CN116868233A

CN116868233A - Image registration evaluation method, device, electronic equipment and readable storage medium

Info

Publication number: CN116868233A
Application number: CN202080108422.4A
Authority: CN
Inventors: 闫浩; 罗春; 李金升
Original assignee: Our United Corp
Current assignee: Our United Corp
Priority date: 2020-12-31
Filing date: 2020-12-31
Publication date: 2023-10-10
Also published as: WO2022141531A1

Abstract

The embodiment of the application discloses an image registration evaluation method, an image registration evaluation device, electronic equipment and a computer-readable storage medium. The image registration evaluation method comprises the following steps: acquiring a target registration position of a target image, wherein the target registration position refers to a position when the similarity between the target image and a preset reference image meets a preset registration condition in a registration process; and determining the target confidence coefficient of the target registration position according to the confidence coefficient evaluation factors to evaluate the accuracy of image registration, wherein the confidence coefficient evaluation factors are a plurality of factors for evaluating the accuracy of image registration. The target confidence coefficient of the target registration position in the embodiment of the application can reflect the accuracy of the actual registration of the target image and the reference image, so that the image registration result with lower accuracy and even errors can be prevented from being displayed, or a user can know the accuracy of the image registration result, and the problem of adopting the image registration result with lower accuracy and even errors to perform further image processing is avoided to a certain extent.

Description

Image registration evaluation method, device, electronic equipment and readable storage medium

Technical Field

The application relates to the technical field of medical treatment, in particular to an image registration evaluation method, an image registration evaluation device, electronic equipment and a computer readable storage medium.

Background

The medical image registration technology is the basis of medical image processing and plays an important role in the fields of image information fusion, auxiliary diagnosis, operation planning, medical basic theory research and the like.

In general, image registration is a process of spatially matching two images, if an image a is to be registered to an image B, B is taken as a reference image, a is taken as a floating image, registration is performed by continuously moving the floating image a and the reference image B, and when the similarity between the floating image a and the reference image B is maximum, an image registration result is output, where the registration result may include a deformation field of the image a registered to the image B.

In the related art, regardless of the degree of accuracy of the image registration result, the image registration result is output to the user. However, it is not clear to the user whether the image registration result is sufficiently accurate, and further image processing, such as medical image processing, may be performed using image registration results with a lower accuracy or even erroneous image registration results (i.e., image registration results with a very low accuracy).

Technical problem

From the above, the user in the related art cannot measure the accuracy of the image registration result, and can easily use the image registration result with lower accuracy or even with error for further image processing.

Technical solution

The application provides an image registration evaluation method, an image registration evaluation device, electronic equipment and a computer readable storage medium, which save time for image registration evaluation and improve efficiency of image registration evaluation.

In one aspect, the present application provides an image registration evaluation method, including:

acquiring a target registration position of a target image, wherein the target registration position refers to a position when the similarity between the target image and a preset reference image meets a preset registration condition in a registration process;

and determining the target confidence coefficient of the target registration position according to a confidence coefficient evaluation factor to evaluate the accuracy of image registration, wherein the confidence coefficient evaluation factor is a plurality of factors for evaluating the accuracy of image registration.

In some embodiments of the application, the confidence evaluation factor includes at least one of an absolute value of the similarity measure, a rate of change of the similarity measure, and a degree of fluctuation of the similarity measure.

In some embodiments of the present application, where the confidence evaluation factor includes a degree of fluctuation of the similarity measure, the determining, according to the confidence evaluation factor, the target confidence of the target registration position includes:

Obtaining similarity measurement of the target image and the ith registration iteration of the reference image, wherein the target image is positioned at the target registration position in the ith registration iteration, and i is an integer greater than 0;

obtaining similarity measures of N registration iterations before the ith registration iteration and/or after the ith registration iteration of the target image and the reference image, wherein N is an integer greater than 0;

determining the fluctuation degree of n+1 similarity measures according to the similarity measure of the ith registration iteration and the similarity measure of the N registration iterations;

and determining the target confidence coefficient of the target registration position according to the fluctuation degree of the N+1 similarity measures.

In some embodiments of the present application, the obtaining a similarity measure for N registration iterations before the ith registration iteration of the target image and the reference image includes:

and obtaining similarity measurement from the ith-N times to the ith-1 times of registration iteration of the target image and the reference image, wherein N is smaller than or equal to i.

In some embodiments of the present application, the obtaining a similarity measure for N registration iterations after the ith registration iteration of the target image and the reference image includes:

And obtaining similarity measurement of the target image and the ith (i+1) th to (i+N) th registration iteration of the reference image, wherein N is larger than i.

In some embodiments of the present application, the obtaining a similarity measure for N registration iterations before the i-th registration iteration and after the i-th registration iteration of the target image and the reference image includes:

obtaining similarity measurement of the ith-n 1 th to ith-1 st registration iteration of the target image and the reference image, wherein n1 is an integer less than or equal to i;

and obtaining a similarity measure of the target image and the reference image from the (i+1th) to the (i+n2) th registration iteration, wherein N2 is an integer greater than 0, and the sum of N1 and N2 is the N.

In some embodiments of the application, the degree of fluctuation of the n+1 similarity measures is determined by any of the following: a variance of the n+1 similarity metrics, a standard deviation of the n+1 similarity metrics, a range of the n+1 similarity metrics, a quartile range of the n+1 similarity metrics, an average difference of the n+1 similarity metrics, or a coefficient of variation of the n+1 similarity metrics.

In some embodiments of the present application, where the confidence evaluation factor includes a rate of change of the similarity measure, the determining the target confidence of the target registration position according to the confidence evaluation factor includes:

determining the change speed of n+1 similarity measures according to the similarity measure of the ith registration iteration and the similarity measure of the N registration iterations;

and determining the target confidence coefficient of the target registration position according to the change speed of the N+1 similarity measures.

In some embodiments of the present application, the determining the change speed of the n+1 similarity metrics according to the similarity metric of the ith registration iteration and the similarity metric of the N registration iterations includes:

constructing a change curve of n+1 similarity measures according to the similarity measure of the ith registration iteration and the similarity measure of the N registration iterations;

obtaining each segment derivative of the change curve;

and obtaining the sum of absolute values of the derivative of each segment as the change speed of the N+1 similarity measures.

In some embodiments of the present application, the determining the target confidence level of the target registration position according to the confidence level evaluation factor further includes:

detecting whether the target confidence coefficient is larger than or equal to a preset confidence coefficient threshold value;

and when the target confidence coefficient is detected to be greater than or equal to the preset confidence coefficient threshold value, displaying an image registration result, wherein the image registration result comprises a target registration position of the target image and/or the target image and the reference image after registration.

In some embodiments of the application, further comprising:

and outputting prompt information indicating that the image registration accuracy of the target image and the reference image is low when the target confidence coefficient is detected to be smaller than the preset confidence coefficient threshold value.

In some embodiments of the present application, the outputting the prompt information indicating that the image registration accuracy of the target image and the reference image is low further includes:

acquiring a display instruction for requesting to display an image registration result;

and displaying an image registration result of the target image and the reference image.

And displaying an image registration result of the target image and the reference image, and displaying the target confidence.

In another aspect, the present application also provides an image registration evaluation apparatus, including:

the device comprises an acquisition unit, a registration unit and a registration unit, wherein the acquisition unit is used for acquiring a target registration position of a target image, and the target registration position refers to a position when the similarity between the target image and a preset reference image meets a preset registration condition in a registration process;

and the evaluation unit is used for determining the target confidence coefficient of the target registration position according to a confidence coefficient evaluation factor so as to evaluate the accuracy of image registration, wherein the confidence coefficient evaluation factor is a plurality of factors for evaluating the accuracy of image registration.

