CN114882079A - Image registration detection method, electronic device and storage medium - Google Patents
Image registration detection method, electronic device and storage medium Download PDFInfo
- Publication number
- CN114882079A CN114882079A CN202210379455.3A CN202210379455A CN114882079A CN 114882079 A CN114882079 A CN 114882079A CN 202210379455 A CN202210379455 A CN 202210379455A CN 114882079 A CN114882079 A CN 114882079A
- Authority
- CN
- China
- Prior art keywords
- image
- pixel point
- registration
- similarity
- pixel
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 80
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 238000000034 method Methods 0.000 claims abstract description 42
- 238000012545 processing Methods 0.000 claims description 36
- 238000004590 computer program Methods 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 12
- 230000004304 visual acuity Effects 0.000 description 25
- 238000010586 diagram Methods 0.000 description 15
- 238000005516 engineering process Methods 0.000 description 8
- 238000013473 artificial intelligence Methods 0.000 description 5
- 230000014509 gene expression Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000004438 eyesight Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 230000003796 beauty Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 108010068977 Golgi membrane glycoproteins Proteins 0.000 description 1
- 206010028980 Neoplasm Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000002583 angiography Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000009529 body temperature measurement Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000003973 paint Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000001360 synchronised 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
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the application discloses an image registration detection method, electronic equipment and a storage medium, wherein the method comprises the following steps: receiving a first image and a second image which are completely registered, wherein the analytic force of the first image is larger than that of the second image; calculating the similarity between each pixel point in the first image and the corresponding position pixel point in the second image to obtain a third image for representing the similarity of each pixel point; and determining a registration detection result of the first image and the second image according to the third image.
Description
Technical Field
The present disclosure relates to the field of machine vision technologies, and in particular, to an image registration detection method, an electronic device, and a storage medium.
Background
The image registration technology is a technology for optimally mapping one or more images onto a target image based on certain evaluation criteria by using a certain method, and is the basis of image fusion. The image fusion is widely applied to the fields of target detection, model reconstruction, motion estimation, feature matching, tumor detection, lesion positioning, angiography, geological exploration, aerial reconnaissance and the like. The quality of subsequent image fusion is directly affected by the correctness of the image registration result, so that the image registration result needs to be detected. At present, the existing image registration detection method is only suitable for two registration images with basically consistent analytical force, but is not suitable for two registration images with different analytical force, and the detection cannot be realized.
Disclosure of Invention
The embodiment of the application provides an image registration detection method, electronic equipment and a storage medium, so as to solve the technical problem that registration detection cannot be realized on two registration images with different resolving powers in the prior art.
According to a first aspect of the present application, an image registration detection method is disclosed, the method comprising:
receiving a first image and a second image which are completely registered, wherein the analytic force of the first image is larger than that of the second image;
calculating the similarity between each pixel point in the first image and the corresponding position pixel point in the second image to obtain a third image for representing the similarity of each pixel point;
and determining a registration detection result of the first image and the second image according to the third image.
According to a second aspect of the present application, an image registration detection apparatus is disclosed, the apparatus comprising:
a receiving module, configured to receive a first image and a second image that have been registered, where an analytic force of the first image is greater than an analytic force of the second image;
the first calculation module is used for calculating the similarity between each pixel point in the first image and the corresponding position pixel point in the second image to obtain a third image for representing the similarity of each pixel point;
a determining module, configured to determine a registration detection result of the first image and the second image according to the third image.
According to a third aspect of the present application, an electronic device is disclosed, comprising a memory, a processor and a computer program stored on the memory, the processor executing the computer program to implement the image registration detection method as in the first aspect.
According to a fourth aspect of the present application, a computer readable storage medium is disclosed, having stored thereon a computer program/instructions which, when executed by a processor, implement the image registration detection method as in the first aspect.
According to a fifth aspect of the present application, a computer program product is disclosed, comprising computer programs/instructions which, when executed by a processor, implement the image registration detection method as in the first aspect.
