CN113592796A - Method, device, equipment and medium for detecting drooping of mouth corner - Google Patents
Method, device, equipment and medium for detecting drooping of mouth corner Download PDFInfo
- Publication number
- CN113592796A CN113592796A CN202110815463.3A CN202110815463A CN113592796A CN 113592796 A CN113592796 A CN 113592796A CN 202110815463 A CN202110815463 A CN 202110815463A CN 113592796 A CN113592796 A CN 113592796A
- Authority
- CN
- China
- Prior art keywords
- image
- region
- closed
- mouth
- preset
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000011218 segmentation Effects 0.000 claims abstract description 74
- 238000007665 sagging Methods 0.000 claims abstract description 60
- 238000001514 detection method Methods 0.000 claims description 33
- 238000001914 filtration Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 10
- 235000002566 Capsicum Nutrition 0.000 claims description 6
- 239000006002 Pepper Substances 0.000 claims description 6
- 235000016761 Piper aduncum Nutrition 0.000 claims description 6
- 235000017804 Piper guineense Nutrition 0.000 claims description 6
- 235000008184 Piper nigrum Nutrition 0.000 claims description 6
- 150000003839 salts Chemical class 0.000 claims description 6
- 244000203593 Piper nigrum Species 0.000 claims 1
- 230000032683 aging Effects 0.000 description 11
- 238000004364 calculation method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 241000722363 Piper Species 0.000 description 5
- 238000012216 screening Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 230000037303 wrinkles Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002829 reductive effect Effects 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 210000000697 sensory organ Anatomy 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method for detecting drooping of a mouth corner, which comprises the following steps: the intercepted mouth corner region image is roughly subjected to local threshold segmentation to obtain a threshold segmentation image, the threshold segmentation image comprises a plurality of closed regions, the region with obvious gray level change in the image can be obtained after local threshold segmentation, and interference of non-line parts such as a background, a cheek and the like can be removed. And then removing the interference region based on the preset area condition and the preset included angle condition to obtain a target closed region only comprising the mouth corner sagging lines, so that the interference of cheek contours, neck contours and the like can be removed. And finally, determining the degree of mouth corner sagging according to the length of the long side and the length of the short side of the minimum circumscribed rectangle. Therefore, the scheme can avoid the influence of irrelevant interference such as background, non-line parts, cheek contours, neck contours and the like, and can accurately determine the degree of corner sagging. Further, a mouth-corner-drop detecting device, an apparatus and a medium are proposed.
Description
Technical Field
The invention relates to the technical field of human face detection, in particular to a method, a device, equipment and a medium for detecting mouth corner sagging.
Background
In contemporary society, people pay more and more attention to their personal appearance state, and everyone wants to keep their state as young as possible. The aging of the human body is usually shown on the face, such as wrinkles, cheek sagging, statute lines, eye bags, mouth corner sagging and the like, which can characterize the aging phenomenon, and the aging phenomenon usually occurs along with the aging phenomenon, and the aging condition of the human face can be laterally reflected by knowing one or more of the wrinkles, the cheek sagging, the statue lines, the eye bags, the mouth corner sagging and the like.
Taking the mouth corner as an example, the degree of mouth corner sagging varies among people in different aging states. The more severe the mouth corner sagging, the more severe the degree of reflection of aging. Therefore, how to accurately obtain the degree of mouth corner sagging is important in judging the aging degree.
Disclosure of Invention
In view of the above, it is necessary to provide a detection method, apparatus, device, and medium for accurately determining the degree of lip-drop of a mouth.
A method of detecting mouth-corner drop, the method comprising:
acquiring a face image to be detected, and intercepting a mouth corner area image in the face image;
performing local threshold segmentation on the mouth corner region image to obtain a threshold segmentation image, wherein the threshold segmentation image comprises a plurality of closed regions, and the pixel difference between pixels in the closed regions and pixels outside the closed regions is greater than a preset degree;
removing interference areas which do not meet the preset area condition and/or the preset included angle condition in the plurality of closed areas to obtain a drooping grain image;
determining the degree of mouth corner sagging according to the length of the long side and the length of the short side of the minimum circumscribed rectangle of the target closed region, wherein the target closed region is a closed region in the sagging grain image.
In one embodiment, the performing local threshold segmentation on the mouth corner region image to obtain a threshold segmentation image includes:
in the mouth corner area image, calculating the gray mean value and the standard variance of the gray value of each pixel point in a preset neighborhood, and calculating the gray threshold value at each pixel point according to the gray mean value and the standard variance;
setting the pixel value of the pixel point with the gray value larger than the gray threshold value as a first pixel value, and setting the pixel value of the pixel point with the gray value smaller than the gray threshold value as a second pixel value to obtain the threshold segmentation image.
In one embodiment, the removing the interference region that does not satisfy the preset area condition and/or the preset included angle condition among the plurality of closed regions includes:
calculating a first included angle between the long edge of the minimum external rectangle of each closed region and the positive direction of a horizontal line X axis, wherein the horizontal line X axis is the axial direction for measuring the width of the face in the face image;
and (3) taking the closed regions with the areas smaller than a first preset area in the plurality of closed regions and/or taking the closed regions with the first included angles smaller than a first preset angle as the interference regions, and removing the interference regions in the plurality of closed regions.
In one embodiment, the removing the interference region that does not satisfy the preset area condition and/or the preset included angle condition among the plurality of closed regions includes:
calculating the rectangular area of the minimum circumscribed rectangle of each closed region;
calculating a second included angle between the major axis of the minimum circumscribed ellipse of each closed region and the positive direction of the X axis of the horizontal line, wherein the X axis of the horizontal line is the axial direction for measuring the width of the face in the face image;
and taking the closed region of which the rectangular area is smaller than a second preset area and/or the closed region of which the second included angle is smaller than a second preset angle from the plurality of closed regions as the interference region, and removing the interference region from the plurality of closed regions.