In some embodiments of the application, the evaluation unit is specifically configured to:

a target confidence level of the target registration position is determined according to at least one of an absolute value of the similarity measure, a rate of change of the similarity measure, and a degree of fluctuation of the similarity measure to evaluate accuracy of image registration.

the degree of fluctuation of the n+1 similarity measures is determined by any of the following means: a variance of the n+1 similarity metrics, a standard deviation of the n+1 similarity metrics, a range of the n+1 similarity metrics, a quartile range of the n+1 similarity metrics, an average difference of the n+1 similarity metrics, or a coefficient of variation of the n+1 similarity metrics.

obtaining each segment derivative of the change curve;

In some embodiments of the present application, the image registration evaluation device further includes a display unit, after the step of determining the target confidence level of the target registration position according to the confidence level evaluation factor, the display unit is specifically configured to:

In some embodiments of the present application, the image registration evaluation apparatus further includes a prompt unit, where the display prompt is specifically configured to:

In some embodiments of the present application, after the step of outputting the hint information indicating that the accuracy of image registration of the target image with the reference image is low, the display unit is specifically configured to:

In some embodiments of the present application, after the step of determining the target confidence level of the target registration position according to the confidence level evaluation factor, the display unit is specifically configured to:

In another aspect, the present application also provides an electronic device, including:

one or more processors;

a memory; and

one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the steps in the image registration evaluation method described above.

In another aspect, the present application also provides a computer readable storage medium having stored thereon a computer program, the computer program being loaded by a processor to perform the steps of the image registration evaluation method.

Advantageous effects

According to the method and the device, the target confidence coefficient of the target registration position is determined according to the confidence coefficient evaluation factor so as to evaluate the accuracy of image registration, and the target confidence coefficient of the target registration position can reflect the accuracy of actual registration of the target image and the reference image to a certain extent, so that the image registration result with lower accuracy and even errors can be prevented from being displayed, or a user can know the accuracy of the image registration result, and the problem of adopting the image registration result with lower accuracy and even errors to perform further image processing is avoided to a certain extent.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic view of a scene of an image registration evaluation system according to an embodiment of the present application;

FIG. 2 is a flow chart of an embodiment of an image registration evaluation method provided by an embodiment of the present application;

FIG. 3 is a schematic view of a scene of an image registration process provided in an embodiment of the present application;

fig. 4 is a schematic representation of the variation of the similarity measure of the ith registration iteration in an embodiment of the present application.

FIG. 5 is a schematic structural view of an embodiment of an image registration evaluation apparatus in an embodiment of the present application;

fig. 6 is a schematic structural diagram of an embodiment of an electronic device according to an embodiment of the present application.

Embodiments of the application

The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to fall within the scope of the application.

In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate orientations or positional relationships based on the drawings are merely for convenience in describing the present application and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present application. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the described features. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.

In the present application, the term "exemplary" is used to mean "serving as an example, instance, or illustration. Any embodiment described as "exemplary" in this disclosure is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the application. In the following description, details are set forth for purposes of explanation. It will be apparent to one of ordinary skill in the art that the present application may be practiced without these specific details. In other instances, well-known structures and processes have not been described in detail so as not to obscure the description of the application with unnecessary detail. Thus, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

The embodiment of the application provides an image registration evaluation method, an image registration evaluation device, electronic equipment and a computer-readable storage medium, and the image registration evaluation method, the device, the electronic equipment and the computer-readable storage medium are respectively described in detail below.

Referring to fig. 1, fig. 1 is a schematic view of a scenario of an image registration evaluation system provided by an embodiment of the present application, where the image registration evaluation system may include an image capturing device 100 and an electronic device 200, where the image capturing device 100 and the electronic device 200 are connected in a network, and an image registration evaluation apparatus, such as the electronic device in fig. 1, is integrated in the electronic device 200, and the image capturing device 100 may capture an image (such as a medical image of a human body) and output the image to the accessing electronic device 200.

In the embodiment of the present application, the electronic device 200 is mainly used for obtaining a target registration position of a target image, where the target registration position refers to a position when a similarity between the target image and a preset reference image meets a preset registration condition in a registration process; and determining the target confidence coefficient of the target registration position according to a confidence coefficient evaluation factor to evaluate the accuracy of image registration, wherein the confidence coefficient evaluation factor is a plurality of factors for evaluating the accuracy of image registration.

In an embodiment of the present application, the image capturing device 100 may be a CT device, a CBCT device or other medical imaging devices, such as an ultrasound device (e.g. a B-ultrasound device or a color ultrasound device), a magnetic resonance imaging (Magnetic Resonance Imaging, MRI) device, etc., which are not limited herein. In a specific application scenario, the preset reference image is an image generated by CBCT in a radiotherapy device, and the target image may be an image generated by a CT device, a CBCT device, or other medical imaging devices (e.g., an ultrasound device, an MRI device).

In an embodiment of the present application, the electronic device 200 may be a device comprising receiving and transmitting hardware, i.e. a device having receiving and transmitting hardware capable of performing bi-directional communication over a bi-directional communication link. Such a device may include: a cellular or other communication device having a single-line display or a multi-line display or a cellular or other communication device without a multi-line display. The specific electronic device 200 may be a desktop terminal or a mobile terminal, and the electronic device 200 may be one of a mobile phone, a tablet computer, a notebook computer, and the like.

It will be understood by those skilled in the art that the application environment shown in fig. 1 is merely an application scenario of the present application, and is not limited to the application scenario of the present application, other application environments may further include more or fewer electronic devices than those shown in fig. 1, or an electronic device network connection relationship, for example, only 1 electronic device and 1 image capturing device are shown in fig. 1, and it is understood that the image registration evaluation system may further include one or more other electronic devices, or/and one or more other image capturing devices connected to the electronic device network, specifically, for example, one electronic device 200 is connected to a plurality of image capturing devices 100, that is, one electronic device 200 is connected to a plurality of electronic devices 200, that is, an image captured by one image capturing device 100 is output to a plurality of electronic devices 200 for display, which is not limited herein.

In addition, as shown in fig. 1, the image registration evaluation system may further comprise a memory 300 for storing data, such as medical image data, e.g. medical image data acquired by the image acquisition device 100.

It should be noted that, the schematic view of the image registration evaluation system shown in fig. 1 is only an example, and the image registration evaluation system and the scene described in the embodiments of the present application are for more clearly describing the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application, and those skilled in the art can know that, with the evolution of the image registration evaluation system and the appearance of a new service scene, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

First, an embodiment of the present application provides an image registration evaluation method, including: acquiring a target registration position of a target image, wherein the target registration position refers to a position when the similarity between the target image and a preset reference image meets a preset registration condition in a registration process; and determining the target confidence coefficient of the target registration position according to a confidence coefficient evaluation factor to evaluate the accuracy of image registration, wherein the confidence coefficient evaluation factor is a plurality of factors for evaluating the accuracy of image registration.

Referring to fig. 2, a flowchart of an embodiment of an image registration evaluation method according to an embodiment of the present application includes steps 201 to 202, wherein:

Step 201, acquiring a target registration position of a target image.

For two images in a set of medical image data sets, the image registration process simply maps one image (floating image) onto another image (reference image) by looking for a spatial transformation, so that points corresponding to the same position in space in the two images are in one-to-one correspondence.

In the embodiment of the application, the target image is a floating image in the image registration process, and the preset reference image is a reference image in the image registration process. Correspondingly, the target registration position is a position when the similarity between the target image and the preset reference image in the image registration process meets the preset registration condition, the target registration position of the target image may be an absolute position of the target image when the target image meets the preset registration condition, for example, an actual position of the target image in an image coordinate system, and the target registration position may also be a relative position of the target image when the target image meets the preset registration condition, for example, a position of the target image relative to the reference image.

