CN103027713A - Muscle thickness measuring method and system based on ultrasonic image - Google Patents
Muscle thickness measuring method and system based on ultrasonic image Download PDFInfo
- Publication number
- CN103027713A CN103027713A CN2012105630569A CN201210563056A CN103027713A CN 103027713 A CN103027713 A CN 103027713A CN 2012105630569 A CN2012105630569 A CN 2012105630569A CN 201210563056 A CN201210563056 A CN 201210563056A CN 103027713 A CN103027713 A CN 103027713A
- Authority
- CN
- China
- Prior art keywords
- image
- tracking
- windows
- muscle thickness
- tracking window
- 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
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a muscle thickness measuring method and system based on an ultrasonic image. The method comprises the following steps of: extracting an interesting image from the ultrasonic image; acquiring the positions of a plurality of initial tracing windows selected in the interesting image; tracing the tracing windows, and determining the positions of a plurality of tracing windows which correspond to every frame of subsequent image through a tracing algorithm; processing tracing windows which are similar to the modes of surrounding images in the tracing windows of each frame of image by taking a diagonal intersection point as a central point, and processing other tracing windows in every frame of image by adopting an edge detection method; and computing a maximum vertical distance between the position of each tracing window processed by using the central point in every frame of image and the position of each tracing window processed through the edge detection method, wherein the maximum vertical distance is taken as a muscle thickness value. Due to the adoption of the muscle thickness measuring method and the muscle thickness measuring system based on the ultrasonic image, the measuring accuracy and measuring efficiency are increased, and the aim of measuring in real time is fulfilled.
Description
Technical field
The present invention relates to image processing field, particularly relate to a kind of muscle thickness measuring method and system based on ultrasonoscopy.
Background technology
The mechanical characteristic of skeletal muscle is relevant with its configuration, and any body movement and sports all are to be finished by the contraction of skeletal muscle, and this has directly affected the strength and stamina of human body.Muscle has certain elasticity, after being elongated, can automatically restore to original degree when pulling force is removed, and the elasticity of muscle can be slowed down external force to the impact of human body, thereby is playing the part of at the volley vital effect.And the formation of muscle is very complicated, and quantitative analysis and assessment muscle function state are difficult point and the focuses in sports medical science and the motion function rehabilitation research.
At present for the measurement of the thickness of muscle, what take such as the measurement major part of thickness is to measure manually, because of manual measurement quite responsive to many subjective factorss such as environment, lack objectivity so that measure, certainty of measurement is difficult to control, and for measuring large batch of muscle thickness picture, worrying about process wastes time and energy, and it is low to measure efficient.The variation of skeletal muscle muscle thickness in motor process is trickleer in every two field picture in addition, measures easy distortion, thereby affects measurement result.
Summary of the invention
Based on this, be necessary for measuring efficient in the prior art lowly and measure inaccurate problem, a kind of muscle thickness measuring method based on ultrasonoscopy that can improve accuracy of measurement and measure efficient is provided.
In addition, also be necessary for measuring efficient in the prior art lowly and measure inaccurate problem, a kind of muscle thickness measuring system based on ultrasonoscopy that can improve accuracy of measurement and measure efficient is provided.
A kind of muscle thickness measuring method based on ultrasonoscopy may further comprise the steps:
From the ultrasonoscopy that catches, extract image of interest;
Obtain the position of a plurality of initial tracking windows of in described image of interest, selecting;
A plurality of tracking windows are followed the tracks of, and determined the position of the corresponding a plurality of tracking windows of follow-up every two field picture by track algorithm;
To tracking window similar to image modalities on every side in a plurality of tracking windows of every two field picture adopt get the diagonal intersection point centered by point process, adopt edge detection methods to process to all the other tracking windows in every two field picture;
Maximum normal distance between the position of the tracking window after process through edge detection method with each position of calculating in every two field picture the tracking window after processing through central point, with described maximum normal distance as the muscle thickness value between the tracking window after the tracking window after processing through central point and the processing of process edge detection method.