In the embodiment of the application, for two registration images with different resolving powers, whether the registration between the two registration images has a problem can be determined according to a third image formed by the similarity between pixels in the two registration images. Compared with the prior art, in the embodiment of the application, the registration degree of the two images with different resolving powers can be reflected to a great extent by the similarity of the pixel points, so that the detection of the two registration images with different resolving powers can be realized.
Drawings
Fig. 1 is a flowchart of an image registration detection method provided in an embodiment of the present application;
FIG. 2 is a diagram of an example of a third image provided by an embodiment of the present application;
FIG. 3 is another exemplary diagram of a third image provided by an embodiment of the present application;
fig. 4 is a flowchart of another image registration detection method provided in the embodiment of the present application;
FIG. 5 is a diagram of an example of a fourth image provided by an embodiment of the present application;
FIG. 6 is another exemplary diagram of a fourth image provided by an embodiment of the present application;
fig. 7 is a schematic structural diagram of an image registration detection apparatus provided in an embodiment of the present application;
fig. 8 is a block diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, the present application is described in further detail with reference to the accompanying drawings and the detailed description.
It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the embodiments are not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the embodiments. Further, those skilled in the art will also appreciate that the embodiments described in the specification are presently preferred and that no particular act is required of the embodiments of the application.
In recent years, technical research based on artificial intelligence, such as computer vision, deep learning, machine learning, image processing, and image recognition, has been actively developed. Artificial Intelligence (AI) is an emerging scientific technology for studying and developing theories, methods, techniques and application systems for simulating and extending human Intelligence. The artificial intelligence subject is a comprehensive subject and relates to various technical categories such as chips, big data, cloud computing, internet of things, distributed storage, deep learning, machine learning and neural networks. Computer vision is used as an important branch of artificial intelligence, particularly a machine is used for identifying the world, and the computer vision technology generally comprises the technologies of face identification, living body detection, fingerprint identification and anti-counterfeiting verification, biological feature identification, face detection, pedestrian detection, target detection, pedestrian identification, image processing, image identification, image semantic understanding, image retrieval, character identification, video processing, video content identification, behavior identification, three-dimensional reconstruction, virtual reality, augmented reality, synchronous positioning and map construction (SLAM), computational photography, robot navigation and positioning and the like. With the research and progress of artificial intelligence technology, the technology is applied to various fields, such as security, city management, traffic management, building management, park management, face passage, face attendance, logistics management, warehouse management, robots, intelligent marketing, computational photography, mobile phone images, cloud services, smart homes, wearable equipment, unmanned driving, automatic driving, smart medical treatment, face payment, face unlocking, fingerprint unlocking, testimony verification, smart screens, smart televisions, cameras, mobile internet, live webcasts, beauty treatment, medical beauty treatment, intelligent temperature measurement and the like.
The embodiment of the application provides an image registration detection method, electronic equipment and a storage medium.
For ease of understanding, some concepts involved in the embodiments of the present application are explained first.
The resolution, also called resolution, is a capability of distinguishing details of an object, and a physical quantity describing the capability of a miniature photography system to reproduce the details of the original object is an important index for evaluating the resolution of an image. The longer the focal length of the camera, the higher the resolving power and the higher the resolution of the image; conversely, the shorter the focal length of the camera, the lower the resolution and the lower the resolution of the image.
Gaussian blur, also known as gaussian smoothing, is a processing effect widely used in image processing software such as Adobe Photoshop, GIMP, and paint.
SSIM (Structural Similarity), an index for measuring the Similarity between two images, is used.
Next, a method for detecting image registration provided by an embodiment of the present application is described.
Fig. 1 is a flowchart of an image registration detection method provided in an embodiment of the present application, and as shown in fig. 1, the method may include the following steps: step 101, step 102 and step 103, wherein,
in step 101, a first image and a second image are received, wherein the first image has a higher resolving power than the second image.