The following explanation is made on the concepts of "similarity of target image to preset reference image" and "preset registration condition":

Regarding the similarity between the target image and the preset reference image, the similarity between the reference region of the reference image and the target region of the target image in the image registration process can be measured by the similarity measurement of the reference region and the target region. The similarity measurement for measuring the similarity between the target image and the preset reference image comprises the following steps: mutual information, mean square error, kappa statistics, etc.

Here, the reference region may be a partial or full image region in the reference image, and the target region is an image region of a similarity to the reference image that is searched for each time in the image registration process, and the target region in the target image is changed in each search comparison.

Regarding the preset registration condition, it is that the similarity between the target image and the reference image is the largest in the image registration process, that is, the similarity between the target region in the target image and the reference region in the reference image is the largest.

In step 202, there are various ways to obtain the target registration position of the target image, which illustratively include:

(1) The target registration position of the target image is acquired during the image registration process.

In the image registration process, when the similarity between the target image and the reference image meets a preset registration condition, a target registration position of the target image is acquired.

(2) And acquiring a target registration position of the target image from a preset database.

In the image registration process, when the similarity between the target image and a preset reference image meets a preset registration condition, storing the target registration position of the target image into a preset database. Acquiring a target registration position of a target image includes: and acquiring a target registration position of the target image from a preset database.

It should be noted that the above-mentioned manner of acquiring the target registration position of the target image is merely an exemplary illustration, and the embodiments of the present application are not limited to the above-mentioned manner.

Step 202, determining the target confidence coefficient of the target registration position according to the confidence coefficient evaluation factor so as to evaluate the accuracy of image registration.

First, a confidence rating factor is obtained, wherein the confidence rating factor is a plurality of factors that evaluate accuracy of image registration, and may include at least one of a similarity measure, a rate of change of the similarity measure, a degree of fluctuation of the similarity measure, and the like.

In an embodiment of the present application, the confidence coefficient evaluation factor may be preset and stored in a database, and when accuracy of image registration needs to be evaluated, the confidence coefficient evaluation factor is obtained from the database, and the target confidence coefficient of the target registration position is determined according to the confidence coefficient evaluation factor obtained from the database.

After the confidence rating factors are obtained, the target confidence of the target registration position can be determined according to the confidence rating factors so as to evaluate the accuracy of image registration. Illustratively, a higher target confidence, e.g., 99% target confidence, indicates a higher accuracy of image registration of the target image with the reference image, whereas a lower target confidence, e.g., 60% target confidence, indicates a lower accuracy of image registration of the target image with the reference image.

In practical application, in order to increase the speed of image registration, a region with the maximum similarity with a reference region in a reference image is locally searched in a target image, and when the similarity between the searched region in the target image and the reference region is the maximum, the target image is considered to be in a target registration position. However, since the region having the greatest similarity to the reference region in the reference image is not globally searched in the target image, the target registration position is only a locally optimal registration position, not a globally optimal registration position. As such, the accuracy of image registration is not accurate if assessed by similarity.

In the embodiment of the application, in order to objectively and comprehensively evaluate the accuracy of image registration and improve the referenceability of an image registration result, a confidence concept is introduced for comprehensively evaluating the accuracy of the target registration position of a target image. And determining the target confidence coefficient of the target registration position according to the confidence coefficient evaluation factor by acquiring the target registration position of the target image so as to evaluate the accuracy of image registration. Because the target confidence coefficient of the target registration position can reflect the accuracy of the actual registration of the target image and the reference image to a certain extent, compared with the accuracy of the image registration directly evaluated by the similarity of the target image and the preset reference image, the accuracy of the target confidence coefficient objectively evaluates the actual accuracy of the registration of the target image and the reference image from different angles, the accuracy of the image registration evaluation is higher, and further, the image registration result with lower display accuracy and even errors can be avoided, or a user can know the accuracy of the image registration result, and the problem of adopting the image registration result with lower accuracy and even errors for further image processing is avoided to a certain extent.

In the embodiment of the present application, the confidence evaluation factor may be one or more of a similarity measure, a change speed of the similarity measure, and a fluctuation degree of the similarity measure, which are described below by way of example.

(1) Confidence rating factors include similarity measures.

Since the similarity measure is an important factor reflecting the degree of image registration, the accuracy of the image registration result can be reflected to a certain extent. Therefore, the confidence evaluation factors including the similarity measurement can evaluate the accuracy of image registration to a certain extent, so that the user can know the accuracy of image registration, and further image processing by adopting image registration results with lower accuracy and even errors is avoided to a certain extent.

In some embodiments of the present application, the similarity of the target image to the reference image may be evaluated by a similarity measure. Similarity measure, i.e., a measure that comprehensively evaluates the degree of closeness between two things. In the embodiment of the application, the similarity measure can have various expression forms, for example, mutual information, mean square error, kappa statistics and the like.

In an embodiment of the present application, as shown in fig. 3, step 202 may specifically include steps 2021A to 2022A:

Step 2021A, obtaining a target similarity measure of the target image with the reference image at the target registration position.

In an embodiment of the present application, obtaining a similarity measure between the target image and the reference image when the target is registered may include: a similarity measure of the reference region to the target region at the target registration position is calculated as a similarity measure of the target image to the reference image at the target registration position.

The similarity measure may be set as desired, and the value range may be 0 to 1 or 0 to 100.

Step 2022A, determining a target confidence level for the target registration location based on the target similarity measure.

Further, step 2022A includes: and determining the target confidence according to the target similarity measure and the preset relation between the similarity measure and the confidence.

The preset relationship between the similarity measure and the confidence level may be a function of the confidence level with respect to the similarity measure. For example, y=f (x), where x is the similarity measure and y is the confidence.

In the first case, when the similarity measure of the target image and the reference image is positively correlated with the similarity, that is, the smaller the similarity measure of the target image and the reference image is, the larger the similarity measure of the target image and the reference image is, and the larger the similarity measure of the target image and the reference image is; the target confidence is positively correlated with the similarity measure, i.e., the smaller the similarity measure, the smaller the target confidence, and the larger the similarity measure, the larger the target confidence.

When the similarity measure is positive, step 2022A may specifically include step a1:

and a1, determining the similarity measure as the target confidence of the target registration position.

For example, the preset relationship between the similarity measure and the confidence level may be a function y=k×x of the confidence level with respect to the similarity measure, where k is a preset coefficient greater than 0, x is the similarity measure, and y is the confidence level.

As an embodiment, the similarity measure may be a similarity measure of the target image with the reference image when the target is registered in position. For example, when k in the function y=k×x takes a value of 1, if the similarity measure between the target image and the reference image at the target registration position is 1, the target confidence of the target registration position is considered to be 1.

As another embodiment, the similarity measure may be a product of the similarity measure of the target image and the reference image and a preset coefficient at the time of target registration position. For example, when the k value in the function y=k×x is not 1, for example, the preset coefficient is 0.9, and if the similarity measure between the target image and the reference image at the target registration position is 1, the target confidence of the target registration position is 1×0.9=0.9.

When the similarity measure is negative, step 2022A may specifically include steps b1 to b2:

And b1, processing the similarity measurement to obtain the processed similarity measurement.

And b2, determining the processed similarity measure as the target confidence coefficient of the target registration position.

For example, the preset relationship between the similarity measure and the confidence level may be a function y=1-k×χ| of the confidence level with respect to the similarity measure, where k is a preset coefficient greater than 0, x is equal to or greater than negative 1, x is the similarity measure, and y is the confidence level.

The processed similarity measure may be 1-k x, where x is the absolute value of the similarity measure of the target image and the reference image at the time of target registration position.

As one embodiment, when k in the function y=1-k×χ| takes a value of 1, (1- |x|) is taken as the similarity measure after processing. The processed similarity measure (1- |x|) is then determined as the target confidence of the target registration position. For example, when k in the function y=1-k×x| takes a value of 1, if the similarity measure of the target image and the reference image at the target registration position is-0.2, the target confidence of the target registration position is considered to be (1- | -0.2|) =0.8.