A kind of muscle thickness measuring system based on ultrasonoscopy comprises:
Extraction module is used for extracting image of interest from the ultrasonoscopy that catches;
Acquisition module is used for the position that obtains a plurality of initial tracking window of selecting in described image of interest;
Tracking module is used for a plurality of tracking windows are followed the tracks of, and determines the position of the corresponding a plurality of tracking windows of follow-up every two field picture by track algorithm;
Processing module, be used for to a plurality of tracking windows of every two field picture tracking window similar with image modalities on every side adopt get the diagonal intersection point centered by point process, all the other tracking windows employing edge detection methods in every two field picture are processed;
Computing module, maximum normal distance between the position of the tracking window after process through edge detection method with each position that is used for calculating the tracking window after every two field picture is processed through central point, with described maximum normal distance as the muscle thickness value between the tracking window after the tracking window after processing through central point and the processing of process edge detection method.
Above-mentioned muscle thickness measuring method and system based on ultrasonoscopy, by a plurality of tracking windows of choosing are followed the tracks of, determine the position of a plurality of tracking windows in follow-up every two field picture by track algorithm, maximum normal distance between the position of the tracking window after the position of calculating the tracking window of processing through central point in every two field picture and the edge detection method processing, as the muscle thickness value, this measuring method is based on ultrasonoscopy, and it is comparatively accurate to adopt image algorithm to carry out the muscle thickness value that correcting process obtains, improve the accuracy of measuring and measured efficient, and can follow the tracks of the tracking window of follow-up every two field picture, and measure muscle thickness value in every two field picture, reached the purpose of real-time measurement.
Description of drawings
Fig. 1 is based on the schematic flow sheet of the muscle thickness measuring method of ultrasonoscopy among the embodiment;
Fig. 2 is pretreated ultrasonoscopy;
Fig. 3 is the defining and pinpoint sketch map of tracking window in the image;
Fig. 4 is for to follow the tracks of a plurality of tracking windows, and determines the schematic flow sheet of position of the tracking window of subsequent image frames by track algorithm;
Fig. 5 is based on the structural representation of the muscle thickness measuring system of ultrasonoscopy among the embodiment;
Fig. 6 is the internal structure sketch map of tracking module among the embodiment;
Fig. 7 is based on the structural representation of the muscle thickness measuring system of ultrasonoscopy among another embodiment.
The specific embodiment
Below in conjunction with specific embodiment and accompanying drawing to being described in detail based on the muscle thickness measuring method of ultrasonoscopy and the technical scheme of system, so that it is clearer.
As shown in Figure 1, in one embodiment, a kind of muscle thickness measuring method based on ultrasonoscopy may further comprise the steps:
Step S110 extracts image of interest from ultrasonoscopy.
In the present embodiment, obtain the ultrasonoscopy of muscle by Real-time B-Mode Ultrasound ripple scanner and electronics linear array probe.Concrete, the long axis direction of ultrasound probe vertically is arranged on experimenter's the thigh, is positioned over the major axis distance of about 40% knee.Using a large amount of ultrasound gel to guarantee to pop one's head in skin is acoustical coupling during muscle contraction, adjusts probe with the muscle package in the optimized contrast ratio demonstration ultrasonoscopy.Adopt the B mode ultrasound scan instrument to obtain ultrasonoscopy and be sent to video capture card, carry out digitized processing by it, and collect digitized image capture card in the computer with the sample rate of speed about 25 frame/seconds.
The ultrasonoscopy that catches is carried out cutting obtain image of interest.Image of interest is the image of the muscle thickness information that includes required measurement.
In one embodiment, after from the ultrasonoscopy that catches, extracting the step of image of interest, also comprise step: this image of interest is carried out pretreatment, comprising: described image of interest is carried out greyscale transformation and adjusted picture contrast.Be illustrated in figure 2 as pretreated ultrasonoscopy.
Step S120, the position that obtains a plurality of initial tracking window of in this image of interest, selecting.
Concrete, at first manually in image of interest, select the position of a plurality of initial tracking windows.In the present embodiment, a plurality of is three, can manually select three initial tracking windows, follows the tracks of respectively femur, rectus femoris top and rectus femoris lower limits, and as shown in Figure 3, window A, B and C represent respectively above-mentioned three initial tracking windows.