In the embodiment of the application, for two images to be registered with different analytical forces, the images with high analytical force can be registered to the images with low analytical force, and the images with low analytical force can also be registered to the images with high analytical force.
In the embodiment of the application, two images to be registered with different resolving powers can be derived from two cameras, for example, one image to be registered is derived from a wide-angle camera, the other image to be registered is derived from a telephoto camera, the resolving powers of the two images shot by the two cameras are different, when the same object is shot, the resolving power of the image shot by the telephoto camera is high, the texture in the image can be clearly seen, the resolving power of the image shot by the wide-angle camera is low, and only the rough contour and the texture cannot be clearly seen in the shot image.
For two images to be registered with different analytical forces, after the registration is completed, a first image and a second image which are registered are obtained, wherein the first image is a high analytical force image, and the second image is a low analytical force image.
In the embodiment of the present application, the resolving power of the first image may be much larger than that of the second image, or may be slightly larger than that of the second image.
In step 102, the similarity between each pixel point in the first image and a pixel point at a corresponding position in the second image is calculated to obtain a third image for representing the similarity of each pixel point.
In some embodiments, in order to ensure the accuracy of the similarity calculation between the two images, a structural similarity calculation method may be used to calculate the similarity between each pixel point in the first image and the corresponding pixel point in the second image. Alternatively, other similarity calculation methods, such as a histogram calculation method, may be employed, and are not limited herein.
In some embodiments, the pixel value of each pixel point in the third image is: and the similarity value of the pixel point at the corresponding position in the first image and the pixel point at the corresponding position in the second image.
When the structural similarity calculation method is adopted to calculate the similarity between each pixel point in the first image and the pixel point at the corresponding position in the second image, the third image is a gray scale image, and the pixel value of each pixel point in the third image is as follows: and the SSIM value of the pixel point at the corresponding position in the first image and the pixel point at the corresponding position in the second image.
For a certain pixel point in the third image, if the SSIM value of the pixel point is higher, it indicates that the first image and the second image are more similar at the position of the pixel point, and conversely, the first image and the second image are more dissimilar, and the dissimilar position often indicates that registration is not performed, that is, an error occurs after registration. The SSIM appears in the third image as: the higher the SSIM value of a certain pixel point is, the brighter the color of the position at the pixel point is, and vice versa, the darker the color is.
In some embodiments, because the gray scale map is directly constructed by using the similarity values of the pixel points at the corresponding positions in the first image and the pixel points at the corresponding positions in the second image, the distribution of the pixel values of the pixel points is relatively wide (0-255), and the processing is relatively difficult.
Correspondingly, the third image is a binary image, and the pixel value of each pixel point in the third image is: and (4) carrying out similarity binarization on the pixel points at the corresponding positions in the first image and the pixel points at the corresponding positions in the second image.
When the binarization processing is performed on the similarity between each pixel point in the first image and the corresponding pixel point in the second image, a threshold thr1 (for example, 0.5) may be set, the binarization result of the pixel point whose similarity is less than thr1 is set to 255, and the binarization result of the pixel point whose similarity is not less than thr is set to 0. Alternatively, the reverse processing concept may be employed: the binarization result of the pixel point with the similarity smaller than thr1 is set to be 0, and the binarization result of the pixel point with the similarity not smaller than thr is set to be 255. For convenience of description, the following binarization processing is described by taking an image obtained by a binarization processing strategy as an example.
In order to facilitate understanding of the above two different forms of the third image, a description is made in connection with the example figures in the drawings. When the structural similarity calculation method is adopted to calculate the similarity between each pixel point in the first image and the pixel point at the corresponding position in the second image, the pixel value of each pixel point in the third image is as follows: the SSIM values of the pixel points at the corresponding positions in the first image and the pixel points at the corresponding positions in the second image are shown in fig. 2, and the third image is a gray scale image.
When the pixel value of each pixel point in the third image is: when the binarization result of the similarity between the pixel point at the corresponding position in the first image and the pixel point at the corresponding position in the second image is obtained, as shown in fig. 3, the third image is a binary image.