As another embodiment, when k in the function y=1-k×|x| takes a value other than 1, (1-k×|x|) is used as the similarity measure after the processing. The processed similarity measure (1-k x) is then determined as the target confidence of the target registration position. For example, when k in the function y=1-k×x| takes a value of 0.9, if the similarity measure of the target image and the reference image at the time of the target registration position is-0.2, the target confidence of the target registration position is considered to be (1-0.9×0.2|) =0.82.

In the second case, when the similarity measure of the target image and the reference image is inversely related to the similarity, that is, the smaller the similarity measure of the target image and the reference image is, the larger the similarity measure of the target image and the reference image is, and the smaller the similarity measure of the target image and the reference image is; the target confidence is inversely related to the similarity measure, i.e. the smaller the similarity measure, the larger the target confidence, and the larger the similarity measure, the smaller the target confidence.

Illustratively, when the similarity measure is mutual information, the similarity measure is generally a negative value, and the smaller the similarity measure, the larger the similarity is instead; when the similarity measure is the mean square error, the similarity measure is usually a positive value, and the smaller the similarity measure, the larger the similarity is instead. It can be seen that the similarity measure can be either positive or negative, but the smaller the similarity measure, the greater the similarity.

When the similarity measure is negative, step 2022A may specifically include steps c1 to c2:

and c1, determining the similarity measure as the target confidence of the target registration position.

For example, the preset relationship between the similarity measure and the confidence level may be a function y=k×χ| of the confidence level with respect to the similarity measure, where k is a preset coefficient greater than 0, x is the similarity measure, and y is the confidence level.

As an embodiment, the similarity measure may be an absolute value of the similarity measure of the target image and the reference image at the time of target registration position. For example, when k in the function y=k×x| takes a value of 1, if the similarity measure between the target image and the reference image at the target registration position is-1, the target confidence of the target registration position is considered to be 1.

As another embodiment, the similarity measure may also be a product of an absolute value of the similarity measure of the target image and the reference image at the target registration position and a preset coefficient. For example, when the k value in the function y=k×|x| is not 1, if the preset coefficient is 0.9, if the similarity measure between the target image and the reference image is-1 at the target registration position, the target confidence coefficient of the target registration position is 0.9×| -1|=0.9.

When the similarity measure is positive, step 2022A may specifically include steps d 1-d 2:

and d1, processing the similarity measurement to obtain the processed similarity measurement.

And d2, determining the processed similarity measure as the target confidence coefficient of the target registration position.

For example, the preset relationship between the similarity measure and the confidence level may be a function y=1-k×x of the confidence level with respect to the similarity measure, where k is a preset coefficient greater than 0, x is less than or equal to 1, x is the similarity measure, and y is the confidence level.

The processed similarity measure may be y=1-k x, where x is the absolute value of the similarity measure of the target image and the reference image at the target registration position.

As an embodiment, when k in the function y=1-k×x takes a value of 1, (1-x) is taken as the similarity measure after the processing. The processed similarity measure (1-x) is then determined as the target confidence of the target registration position. For example, when k in the function y=1-k×x takes a value of 1, if the similarity measure between the target image and the reference image at the target registration position is 0.2, the target confidence of the target registration position is considered to be (1-0.2) =0.8.

As another embodiment, when k in the function y=1-k×x takes a value other than 1, (1-k×x) is taken as the similarity measure after the processing. The processed similarity measure (1-k x) is then determined as the target confidence of the target registration position. For example, when k in the function y=1-k×x takes a value of 0.9, if the similarity measure between the target image and the reference image at the target registration position is 0.2, the target confidence of the target registration position is considered to be (1-0.9×0.2) =0.82.

(2) The confidence rating factors include the degree of fluctuation of the similarity measure.

Due to the fluctuation degree between the similarity measurement of the target registration position and the similarity measurement of other positions, the intensity of the change between the similarity measurement of the target registration position and the similarity measurement of other positions can be reflected to a certain degree, and the registration accuracy of the target registration position can be reflected to a certain degree. Therefore, the confidence evaluation factors comprise the fluctuation degree of the similarity measurement, so that a user can know the accuracy of image registration, and further image processing by adopting an image registration result with lower accuracy or even an error is avoided to a certain extent.

Here, the similarity measure of the target registration position is the similarity measure of the target image and the reference image at the time of the target registration position. The similarity measure for the other locations is the similarity measure for the target image and the reference image at the other locations. The other positions are positions where the target image is located in addition to the target registration position in the image registration process.

When the confidence evaluation factor includes the degree of fluctuation of the similarity measure, step 202 may specifically include steps 2021B to 2024B:

step 2021B, obtaining a similarity measure of the target image and the ith registration iteration of the reference image.

Wherein, the target image is positioned at the target registration position in the ith registration iteration, and i is an integer greater than 0.

Referring to fig. 3, in general, the image registration process is essentially a process of continuously searching for similar regions in the target image. Once searching, that is, once moving the position, a similarity measure (between the target area and the reference area) is calculated once, and then the moving direction of the next step is determined according to the similarity measure and the similarity measure of all the previous positions, and the process is a registration iteration.

The ith registration iteration is the process of searching and calculating similarity measurement in the image registration process. The similarity measure of the ith registration iteration is the similarity measure of the target image and the reference image at the ith registration iteration.

In some embodiments, obtaining a similarity measure of the target image and the ith registration iteration of the reference image may specifically include: when the target image is located at the target registration position, calculating the similarity measure of the target region and the reference region to serve as the similarity measure of the ith registration iteration.

Step 2022B, obtaining a similarity measure of the target image with N registration iterations of the reference image before the i-th registration iteration and/or after the i-th registration iteration.

Wherein N is an integer greater than 0. The similarity measure for the N registration iterations includes a similarity measure for the target image and the reference image for each of the N registration iterations.

Step 2022B includes the following three cases:

in the first case, the similarity measure of the target image and the reference image N registration iterations before the ith registration iteration is acquired in a plurality of ways, and the following is exemplified:

(1) In one embodiment, the obtaining a similarity measure of N registration iterations before the ith registration iteration of the target image and the reference image may specifically include: and obtaining a similarity measure of any N iterations before the ith registration iteration of the target image and the reference image. For example, n=5, when the target image is located at the target registration position in the 10 th registration iteration, the similarity measure of the 1 st registration iteration, the similarity measure of the 3 rd registration iteration, the similarity measure of the 6 th registration iteration, the similarity measure of the 7 th registration iteration, and the similarity measure of the 8 th registration iteration may be obtained, which are the similarity measures of the 5 th registration iteration in total.

(2) In an embodiment, the obtaining a similarity measure of N registration iterations before the ith registration iteration of the target image and the reference image may further specifically include: and obtaining similarity measurement from the ith-N to the ith-1 registration iteration of the target image and the reference image. Wherein N is greater than i. For example, n=5, when the target image is located at the target registration position in the 10 th registration iteration, the similarity measure of the 5 th registration iteration, the similarity measure of the 6 th registration iteration, the similarity measure of the 7 th registration iteration, the similarity measure of the 8 th registration iteration, and the similarity measure of the 9 th registration iteration may be obtained, which are the similarity measures of the 5 th registration iteration in total.

In the second case, the similarity measure of the target image and the reference image is obtained for N registration iterations after the ith registration iteration.