In one embodiment, the determining the degree of mouth corner sagging according to the length of the long side and the length of the short side of the minimum bounding rectangle of the target closed region includes:
calculating the sum of the lengths of the long sides of the minimum circumscribed rectangles of all the target closed regions, and calculating the average value of the lengths of the short sides of the minimum circumscribed rectangles of all the target closed regions;
and acquiring a preset formula, and substituting the sum of the lengths of the long sides and the average value of the lengths of the short sides into the preset formula to obtain a result value, wherein the result value represents the degree of the mouth corner sagging.
In one embodiment, before the local threshold segmentation is performed on the mouth corner region image, the method further includes:
and carrying out noise detection on the mouth angle region image, and carrying out mean value filtering on the mouth angle region image when Gaussian noise exists in the mouth angle region image, so as to obtain a filtered mouth angle region image.
In one embodiment, before the local threshold segmentation is performed on the mouth corner region image, the method further includes:
and carrying out noise detection on the mouth corner area image, and carrying out median filtering on the mouth corner area image when salt and pepper noise exists in the mouth corner area image to obtain a filtered mouth corner area image.
A mouth corner drop detection apparatus, the apparatus comprising:
the mouth corner area image acquisition module is used for acquiring a face image to be detected and intercepting a mouth corner area image in the face image;
the threshold segmentation image acquisition module is used for carrying out local threshold segmentation on the mouth corner region image to obtain a threshold segmentation image, the threshold segmentation image comprises a plurality of closed regions, and the pixel difference between pixels in the closed regions and pixels outside the closed regions is greater than a preset degree;
the drooping texture image acquisition module is used for removing interference areas which do not meet the preset area condition and/or the preset included angle condition in the plurality of closed areas to obtain drooping texture images;
and the mouth corner sagging degree determining module is used for determining the mouth corner sagging degree according to the length of the long side and the length of the short side of the minimum circumscribed rectangle of the target closed region, wherein the target closed region is a closed region in the sagging line image.
A computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of:
acquiring a face image to be detected, and intercepting a mouth corner area image in the face image;
performing local threshold segmentation on the mouth corner region image to obtain a threshold segmentation image, wherein the threshold segmentation image comprises a plurality of closed regions, and the pixel difference between pixels in the closed regions and pixels outside the closed regions is greater than a preset degree;
removing interference areas which do not meet the preset area condition and/or the preset included angle condition in the plurality of closed areas to obtain a drooping grain image;
determining the degree of mouth corner sagging according to the length of the long side and the length of the short side of the minimum circumscribed rectangle of the target closed region, wherein the target closed region is a closed region in the sagging grain image.
A mouth-corner-drop detection apparatus comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of:
acquiring a face image to be detected, and intercepting a mouth corner area image in the face image;
performing local threshold segmentation on the mouth corner region image to obtain a threshold segmentation image, wherein the threshold segmentation image comprises a plurality of closed regions, and the pixel difference between pixels in the closed regions and pixels outside the closed regions is greater than a preset degree;
removing interference areas which do not meet the preset area condition and/or the preset included angle condition in the plurality of closed areas to obtain a drooping grain image;
determining the degree of mouth corner sagging according to the length of the long side and the length of the short side of the minimum circumscribed rectangle of the target closed region, wherein the target closed region is a closed region in the sagging grain image.
The invention provides a mouth corner sagging detection method, a device, equipment and a medium, wherein a captured mouth corner region image is subjected to rough local threshold segmentation to obtain a threshold segmentation image, the threshold segmentation image comprises a plurality of closed regions, a region with obvious gray change in the image can be obtained after the local threshold segmentation, and the interference of non-line parts such as a background, a cheek and the like can be removed. And then removing the interference region based on the preset area condition and the preset included angle condition to obtain a target closed region only comprising the mouth corner sagging lines, so that the interference of cheek contours, neck contours and the like can be removed. And finally, determining the degree of mouth corner sagging according to the length of the long side and the length of the short side of the minimum circumscribed rectangle. Therefore, the scheme can avoid the influence of irrelevant interference such as background, non-line parts, cheek contours, neck contours and the like, and can accurately determine the degree of corner sagging.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Wherein:
FIG. 1 is a schematic flow chart of a method for detecting mouth corner drop according to one embodiment;
FIG. 2 is a diagram illustrating key points in a face image according to an embodiment;
FIG. 3 is a schematic representation of an image of a corner region of a mouth in one embodiment;
FIG. 4 is a diagram of thresholding an image in one embodiment;
FIG. 5 is a schematic illustration of calculating a first included angle in one embodiment;
FIG. 6 is a diagram illustrating calculation of a second included angle according to one embodiment;
FIG. 7 is a schematic view of a sag grain image in accordance with an embodiment;
FIG. 8 is a schematic view showing the structure of a device for detecting the drop in the mouth angle in one embodiment;
fig. 9 is a block diagram showing a configuration of a mouth-corner-drop detecting apparatus according to an embodiment.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, fig. 1 is a schematic flow chart of a method for detecting mouth-corner drop in one embodiment, and the method for detecting mouth-corner drop in this embodiment provides steps including:
102, acquiring a face image to be detected, and intercepting a mouth corner area image in the face image.
The image of the mouth corner region, that is, the image of the face image, which covers only the mouth corner region, is obtained by cutting out the mouth corner region alone in order to avoid interference because the correlation between the features of the face background and other regions, such as the eye region and the nose region, and the drooping mouth corner is not great.