In step 103, a registration detection result of the first image and the second image is determined based on the third image.
In some embodiments, the registration detection result may be determined by connected component information in the image, and the step 103 may specifically include the following steps:
and detecting whether a connected region exists in the third image, and if the connected region exists in the third image, determining that the registration between the first image and the second image is wrong, wherein the registration wrong region is the connected region.
Taking the third image as the image shown in fig. 3 as an example, the third image shown in fig. 3 is subjected to connected region detection, a plurality of connected regions (i.e., a plurality of white regions) are detected to be present in the third image, it is determined that there is an error in registration between the first image and the second image, and the registration error region is a white region in the third image.
As can be seen from the above embodiments, in this embodiment, for two registration images with different resolving powers, it can be determined whether there is a problem in registration between the two registration images according to a third image formed by the similarity between the pixels in the two registration images. Compared with the prior art, in the embodiment of the application, the registration degree of the two images with different resolving powers can be reflected to a great extent by the similarity of the pixel points, so that the detection of the two registration images with different resolving powers can be realized.
Fig. 4 is a flowchart of another image registration detection method provided in the embodiment of the present application, in order to improve the accuracy of registration detection, in the embodiment of the present application, a blurring process may be performed on an image that has been registered, and a registration detection result is guided by the blurred image, so as to reduce false detection caused by a difference in resolving power, as shown in fig. 4, the method may include the following steps: step 401, step 402, step 403, step 404 and step 405, wherein,
in step 401, a first image and a second image are received after registration is completed, wherein the resolving power of the first image is greater than that of the second image.
In step 402, the similarity between each pixel point in the first image and the corresponding pixel point in the second image is calculated to obtain a third image for representing the similarity of each pixel point.
In step 403, at least the first image is blurred.
In order to reduce the difference of the resolving power between the first image and the second image, and thus reduce the interference of the dissimilar textures of the two images after the registration on the detection result, in the embodiment of the present application, at least the first image with high resolving power needs to be subjected to blurring processing.
In some embodiments, only the high resolution first image may be blurred.
In some embodiments, the blurring process may be performed on both the first image and the second image, wherein the degree of blurring of the first image is not lower than the degree of blurring of the second image.
When the image is blurred, in order to achieve uniform blurring effect, a gaussian blurring algorithm may be used for blurring. Alternatively, other fuzzy algorithms, such as a mean fuzzy algorithm, may be used, and are not limited herein.
In step 404, if the first image is blurred, calculating the similarity between each pixel point in the blurred image and a pixel point at a corresponding position in the second image to obtain a fourth image for representing the similarity of each pixel point; if the first image and the second image are subjected to fuzzy processing, calculating the similarity between the pixel points in the two images obtained by the fuzzy processing to obtain a fourth image for representing the similarity of the pixel points, wherein the fuzzy degree of the first image is not lower than that of the second image.
In the embodiment of the present application, similar to the two expressions of the third image, the fourth image may have two expressions, one expression is a gray-scale map as shown in fig. 5, and the other expression is a binary map as shown in fig. 6.
It should be noted that, when the third image and the fourth image are both binary images, the corresponding binarization strategies should be the same.
In step 405, a registration detection result of the first image and the second image is determined from the third image and the fourth image.
In some embodiments, since the fourth image further eliminates the influence of texture dissimilarity caused by the difference of resolving power, the registration detection result of the third image can be guided by the fourth image, and at this time, the step 405 may specifically include the following steps (not shown in the figure): steps 4051 and 4052, wherein,
in step 4051, detecting whether a connected region exists in the third image, and if a connected region exists in the third image, obtaining a pixel value of each pixel point at a corresponding position in the fourth image;
in step 4052, a registration detection result of the first image and the second image is determined according to the connected region in the third image and the pixel value of each pixel point in the corresponding position in the fourth image.