Step S130 follows the tracks of a plurality of tracking windows, and determines the position of the tracking window of subsequent image frames by track algorithm.
Concrete, track algorithm is compression track algorithm, cross-correlation track algorithm, centre of form track algorithm, centroid tracking algorithm, gate tracking algorithm, border following algorithm, regional balance track algorithm etc.The cross-correlation track algorithm is based on the similarity measurement of image, in present image, seek a kind of track algorithm near benchmark image template zone, it is not high to the scene image prescription, do not need segmentation object and background, to insensitive with selected dissimilar other all scenery of tracking target image, can follow the tracks of less target and a certain special part or the poor target of contrast of target area, have stronger local capacity of resisting disturbance.Cross correlation algorithm with benchmark image on present image with different deviant positions, judge the position of tracking window in present image according to the degree of association function of measuring between two width of cloth images, tracking window is two positions that images match is best, the i.e. peak value of correlation function.
Step S140, to tracking window similar to image modalities on every side in a plurality of tracking windows of every two field picture adopt get the diagonal intersection point centered by point process, adopt edge detection methods to process to all the other tracking windows in every two field picture.
Wherein, refer to that to image modalities is similar image in the window is very similar near the image it on every side, usually determine by priori that the part mode near skin in this routine ultrasonoscopy is similar.
As shown in Figure 3, because to image modalities is similar on every side, tracking window A employing is got the Central Point Method of putting centered by the diagonal intersection point and processed, tracking window B and C adopt edge detection method to process, and this edge detection method can be the edge detection method of canny operator.Adopt the rim detection of canny operator that video in window is for conversion into binary picture, parameter is adjusted to guarantee to obtain more to organize details, uses largest connected range searching technology to seek each window boundary that really cuts edge again.
Step S150, maximum normal distance between the position of the tracking window after process through edge detection method with each position of calculating in every two field picture the tracking window after processing through central point, with described maximum normal distance as the muscle thickness value between the tracking window after the tracking window after processing through central point and the processing of process edge detection method.
Concrete, take such as tracking window A, B and C among Fig. 3 as example, calculate the maximum normal distance between the tracking window A and B in every two field picture of per moment, obtain thickness (the Rectus femorisThickness of rectus femoris, RFT), maximum normal distance between tracking window A and the C obtains the thickness (QMT) of quadriceps femoris.
Above-mentioned muscle thickness measuring method based on ultrasonoscopy, by a plurality of tracking windows of choosing are followed the tracks of, determine the position of a plurality of tracking windows in follow-up every two field picture by track algorithm, maximum normal distance between the position of the tracking window after the position of calculating the tracking window of processing through central point in every two field picture and the edge detection method processing, as the muscle thickness value, this measuring method is based on ultrasonoscopy, and it is comparatively accurate to adopt image algorithm to carry out the muscle thickness value that correcting process obtains, improve the accuracy of measuring and measured efficient, and can follow the tracks of the tracking window of follow-up every two field picture, and measure muscle thickness value in every two field picture, reached the purpose of real-time measurement.
Further, in one embodiment, as shown in Figure 4, track algorithm is the compression track algorithm.Step S130 is specially:
Step S131 samples to tracking window place two field picture, obtains belonging to the sample set in the tracking window position range.
Concrete, input the t two field picture, a series of images fragment of t two field picture is sampled, according to condition be:
D
r={z|||I(z)-I
t-1||<r}
Wherein, I
T-1At t-1 tracing positional constantly;
R is tolerance present image and the I that sets
T-1Between the parameter value of difference, r is less, and present image I (z) and I are described
T-1Differ less;
D
rThe pixel that refers to belong in the position of all tracking in the tracking window position range is the set of positive sample;
I (z) is illustrated in the position of the tracking window that t obtains constantly.
In addition, by gathering near the positive sample of the tracking window of selecting with away from the negative sample of tracking window grader is upgraded.
Can adopt high-resolution to carry out filtering to interested image, other parts are taked low resolution, to improve processing speed.
Step S132 adopts sparse matrix that each sample in the sample set is carried out dimension-reduction treatment, obtains the compressive features vector.
