x, y) of B is completely contained in the overlapped area of the image A, namely the corresponding A image value of the element position of 1 in B is all 1, the image element (x, y) corresponding to the output image is assigned to 1, otherwise, the image element (x, y) is assigned to 0;
2) expanding the pixel matrix of the corroded vein blood vessel image:
wherein:
a' represents a pixel matrix of the vein blood vessel image after corrosion;
c denotes the expansion matrix, which in one embodiment of the invention is used:
translating B to an image pel (x, y) position; if the intersection of the B and the A 'at the image pixel (x, y) is not empty, namely at least one image value corresponding to the A' at the element position of 1 in the B is 1, the pixel (x, y) corresponding to the output image is assigned to be 1, otherwise, the pixel is assigned to be 0;
3) detecting all vein endpoints and intersections of the vein blood vessel image after expansion processing, starting from a certain vein endpoint i, searching the intersections or endpoints along vein lines, marking pixel points between the intersections or endpoints, counting the number, and marking as M; 4) setting a threshold value T, if M is less than T, considering that the vein endpoint i is a burr, and setting the marked pixel point as a background; otherwise, the vein is regarded as the vein endpoint, and the marked pixel point is reserved;
5) and 3) performing the step 4) on all vein end points to obtain the vein vessel image after deburring and thinning.
In addition, in order to achieve the above object, the present invention further provides a medical palm vein image acquisition monitoring system, including:
the image acquisition device is used for irradiating the palm with infrared light emitted by the LED and collecting the reflected infrared light through the image sensor;
the image processor is used for carrying out graying and linear stretching processing on the acquired image to obtain a palm vein image; processing the collected palm vein image by adopting a histogram equalization method to obtain an image-enhanced palm vein image;
the medical palm vein image acquisition device is used for carrying out segmentation processing on a palm vein image by using a vein image segmentation algorithm based on vein curvature to obtain a vein blood vessel image; and (4) deburring and thinning the vein blood vessel image, and storing the processed vein blood vessel image into a medical database.
In addition, to achieve the above object, the present invention also provides a computer readable storage medium, which stores thereon medical palm vein image acquisition program instructions executable by one or more processors to implement the steps of the implementation method of medical palm vein image acquisition monitoring as described above.
Compared with the prior art, the invention provides a medical palm vein image acquisition monitoring method, which has the following advantages:
first, the conventional image contrast enhancement method is a histogram equalization method, which equalizes the number of pixels per gray level, i.e., there are no large number of similar pixels, the contrast of the image is improved, since the number of pixels of the image is fixed, in order to make the number of pixels of each gray level equal, it is necessary to make the gray level of the image span a wider range of gray levels, for example, the histogram equalization method may equalize pixels with gray levels of 0-4 to gray levels of 1-3, and if the number of pixels in 0, 4 gray levels is small, the number of pixels with 0 and 4 gray levels is set to be null, but when the gray level of the image is more, the traditional histogram equalization method can obviously reduce the gray level of the image, so that the vein detail information of the palm image is lost, therefore, the invention improves the traditional histogram equalization method, and the improved histogram equalization method comprises the following processes: dividing the palm vein image into M continuous and non-overlapping subregions; calculating a gray level histogram of each subregion; calculate the average number of pixels per sub-region:
wherein: m represents the total number of pixels in the sub-region; l represents the number of gray levels of the sub-region; set the enhancement threshold toMaking the gray level histogram of the subarea larger thanIs truncated to limit the image contrast, and the truncated pixel numbers are added to average the scoreAssigning each gray level to ensure that all gray levels have higher pixel number and the pixel number difference of each gray level is reduced; calculating the probability of the occurrence of each gray level pixel in each sub-region gray level histogram after distribution:
wherein: i represents a gray level, and L gray levels are total; n isiRepresenting the number of pixels with the gray level i in the sub-area; m represents the total number of pixels in the sub-region; piA probability of occurrence of a pixel representing a gray level i in the sub-region; performing histogram equalization processing on each subarea:
wherein: pjA probability of occurrence of a pixel representing a gray level j in the sub-region; i' represents the gray level after histogram equalization processing; obtaining a balanced subregion image; and combining the equalized subarea images to obtain an image-enhanced palm vein image. Compared with the traditional algorithm, the improved algorithm provided by the invention has the advantages that the pixel number of the image is truncated, the truncated pixel numbers are added and averagely distributed to each gray level, so that the pixel number difference of each gray level is reduced, and the problem that the image gray level is obviously reduced to cause the loss of the detail of the palm vein image during the histogram equalization can be avoided.