In the embodiment of the present application, taking the third image and the fourth image as an example, a connected region in the third image (i.e., a binary image corresponding to a clear first image and a clear second image) is a region where registration errors may exist, and in order to determine whether the region is a real registration error or a false detection due to a correct self-registration but dissimilar texture, further determination is performed by combining pixel points in corresponding positions in the fourth image (i.e., a binary image corresponding to a blurred first image and a blurred second image).
In some embodiments, when further determining, by combining with the pixel points at the corresponding positions in the fourth image (i.e., the binary image corresponding to the blurred first and second images), step 4052 may specifically include the following steps:
and for at least one connected region in the third image, adjusting the registration detection result between the first image and the second image according to the pixel value of each pixel point at the corresponding position in the fourth image.
If the pixel value of each pixel point at the corresponding position in the fourth image is the same as the pixel value of the pixel point in the connected region, determining the connected region as a registration error region;
and if the pixel value of each pixel point at the corresponding position in the fourth image is different from the pixel value of the pixel point in the connected region, determining the connected region as a correct registration region.
In the embodiment of the present application, since the fourth image has eliminated the interference caused by the texture dissimilarity, if the region of the corresponding position in the fourth image is also detected as the registration error region, it is determined that the connected region in the third image is the true registration error region. And if the area of the corresponding position in the fourth image is detected not to be the registration error area, determining that the connected area in the third image is misdetection which is correct in self registration but caused by dissimilar textures.
In some embodiments, in order to reduce some interferences caused by detection itself, for example, some connected regions (also referred to as interference points) with very small areas may exist in an image, in order to reduce the interference of the connected regions to the detection result, an island removing operation may be performed on the image to remove the interference points in the image, at this time, the fourth image is an image formed by similarity of each pixel point in two images obtained by calculation after the blurring processing, and the image obtained by the island removing processing is performed; wherein the island removal process comprises: and eliminating isolated small regions in the image, wherein the pixel values of the pixels in the small regions are the same as those of the pixels in the connected regions, and the number of the pixels in the small regions is less than the preset number.
In some embodiments, in order to enable the maintenance personnel to visually understand the registration error, the registration error region in the image may be marked and output, which is described below with reference to an example.
After acquiring the third image shown in fig. 3 and the fourth image shown in fig. 6, performing connected region detection on the third image, and detecting that a plurality of white regions, that is, connected regions, exist in the third image, taking a white region a with a large area in the third image as an example, the white region a is a region where registration errors may exist, in order to determine whether the region a is a real registration error, or a false detection due to correct registration itself but due to dissimilar textures, further judgment needs to be performed in combination with the fourth image, since the fourth image has eliminated interference caused by dissimilar textures, if there are white pixel points in a region at a corresponding position in the fourth image, it is determined that the region a is a real registration error region. If the area of the corresponding position in the fourth image has no white pixel point, the registration of the area A is correct, but the false detection is caused by dissimilar textures, and at the moment, the pixel value of the pixel point in the area A is changed from 255 to 0. And performing the above processing on each white area in the third image to obtain a final output image, wherein if the white area still exists in the output image, the white area is a registration error area.
It can be seen from the above embodiment that, in this embodiment, because the blurring processing is performed on the image with large resolving power in the two registered images, the resolving power difference between the two images can be reduced, and the interference of dissimilar textures of the two registered images on the detection result can be reduced.
In order to improve the accuracy of the registration detection result and eliminate the false detection caused by the difference in resolving power, in another embodiment provided in the embodiment of the present application, the two registered images may be first subjected to blurring processing, and then registration detection is performed based on the two blurred images, and the registration detection process is similar to steps 102 and 103 in the embodiment shown in fig. 1, and is not described again here.
In some embodiments, the first image is a blurred image, i.e. only high resolution images in the two registered images may be blurred.
In some embodiments, the first and second images are both blurred images, i.e., both registered images may be blurred.