Specifically, referring to fig. 2, a 127-point Landmark model of a human face in a Dlib library is used to extract 68 key points in the human face image, and these key points are used to describe the positions of five sense organs of a human body. And then determining part of the key points as target key points and acquiring coordinate values of the target key points. Illustratively, the coordinate x value and the coordinate y value of the number 90, the coordinate y value of the number 18, and the coordinate x value of the number 23 are acquired. Then, the image of the mouth corner region as shown in fig. 3 can be obtained by intercepting the face image based on the coordinate values. Of course, the right half mouth corner area image is cut, and the preset number may be extended to cut the left half mouth corner area image, for example, the coordinate x value and the coordinate y value of the number 84, the coordinate y value of the number 14, and the coordinate x value of the number 9 are obtained to be cut.
And 104, performing local threshold segmentation on the mouth corner region image to obtain a threshold segmentation image.
The local threshold segmentation is a scheme in which a threshold is set individually for each pixel or local region, and the pixel or local region is segmented based on the individually set threshold. The threshold segmentation image comprises a plurality of closed regions with obvious gray scale change in the mouth corner region image, the pixel difference between pixels in the closed regions and pixels outside the closed regions is larger than a preset degree, and the interference of non-line parts such as a background, a cheek and the like can be removed after local threshold segmentation.
Furthermore, in order to avoid the noise and skin noise generated in the process of acquiring and transmitting the picture from interfering the detection of the mouth-corner sagging, denoising processing is performed before the local threshold segmentation. In a specific embodiment, noise detection is performed on a mouth corner region image based on an opencv library or matlab of python, a corresponding denoising mode is selected for denoising according to the characteristics of noise, different denoising modes are selected for denoising according to the different characteristics of the noise, and more accurate denoising processing can be realized, so that more accurate detection of mouth corner sagging is facilitated. For example, when a probability density function of noise in the image of the mouth corner region is detected to obey gaussian distribution, the noise is determined to be gaussian noise, mean filtering is performed at this time, that is, a current pixel (x, y) to be processed is subjected to current processing, a neighboring region is selected, the neighboring region consists of a plurality of pixels (generally 3 × 3) adjacent to the neighboring region, the mean value of all pixels in the neighboring region is obtained, and then the mean value is given to the current pixel (x, y) to serve as a gray value of the processed image at the point. And carrying out the treatment on all the pixel points to obtain the mouth angle area image after mean value filtering. The influence on the image quality caused by the reasons that the image sensor is not bright enough and the brightness is not uniform enough when shooting, and all components of the circuit are mutually influenced can be reduced after the mean value filtering.
For another example, when a randomly appearing white point or black point is detected in the mouth corner region image, the noise is determined to be salt and pepper noise, then median filtering is performed, namely, a current pixel point (x, y) to be processed is selected to be a neighboring region, the neighboring region consists of a plurality of N pixels (generally 3 x 3) adjacent to the neighboring region, the pixels in the neighboring region are sorted according to the size of the pixel value, a monotonously rising (or falling) two-dimensional data sequence is generated, and the median value is taken as the gray value of the processed image on the point, wherein the two-dimensional data sequence is obtained by giving the current pixel point (x, y) the monotonically rising (or falling) two-dimensional data sequence. And carrying out the treatment on all the pixel points to obtain a mouth angle area image after median filtering. After median filtering, the black and white bright and dark point noise generated by image sensor, transmission channel, decoding process and other links in the image can be eliminated.
In one possible implementation, the local threshold segmentation may be performed on the corner region image as follows: in the mouth corner area image, calculating the standard deviation of the gray level mean value and the gray level value of each pixel point in a preset neighborhood taking the pixel point as the center, and calculating the standard deviation according to the following formula:
wherein m (x, y) is a gray level mean value of the current pixel point in a preset neighborhood, (x, y) is a coordinate, the size of the preset neighborhood is r, g (i, j) represents a gray level value at (i, j) in the neighborhood, and s (x, y) is a standard deviation.
Then, the gray threshold at each pixel point is calculated according to the gray mean and the standard deviation, as follows:
wherein, R is a dynamic range of the standard deviation, and if the currently input image is an 8-bit grayscale image, R is 128; k is a self-defined correction parameter, and k is more than 0 and less than 1.
Finally, comparing the size of each pixel point with the respective gray threshold T (x, y), setting the pixel value of the pixel point with the gray value larger than the gray threshold T (x, y) as a first pixel value, and setting the pixel value of the pixel point with the gray value smaller than the gray threshold as a second pixel value, for example, the first pixel value is 0, and the second pixel value is 1; alternatively, the first pixel value is 1 and the second pixel value is 0. The result is a thresholded segmented image as shown in figure 4 (the numbers indicate the closed regions 1-8). The gray threshold obtained by the above local threshold segmentation is not fixed, but is determined by the gray mean of the surrounding neighborhood pixels and the standard deviation of the gray values. The gray level threshold value in the image area with higher brightness is usually higher after calculation, and the gray level threshold value in the image area with lower brightness is reduced correspondingly, so that the influence of the brightness on the threshold value division can be eliminated. In addition, the present scheme is provided with a coefficient k to perform detail correction of the partial region.
In another embodiment, the local threshold segmentation scheme may be: two preset values S-15 and TT-128 are set manually. Then, the maximum value M and the minimum value N of all pixels in a k multiplied by k window with the size of any pixel P as the center in the image are calculated, and the mean value of M and N is calculated as T. If M-N is larger than S, the gray level difference of the area where the window is located is larger, and the gray level threshold value of the current pixel P is set to be T; if M-N is smaller than S, the gray level difference of the area where the window is located is smaller, the window is in a closed area or a background area, the relation between T and TT is judged at the moment, if T is larger than TT, the gray value of the pixel P is the first pixel value, and otherwise, the gray value of the current point is the second pixel value.