Concrete, the matrix of sparse matrix for introducing, such as accidental projection V=RX, wherein, R is a random matrix, R ∈ R
N * m, m wherein〉and n, the vector that uses this formula the vectorial X dimensionality reduction of m dimension can be tieed up to n, thus reaching the effect of dimensionality reduction, V is the compressive features vector.For each sample z ∈ R
m, its low-dimensional is expressed as v=(υ
1..., υ
n)
T∈ R
n, and need satisfy m>>n.
The selection of random matrix is according to as follows:
At first select stable projection matrix, in order to ensure the linear projection of signal can inhibit signal prototype structure, projection matrix must satisfy constraint isometry (Restricted isometry property, RIP) then condition is measured by primary signal and the linear projection of measuring product of two matrices acquisition primary signal.That choose is random Gaussian matrix R herein, works as r
Ij~ N (0,1), R ∈ R
N * m,
Wherein, r
IjRepresent the element among this random matrix R, p represents probit, and s=2 or s=3 satisfy the Johnson-Lindenstrauss theorem this moment.
Step S133 adopts grader to classify to the compressive features vector.
Concrete, the compressive features vector is adopted the Naive Bayes Classifier classification, and the conditional probability in the grader satisfies Gauss normal distribution.
All elements all is assumed that separate in the vector.When p (y=1)=p (y=0), each compressive features vector is used Naive Bayes Classifier classification.Computing formula is as follows:
{ 0,1} is a binary system stochastic variable to y ∈, is used for representing sample label.Conditional probability p (v among the grader H (v)
i| y=1) and p (v
I|| y=0) be assumed that satisfying parameter is
Gauss normal distribution, and
Step S134, sampling from sample set obtains two groups of image patterns.
Concrete, sampling is satisfied and is satisfied α<ζ<β, and the sampling condition is respectively:
D
α={ z|||I (z)-I
t||<α }, D
ζ, β=z| ζ<| I (z)-I
t||<β }, D wherein
αAnd D
ζ, βBe two groups of image patterns;
α, ζ, β are tolerance present image I (z) and the I that sets
tBetween the parameter value of difference.
Step S135 extracts Lis Hartel to described two groups of image patterns and levies, and adopts described grader iteration to obtain the position of the tracking window of adjacent subsequent image frames.
Concrete, iterative formula is:
Adopt the parameter in the formula (2) that the grader iteration is upgraded, obtain position and the classifier parameters of the tracking window of t+1 two field picture.
As shown in Figure 5, in one embodiment, a kind of muscle thickness measuring system based on ultrasonoscopy comprises extraction module 110, acquisition module 120, tracking module 130, processing module 140 and computing module 150.Wherein:
Concrete, at first manually in image of interest, select the position of a plurality of initial tracking windows.
In the present embodiment, a plurality of is three, can manually select three initial tracking windows, follows the tracks of respectively femur, rectus femoris top and rectus femoris lower limits, and as shown in Figure 3, window A, B and C represent respectively above-mentioned three initial tracking windows.
Concrete, track algorithm is compression track algorithm, cross-correlation track algorithm, centre of form track algorithm, centroid tracking algorithm, gate tracking algorithm, border following algorithm, regional balance track algorithm etc.The cross-correlation track algorithm is based on the similarity measurement of image, in present image, seek a kind of track algorithm near benchmark image template zone, it is not high to the scene image prescription, do not need segmentation object and background, to insensitive with selected dissimilar other all scenery of tracking target image, can follow the tracks of less target and a certain special part or the poor target of contrast of target area, have stronger local capacity of resisting disturbance.Cross correlation algorithm with benchmark image on present image with different deviant positions, judge the position of tracking window in present image according to the degree of association function of measuring between two width of cloth images, tracking window is two positions that images match is best, the i.e. peak value of correlation function.
As shown in Figure 3, the tracking window A similar to image modalities on every side adopts and gets the Central Point Method of putting centered by the diagonal intersection point and process, and tracking window B and C adopt edge detection method to process, and this edge detection method can be the edge detection method of canny operator.Adopt the rim detection of canny operator that video in window is for conversion into binary picture, parameter is adjusted to guarantee to obtain more to organize details, uses largest connected range searching technology to seek each window boundary that really cuts edge again.