Fig. 7 is a schematic structural diagram of an image registration detection apparatus according to an embodiment of the present application, and as shown in fig. 7, an image registration detection apparatus 700 may include: a receiving module 701, a first calculation module 702 and a determination module 703, wherein,
a receiving module 701, configured to receive a first image and a second image that have been registered, where an analytic force of the first image is greater than an analytic force of the second image;
a first calculating module 702, configured to calculate similarity between each pixel point in the first image and a pixel point at a corresponding position in the second image, so as to obtain a third image for representing the similarity of each pixel point;
a determining module 703 is configured to determine a registration detection result of the first image and the second image according to the third image.
As can be seen from the above embodiments, in this embodiment, for two registration images with different resolving powers, it can be determined whether there is a problem in registration between the two registration images according to a third image formed by the similarity between the pixels in the two registration images. Compared with the prior art, in the embodiment of the application, the registration degree of the two images with different resolving powers can be reflected to a great extent by the similarity of the pixel points, so that the detection of the two registration images with different resolving powers can be realized.
Optionally, as an embodiment, the determining module 703 may include:
the detection submodule is used for detecting whether a connected region exists in the third image;
a first determining sub-module, configured to determine that a registration error exists between the first image and the second image if a connected region exists in the third image.
Optionally, as an embodiment, the image registration detection apparatus 700 may further include:
the blurring processing module is used for blurring at least the first image;
the second calculation module is used for calculating the similarity between each pixel point in the image obtained by the fuzzy processing and the pixel point at the corresponding position in the second image if the first image is subjected to the fuzzy processing, so as to obtain a fourth image for representing the similarity of each pixel point;
the third calculation module is used for calculating the similarity between pixel points in the two images obtained by the fuzzy processing if the first image and the second image are subjected to the fuzzy processing to obtain a fourth image used for representing the similarity of the pixel points, wherein the fuzzy degree of the first image is not lower than that of the second image;
the determining module 703 may include:
and the second determining submodule is used for determining a registration detection result of the first image and the second image according to the third image and the fourth image.
Optionally, as an embodiment, the second determining sub-module may include:
a detection unit configured to detect whether a connected region exists in the third image;
an obtaining unit, configured to obtain a pixel value of each pixel point at a corresponding position in the fourth image if a connected region exists in the third image;
and the determining unit is used for determining the registration detection result of the first image and the second image according to the connected region in the third image and the pixel value of each pixel point at the corresponding position in the fourth image.
Optionally, as an embodiment, the determining unit may include:
and the determining subunit is configured to, for at least one connected region in the third image, adjust a registration detection result between the first image and the second image according to a pixel value of each pixel point at a corresponding position in the fourth image.
Optionally, as an embodiment, the determining the sub-unit is specifically configured to:
if the pixel value of each pixel point at the corresponding position in the fourth image is the same as the pixel value of the pixel point in the connected region, determining that the connected region is a registration error region;
and if the pixel value of each pixel point at the corresponding position in the fourth image is different from the pixel value of the pixel point in the connected region, determining that the connected region is a correct registration region.
Optionally, as an embodiment, the fourth image is an image formed by performing island removal processing on an image formed by similarity of each pixel point in two images obtained by calculation after the blurring processing;
wherein the island removal process comprises: and eliminating isolated small regions in the image, wherein the pixel values of the pixels in the small regions are the same as those of the pixels in the connected regions, and the number of the pixels in the small regions is smaller than the preset number.
Optionally, as an embodiment, the first image is an image subjected to a blurring process.
Any one step and specific operation in any one step in the embodiment of the image registration detection method provided by the application can be completed by a corresponding module in the image registration detection apparatus. The processes of the respective operations performed by the respective modules in the image registration detection apparatus refer to the processes of the respective operations described in the embodiment of the image registration detection method.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
Fig. 8 is a block diagram of an electronic device according to an embodiment of the present application. The electronic device includes a processing component 822 further including one or more processors and memory resources, represented by memory 832, for storing instructions, such as application programs, that are executable by the processing component 822. The application programs stored in memory 832 may include one or more modules that each correspond to a set of instructions. Further, the processing component 822 is configured to execute instructions to perform the above-described methods.