And 106, removing interference areas which do not meet the preset area condition and/or the preset included angle condition in the plurality of closed areas to obtain the drooping grain images.
The preset area condition is used for removing the interference areas such as the moles and the wrinkles, and the preset included angle condition is used for the interference areas such as the cheek contour and the neck contour. In this way, a target closure zone can be obtained that includes only the drop-mouth texture within the drop texture image.
In a specific embodiment, traversing each closed region in the threshold segmentation image, firstly, determining the area S of the closed region by calculating the number of pixel points in the closed region1Then, the area is smaller than the first preset area S2The occlusion regions of (a) serve as interference regions, so that the occlusion regions of fig. 4, which are too small in area, for example, the occlusion regions numbered 3, 4, 6, 7, can be eliminated. In addition, a minimum bounding rectangle for each closed region is formed, and as shown in FIG. 5, a first angle α between the long side of the minimum bounding rectangle and the positive direction of the X-axis of the horizontal line is calculated1The horizontal line X axis is the axial direction for measuring the width of the face in the face image, and the first included angle alpha is formed1Is smaller than a first preset angle alpha2As the interference region, for example, will be α2Set to 90 °. This eliminates the regions of figure 4 which are not aligned with the true drop of the mouth angle, such as the closure regions numbered 5 and 8. Of course, if the left-half mouth corner region image is captured in step 102, the preset angle condition can be set to the first angle α accordingly1Greater than a first predetermined angle alpha2As an interference area. In the embodiment, the screening is directly performed based on the area of the closed region, so that the closed region with an excessively small area can be accurately screened. And the included angle between the closed area and the positive direction of the X axis is determined based on the minimum circumscribed rectangle, the included angle in the closed area can be integrally reflected, and the screening of the preset included angle condition can be rapidly completed.
In another embodiment, traversing each closed region in the graph, firstly making the minimum bounding rectangle of each closed region, and determining the rectangular area S of the minimum bounding rectangle by calculating the number of pixel points in the minimum bounding rectangle3A rectangular area S3Is smaller than the second preset area S4As an interference area. In addition, a minimum circumscribed ellipse of each closed region is made, and as shown in fig. 6, a second angle α in which the major axis of the minimum circumscribed ellipse is in the positive direction of the X-axis of the horizontal line is calculated3At the second angle alpha3Less than a second predetermined angle alpha4As an interference area. Similarly, if the left-half mouth corner region image is captured in step 102, the preset angle condition can be set to the second angle α accordingly3Greater than a second predetermined angle alpha4As an interference area. This embodiment proceeds based on the area of the smallest bounding rectangleAnd (4) performing line screening, wherein the minimum circumscribed rectangle is a regular graph, so that a closed region with an excessively small area can be quickly screened. And the included angle between the closed area and the positive direction of the X axis is determined based on the minimum circumscribed ellipse, the included angle in the closed area can be integrally reflected, and the screening of the preset included angle condition can be rapidly completed.
Finally, the interference areas 3, 4, 5, 6, 7, 8 are removed to obtain the sagging line image shown in fig. 7.
And step 108, determining the degree of mouth corner sagging according to the length of the long side and the length of the short side of the minimum circumscribed rectangle of the target closed area.
In one embodiment, the calculation of the degree of mouth corner drop is: firstly, the sum m of the lengths of the long sides of the minimum circumscribed rectangles of all the target closed regions is calculated1Then, the length average value m of the short sides of the minimum bounding rectangle of all the target closed regions is calculated2. Finally m is put1And m2Substituting the following formula for calculation:
L＝a*m1+b*m2
and a and b can be flexibly assigned according to specific conditions, and L represents the dropping degree of the mouth corner and is hooked with the aging degree of the human face. The calculation mode is simple in calculation process, and can be flexibly adjusted for different users based on the assignments a and b. The larger the L, the larger the degree of mouth corner sagging, and the more serious the degree of face aging is reflected.
Or, due to the sum of the lengths of the long sides m1Average length of sag of approximate nozzle angle lines2Approximately reflecting the width of the nozzle corner lines. Generally, m is1The longer, the more pronounced the aging. Thus m1The hook is more compact with the drooping degree of the mouth corner, and m can be also hung1And m2Substituting the following formula for calculation:
L＝m1+ln(m2)
m in the above formula1The effect on L is relatively greater, and m2The effect on L is relatively smaller.
Furthermore, the degree of mouth corner sagging can be detected by combining the mouth corner area of the right half and the mouth corner area of the left half, for exampleThe degree L of the drooping of the mouth angle of the left half is obtained first as in the above embodiment1And degree of drop L of the right half of the mouth angle2Is then based on L1And L2The degree L of the drooping mouth corner reflecting the whole human face can be calculated0：
Or the like, or, alternatively,
L0＝K1L1+K2L2
the K is1And K2The user can set the setting by himself. L obtained after calculation0Compared with L1Or L2And is more representative.
According to the mouth corner sagging detection method, the intercepted mouth corner region image is roughly subjected to local threshold segmentation to obtain a threshold segmentation image, the threshold segmentation image comprises a plurality of closed regions, the region with obvious gray level change in the image can be obtained after the local threshold segmentation, and the interference of non-line parts such as a background, a cheek and the like can be removed. And then removing the interference region based on the preset area condition and the preset included angle condition to obtain a target closed region only comprising the mouth corner sagging lines, so that the interference of cheek contours, neck contours and the like can be removed. And finally, determining the degree of mouth corner sagging according to the length of the long side and the length of the short side of the minimum circumscribed rectangle. Therefore, the scheme can avoid the influence of irrelevant interference such as background, non-line parts, cheek contours, neck contours and the like, and can accurately determine the degree of corner sagging.