Concrete, take such as tracking window A, B and C among Fig. 3 as example, calculate the maximum normal distance between the tracking window A and B in every two field picture of per moment, obtain thickness (the Rectus femorisThickness of rectus femoris, RFT), maximum normal distance between tracking window A and the C obtains the thickness (QMT) of quadriceps femoris.
Above-mentioned muscle thickness measuring system based on ultrasonoscopy, by a plurality of tracking windows of choosing are followed the tracks of, determine the position of a plurality of tracking windows in follow-up every two field picture by track algorithm, maximum normal distance between the position of the tracking window after the position of calculating the tracking window of processing through central point in every two field picture and the edge detection method processing, as the muscle thickness value, this measuring method is based on ultrasonoscopy, and it is comparatively accurate to adopt image algorithm to carry out the muscle thickness value that correcting process obtains, improve the accuracy of measuring and measured efficient, and can follow the tracks of the tracking window of follow-up every two field picture, and measure muscle thickness value in every two field picture, reached the purpose of real-time measurement.
In one embodiment, when track algorithm was the compression track algorithm, as shown in Figure 6, tracking module 130 comprised sampling module 131, dimensionality reduction module 132, sort module 133, decimation blocks 134 and iteration module 135.Wherein:
Concrete, input the t two field picture, a series of images fragment of t two field picture is sampled, according to condition be:
D
γ={z|||I(z)-I
t-1||<γ}
Wherein, I
T-1At t-1 tracing positional constantly;
R is tolerance present image and the I that sets
T-1Between the parameter value of difference, r is less, and present image I (z) and I are described
T-1Differ less
D
rThe pixel that refers to belong in the position of all tracking in the tracking window position range is the set of positive sample;
I (z) is illustrated in the position of the tracking window that t obtains constantly.
In addition, by gathering near the positive sample of the tracking window of selecting with away from the negative sample of tracking window grader is upgraded.
Can adopt high-resolution to carry out filtering to interested image, other parts are taked low resolution, to improve processing speed.
Concrete, the matrix of sparse matrix for introducing, such as accidental projection V=RX, wherein, R is a random matrix, R ∈ R
N * m, m wherein〉and n, the vector that uses this formula the vectorial X dimensionality reduction of m dimension can be tieed up to n, thus reaching the effect of dimensionality reduction, V is the compressive features vector.For each sample z ∈ R
m, its low-dimensional is expressed as v=(υ
1..., υ
n)
T∈ R
n, and need satisfy m>>n.
The selection of random matrix is according to as follows:
At first select stable projection matrix, in order to ensure the linear projection of signal can inhibit signal prototype structure, projection matrix must satisfy constraint isometry (Restricted isometry property, RIP) then condition is measured by primary signal and the linear projection of measuring product of two matrices acquisition primary signal.That choose is random Gaussian matrix R herein, works as r
Ij~ N (0,1), R ∈ R
N * m,
Wherein, r
IjRepresent the element among this random matrix R, p represents probit, and s=2 or s=3 satisfy the Johnson-Lindenstrauss theorem this moment.
Concrete, the compressive features vector is adopted the Naive Bayes Classifier classification, and the conditional probability in the grader satisfies Gauss normal distribution.
All elements all is assumed that separate in the vector.When p (y=1)=p (y=0), each compressive features vector is used Naive Bayes Classifier classification.Computing formula is as follows:
{ 0,1} is a binary system stochastic variable to y ∈, is used for representing sample label.Conditional probability p (v among the grader H (v)
i| y=1) and p (v
I|| y=0) be assumed that satisfying parameter is
Gauss normal distribution, and
Decimation blocks 134 obtains two groups of image patterns for sampling from described sample set.
Concrete, sampling is satisfied and is satisfied α<ζ<β, and the sampling condition is respectively:
D
α={ z|||I (z)-I
t||<α }, D
ζ, β=z| ζ<| I (z)-I
t||<β }, D wherein
αAnd D
ζ, βBe two groups of image patterns; α, ζ, β are tolerance present image I (z) and the I that sets
tBetween the parameter value of difference.