Specifically, the method comprises the following steps: and obtaining similarity measurement of the target image and the ith (i+1) th to (i+N) th registration iteration of the reference image. There are various ways to obtain the similarity measure of the i+1th to i+nth registration iterations of the target image and the reference image, and the following are exemplified:

(1) In one embodiment, obtaining the similarity measure of the target image and the i+1st to i+nth registration iteration of the reference image may specifically include: performing local search on a preset area in the target image, namely searching any N target areas in the preset area, and respectively calculating similarity measurement of the target area and a reference area from the (i+1) th registration iteration to the (i+N) th registration iteration to serve as similarity measurement of the N registration iterations; the preset area is an image area in a preset range in the target image, and the image area comprises the target area searched during the ith registration iteration.

(2) In one embodiment, obtaining the similarity measure of the target image and the i+1st to i+nth registration iteration of the reference image may specifically include: performing global search on a preset area in a target image, namely traversing and searching the whole preset area, and respectively calculating similarity measurement of the target area and a reference area from the (i+1) th registration iteration to the (i+N) th registration iteration to serve as the similarity measurement of the N registration iterations; the preset area is an image area in a preset range in the target image, and the image area comprises the target area searched during the ith registration iteration.

In the third case, similarity measures of N registration iterations before the ith registration iteration and after the ith registration iteration of the target image and the reference image are acquired, and various acquisition modes exist.

In some embodiments, the obtaining the similarity measure of the target image and the reference image for N registration iterations before the ith registration iteration and after the ith registration iteration may specifically include steps e 1-e 2:

and e1, obtaining similarity measurement of the i-n1 th to i-1 th registration iteration of the target image and the reference image.

Wherein n1 is an integer of i or less.

For example, n=5, n1=3, the target image is located at the target registration position at the 10 th registration iteration, and the similarity measure of the 7 th registration iteration, the similarity measure of the 8 th registration iteration, and the similarity measure of the 9 th registration iteration can be obtained, which are the similarity measures of the 3 th registration iteration in total.

And e2, obtaining similarity measurement of the i+1th to i+n2 th registration iteration of the target image and the reference image.

Wherein N2 is an integer greater than 0, and the sum of N1 and N2 is N.

Similar to the similarity measure of the N registration iterations after the i-th registration iteration of the target image and the reference image, there are also various ways of obtaining the similarity measure of the i+1th to i+n2-th registration iterations of the target image and the reference image, as will be explained below.

In one embodiment, obtaining a similarity measure of the target image and the i+1st to i+n2nd registration iteration of the reference image may specifically include: performing local search on a preset area in the target image, namely searching any N target areas in the preset area, and respectively calculating similarity metrics of the target area and a reference area from the (i+1) th to the (i+n 2) th registration iteration to obtain similarity metrics of the N2 registration iterations; the preset area is an image area in a preset range in the target image, and the image area comprises the target area searched during the ith registration iteration.

In one embodiment, obtaining a similarity measure of the target image and the i+1st to i+n2nd registration iteration of the reference image may specifically include: performing the (i+1) -th to (i+n2) -th registration iterations on a preset region in the target image, and respectively calculating similarity metrics of the target region and a reference region during the (i+1) -th to (i+n2) -th registration iterations to obtain the similarity metrics of the n 2-th registration iterations; the preset area is an image area in a preset range in the target image, and the image area comprises the target area searched during the ith registration iteration.

In some embodiments, the obtaining the similarity measure of the target image and the reference image before the ith registration iteration and after the ith registration iteration for N registration iterations may specifically include steps f 1-f 2:

and f1, acquiring similarity measurement of any n1 iterations before the ith registration iteration of the target image and the reference image.

Wherein n1 is an integer of i or less. The similarity measure of any N1 iterations before the ith registration iteration of the target image and the reference image is similar to the similarity measure of any N iterations before the ith registration iteration of the target image and the reference image, and specific reference may be made to the above description and examples, and details are not repeated here.

And f2, obtaining similarity measurement of the i+1st to i+n2 th registration iteration of the target image and the reference image.

Wherein N2 is an integer greater than 0, and the sum of N1 and N2 is N. Step b2 is similar to step a2, and reference may be made to the description and examples of step a2, which are not repeated here.

Step 2023B, determining the fluctuation degree of the n+1 similarity metrics according to the similarity metrics of the ith registration iteration and the similarity metrics of the N registration iterations.

In the embodiment of the application, a plurality of ways of determining the fluctuation degree of the n+1 similarity measures are available, for example, the variance of the n+1 similarity measures, the standard deviation of the n+1 similarity measures, the range of the n+1 similarity measures, the quarter-bit difference of the n+1 similarity measures, the average difference of the n+1 similarity measures or the variation coefficient of the n+1 similarity measures can be used as the fluctuation degree of the n+1 similarity measures.

Taking n+1 similarity measures obtained by the i-N1 th to i+n2 th registration iterations of the target image and the reference image as an example, how to calculate the variance of the n+1 similarity measures, the standard deviation of the n+1 similarity measures, the range of the n+1 similarity measures, the quartile range of the n+1 similarity measures, the average difference of the n+1 similarity measures or the variation coefficient of the n+1 similarity measures are respectively described below.

1. Variance: is one of the most commonly used measures of the degree of fluctuation of data. The variance (sample variance) is the average of the squared values of the differences between each sample value and the average of the total sample values.

As shown in fig. 4, the similarity metrics of the 1 st to 9 th registration iterations of the target image and the reference image are respectively: 0.5, 0.6, 0.5, 0.7, 0.6, 0.9, 0.8, 0.1, 0.

For example, i=6, n=4, n+1=5, n1=2, n2=2. If the target image is located at the target registration position during the 6 th registration iteration, taking the similarity measure of the 6 th registration iteration, the similarity measure of the 2 registration iterations before the 6 th registration iteration, and the similarity measure of the 2 registration iterations after the 6 th registration iteration, and obtaining 5 similarity measures of the 4 th to 8 th registration iterations as follows: 0.7, 0.6, 0.9, 0.8, 0.1.

At this time, the average of 5 similarity measures is: (0.7+0.6+0.9+0.8+0.1)/5=0.62, the variance of 5 similarity measures can be calculated as: [ (0.7-0.62) ² +(0.6-0.62) ² +(0.9-0.62) ² +(0.8-0.62) ² +(0.1-0.62) ² ]/5＝0.097

2. Standard deviation: and is one of the most commonly used measures for measuring the degree of fluctuation of data. The standard deviation is obtained by taking the square of the variance.

At this time, the standard deviation of the 5 similarity measures is:

3. extremely bad: also called full distance, the difference between the maximum value and the minimum value in the data set can reflect the discrete condition of the data set to a certain extent.

At this time, the extreme differences of the 5 similarity measures are: 0.9-0.1=0.8.

4. Average difference: is one of the numerical values representing the degree of difference between the respective variable values, and may reflect the degree of fluctuation of a set of data to some extent. The average difference is the arithmetic mean of the absolute value of the dispersion of all units of the population from its arithmetic mean.

At this time, (n+1) =5 average differences of similarity metrics are: 0.216.

5. coefficient of variation: the method is used for measuring the fluctuation degree of classified data and measuring the representing degree of the mode to a group of data. The coefficient of variation is the ratio of the standard deviation of the raw data to the average of the raw data.

At this time, the coefficient of variation of the 5 similarity measures is:

the variance, standard deviation, polar difference, quarter-bit difference, average difference or variation coefficient represent that the fluctuation degree of the n+1 similarity measures has respective advantages, and the actual application can be selected according to the requirements, and of course, other statistical measures capable of reflecting the fluctuation degree can also be selected.

Step 2024B, determining a target confidence level of the target registration position according to the fluctuation degrees of the n+1 similarity metrics.

Wherein the target confidence is positively correlated with the degree of fluctuation of the n+1 similarity metrics.

Determining the target confidence coefficient of the target registration position according to the fluctuation degree of the n+1 similarity measures may specifically include: and determining the target confidence coefficient of the target registration position according to the preset relation between the fluctuation degree and the confidence coefficient and the fluctuation degree of the N+1 similarity measures.