Meanwhile, the invention provides a vein image segmentation algorithm based on vein curvature, which firstly calculates the curvature k of the palm vein image at different direction angles thetaθ:
d′θ=d′xcosθ+d′ycosθ
Wherein: (x, y) represents coordinates of the palm vein image; d'θA first directional derivative representing a palm vein image; d ″)θRepresenting the second directional derivative of the palm vein image; by detecting curvature kθThe detected local maximum point is taken as Q ═ Q1,q2,…,qnAnd n is the number of local maximum points detected, since the vein curve in the palm vein image is a concave curve, the lowest point of the concave curve is the center point of the vein, the curvature of the lowest point of the concave curve is the maximum, and the value with the curvature greater than 0 in the concave curve is the vein, for the palm vein image, the pixel point with the maximum curvature may be the center point of the vein, and Q is { Q ═ Q { (Q) } Q { (Q) for the palm vein image, where the value with the maximum curvature is the value of the vein, and the value with the maximum curvature is the value of the lowest point of the concave curve1,q2,…,qnThe candidate pixel points are the vein central point candidate pixel points of the palm image; for detected local maximum points qiIn the neighborhood of (2), counting the number N (q) of continuous pixels with curvature value larger than 0i) And calculating the score of the local maximum point:
S(qi)=k(qi)*N(qi)
wherein: k (q)i) Denotes qiA curvature value of; storing the scores of all local maximum points in a matrix F; because of the interference of factors such as burrs and noise, the detected local maximum point may not be the true vein central point, and this local maximum point needs to be eliminated, therefore in the matrix F, the pixel point (x, y) and the two pixel points adjacent to the left side and the two pixel points adjacent to the right side are found respectively, if the value of the pixel point (x, y) is less than or greater than the value of the 4 pixel points adjacent to the two sides, the value of the pixel point (x, y) is increased or reduced, and these 5 pixel points are horizontally connected, that is, the vein central point is connected, the connection result is the vein, the formula for increasing or reducing the value of the pixel point (x, y) is:
G(x,y)=min{max(F(x+1),y),F(x+2,y)),max(F(x-1),y),F(x-2,y))}
wherein: g (x, y) is the pixel value of the pixel (x, y) after enhancement or reduction; processing all pixel values to obtain a vein blood vessel image based on curvature; the invention carries out cross-section processing on a palm vein image, expresses the position of a pixel point on a cross-section line and the gray value of the pixel point in a Cartesian coordinate system, finds that the gray curve of a vein area is a concave curve, the lowest point of the concave curve is the center point of a vein, the curvature of the lowest point of the concave curve is the maximum, the value with the curvature larger than 0 in the concave curve is the vein, and for the palm vein image, the pixel point with the maximum curvature is probably the center point of the vein, therefore, the invention uses the value with the maximum curvature in a local palm vein image as a candidate pixel point at the center of the vein by detecting the curvature of the image gray curve, calculates the number of pixel points with the curvature larger than 0 around the candidate pixel point at the center of the vein, calculates the score of the candidate pixel point at the center of each vein, and carries out denoising and deburring on each pixel point in the score matrix F, the method comprises the steps of selecting values of pixel points, namely the values of the pixel points are smaller than or larger than values of 4 adjacent pixel points on two sides, increasing or reducing the values of the pixel points, horizontally connecting the 5 pixel points, namely connecting vein central points, wherein the connection result is a vein vessel, so that vein labeling in a palm vein image is realized.