Concrete, iterative formula is:
Adopt the parameter in the formula (2) that the grader iteration is upgraded, obtain position and the classifier parameters of the tracking window of t+1 two field picture.
As shown in Figure 7, in one embodiment, above-mentioned muscle thickness measuring system based on ultrasonoscopy except comprising extraction module 110, acquisition module 120, tracking module 130, processing module 140 and computing module 150, also comprises pretreatment module 160.Wherein:
The above embodiment has only expressed several embodiment of the present invention, and it describes comparatively concrete and detailed, but can not therefore be interpreted as the restriction to claim of the present invention.Should be pointed out that for the person of ordinary skill of the art without departing from the inventive concept of the premise, can also make some distortion and improvement, these all belong to protection scope of the present invention.Therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (10)
1. muscle thickness measuring method based on ultrasonoscopy may further comprise the steps:
From ultrasonoscopy, extract image of interest;
Obtain the position of a plurality of initial tracking windows of in described image of interest, selecting;
A plurality of tracking windows are followed the tracks of, and determined the position of the corresponding a plurality of tracking windows of follow-up every two field picture by track algorithm;
To tracking window similar to image modalities on every side in a plurality of tracking windows of every two field picture adopt get the diagonal intersection point centered by point process, adopt edge detection methods to process to all the other tracking windows in every two field picture;
Maximum normal distance between the position of the tracking window after process through edge detection method with each position of calculating in every two field picture the tracking window after processing through central point, with described maximum normal distance as the muscle thickness value between the tracking window after the tracking window after processing through central point and the processing of process edge detection method.
2. the muscle thickness measuring method based on ultrasonoscopy according to claim 1 is characterized in that, described track algorithm is compression track algorithm or cross-correlation track algorithm.
3. the muscle thickness measuring method based on ultrasonoscopy according to claim 1 is characterized in that, described track algorithm is the compression track algorithm;
Described a plurality of tracking windows are followed the tracks of, and are determined that by track algorithm the step of the position of the corresponding a plurality of tracking windows of follow-up every two field picture is:
Tracking window place two field picture is sampled, obtain belonging to the sample set in the described tracking window position range;
Adopt sparse matrix that each sample in the sample set is carried out dimension-reduction treatment, obtain the compressive features vector;
Adopt grader to classify to described compressive features vector;
From described sample set, sample and obtain two groups of image patterns;
Described two groups of image patterns are extracted Lis Hartel levy, and adopt described grader iteration to obtain the position of the corresponding tracking window of follow-up consecutive frame image.
4. the muscle thickness measuring method based on ultrasonoscopy according to claim 3 is characterized in that, the described step that adopts grader to classify to described compressive features vector comprises:
Described compressive features vector is adopted the Naive Bayes Classifier classification, and the conditional probability in the grader satisfies Gauss normal distribution.
5. the muscle thickness measuring method based on ultrasonoscopy according to claim 1 is characterized in that, after the described step of extracting image of interest from the ultrasonoscopy that catches, also comprises step:
Described image of interest is carried out pretreatment, comprising:
Described image of interest is carried out greyscale transformation and adjusted picture contrast.
6. the muscle thickness measuring system based on ultrasonoscopy is characterized in that, comprising:
Extraction module is used for extracting image of interest from the ultrasonoscopy that catches;
Acquisition module is used for the position that obtains a plurality of initial tracking window of selecting in described image of interest;
Tracking module is used for a plurality of tracking windows are followed the tracks of, and determines the position of the corresponding a plurality of tracking windows of follow-up every two field picture by track algorithm;
Processing module, be used for to a plurality of tracking windows of every two field picture tracking window similar with image modalities on every side adopt get the diagonal intersection point centered by point process, all the other tracking windows employing edge detection methods in every two field picture are processed;
Computing module, maximum normal distance between the position of the tracking window after process through edge detection method with each position that is used for calculating the tracking window after every two field picture is processed through central point, with described maximum normal distance as the muscle thickness value between the tracking window after the tracking window after processing through central point and the processing of process edge detection method.
7. the muscle thickness measuring system based on ultrasonoscopy according to claim 6 is characterized in that, described track algorithm is compression track algorithm or cross-correlation track algorithm.