In one embodiment, the preset relationship between the degree of fluctuation and the confidence level may be represented by a preset relationship map. Illustratively, the degree of fluctuation and the confidence level have the relationship shown in the following table 1, and if the degree of fluctuation of the n+1 similarity measures is 0.005 or less, it can be determined that the target confidence level is 0; if the degree of fluctuation of the n+1 similarity measures is 0.05 or more, the target confidence level may be determined to be 1.

TABLE 1

Degree of fluctuation	Confidence level
0.005 or less	0
0.015	0.3
0.02	0.6
...	...
0.05 or more	1

In one embodiment, the predetermined relationship between the degree of fluctuation and the confidence level may be represented by a predetermined functional relationship. Illustratively, there is a functional relationship between the degree of fluctuation and the confidence level as follows: y=f (x) =20×x. Where y represents the confidence level and x represents the degree of fluctuation. If the degree of fluctuation of the n+1 similarity measures is 0.01, the target confidence level can be determined to be 0.2.

In the embodiment of the application, the intensity of the change between the similarity measurement of the target registration position and the similarity measurement of other positions can reflect the registration accuracy of the target registration position to a certain extent. The degree of fluctuation of the data can reflect the degree of intensity of change of the data, and the confidence level of the target registration position is determined according to the degree of fluctuation between N+1 similarity measures (including the similarity measures of N other positions and the similarity measure of the target registration position) so as to evaluate the accuracy of image registration at the target registration position, so that the single similarity measure can be prevented from being relied on as a measurement standard of image registration, and the accuracy of an image registration result is improved to a certain extent.

(3) The confidence rating factors include the rate of change of the similarity measure.

Since the fluctuation degree (i.e., the intensity of the change) of the numerical value is proportional to the fluctuation amplitude and inversely proportional to the time of the amplitude change, the fluctuation amplitude is divided by the time of the amplitude change, which is physically the change speed, and the change speed of the numerical value is still proportional to the fluctuation degree. Therefore, the change speed between the similarity measure of the target registration position and the similarity measure of other positions can reflect the intensity of the change between the similarity measure of the target registration position and the similarity measure of other positions to a certain extent, and further can reflect the registration accuracy of the target registration position to a certain extent.

When the confidence evaluation factor includes a rate of change of the similarity measure, as shown in fig. 8, step 202 may specifically include steps 2021C to 2024C:

2021C, obtaining a similarity measure of the target image and the ith registration iteration of the reference image.

And in the ith registration iteration, the target image is positioned at a target registration position, and i is an integer greater than 0. Step 2021C is similar to step 2021B, and reference may be made to the description and examples of step 2021B, which are not repeated herein.

2022C, obtaining a similarity measure of the target image with N registration iterations of the reference image before the i-th registration iteration and/or after the i-th registration iteration.

Wherein N is an integer greater than 0. Step 2022C is similar to step 2022B described above, and reference may be made to the description and examples of step 2022B described above, which are not repeated herein.

2023C, determining the change speed of the n+1 similarity measures according to the similarity measure of the ith registration iteration and the similarity measure of the N registration iterations.

In some embodiments, determining the change speed of the n+1 similarity metrics according to the similarity metric of the ith registration iteration and the similarity metric of the N registration iterations may specifically include: constructing a change curve of n+1 similarity measures according to the similarity measure of the ith registration iteration and the similarity measure of the N registration iterations; obtaining each segment derivative of the change curve; and obtaining the sum of absolute values of the derivative of each segment as the change speed of the N+1 similarity measures.

Since the fluctuation degree of the curve is proportional to the fluctuation amplitude and inversely proportional to the time of the amplitude change, the fluctuation amplitude is divided by the time of the amplitude change, i.e. the slope in a physical sense. Thus, the slope of the curve formed between the n+1 similarity measures may be used to reflect the rate of change of the n+1 similarity measures.

In the embodiment of the application, in order to observe the change speed of N+1 similarity measures, a plurality of observation points are extracted from the change curves of the N+1 similarity measures, and a section is formed between two adjacent observation points; the slope of each segment is calculated to determine the rate of change of the n+1 similarity measures.

The piecewise derivative refers to the slope between two adjacent observation points in the change curve of the n+1 similarity measures.

Taking n+1 similarity measures obtained by the i-N1 th to i+n2 th registration iterations of the target image and the reference image and the similarity measure of each registration iteration as an observation point as an example, how to calculate the change speed of the n+1 similarity measures is described below.

With continued reference to fig. 4, for example, i=6, n=4, n+1=5, n1=2, n2=2. If the target image is located at the target registration position during the 6 th registration iteration, taking the similarity measure of the 6 th registration iteration, the similarity measure of the 2 registration iterations before the 6 th registration iteration, and the similarity measure of the 2 registration iterations after the 6 th registration iteration, and obtaining 5 similarity measures of the 4 th to 8 th registration iterations as follows: 0.7, 0.6, 0.9, 0.8, 0.1.

According to 5 similarity metrics: 0.7, 0.6, 0.9, 0.8, and 0.1, a change curve of the similarity measure at points P4 to P8 as shown in fig. 4 can be constructed. Wherein P4, P5, P6, P7, P8 represent similarity measures for the 4 th, 5 th, 6 th, 7 th, 8 th registration iterations, respectively.

At this time, the segment derivative is the slope between the point where the similarity measure of the x-th registration iteration is located and the point where the similarity measure of the x+1th registration iteration is located in the change curve of the similarity measure. Wherein x is more than or equal to 4 and less than or equal to 7. I.e. between P4 and P5, between P5 and P6, between P7 and P8, respectively.

The slope between points P4 and P5 was calculated separately: (0.7-0.6)/1=0.1, slope between points P5 and P6: slope between points (0.6-0.9)/1= -0.3, P6 and P7: (0.9-0.8)/1=0.1, slope between points P7 and P8: (0.8-0.1)/1=0.7. And calculates the sum of the absolute values of the respective segment derivatives: 0.1+| -0.3|+0.1+0.7=1.2 as the rate of change of 5 similarity measures.

2024C, determining the target confidence level of the target registration position according to the change speed of the n+1 similarity measures.

Wherein the target confidence is positively correlated with the rate of change of the n+1 similarity metrics.

In some embodiments, determining the target confidence level of the target registration position according to the change speed of the n+1 similarity metrics may specifically include: and determining the target confidence coefficient of the target registration position according to the preset relation between the change speed and the confidence coefficient and the change speeds of the N+1 similarity measures.

In one embodiment, the preset relationship between the speed of change and the confidence level may be represented by a preset relationship map. Illustratively, the change speed and the confidence exist in the relationship shown in the following table 2, and if the change speed of the n+1 similarity measures is 1.1, it can be determined that the target confidence is 0.1; if the rate of change of the n+1 similarity measures is 1.3, then the target confidence level can be determined to be 0.3.

TABLE 2

Speed of change	Confidence level
1.1	0.1
1.2	0.2

1.3	0.3
...	...

In one embodiment, the preset relationship between the rate of change and the confidence level may be represented by a preset functional relationship. Illustratively, there is a functional relationship between the rate of change and the confidence level as follows: y=f (x) =0.1×x. Where y represents the confidence and x represents the rate of change. If the change speed of the n+1 similarity measures is 1.1, the target confidence level can be determined to be 0.11.

In the embodiment of the application, the intensity of the change between the similarity measurement of the target registration position and the similarity measurement of other positions can reflect the registration accuracy of the target registration position to a certain extent. The data change speed can reflect the change intensity of the data, and the confidence coefficient of the target registration position is determined according to the change speed between N+1 similarity measures (including the similarity measures of N other positions and the similarity measure of the target registration position) so as to evaluate the accuracy of image registration at the target registration position, so that the single similarity measure can be prevented from being relied on as a measurement standard of image registration, and the accuracy of an image registration result is improved to a certain extent.