Drawings
Fig. 1 is a schematic flow chart of a medical palm vein image acquisition monitoring method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a medical palm vein image acquisition and monitoring system according to an embodiment of the present invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Emitting infrared light by using an LED to irradiate the palm, collecting the reflected infrared light by using an image sensor to obtain a palm vein image, and processing the collected palm vein image by adopting a histogram equalization method to obtain an image-enhanced palm vein image; and carrying out segmentation processing on the palm vein image by using a vein image segmentation algorithm based on vein curvature to obtain a vein image, simultaneously carrying out deburring and thinning processing on the vein image, and storing the processed vein image into a medical database. Fig. 1 is a schematic view of a medical palm vein image acquisition monitoring method according to an embodiment of the present invention.
In this embodiment, the medical palm vein image acquisition monitoring method includes:
and S1, emitting infrared light by an LED to irradiate the palm, collecting the reflected infrared light by an image sensor, and carrying out graying and linear stretching processing on the collected image to obtain a palm vein image.
Firstly, the invention uses LED to emit infrared light to irradiate the palm, and in a specific embodiment of the invention, the wavelength of the emitted infrared light is 780 nm;
infrared light penetrates through tissues and enters blood vessels, hemoglobin in vein blood vessels absorbs near infrared light, other palm tissues reflect the near infrared light, the reflected light returns to an image sensor, and the image sensor collects the reflected light to obtain a palm vein image with a bright background and a dark target;
further, the invention performs graying and grayscale stretching processing on the collected palm vein image, and the flow of the image graying and grayscale stretching processing is as follows:
1) solving the maximum value of three components of each pixel in the collected palm vein image, and setting the maximum value as the gray value of the pixel point to obtain the gray image of the palm vein image, wherein the formula of the graying treatment is as follows:
G(i,j)=max{R(i,j),G(i,j),B(i,j)}
wherein:
(i, j) is a pixel point in the palm vein image;
r (i, j), G (i, j) and B (i, j) are respectively the values of the pixel point (i, j) in R, G, B three color channels;
g (i, j) is the gray value of the pixel point (i, j);
2) for the gray-scale image, the gray scale of the image is linearly stretched by utilizing a piecewise linear transformation mode, and the formula is as follows:
wherein:
f (x, y) is a gray value of the gray image;
MAXf(x,y),MINf(x,y)respectively the maximum and minimum grey values of the grey map.
And S2, processing the collected palm vein image by adopting a histogram equalization method to obtain an image-enhanced palm vein image.
Furthermore, the invention adopts a histogram equalization method to enhance the collected palm vein image, and the flow of the histogram equalization method is as follows:
1) dividing the palm vein image into M continuous and non-overlapping subregions;
2) calculating a gray level histogram of each subregion;
3) calculate the average number of pixels per sub-region:
wherein:
m represents the total number of pixels in the sub-region;
l represents the number of gray levels of the sub-region;
set the enhancement threshold toMaking the gray level histogram of the subarea larger thanTruncating the pixel number, adding the truncated pixel number, and averagely distributing the pixel number to each gray level;
4) calculating the probability of the occurrence of each gray level pixel in each sub-region gray level histogram after distribution:
wherein:
i represents a gray level, and L gray levels are total;
nirepresenting the number of pixels with the gray level i in the sub-area;
m represents the total number of pixels in the sub-region;
Pia probability of occurrence of a pixel representing a gray level i in the sub-region;
5) performing histogram equalization processing on each subarea:
wherein:
Pja probability of occurrence of a pixel representing a gray level j in the sub-region;
i' represents the gray level after histogram equalization processing;
obtaining a balanced subregion image;
6) and combining the equalized subarea images to obtain an image-enhanced palm vein image.
And S3, carrying out segmentation processing on the palm vein image by using a vein image segmentation algorithm based on the vein curvature to obtain a vein blood vessel image.