8. the muscle thickness measuring system based on ultrasonoscopy according to claim 6 is characterized in that, described track algorithm is the compression track algorithm;
Described tracking module comprises:
Sampling module is used for tracking window place two field picture is sampled, and obtains belonging to the sample set in the tracking window position range;
The dimensionality reduction module is used for adopting sparse matrix that each sample of sample set is carried out dimension-reduction treatment, obtains the compressive features vector;
Sort module is used for adopting grader to classify to described compressive features vector;
Decimation blocks obtains two groups of image patterns for sampling from described sample set;
Iteration module is used for that described two groups of image patterns are extracted Lis Hartel and levies, and adopts the grader iteration to obtain the position of the tracking window of adjacent subsequent image frames.
9. the muscle thickness measuring system based on ultrasonoscopy according to claim 8, it is characterized in that, described sort module also is used for described compressive features vector is adopted the Naive Bayes Classifier classification, and the conditional probability in the grader satisfies Gauss normal distribution.
10. the muscle thickness measuring system based on ultrasonoscopy according to claim 6 is characterized in that described system also comprises:
Pretreatment module is used for described image of interest is carried out pretreatment, and described pretreatment comprises to be carried out greyscale transformation and adjust picture contrast described image of interest.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012105630569A CN103027713A (en) | 2012-12-22 | 2012-12-22 | Muscle thickness measuring method and system based on ultrasonic image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012105630569A CN103027713A (en) | 2012-12-22 | 2012-12-22 | Muscle thickness measuring method and system based on ultrasonic image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103027713A true CN103027713A (en) | 2013-04-10 |
Family
ID=48015481
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2012105630569A Pending CN103027713A (en) | 2012-12-22 | 2012-12-22 | Muscle thickness measuring method and system based on ultrasonic image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103027713A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103679754A (en) * | 2013-12-20 | 2014-03-26 | 河北汉光重工有限责任公司 | Real-time target searching and tracking technique |
CN106683115A (en) * | 2016-12-21 | 2017-05-17 | 中国矿业大学 | Video tracking method based on spiral vision-motion model |
CN107684438A (en) * | 2016-08-03 | 2018-02-13 | 深圳先进技术研究院 | A kind of pain degree detection method and device based on ultrasonoscopy |
CN108510475A (en) * | 2018-03-09 | 2018-09-07 | 南京索聚医疗科技有限公司 | The measurement method and system of muscle tendon knot in a kind of muscle continuous ultrasound image |
CN110694149A (en) * | 2019-10-16 | 2020-01-17 | 山东大学齐鲁医院 | Ultrasonic-assisted muscle identification method and system and auxiliary injection device |
CN110693526A (en) * | 2019-11-11 | 2020-01-17 | 深圳先进技术研究院 | Muscle disease assessment method and system and electronic equipment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5247938A (en) * | 1990-01-11 | 1993-09-28 | University Of Washington | Method and apparatus for determining the motility of a region in the human body |
CN1681439A (en) * | 2002-09-12 | 2005-10-12 | 株式会社日立医药 | Biological tissue motion trace method and image diagnosis device using the trace method |
CN101145688A (en) * | 2006-05-23 | 2008-03-19 | 沙诺夫公司 | Electrostatic discharge protection structures with reduced latch-up risks |
CN101464948A (en) * | 2009-01-14 | 2009-06-24 | 北京航空航天大学 | Object identification method for affine constant moment based on key point |
-
2012
- 2012-12-22 CN CN2012105630569A patent/CN103027713A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5247938A (en) * | 1990-01-11 | 1993-09-28 | University Of Washington | Method and apparatus for determining the motility of a region in the human body |
CN1681439A (en) * | 2002-09-12 | 2005-10-12 | 株式会社日立医药 | Biological tissue motion trace method and image diagnosis device using the trace method |
CN101145688A (en) * | 2006-05-23 | 2008-03-19 | 沙诺夫公司 | Electrostatic discharge protection structures with reduced latch-up risks |