In one embodiment, as shown in fig. 8, there is provided a mouth-corner-drop detecting device, including:
a mouth corner region image obtaining module 802, configured to obtain a face image to be detected, and intercept a mouth corner region image in the face image;
a threshold segmentation image obtaining module 804, configured to perform local threshold segmentation on the mouth corner region image to obtain a threshold segmentation image, where the threshold segmentation image includes a plurality of closed regions, and a pixel difference between a pixel in the closed region and a pixel outside the closed region is greater than a preset degree;
a drooping texture image obtaining module 806, configured to remove an interference region that does not satisfy a preset area condition and/or a preset included angle condition among the plurality of closed regions, to obtain a drooping texture image;
a mouth corner sagging degree determining module 808, configured to determine the mouth corner sagging degree according to the length of the long side and the length of the short side of the minimum circumscribed rectangle of the target closed region, where the target closed region is a closed region in the sagging line image.
According to the mouth corner droop detection device, the intercepted mouth corner region image is roughly subjected to local threshold segmentation to obtain a threshold segmentation image, the threshold segmentation image comprises a plurality of closed regions, the region with obvious gray change in the image can be obtained after the local threshold segmentation, and the interference of non-line parts such as a background, a cheek and the like can be removed. And then removing the interference region based on the preset area condition and the preset included angle condition to obtain a target closed region only comprising the mouth corner sagging lines, so that the interference of cheek contours, neck contours and the like can be removed. And finally, determining the degree of mouth corner sagging according to the length of the long side and the length of the short side of the minimum circumscribed rectangle. Therefore, the scheme can avoid the influence of irrelevant interference such as background, non-line parts, cheek contours, neck contours and the like, and can accurately determine the degree of corner sagging.
In an embodiment, the threshold segmentation image obtaining module 804 is specifically configured to: in the mouth corner area image, calculating the gray level mean value and the standard variance of the gray level of each pixel point in a preset neighborhood, and calculating the gray level threshold value at each pixel point according to the gray level mean value and the standard variance; setting the pixel value of the pixel point with the gray value larger than the gray threshold value as a first pixel value, and setting the pixel value of the pixel point with the gray value smaller than the gray threshold value as a second pixel value to obtain a threshold segmentation image.
In an embodiment, the drooping texture image obtaining module 806 is specifically configured to: calculating a first included angle between the long edge of the minimum external rectangle of each closed region and the positive direction of a horizontal line X axis, wherein the horizontal line X axis is the axial direction for measuring the width of the face in the face image; and (3) taking the closed areas with the areas smaller than a first preset area in the plurality of closed areas and/or taking the closed areas with the first included angles smaller than a first preset angle as interference areas, and removing the interference areas in the plurality of closed areas.
In an embodiment, the drooping texture image obtaining module 806 is specifically configured to: calculating the rectangular area of the minimum circumscribed rectangle of each closed region; calculating a second included angle between the major axis of the minimum circumscribed ellipse of each closed region and the positive direction of the X axis of the horizontal line, wherein the X axis of the horizontal line is the axial direction for measuring the width of the face in the face image; and taking the closed region with the rectangular area smaller than the second preset area and/or the closed region with the second included angle smaller than the second preset angle from the plurality of closed regions as an interference region, and removing the interference region from the plurality of closed regions.
In one embodiment, the mouth-corner-sagging-degree determining module 808 is specifically configured to: calculating the sum of the lengths of the long sides of the minimum circumscribed rectangles of all the target closed regions, and calculating the average value of the lengths of the short sides of the minimum circumscribed rectangles of all the target closed regions; and obtaining a preset formula, and substituting the sum of the lengths of the long sides and the average value of the lengths of the short sides into the preset formula to obtain a result value, wherein the result value represents the degree of mouth corner sagging.
In one embodiment, the mouth corner drop detecting device further comprises: and the filtering module is used for carrying out noise detection on the mouth angle region image, and carrying out mean filtering on the mouth angle region image when Gaussian noise exists in the mouth angle region image, so as to obtain the filtered mouth angle region image.
In an embodiment, the filtering module is further configured to perform noise detection on the corner region image, and perform median filtering on the corner region image when salt and pepper noise is detected in the corner region image, so as to obtain a filtered corner region image.
Fig. 9 is a diagram showing an internal structure of a mouth corner drop detecting apparatus in one embodiment. As shown in fig. 9, the nozzle droop detecting apparatus includes a processor, a memory, and a network interface connected by a system bus. Wherein the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the mouth-corner-sagging detection apparatus stores an operating system, and may further store a computer program, which, when executed by the processor, causes the processor to implement a mouth-corner-sagging detection method. The internal memory may also have stored thereon a computer program that, when executed by the processor, causes the processor to perform a method of detecting a drop in mouth angle. It will be appreciated by those skilled in the art that the arrangement shown in figure 9 is a block diagram of only a portion of the arrangement relevant to the present application and does not constitute a limitation of the mouth droop detection apparatus to which the present application is applied, and that a particular mouth droop detection apparatus may include more or fewer components than shown in the figures, or may combine certain components, or have a different arrangement of components.
A mouth corner drop detection apparatus comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the following steps when executing the computer program: acquiring a face image to be detected, and intercepting a mouth corner area image in the face image; performing local threshold segmentation on the mouth corner region image to obtain a threshold segmentation image, wherein the threshold segmentation image comprises a plurality of closed regions, and the pixel difference between pixels in the closed regions and pixels outside the closed regions is greater than a preset degree; removing interference areas which do not meet the preset area condition and/or the preset included angle condition in the plurality of closed areas to obtain a drooping grain image; determining the degree of mouth corner sagging according to the length of the long side and the length of the short side of the minimum circumscribed rectangle of the target closed region, wherein the target closed region is a closed region in the sagging grain image.