Furthermore, the invention utilizes a vein image segmentation algorithm based on vein curvature to segment the palm vein image, and the vein image segmentation algorithm based on vein curvature comprises the following steps:
1) calculating the curvature k of the palm vein image at different direction angles thetaθ:
d′θ=d′xcosθ+d′ycosθ
Wherein:
(x, y) represents coordinates of the palm vein image;
d′θa first directional derivative representing a palm vein image;
d″θrepresenting the second directional derivative of the palm vein image;
in one embodiment of the present invention, the selected directional angle is 45 °;
2) detecting kθThe detected local maximum point is taken as Q ═ Q1,q2,…,qnN is the number of detected local maximum points; for detected local maximum points qiIn the neighborhood of (2), counting the number N (q) of continuous pixels with curvature value larger than 0i) And calculating the score of the local maximum point:
S(qi)=k(qi)*N(qi)
wherein:
k(qi) Denotes qiA curvature value of;
storing the scores of all local maximum points in a matrix F;
3) in the matrix F, respectively finding a pixel point (x, y), two pixel points adjacent to the left side of the pixel point and two pixel points adjacent to the right side of the pixel point; if the value of the pixel point (x, y) is smaller than or larger than the values of the two adjacent 4 pixel points, increasing or decreasing the value of the pixel point (x, y), and horizontally connecting the 5 pixel points, wherein the formula for increasing or decreasing the value of the pixel point (x, y) is as follows:
G(x,y)=min{max(F(x+1),y),F(x+2,y)),max(F(x-1),y),F(x-2,y))}
wherein:
g (x, y) is the pixel value of the pixel (x, y) after enhancement or reduction;
processing all pixel values to obtain a vein blood vessel image based on curvature;
4) and carrying out binarization processing on the vein image based on the curvature, selecting a threshold value T, marking pixel points smaller than the threshold value T in the vein image based on the curvature as a background, and marking the rest pixel points as veins to obtain the vein image.
And S4, deburring and thinning the vein blood vessel image, and storing the processed vein blood vessel image into a medical database.
Further, the invention carries out deburring and thinning processing on the vein blood vessel image, and the deburring and thinning processing method of the vein blood vessel image comprises the following steps:
1) carrying out corrosion treatment on the vein blood vessel image pixel matrix:
wherein:
a represents a vein blood vessel image pixel matrix;
(x, y) represents image pixels;
b represents the erosion matrix, which in one embodiment of the invention is:
b is sequentially moved on A, when the image element (x, y) of A is translated, if the image element (x, y) of B is completely contained in the overlapped area of the image A, namely the corresponding A image value of the element position of 1 in B is all 1, the image element (x, y) corresponding to the output image is assigned to 1, otherwise, the image element (x, y) is assigned to 0;
2) expanding the pixel matrix of the corroded vein blood vessel image:
wherein:
a' represents a pixel matrix of the vein blood vessel image after corrosion;
c denotes the expansion matrix, which in one embodiment of the invention is used:
translating B to an image pel (x, y) position; if the intersection of the B and the A 'at the image pixel (x, y) is not empty, namely at least one image value corresponding to the A' at the element position of 1 in the B is 1, the pixel (x, y) corresponding to the output image is assigned to be 1, otherwise, the pixel is assigned to be 0;
3) detecting all vein endpoints and intersections of the vein blood vessel image after expansion processing, starting from a certain vein endpoint i, searching the intersections or endpoints along vein lines, marking pixel points between the intersections or endpoints, counting the number, and marking as M;
4) setting a threshold value T, if M is less than T, considering that the vein endpoint i is a burr, and setting the marked pixel point as a background; otherwise, the vein is regarded as the vein endpoint, and the marked pixel point is reserved;
5) and 3) performing the step 4) on all vein end points to obtain the vein vessel image after deburring and thinning.
Further, the present invention stores the vein image of the deburred and refined vein image in a medical database.
The following describes embodiments of the present invention through an algorithmic experiment and tests of the inventive treatment method. The hardware test environment of the algorithm of the invention is as follows: inter (R) core (TM) i7-6700KCPU with software Matlab2018 b; the contrast method is a medical palm vein image acquisition method based on random forests and a medical palm vein image acquisition method based on sensors.
In the algorithm experiment, the data set is 10G of medical palm vein images to be acquired. In the experiment, the medical palm vein image to be acquired is acquired by using the medical image acquisition method, the quality of the acquired image is used as an evaluation index of algorithm feasibility, and the higher the quality of the acquired medical palm vein image is, the higher the effectiveness and the feasibility of the algorithm are.