CN101464948A (en) * | 2009-01-14 | 2009-06-24 | 北京航空航天大学 | Object identification method for affine constant moment based on key point |
Non-Patent Citations (2)
Title |
---|
JIZHOU LI ETC.: "Real-Time Detection of Muscle Thickness Changes during Isometric Contraction from Ultrasonography:A Feasibility Study", 《COMPUTERIZED HEALTHCARE(ICCH),2012 INTERNATIONAL CONFERENCE ON》, 18 December 2012 (2012-12-18) * |
李敏等: "下颌角弧形截骨术后咬肌厚度的变化", 《中华医学美学美容杂志》, vol. 13, no. 2, 30 April 2007 (2007-04-30) * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103679754A (en) * | 2013-12-20 | 2014-03-26 | 河北汉光重工有限责任公司 | Real-time target searching and tracking technique |
CN107684438A (en) * | 2016-08-03 | 2018-02-13 | 深圳先进技术研究院 | A kind of pain degree detection method and device based on ultrasonoscopy |
CN107684438B (en) * | 2016-08-03 | 2024-04-19 | 深圳先进技术研究院 | Pain degree detection method and device based on ultrasonic image |
CN106683115A (en) * | 2016-12-21 | 2017-05-17 | 中国矿业大学 | Video tracking method based on spiral vision-motion model |
CN108510475A (en) * | 2018-03-09 | 2018-09-07 | 南京索聚医疗科技有限公司 | The measurement method and system of muscle tendon knot in a kind of muscle continuous ultrasound image |
CN110694149A (en) * | 2019-10-16 | 2020-01-17 | 山东大学齐鲁医院 | Ultrasonic-assisted muscle identification method and system and auxiliary injection device |
CN110694149B (en) * | 2019-10-16 | 2021-06-22 | 山东大学齐鲁医院 | Ultrasonic-assisted muscle identification method and system and auxiliary injection device |
CN110693526A (en) * | 2019-11-11 | 2020-01-17 | 深圳先进技术研究院 | Muscle disease assessment method and system and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103027713A (en) | Muscle thickness measuring method and system based on ultrasonic image | |
CN102722712B (en) | Multiple-scale high-resolution image object detection method based on continuity | |
CN102389361B (en) | Blindman outdoor support system based on computer vision | |
CN101558996B (en) | Gait recognition method based on orthogonal projection three-dimensional reconstruction of human motion structure | |
CN103218603B (en) | A kind of face automatic marking method and system | |
CN104463877B (en) | A kind of water front method for registering based on radar image Yu electronic chart information | |
CN111505632B (en) | Ultra-wideband radar action attitude identification method based on power spectrum and Doppler characteristics | |
CN104794463A (en) | System and method for achieving indoor human body falling detection based on Kinect | |
CN104123543A (en) | Eyeball movement identification method based on face identification | |
CN104537356B (en) | Pedestrian identification method and the device again that sequence carries out Gait Recognition are taken turns using Switzerland | |
CN103942540A (en) | False fingerprint detection algorithm based on curvelet texture analysis and SVM-KNN classification | |
CN104239852B (en) | A kind of infrared pedestrian detection method based on motion platform | |
CN108288015A (en) | Human motion recognition method and system in video based on THE INVARIANCE OF THE SCALE OF TIME | |
CN101551854B (en) | A processing system of unbalanced medical image and processing method thereof | |
CN102332084A (en) | Identity identification method based on palm print and human face feature extraction | |
CN103106414A (en) | Detecting method of passer-bys in intelligent video surveillance | |
CN104778482A (en) | Hyperspectral image classifying method based on tensor semi-supervised scale cutting dimension reduction | |
CN103902989A (en) | Human body motion video recognition method based on non-negative matrix factorization | |
CN106326828A (en) | Eye positioning method applied to face recognition | |
Vandaele et al. | Automatic cephalometric x-ray landmark detection challenge 2014: A tree-based algorithm | |
CN102136060A (en) | Method for detecting population density | |
Franco et al. | Wideband spectral monitoring using deep learning | |
CN111695520A (en) | High-precision child sitting posture detection and correction method and device | |
CN104063682A (en) | Pedestrian detection method based on edge grading and CENTRIST characteristic | |
CN106548195A (en) | A kind of object detection method based on modified model HOG ULBP feature operators |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C12 | Rejection of a patent application after its publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130410 |