In one embodiment, the local threshold segmentation is performed on the mouth corner region image to obtain a threshold segmentation image, and the method includes: in the mouth corner area image, calculating the gray level mean value and the standard variance of the gray level of each pixel point in a preset neighborhood, and calculating the gray level threshold value at each pixel point according to the gray level mean value and the standard variance; setting the pixel value of the pixel point with the gray value larger than the gray threshold value as a first pixel value, and setting the pixel value of the pixel point with the gray value smaller than the gray threshold value as a second pixel value to obtain a threshold segmentation image.
In one embodiment, removing the interference region that does not satisfy the preset area condition and/or the preset included angle condition among the plurality of closed regions includes: calculating a first included angle between the long edge of the minimum external rectangle of each closed region and the positive direction of a horizontal line X axis, wherein the horizontal line X axis is the axial direction for measuring the width of the face in the face image; and (3) taking the closed areas with the areas smaller than a first preset area in the plurality of closed areas and/or taking the closed areas with the first included angles smaller than a first preset angle as interference areas, and removing the interference areas in the plurality of closed areas.
In one embodiment, removing the interference region that does not satisfy the preset area condition and/or the preset included angle condition among the plurality of closed regions includes: calculating the rectangular area of the minimum circumscribed rectangle of each closed region; calculating a second included angle between the major axis of the minimum circumscribed ellipse of each closed region and the positive direction of the X axis of the horizontal line, wherein the X axis of the horizontal line is the axial direction for measuring the width of the face in the face image; and taking the closed region with the rectangular area smaller than the second preset area and/or the closed region with the second included angle smaller than the second preset angle from the plurality of closed regions as an interference region, and removing the interference region from the plurality of closed regions.
In one embodiment, determining the degree of mouth corner drop from the length of the long side and the length of the short side of the minimum bounding rectangle of the target closed area comprises: calculating the sum of the lengths of the long sides of the minimum circumscribed rectangles of all the target closed regions, and calculating the average value of the lengths of the short sides of the minimum circumscribed rectangles of all the target closed regions; and obtaining a preset formula, and substituting the sum of the lengths of the long sides and the average value of the lengths of the short sides into the preset formula to obtain a result value, wherein the result value represents the degree of mouth corner sagging.
In one embodiment, before the local threshold segmentation is performed on the corner region image, the method further includes: and carrying out noise detection on the mouth angle region image, and carrying out mean value filtering on the mouth angle region image when Gaussian noise exists in the mouth angle region image, so as to obtain the filtered mouth angle region image.
In one embodiment, before the local threshold segmentation is performed on the corner region image, the method further includes: and carrying out noise detection on the image of the corner region, and carrying out median filtering on the image of the corner region when salt and pepper noise exists in the image of the corner region to obtain a filtered image of the corner region.
A computer-readable storage medium storing a computer program which, when executed by a processor, performs the steps of:
acquiring a face image to be detected, and intercepting a mouth corner area image in the face image; performing local threshold segmentation on the mouth corner region image to obtain a threshold segmentation image, wherein the threshold segmentation image comprises a plurality of closed regions, and the pixel difference between pixels in the closed regions and pixels outside the closed regions is greater than a preset degree; removing interference areas which do not meet the preset area condition and/or the preset included angle condition in the plurality of closed areas to obtain a drooping grain image; determining the degree of mouth corner sagging according to the length of the long side and the length of the short side of the minimum circumscribed rectangle of the target closed region, wherein the target closed region is a closed region in the sagging grain image.
In one embodiment, the local threshold segmentation is performed on the mouth corner region image to obtain a threshold segmentation image, and the method includes: in the mouth corner area image, calculating the gray level mean value and the standard variance of the gray level of each pixel point in a preset neighborhood, and calculating the gray level threshold value at each pixel point according to the gray level mean value and the standard variance; setting the pixel value of the pixel point with the gray value larger than the gray threshold value as a first pixel value, and setting the pixel value of the pixel point with the gray value smaller than the gray threshold value as a second pixel value to obtain a threshold segmentation image.
In one embodiment, removing the interference region that does not satisfy the preset area condition and/or the preset included angle condition among the plurality of closed regions includes: calculating a first included angle between the long edge of the minimum external rectangle of each closed region and the positive direction of a horizontal line X axis, wherein the horizontal line X axis is the axial direction for measuring the width of the face in the face image; and (3) taking the closed areas with the areas smaller than a first preset area in the plurality of closed areas and/or taking the closed areas with the first included angles smaller than a first preset angle as interference areas, and removing the interference areas in the plurality of closed areas.
In one embodiment, removing the interference region that does not satisfy the preset area condition and/or the preset included angle condition among the plurality of closed regions includes: calculating the rectangular area of the minimum circumscribed rectangle of each closed region; calculating a second included angle between the major axis of the minimum circumscribed ellipse of each closed region and the positive direction of the X axis of the horizontal line, wherein the X axis of the horizontal line is the axial direction for measuring the width of the face in the face image; and taking the closed region with the rectangular area smaller than the second preset area and/or the closed region with the second included angle smaller than the second preset angle from the plurality of closed regions as an interference region, and removing the interference region from the plurality of closed regions.
In one embodiment, determining the degree of mouth corner drop from the length of the long side and the length of the short side of the minimum bounding rectangle of the target closed area comprises: calculating the sum of the lengths of the long sides of the minimum circumscribed rectangles of all the target closed regions, and calculating the average value of the lengths of the short sides of the minimum circumscribed rectangles of all the target closed regions; and obtaining a preset formula, and substituting the sum of the lengths of the long sides and the average value of the lengths of the short sides into the preset formula to obtain a result value, wherein the result value represents the degree of mouth corner sagging.