According to the experimental result, the image quality of the medical palm vein image acquisition method based on the sensor is 84.62%, the image quality of the medical palm vein image acquisition method based on the neural network is 87.66%, the image quality of the method is 90.11%, and compared with a comparison algorithm, the medical palm vein image acquisition monitoring method provided by the invention can acquire a medical palm vein image with higher quality.
The invention also provides a medical palm vein image acquisition monitoring system. Fig. 2 is a schematic diagram of an internal structure of a medical palm vein image acquisition and monitoring system according to an embodiment of the present invention.
In the present embodiment, the medical palm vein image acquisition monitoring system 1 includes at least an image acquisition device 11, an image processor 12, a medical palm vein image acquisition device 13, a communication bus 14, and a network interface 15.
The image capturing device 11 may be a PC (Personal Computer), a terminal device such as a smart phone, a tablet Computer, or a mobile Computer, or may be a server.
The medical palm vein image capture device 13 may be, in some embodiments, a Central Processing Unit (CPU), controller, microcontroller, microprocessor or other data Processing chip including a monitoring Unit for running program code stored in the image processor 12 or Processing data, such as medical palm vein image capture program instructions 16.
The communication bus 14 is used to enable connection communication between these components.
The network interface 15 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), and is typically used to establish a communication link between the system 1 and other electronic devices.
Optionally, the medical palm vein image acquisition monitoring system 1 may further include a user interface, the user interface may include a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface may further include a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display may also be referred to as a display screen or a display unit, where appropriate, for displaying information processed in the medical palm vein image acquisition monitoring system 1 and for displaying a visual user interface.
Fig. 2 only shows the medical palm vein image acquisition monitoring system 1 with the components 11-15, and it will be understood by those skilled in the art that the structure shown in fig. 1 does not constitute a limitation of the medical palm vein image acquisition monitoring system 1, and may include fewer or more components than those shown, or some components in combination, or a different arrangement of components.
In the embodiment of the medical palm vein image acquisition monitoring system 1 shown in fig. 2, the image processor 12 stores therein medical palm vein image acquisition program instructions 16; the steps of the medical palm vein image acquisition device 13 executing the medical palm vein image acquisition program instructions 16 stored in the image processor 12 are the same as the implementation method of the medical palm vein image acquisition monitoring method, and are not described here.
Furthermore, an embodiment of the present invention also provides a computer-readable storage medium having stored thereon medical palm vein image acquisition program instructions executable by one or more processors to implement the following operations:
emitting infrared light by using an LED to irradiate the palm, collecting the reflected infrared light by using an image sensor, and carrying out graying and linear stretching treatment on the collected image to obtain a palm vein image;
processing the collected palm vein image by adopting a histogram equalization method to obtain an image-enhanced palm vein image;
carrying out segmentation processing on the palm vein image by using a vein image segmentation algorithm based on vein curvature to obtain a vein blood vessel image;
and (4) deburring and thinning the vein blood vessel image, and storing the processed vein blood vessel image into a medical database.
It should be noted that the above-mentioned numbers of the embodiments of the present invention are merely for description, and do not represent the merits of the embodiments. And the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (8)
1. A medical palm vein image acquisition monitoring method is characterized by comprising the following steps:
emitting infrared light by using an LED to irradiate the palm, collecting the reflected infrared light by using an image sensor, and carrying out graying and linear stretching treatment on the collected image to obtain a palm vein image;
processing the collected palm vein image by adopting a histogram equalization method to obtain an image-enhanced palm vein image;
carrying out segmentation processing on the palm vein image by using a vein image segmentation algorithm based on vein curvature to obtain a vein blood vessel image;
and (4) deburring and thinning the vein blood vessel image, and storing the processed vein blood vessel image into a medical database.
2. The medical palm vein image acquisition monitoring method according to claim 1, wherein the illuminating the palm with the infrared light emitted by the LED and collecting the reflected infrared light by the image sensor comprises:
irradiating the palm with infrared light emitted by the LED;
the infrared light penetrates through tissues and enters blood vessels, hemoglobin in the vein blood vessels absorbs the near infrared light, other palm tissues reflect the near infrared light, the reflected light returns to the image sensor, and the image sensor collects the reflected light to obtain a palm vein image with a bright background and a dark target.