Further, in order to improve accuracy of image registration evaluation, two or three of the target confidence coefficient determined when the confidence coefficient evaluation factor is the similarity measure, the target confidence coefficient determined when the confidence coefficient evaluation factor is the fluctuation degree of the similarity measure, and the target confidence coefficient determined when the confidence coefficient evaluation factor is the change speed of the similarity measure may be added according to a certain weight ratio, so as to be used as the target confidence coefficient of the final target registration position.

For example, the target confidence determined when the confidence evaluation factor is the similarity measure is 0.9, the target confidence determined when the confidence evaluation factor is the degree of fluctuation of the similarity measure is 0.8, and the target confidence determined when the confidence evaluation factor is the rate of change of the similarity measure is 0.8. According to a preset weighting formula h=0.4xh1+0.3xh2+0.3xh3, the target confidence of the final target registration position can be determined as follows: 0.4 x 0.9+0.3 x 0.8+0.3 x 0.8=0.84.

Wherein h1, h2, h3 respectively represent the target confidence coefficient determined when the confidence coefficient evaluation factor is the similarity measure, the target confidence coefficient determined when the confidence coefficient evaluation factor is the fluctuation degree of the similarity measure, and the target confidence coefficient determined when the confidence coefficient evaluation factor is the change speed of the similarity measure, and h represents the target confidence coefficient of the final target registration position. The weight coefficients of h1, h2 and h3 of 0.4, 0.3 and 0.3 respectively, and the weight coefficients of h1, h2 and h3 can be adjusted according to practical situations and requirements, which are only examples and not limited thereto.

In some embodiments of the present application, in order to improve the referenceability of the image registration result, when the similarity between the target image and the preset reference image satisfies the position when the preset registration condition, that is, when the target registration position, if the target confidence coefficient of the target pre-registration position is higher, the image registration result is output. And if the target confidence coefficient of the target registration position is lower, not outputting an image registration result. So as to avoid the user from adopting the image registration result with lower accuracy and even error to further process the image.

That is, in some embodiments of the present application, after step 202, it may further include: detecting whether the target confidence coefficient is larger than or equal to a preset confidence coefficient threshold value; and when the target confidence coefficient is detected to be greater than or equal to the preset confidence coefficient threshold value, displaying an image registration result, wherein the image registration result comprises a target registration position of the target image and/or the target image and the reference image after registration.

Further, in order to facilitate the user to know the image registration, when the target confidence coefficient is detected to be smaller than the preset confidence coefficient threshold value, prompt information indicating that the image registration accuracy of the target image and the reference image is low is output.

For example, the range of the target confidence is 0% -100%, the higher the confidence coefficient is, the higher the accuracy of the image registration result is represented, and when the target confidence coefficient is smaller than a preset confidence coefficient threshold value such as 50%, the information amount of the image data to be registered is considered to be insufficient, and the image registration result is not displayed. And when the target confidence is greater than or equal to 50%, displaying an image registration result, such as displaying a target registration position of the target image and/or displaying the registered target image and the reference image.

The preset confidence threshold may be set according to actual requirements, which is not limited herein.

Further, if the target confidence of the target registration position is low, the image registration result is not automatically displayed, but the user can autonomously select to display the image registration result. At this time, the step of outputting the hint information indicating that the image registration accuracy of the target image and the reference image is low further includes, after: acquiring a display instruction for requesting to display an image registration result; and displaying an image registration result of the target image and the reference image.

In some embodiments of the present application, the image registration results of the target image and the reference image are displayed regardless of the image registration results, and the target confidence of the target registration position is displayed. So that the user can know the accuracy of the displayed image registration result and determine whether to adopt the displayed image registration result for further image processing according to actual requirements. That is, in some embodiments of the present application, after step 202, it may further include: and displaying an image registration result of the target image and the reference image, and displaying the target confidence.

In order to better implement the image registration evaluation method in the embodiment of the present application, an image registration evaluation device is further provided in the embodiment of the present application, as shown in fig. 5, where the image registration evaluation device 500 includes:

an obtaining unit 501, configured to obtain a target registration position of a target image, where the target registration position refers to a position when a similarity between the target image and a preset reference image in a registration process meets a preset registration condition;

an evaluation unit 502, configured to determine a target confidence coefficient of the target registration position according to a confidence coefficient evaluation factor, so as to evaluate accuracy of image registration, where the confidence coefficient evaluation factor is a plurality of factors for evaluating accuracy of image registration.

In some embodiments of the present application, the evaluation unit 502 is specifically configured to:

A similarity measure of the target image and the reference image is obtained from the (i+1) th to (i+n2) th registration iteration, N2 is an integer of 0, and the sum of N1 and N2 is the N.

obtaining each segment derivative of the change curve;

In some embodiments of the present application, the image registration evaluation apparatus 500 further includes a display unit (not shown in the figure), and after the step of determining the target confidence level of the target registration position according to the confidence level evaluation factor, the display unit is specifically configured to:

In some embodiments of the present application, the image registration evaluation apparatus 500 further includes a prompt unit (not shown in the figure), where the display prompt is specifically configured to:

In the implementation, each unit may be implemented as an independent entity, or may be implemented as the same entity or several entities in any combination, and the implementation of each unit may be referred to the foregoing method embodiment, which is not described herein again.

Since the image registration evaluation device can execute the steps in the image registration evaluation method in any embodiment of the present application, the beneficial effects that can be achieved by the image registration evaluation method in any embodiment of the present application can be achieved, and detailed descriptions are omitted herein.

In addition, in order to better implement the image registration evaluation method in the embodiment of the present application, on the basis of the image registration evaluation method, the embodiment of the present application further provides an electronic device, which integrates any one of the image registration evaluation apparatuses provided in the embodiment of the present application, and the electronic device includes:

one or more processors;

a memory;

and one or more applications, wherein the one or more applications are stored in the memory and configured to perform the steps of the image registration evaluation method described in any of the above embodiments of the image registration evaluation method by the processor.

The embodiment of the application also provides electronic equipment which integrates any one of the image registration evaluation methods provided by the embodiment of the application. As shown in fig. 6, a schematic structural diagram of an electronic device according to an embodiment of the present application is shown, specifically:

The electronic device may include one or more processing cores 'processors 601, one or more computer-readable storage media's memory 602, power supply 603, and input unit 604, among other components. It will be appreciated by those skilled in the art that the electronic device structure shown in fig. 6 is not limiting of the electronic device and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components. Wherein:

the processor 601 is a control center of the electronic device, connects various parts of the entire electronic device using various interfaces and lines, and performs various functions of the electronic device and processes data by running or executing software programs and/or modules stored in the memory 602, and calling data stored in the memory 602, thereby performing overall monitoring of the electronic device. Optionally, the processor 601 may include one or more processing cores; preferably, the processor 601 may integrate an application processor and a modem processor, wherein the application processor primarily handles operating systems, user interfaces, applications, etc., and the modem processor primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 601.

The memory 602 may be used to store software programs and modules, and the processor 601 may execute various functional applications and data processing by executing the software programs and modules stored in the memory 602. The memory 602 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data created according to the use of the electronic device, etc. In addition, the memory 602 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 602 may also include a memory controller to provide access to the memory 602 by the processor 601.

The electronic device further comprises a power supply 603 for supplying power to the various components, preferably the power supply 603 may be logically connected to the processor 601 by a power management system, so that functions of charging, discharging, power consumption management and the like are managed by the power management system. The power supply 603 may also include one or more of any components, such as a direct current or alternating current power supply, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like.

The electronic device may further comprise an input unit 604, which input unit 604 may be used for receiving input digital or character information and for generating keyboard, mouse, joystick, optical or trackball signal inputs in connection with user settings and function control.