In one embodiment, before the local threshold segmentation is performed on the corner region image, the method further includes: and carrying out noise detection on the mouth angle region image, and carrying out mean value filtering on the mouth angle region image when Gaussian noise exists in the mouth angle region image, so as to obtain the filtered mouth angle region image.
In one embodiment, before the local threshold segmentation is performed on the corner region image, the method further includes: and carrying out noise detection on the image of the corner region, and carrying out median filtering on the image of the corner region when salt and pepper noise exists in the image of the corner region to obtain a filtered image of the corner region.
It should be noted that the method, the apparatus, the device and the computer-readable storage medium for detecting the mouth-corner sagging described above belong to one general inventive concept, and the contents in the embodiments of the method, the apparatus, the device and the computer-readable storage medium for detecting the mouth-corner sagging can be mutually applied.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of detecting mouth-corner drop, the method comprising:
acquiring a face image to be detected, and intercepting a mouth corner area image in the face image;
performing local threshold segmentation on the mouth corner region image to obtain a threshold segmentation image, wherein the threshold segmentation image comprises a plurality of closed regions, and the pixel difference between pixels in the closed regions and pixels outside the closed regions is greater than a preset degree;
removing interference areas which do not meet the preset area condition and/or the preset included angle condition in the plurality of closed areas to obtain a drooping grain image;
determining the degree of mouth corner sagging according to the length of the long side and the length of the short side of the minimum circumscribed rectangle of a target closed region, wherein the target closed region is a closed region in the sagging line image.
2. The detection method according to claim 1, wherein the local thresholding of the mouth corner region image to obtain a thresholded image comprises:
in the mouth corner area image, calculating the gray mean value and the standard variance of the gray value of each pixel point in a preset neighborhood, and calculating the gray threshold value at each pixel point according to the gray mean value and the standard variance;
setting the pixel value of the pixel point with the gray value larger than the gray threshold value as a first pixel value, and setting the pixel value of the pixel point with the gray value smaller than the gray threshold value as a second pixel value to obtain the threshold segmentation image.
3. The detection method according to claim 1, wherein the removing of the interference region which does not satisfy the preset area condition and/or the preset included angle condition among the plurality of closed regions comprises:
calculating a first included angle between the long edge of the minimum external rectangle of each closed region and the positive direction of a horizontal line X axis, wherein the horizontal line X axis is the axial direction for measuring the width of the face in the face image;
and (3) taking the closed regions with the areas smaller than a first preset area in the plurality of closed regions and/or taking the closed regions with the first included angles smaller than a first preset angle as the interference regions, and removing the interference regions in the plurality of closed regions.
4. The detection method according to claim 1, wherein the removing of the interference region which does not satisfy the preset area condition and/or the preset included angle condition among the plurality of closed regions comprises:
calculating the rectangular area of the minimum circumscribed rectangle of each closed region;
calculating a second included angle between the major axis of the minimum circumscribed ellipse of each closed region and the positive direction of the X axis of the horizontal line, wherein the X axis of the horizontal line is the axial direction for measuring the width of the face in the face image;
and taking the closed region of which the rectangular area is smaller than a second preset area and/or the closed region of which the second included angle is smaller than a second preset angle from the plurality of closed regions as the interference region, and removing the interference region from the plurality of closed regions.
5. The detection method according to claim 1, wherein the determining of the degree of mouth corner sagging from the length of the long side and the length of the short side of the minimum bounding rectangle of the target closed region comprises:
calculating the sum of the lengths of the long sides of the minimum circumscribed rectangles of all the target closed regions, and calculating the average value of the lengths of the short sides of the minimum circumscribed rectangles of all the target closed regions;
and acquiring a preset formula, and substituting the sum of the lengths of the long sides and the average value of the lengths of the short sides into the preset formula to obtain a result value, wherein the result value represents the degree of the mouth corner sagging.
6. The detection method according to claim 1, further comprising, before the local thresholding the mouth corner region image:
and carrying out noise detection on the mouth angle region image, and carrying out mean value filtering on the mouth angle region image when Gaussian noise exists in the mouth angle region image, so as to obtain a filtered mouth angle region image.
7. The detection method according to claim 1, further comprising, before the local thresholding the mouth corner region image:
and carrying out noise detection on the mouth corner area image, and carrying out median filtering on the mouth corner area image when salt and pepper noise exists in the mouth corner area image to obtain a filtered mouth corner area image.
8. A mouth corner drop detection device, the device comprising:
the mouth corner area image acquisition module is used for acquiring a face image to be detected and intercepting a mouth corner area image in the face image;
the threshold segmentation image acquisition module is used for carrying out local threshold segmentation on the mouth corner region image to obtain a threshold segmentation image, the threshold segmentation image comprises a plurality of closed regions, and the pixel difference between pixels in the closed regions and pixels outside the closed regions is greater than a preset degree;
the drooping texture image acquisition module is used for removing interference areas which do not meet the preset area condition and/or the preset included angle condition in the plurality of closed areas to obtain drooping texture images;
and the mouth corner sagging degree determining module is used for determining the mouth corner sagging degree according to the length of the long side and the length of the short side of the minimum circumscribed rectangle of the target closed region, wherein the target closed region is a closed region in the sagging line image.
9. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, causes the processor to carry out the steps of the method according to any one of claims 1 to 7.