3. The medical palm vein image acquisition monitoring method according to claim 2, wherein the graying and linear stretching processing of the acquired image comprises:
1) solving the maximum value of three components of each pixel in the collected palm vein image, and setting the maximum value as the gray value of the pixel point to obtain the gray image of the palm vein image, wherein the formula of the graying treatment is as follows:
G(i,j)=max{R(i,j),G(i,j),B(i,j)}
wherein:
(i, j) is a pixel point in the palm vein image;
r (i, j), G (i, j) and B (i, j) are respectively the values of the pixel point (i, j) in R, G, B three color channels;
g (i, j) is the gray value of the pixel point (i, j);
2) for the gray-scale image, the gray scale of the image is linearly stretched by utilizing a piecewise linear transformation mode, and the formula is as follows:
wherein:
f (x, y) is a gray value of the gray image;
MAXf(x,y),MINf(x,y)respectively the maximum and minimum grey values of the grey map.
4. The medical palm vein image acquisition monitoring method according to claim 3, wherein the processing the acquired palm vein image by using the histogram equalization method comprises:
1) dividing the palm vein image into M continuous and non-overlapping subregions;
2) calculating a gray level histogram of each subregion;
3) calculate the average number of pixels per sub-region:
wherein:
m represents the total number of pixels in the sub-region;
l represents the number of gray levels of the sub-region;
set the enhancement threshold toMaking the gray level histogram of the subarea larger thanTruncating the pixel number, adding the truncated pixel number, and averagely distributing the pixel number to each gray level;
4) calculating the probability of the occurrence of each gray level pixel in each sub-region gray level histogram after distribution:
wherein:
i represents a gray level, and L gray levels are total;
nirepresenting the number of pixels with the gray level i in the sub-area;
m represents the total number of pixels in the sub-region;
Pia probability of occurrence of a pixel representing a gray level i in the sub-region;
5) performing histogram equalization processing on each subarea:
wherein:
Pja probability of occurrence of a pixel representing a gray level j in the sub-region;
i' represents the gray level after histogram equalization processing;
obtaining a balanced subregion image;
6) and combining the equalized subarea images to obtain an image-enhanced palm vein image.
5. The medical palm vein image acquisition monitoring method according to claim 4, wherein the palm vein image segmentation processing by using the vein image segmentation algorithm based on vein curvature comprises:
1) calculating the curvature k of the palm vein image at different direction angles thetaθ:
d′θ=d′xcosθ+d′ycosθ
Wherein:
(x, y) represents coordinates of the palm vein image;
d′θa first directional derivative representing a palm vein image;
d″θrepresenting the second directional derivative of the palm vein image;
2) detecting kθThe detected local maximum point is taken as Q ═ Q1,q2,...,qnN is the number of detected local maximum points; for detected local maximum points qiIn the neighborhood of (2), counting the number N (q) of continuous pixels with curvature value larger than 0i) And calculating the score of the local maximum point:
S(qi)=k(qi)*N(qi)
wherein:
k(qi) Denotes qiA curvature value of;
storing the scores of all local maximum points in a matrix F;
3) in the matrix F, respectively finding a pixel point (x, y), two pixel points adjacent to the left side of the pixel point and two pixel points adjacent to the right side of the pixel point; if the value of the pixel point (x, y) is smaller than or larger than the values of the two adjacent 4 pixel points, increasing or decreasing the value of the pixel point (x, y), and horizontally connecting the 5 pixel points, wherein the formula for increasing or decreasing the value of the pixel point (x, y) is as follows:
G(x,y)=min{max(F(x+1),y),F(x+2,y)),max(F(x-1),y),F(x-2,y))}
wherein:
g (x, y) is the pixel value of the pixel (x, y) after enhancement or reduction;
processing all pixel values to obtain a vein blood vessel image based on curvature;
4) and carrying out binarization processing on the vein image based on the curvature, selecting a threshold value T, marking pixel points smaller than the threshold value T in the vein image based on the curvature as a background, and marking the rest pixel points as veins to obtain the vein image.