Although not shown, the electronic device may further include a display unit or the like, which is not described herein. In particular, in this embodiment, the processor 601 in the electronic device loads executable files corresponding to the processes of one or more application programs into the memory 602 according to the following instructions, and the processor 601 executes the application programs stored in the memory 602, so as to implement various functions as follows:

Those of ordinary skill in the art will appreciate that all or a portion of the steps of the various methods of the above embodiments may be performed by instructions, or by instructions controlling associated hardware, which may be stored in a computer-readable storage medium and loaded and executed by a processor.

To this end, an embodiment of the present application provides a computer-readable storage medium, which may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disk, and the like. On which a computer program is stored, which computer program is loaded by a processor for performing the steps of any of the image registration evaluation methods provided by the embodiments of the present application. For example, the loading of the computer program by the processor may perform the steps of:

In the foregoing embodiments, the descriptions of the embodiments are focused on, and the portions of one embodiment that are not described in detail in the foregoing embodiments may be referred to in the foregoing detailed description of other embodiments, which are not described herein again.

In the implementation, each unit or structure may be implemented as an independent entity, or may be implemented as the same entity or several entities in any combination, and the implementation of each unit or structure may refer to the foregoing method embodiment and will not be repeated herein.

The specific implementation of each operation above may be referred to the previous embodiments, and will not be described herein.

The foregoing describes in detail an image registration evaluation method, apparatus, electronic device and computer readable storage medium provided by the embodiments of the present application, and specific examples are applied to illustrate the principles and embodiments of the present application, where the foregoing examples are only used to help understand the method and core idea of the present application; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in light of the ideas of the present application, the present description should not be construed as limiting the present application.

Claims

An image registration evaluation method, characterized in that the image registration evaluation method comprises:

acquiring a target registration position of a target image, wherein the target registration position refers to a position when the similarity between the target image and a preset reference image meets a preset registration condition in a registration process;

And determining the target confidence coefficient of the target registration position according to a confidence coefficient evaluation factor to evaluate the accuracy of image registration, wherein the confidence coefficient evaluation factor is a plurality of factors for evaluating the accuracy of image registration.
The image registration evaluation method according to claim 1, wherein the confidence evaluation factor includes at least one of a similarity measure, a change speed of the similarity measure, and a degree of fluctuation of the similarity measure.
The image registration evaluation method according to claim 2, wherein in the case where the confidence evaluation factor includes a degree of fluctuation of a similarity measure, the determining the target confidence of the target registration position according to the confidence evaluation factor includes:

obtaining similarity measurement of the target image and the ith registration iteration of the reference image, wherein the target image is positioned at the target registration position in the ith registration iteration, and i is an integer greater than 0;

obtaining similarity measures of N registration iterations before the ith registration iteration and/or after the ith registration iteration of the target image and the reference image, wherein N is an integer greater than 0;

Determining the fluctuation degree of n+1 similarity measures according to the similarity measure of the ith registration iteration and the similarity measure of the N registration iterations;

and determining the target confidence coefficient of the target registration position according to the fluctuation degree of the N+1 similarity measures.
The image registration evaluation method according to claim 3, wherein the acquiring a similarity measure of N registration iterations before the ith registration iteration of the target image and the reference image comprises:

and obtaining similarity measurement from the ith-N times to the ith-1 times of registration iteration of the target image and the reference image, wherein N is smaller than or equal to i.
The image registration evaluation method according to claim 3, wherein the obtaining a similarity measure of N registration iterations after the ith registration iteration of the target image and the reference image comprises:

and obtaining similarity measurement of the target image and the ith (i+1) th to (i+N) th registration iteration of the reference image, wherein N is larger than i.
The image registration evaluation method according to claim 3, wherein the acquiring a similarity measure of the target image with N registration iterations before the i-th registration iteration and after the i-th registration iteration of the reference image includes:

Obtaining similarity measurement of the ith-n 1 th to ith-1 st registration iteration of the target image and the reference image, wherein n1 is an integer less than or equal to i;

and obtaining a similarity measure of the target image and the reference image from the (i+1th) to the (i+n2) th registration iteration, wherein N2 is an integer greater than 0, and the sum of N1 and N2 is the N.
The image registration evaluation method according to claim 3, wherein the degree of fluctuation of the n+1 similarity metrics is determined by any one of the following means:

a variance of the n+1 similarity metrics, a standard deviation of the n+1 similarity metrics, a range of the n+1 similarity metrics, a quartile range of the n+1 similarity metrics, an average difference of the n+1 similarity metrics, or a coefficient of variation of the n+1 similarity metrics.
The image registration evaluation method according to claim 2, wherein in a case where the confidence evaluation factor includes a change speed of a similarity measure, the determining the target confidence of the target registration position according to the confidence evaluation factor includes:

obtaining similarity measurement of the target image and the ith registration iteration of the reference image, wherein the target image is positioned at the target registration position in the ith registration iteration, and i is an integer greater than 0;

Obtaining similarity measures of N registration iterations before the ith registration iteration and/or after the ith registration iteration of the target image and the reference image, wherein N is an integer greater than 0;

determining the change speed of n+1 similarity measures according to the similarity measure of the ith registration iteration and the similarity measure of the N registration iterations;

and determining the target confidence coefficient of the target registration position according to the change speed of the N+1 similarity measures.
The image registration evaluation method according to claim 8, wherein the determining a change speed of n+1 similarity measures from the similarity measure of the i-th registration iteration and the similarity measure of the N registration iterations includes:

constructing a change curve of n+1 similarity measures according to the similarity measure of the ith registration iteration and the similarity measure of the N registration iterations;

obtaining each segment derivative of the change curve;

and obtaining the sum of absolute values of the derivative of each segment as the change speed of the N+1 similarity measures.
The image registration evaluation method according to claim 1, wherein the determining the target confidence level of the target registration position according to a confidence level evaluation factor, further comprises:

Detecting whether the target confidence coefficient is larger than or equal to a preset confidence coefficient threshold value;

and when the target confidence coefficient is detected to be greater than or equal to the preset confidence coefficient threshold value, displaying an image registration result, wherein the image registration result comprises a target registration position of the target image and/or the target image and the reference image after registration.
The image registration evaluation method according to claim 10, further comprising:

and outputting prompt information indicating that the image registration accuracy of the target image and the reference image is low when the target confidence coefficient is detected to be smaller than the preset confidence coefficient threshold value.
The image registration evaluation method according to claim 11, wherein the outputting of the hint information indicating that the image registration accuracy of the target image with the reference image is low further includes:

acquiring a display instruction for requesting to display an image registration result;

and displaying an image registration result of the target image and the reference image.
The image registration evaluation method according to claim 1, wherein the determining the target confidence level of the target registration position according to a confidence level evaluation factor, further comprises:

And displaying an image registration result of the target image and the reference image, and displaying the target confidence.
An image registration evaluation device, characterized in that the image registration evaluation device comprises:

the device comprises an acquisition unit, a registration unit and a registration unit, wherein the acquisition unit is used for acquiring a target registration position of a target image, and the target registration position refers to a position when the similarity between the target image and a preset reference image meets a preset registration condition in a registration process;

and the evaluation unit is used for determining the target confidence coefficient of the target registration position according to a confidence coefficient evaluation factor so as to evaluate the accuracy of image registration, wherein the confidence coefficient evaluation factor is a plurality of factors for evaluating the accuracy of image registration.
An electronic device comprising a processor and a memory, the memory having stored therein a computer program, the processor executing the image registration evaluation method according to any one of claims 1 to 13 when invoking the computer program in the memory.
A computer-readable storage medium, having stored thereon a computer program, the computer program being loaded by a processor to perform the steps of the image registration evaluation method of any one of claims 1 to 13.