The electronic device may also include a power component 826 configured to perform power management of the electronic device, a wired or wireless network interface 850 configured to connect the electronic device to a network, and an input/output (I/O) interface 858. The electronic device may operate based on an operating system stored in memory 832, such as Windows Server, MacOS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.
According to yet another embodiment of the present application, there is also provided a computer-readable storage medium having stored thereon a computer program/instructions which, when executed by a processor, implement the steps in the image registration detection method according to any one of the above embodiments.
According to yet another embodiment of the present application, there is also provided a computer program product comprising computer program/instructions which, when executed by a processor, implement the steps in the image registration detection method according to any one of the above embodiments.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one of skill in the art, embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the true scope of the embodiments of the application.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The image registration detection method, the electronic device, and the storage medium provided by the present application are introduced in detail above, and specific examples are applied in the present application to explain the principles and embodiments of the present application, and the descriptions of the above embodiments are only used to help understand the method and the core ideas of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (11)
1. An image registration detection method, characterized in that the method comprises:
receiving a first image and a second image which are completely registered, wherein the analytic force of the first image is larger than that of the second image;
calculating the similarity between each pixel point in the first image and the corresponding position pixel point in the second image to obtain a third image for representing the similarity of each pixel point;
and determining a registration detection result of the first image and the second image according to the third image.
2. The method of claim 1, wherein determining registration detection results of the first image and the second image from the third image comprises:
detecting whether a connected region exists in the third image;
determining that there is an error in the registration between the first image and the second image if there is a connected region in the third image.
3. The method of claim 1, wherein prior to determining the registration detection result of the first image and the second image from the third image, the method further comprises:
blurring at least the first image;
if the first image is subjected to fuzzy processing, calculating the similarity between each pixel point in the image obtained by fuzzy processing and the pixel point at the corresponding position in the second image to obtain a fourth image for representing the similarity of each pixel point;
if the first image and the second image are subjected to fuzzy processing, calculating the similarity between the pixel points in the two images obtained by the fuzzy processing to obtain a fourth image for representing the similarity of the pixel points, wherein the fuzzy degree of the first image is not lower than that of the second image;
the determining, according to the third image, a registration detection result of the first image and the second image includes:
and determining a registration detection result of the first image and the second image according to the third image and the fourth image.
4. The method of claim 3, wherein determining registration detection results for the first image and the second image from the third image and the fourth image comprises:
detecting whether a connected region exists in the third image;
if the third image has a connected region, acquiring the pixel value of each pixel point at the corresponding position in the fourth image;
and determining a registration detection result of the first image and the second image according to the connected region in the third image and the pixel value of each pixel point at the corresponding position in the fourth image.
5. The method according to claim 4, wherein the determining the registration detection result of the first image and the second image according to the connected region in the third image and the pixel value of each pixel point in the corresponding position in the fourth image comprises:
and for at least one connected region in the third image, adjusting the registration detection result between the first image and the second image according to the pixel value of each pixel point at the corresponding position in the fourth image.
6. The method according to claim 5, wherein the adjusting the registration detection result between the first image and the second image according to the pixel value of each pixel point in the corresponding position in the fourth image comprises:
if the pixel value of each pixel point at the corresponding position in the fourth image is the same as the pixel value of the pixel point in the connected region, determining that the connected region is a registration error region;
and if the pixel value of each pixel point at the corresponding position in the fourth image is different from the pixel value of the pixel point in the connected region, determining that the connected region is a correct registration region.
7. The method according to any one of claims 3 to 6, wherein the fourth image is an image obtained by performing island removal processing on an image formed by similarity of each pixel point in two images obtained by calculation after the blurring processing;
wherein the island removal process comprises: and eliminating isolated small regions in the image, wherein the pixel values of the pixels in the small regions are the same as those of the pixels in the connected regions, and the number of the pixels in the small regions is smaller than the preset number.