6. The medical palm vein image acquisition monitoring method according to claim 5, wherein the deburring and thinning processing on the vein blood vessel image comprises the following steps:
1) carrying out corrosion treatment on the vein blood vessel image pixel matrix:
wherein:
a represents a vein blood vessel image pixel matrix;
(x, y) represents image pixels;
b represents a corrosion matrix, and the adopted corrosion matrix is as follows:
b is sequentially moved on A, when the image element (x, y) of A is translated, if the image element (x, y) of B is completely contained in the overlapped area of the image A, namely the corresponding A image value of the element position of 1 in B is all 1, the image element (x, y) corresponding to the output image is assigned to 1, otherwise, the image element (x, y) is assigned to 0;
2) expanding the pixel matrix of the corroded vein blood vessel image:
wherein:
a' represents a pixel matrix of the vein blood vessel image after corrosion;
c represents the expansion matrix, the expansion matrix used is:
translating B to an image pel (x, y) position; if the intersection of the B and the A 'at the image pixel (x, y) is not empty, namely at least one image value corresponding to the A' at the element position of 1 in the B is 1, the pixel (x, y) corresponding to the output image is assigned to be 1, otherwise, the pixel is assigned to be 0;
3) detecting all vein endpoints and intersections of the vein blood vessel image after expansion processing, starting from a certain vein endpoint i, searching the intersections or endpoints along vein lines, marking pixel points between the intersections or endpoints, counting the number, and marking as M;
4) setting a threshold value T, if M is less than T, considering that the vein endpoint i is a burr, and setting the marked pixel point as a background; otherwise, the vein is regarded as the vein endpoint, and the marked pixel point is reserved;
5) and 3) performing the step 4) on all vein end points to obtain the vein vessel image after deburring and thinning.
7. A medical palm vein image acquisition monitoring system, the system comprising:
the image acquisition device is used for irradiating the palm with infrared light emitted by the LED and collecting the reflected infrared light through the image sensor;
the image processor is used for carrying out graying and linear stretching processing on the acquired image to obtain a palm vein image; processing the collected palm vein image by adopting a histogram equalization method to obtain an image-enhanced palm vein image;
the medical palm vein image acquisition device is used for carrying out segmentation processing on a palm vein image by using a vein image segmentation algorithm based on vein curvature to obtain a vein blood vessel image; and (4) deburring and thinning the vein blood vessel image, and storing the processed vein blood vessel image into a medical database.
8. A computer readable storage medium having stored thereon medical palm vein image acquisition program instructions executable by one or more processors to implement the steps of an implementation method of medical palm vein image acquisition monitoring as described above.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110761588.2A CN113435377A (en) | 2021-07-06 | 2021-07-06 | Medical palm vein image acquisition monitoring method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110761588.2A CN113435377A (en) | 2021-07-06 | 2021-07-06 | Medical palm vein image acquisition monitoring method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113435377A true CN113435377A (en) | 2021-09-24 |
Family
ID=77759261
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110761588.2A Pending CN113435377A (en) | 2021-07-06 | 2021-07-06 | Medical palm vein image acquisition monitoring method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113435377A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117152803A (en) * | 2023-10-30 | 2023-12-01 | 江苏圣点世纪科技有限公司 | Facial vein image equalization method |
CN117392038A (en) * | 2023-12-05 | 2024-01-12 | 北京智源人工智能研究院 | Medical image histogram equalization method and device, electronic equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109934118A (en) * | 2019-02-19 | 2019-06-25 | 河北大学 | A kind of hand back vein personal identification method |
CN110147769A (en) * | 2019-05-22 | 2019-08-20 | 成都艾希维智能科技有限公司 | A kind of finger venous image matching process |
CN112418150A (en) * | 2020-12-03 | 2021-02-26 | 佳都新太科技股份有限公司 | Palm vein image evaluation method and device, computer equipment and storage medium |