10. A mouth-corner-drop detection apparatus comprising a memory and a processor, characterized in that the memory stores a computer program which, when executed by the processor, causes the processor to carry out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110815463.3A CN113592796A (en) | 2021-07-19 | 2021-07-19 | Method, device, equipment and medium for detecting drooping of mouth corner |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110815463.3A CN113592796A (en) | 2021-07-19 | 2021-07-19 | Method, device, equipment and medium for detecting drooping of mouth corner |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113592796A true CN113592796A (en) | 2021-11-02 |
Family
ID=78248138
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110815463.3A Pending CN113592796A (en) | 2021-07-19 | 2021-07-19 | Method, device, equipment and medium for detecting drooping of mouth corner |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113592796A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116563223A (en) * | 2023-04-11 | 2023-08-08 | 新创碳谷集团有限公司 | Glass fiber yarn winding roller detection method, equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140205159A1 (en) * | 2011-09-22 | 2014-07-24 | Fujifilm Corporation | Wrinkle detection method, wrinkle detection device and recording medium storing wrinkle detection program, as well as wrinkle evaluation method, wrinkle evaluation device and recording medium storing wrinkle evaluation program |
| CN110210448A (en) * | 2019-06-13 | 2019-09-06 | 广州纳丽生物科技有限公司 | A kind of identification and appraisal procedure of Intelligent human-face skin aging degree |
| CN111160358A (en) * | 2019-12-30 | 2020-05-15 | 浪潮(北京)电子信息产业有限公司 | Image binarization method, device, equipment and medium |
| CN111566693A (en) * | 2018-07-16 | 2020-08-21 | 华为技术有限公司 | Wrinkle detection method and electronic equipment |
| JP2021099749A (en) * | 2019-12-23 | 2021-07-01 | 花王株式会社 | Detection method of nasolabial folds |
| CN113128376A (en) * | 2021-04-02 | 2021-07-16 | 西安融智芙科技有限责任公司 | Wrinkle recognition method based on image processing, wrinkle recognition device and terminal equipment |
-
2021
- 2021-07-19 CN CN202110815463.3A patent/CN113592796A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140205159A1 (en) * | 2011-09-22 | 2014-07-24 | Fujifilm Corporation | Wrinkle detection method, wrinkle detection device and recording medium storing wrinkle detection program, as well as wrinkle evaluation method, wrinkle evaluation device and recording medium storing wrinkle evaluation program |
| CN111566693A (en) * | 2018-07-16 | 2020-08-21 | 华为技术有限公司 | Wrinkle detection method and electronic equipment |
| CN110210448A (en) * | 2019-06-13 | 2019-09-06 | 广州纳丽生物科技有限公司 | A kind of identification and appraisal procedure of Intelligent human-face skin aging degree |
| JP2021099749A (en) * | 2019-12-23 | 2021-07-01 | 花王株式会社 | Detection method of nasolabial folds |
| CN111160358A (en) * | 2019-12-30 | 2020-05-15 | 浪潮(北京)电子信息产业有限公司 | Image binarization method, device, equipment and medium |
| CN113128376A (en) * | 2021-04-02 | 2021-07-16 | 西安融智芙科技有限责任公司 | Wrinkle recognition method based on image processing, wrinkle recognition device and terminal equipment |
Non-Patent Citations (1)
| Title |
|---|
| 张春伟，等: "基于机器视觉的轨道车辆零部件形位尺寸检测方法研究", 《计算机测量与控制》, 25 September 2020 (2020-09-25), pages 4 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116563223A (en) * | 2023-04-11 | 2023-08-08 | 新创碳谷集团有限公司 | Glass fiber yarn winding roller detection method, equipment and storage medium |
| CN116563223B (en) * | 2023-04-11 | 2023-09-26 | 新创碳谷集团有限公司 | Glass fiber yarn winding roller detection method, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114418957B (en) | Global and local binary pattern image crack segmentation method based on robot vision | |
| CN107330979B (en) | Vector diagram generation method and device for building house type and terminal | |
| EP1725975B1 (en) | Method, apparatus and program for detecting an object | |
| CN113011385B (en) | Face silence living body detection method, face silence living body detection device, computer equipment and storage medium | |
| US8548257B2 (en) | Distinguishing between faces and non-faces | |
| US8358846B2 (en) | Scanning images for pornography | |
| CN109658424B (en) | Improved robust two-dimensional OTSU threshold image segmentation method | |
| EP2797052B1 (en) | Detecting a saliency region in an image | |
| CN112446838A (en) | Image noise detection method and device based on local statistical information | |
| CN107622501B (en) | Boundary detection method for medical image | |
| KR20190088089A (en) | Apparatus and method for detecting defects on welding surface | |
| JPH08125857A (en) | Picture processor | |
| CN110807780B (en) | Image processing method and device | |
| CN115797872A (en) | Machine vision-based packaging defect identification method, system, equipment and medium | |
| CN111915541B (en) | Image enhancement processing method, device, equipment and medium based on artificial intelligence | |
| CN108710837A (en) | Cigarette smoking recognition methods, device, computer equipment and storage medium | |
| CN111145086A (en) | Image processing method and device and electronic equipment | |
| CN107146231B (en) | Retinal image bleeding area segmentation method and device and computing equipment | |
| CN116245880A (en) | Electric vehicle charging pile fire risk detection method based on infrared identification | |
| CN113592796A (en) | Method, device, equipment and medium for detecting drooping of mouth corner | |
| CN117245104B (en) | Monitoring method, device, equipment and medium for 3DP metal printing defect identification | |
| CN113496215A (en) | Method and device for detecting human face of living body and electronic equipment | |
| Jafar et al. | Multilevel component-based histogram equalization for enhancing the quality of grayscale images | |
| Shetter et al. | Finger print image enhancement using thresholding and binarization techniques | |
| CN112183454B (en) | Image detection method and device, storage medium and terminal |
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 |