8. The method of claim 1, wherein the first image is a blurred image.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory, characterized in that the processor executes the computer program to implement the method of any of claims 1-8.
10. A computer-readable storage medium, on which a computer program/instructions is stored, characterized in that the computer program/instructions, when executed by a processor, implements the method of any one of claims 1-8.
11. A computer program product comprising computer programs/instructions, characterized in that the computer programs/instructions, when executed by a processor, implement the method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210379455.3A CN114882079A (en) | 2022-04-12 | 2022-04-12 | Image registration detection method, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210379455.3A CN114882079A (en) | 2022-04-12 | 2022-04-12 | Image registration detection method, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114882079A true CN114882079A (en) | 2022-08-09 |
Family
ID=82669339
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210379455.3A Pending CN114882079A (en) | 2022-04-12 | 2022-04-12 | Image registration detection method, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114882079A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103186897A (en) * | 2011-12-29 | 2013-07-03 | 北京大学 | Method and device for obtaining image diversity factor result |
| CN108682025A (en) * | 2018-05-23 | 2018-10-19 | 沈阳东软医疗系统有限公司 | A kind of method for registering images and device |
| CN112465886A (en) * | 2020-12-09 | 2021-03-09 | 苍穹数码技术股份有限公司 | Model generation method, device, equipment and readable storage medium |
-
2022
- 2022-04-12 CN CN202210379455.3A patent/CN114882079A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103186897A (en) * | 2011-12-29 | 2013-07-03 | 北京大学 | Method and device for obtaining image diversity factor result |
| CN108682025A (en) * | 2018-05-23 | 2018-10-19 | 沈阳东软医疗系统有限公司 | A kind of method for registering images and device |
| CN112465886A (en) * | 2020-12-09 | 2021-03-09 | 苍穹数码技术股份有限公司 | Model generation method, device, equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108805016B (en) | Head and shoulder area detection method and device | |
| CN117593304B (en) | Semi-supervised industrial product surface defect detection method based on cross local global features | |
| CN112989889B (en) | Gait recognition method based on gesture guidance | |
| CN114049512A (en) | Model distillation method, target detection method and device and electronic equipment | |
| CN113673505A (en) | Example segmentation model training method, device and system and storage medium | |
| CN115147936A (en) | Living body detection method, electronic device, storage medium, and program product | |
| CN116797504A (en) | Image fusion method, electronic device and storage medium | |
| CN115049675A (en) | Generation area determination and light spot generation method, apparatus, medium, and program product | |
| CN113673308B (en) | Object identification method, device and electronic system | |
| CN116977209A (en) | Image noise reduction method, electronic device and storage medium | |
| CN116469177A (en) | Living body target detection method with mixed precision and training method of living body detection model | |
| CN114882079A (en) | Image registration detection method, electronic device and storage medium | |
| CN115223141A (en) | Traffic light detection method, electronic device and storage medium | |
| CN112926498B (en) | Living body detection method and device based on multichannel fusion and depth information local dynamic generation | |
| CN115620403A (en) | Living body detection method, electronic device, and storage medium | |
| CN114005017A (en) | Target detection method and device, electronic equipment and storage medium | |
| CN114648604A (en) | Image rendering method, electronic device, storage medium and program product | |
| CN113592902A (en) | Target tracking method and device, computer equipment and storage medium | |
| CN114764948A (en) | Living body detection method, living body detection device, living body detection equipment and storage medium | |
| Zhu et al. | A Stereo Matching and Depth Map Acquisition Algorithm Based on Deep Learning and Improved Winner Takes All-Dynamic Programming | |
| CN114743127A (en) | Feature extraction method, electronic device, and storage medium | |
| CN115841705A (en) | Living body detection method | |
| CN114155157A (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| CN115631296A (en) | 3D target detection method, computer program product and electronic equipment | |
| CN115879488A (en) | DM code decoding method, electronic device, storage medium and program product |
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 |