CN112991217A (en) * | 2021-03-24 | 2021-06-18 | 吴统明 | Medical image acquisition method, device and equipment |
-
2021
- 2021-07-06 CN CN202110761588.2A patent/CN113435377A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109934118A (en) * | 2019-02-19 | 2019-06-25 | 河北大学 | A kind of hand back vein personal identification method |
CN110147769A (en) * | 2019-05-22 | 2019-08-20 | 成都艾希维智能科技有限公司 | A kind of finger venous image matching process |
CN112418150A (en) * | 2020-12-03 | 2021-02-26 | 佳都新太科技股份有限公司 | Palm vein image evaluation method and device, computer equipment and storage medium |
CN112991217A (en) * | 2021-03-24 | 2021-06-18 | 吴统明 | Medical image acquisition method, device and equipment |
Non-Patent Citations (9)
Title |
---|
吴留生: "手掌静脉网图像的获取与细化技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, pages 138 - 2090 * |
孙晓琳: "指静脉图像模式提取算法研究", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》, 31 January 2013 (2013-01-31), pages 138 - 1698 * |
孙晓琳: "指静脉图像模式提取算法研究", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》, pages 138 - 1698 * |
宋丽梅: "《机器视觉与机器学习》", 31 May 2020, 机械工业出版社, pages: 55 - 56 * |
朱丛虎: "低质量手背静脉图像的增强和分割", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》, pages 138 - 933 * |
桂青: "多特征点融合的手背静脉身份识别算法研究", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》, 28 February 2021 (2021-02-28), pages 138 - 1468 * |
王凤华: "《空间遥感图像预处理技术》", 30 June 2020, 国防工业出版社, pages: 41 - 46 * |
肖潇: "基于手指静脉的身份识别技术研究", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》, pages 138 - 679 * |
饶青: "基于位置方向编码的手指静脉识别方法研究", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》, pages 138 - 645 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117152803A (en) * | 2023-10-30 | 2023-12-01 | 江苏圣点世纪科技有限公司 | Facial vein image equalization method |
CN117152803B (en) * | 2023-10-30 | 2024-02-09 | 江苏圣点世纪科技有限公司 | Facial vein image equalization method |
CN117392038A (en) * | 2023-12-05 | 2024-01-12 | 北京智源人工智能研究院 | Medical image histogram equalization method and device, electronic equipment and storage medium |
CN117392038B (en) * | 2023-12-05 | 2024-03-08 | 北京智源人工智能研究院 | Medical image histogram equalization method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110148121B (en) | Skin image processing method and device, electronic equipment and medium | |
WO2019109526A1 (en) | Method and device for age recognition of face image, storage medium | |
CN108875734B (en) | Liver canceration positioning method, device and storage medium | |
US10275677B2 (en) | Image processing apparatus, image processing method and program | |
CN113436162B (en) | Method and device for identifying weld defects on surface of hydraulic oil pipeline of underwater robot | |
CN113435377A (en) | Medical palm vein image acquisition monitoring method and system | |
CN111310705A (en) | Image recognition method and device, computer equipment and storage medium | |
CN110008997B (en) | Image texture similarity recognition method, device and computer readable storage medium | |
CN112464829B (en) | Pupil positioning method, pupil positioning equipment, storage medium and sight tracking system | |
CN110852311A (en) | Three-dimensional human hand key point positioning method and device | |
WO2019033570A1 (en) | Lip movement analysis method, apparatus and storage medium | |
WO2019033568A1 (en) | Lip movement capturing method, apparatus and storage medium | |
CN110751024A (en) | User identity identification method and device based on handwritten signature and terminal equipment | |
JP5556663B2 (en) | Verification device, verification method, and program | |
CN112419207A (en) | Image correction method, device and system | |
CN112149570A (en) | Multi-person living body detection method and device, electronic equipment and storage medium | |
CN108764121B (en) | Method for detecting living object, computing device and readable storage medium | |
CN113077464A (en) | Medical image processing method, medical image identification method and device | |
CN112991217A (en) | Medical image acquisition method, device and equipment | |
CN111191584B (en) | Face recognition method and device | |
CN110222571B (en) | Intelligent judgment method and device for black eye and computer readable storage medium | |
CN108875467B (en) | Living body detection method, living body detection device and computer storage medium | |
CN113228105A (en) | Image processing method and device and electronic equipment | |
CN114529570A (en) | Image segmentation method, image identification method, user certificate subsidizing method and system | |
CN110751158B (en) | Digital identification method, device and storage medium in therapeutic bed display |
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 |