CN108256565A - A kind of adaptive masterplate matching process and device based on cross entropy distinctiveness ratio - Google Patents

Abstract

The present application discloses an adaptive template matching method based on cross-entropy dissimilarity, which includes: determining the effective range of coordinates and the initial value of the coordinates of the matching starting point of the image to be recognized; within the effective range of coordinates, successively follow the preset translation direction Adjust the matching starting point with the translation amount, and calculate the dissimilarity to obtain the corresponding dissimilarity value of each matching starting point; determine the minimum value of all dissimilarity values; according to the matching starting point corresponding to each minimum value The coordinates of the starting point determine the position of the matching target in the image to be recognized; wherein, the translation amount has the same increase or decrease as the dissimilarity value corresponding to each matching starting point. The present application adaptively adjusts the translation amount according to the cross-entropy dissimilarity, which can effectively improve the matching speed while ensuring the matching accuracy. The present application also discloses an adaptive template matching device, equipment and computer-readable storage medium based on cross-entropy dissimilarity, which also have the above beneficial effects.

Description

A self-adaptive template matching method and device based on cross-entropy dissimilarity

technical field

The present application relates to the technical field of image recognition, and in particular to an adaptive template matching method, device, equipment and computer-readable storage medium based on cross-entropy dissimilarity.

Background technique

Since template matching is one of the most representative and commonly used methods in image recognition, how to effectively improve the performance of template matching algorithms is of great significance for the study of whether there is a matching target in the image to be recognized.

The algorithm idea of template matching is to sequentially move and select the local area with the same shape and size as the template image of the matching target from the image to be recognized, so as to match and compare with the template image, calculate the degree of difference or similarity between the two, and then determine the Whether there is a matching target in the local area is judged.

The main criterion for controlling the translation of the local area during the template matching process is to cover all the pixels of the image to be recognized as much as possible after multiple translations. In the prior art, the matching speed is generally increased by increasing the number of pixels translated each time in the local area. However, if the number of pixels translated is increased blindly globally, the positioning accuracy of the matching target will be reduced. Therefore, the matching speed and matching accuracy in the prior art are often a pair of irreconcilable contradictions.

It can be seen that what kind of adaptive template matching method to use so as to simultaneously solve the speed problem and the precision problem in the template matching process is a technical problem to be solved urgently by those skilled in the art.

Contents of the invention

The purpose of the present application is to provide an adaptive template matching method, device, equipment and computer-readable storage medium based on cross-entropy dissimilarity, so as to effectively improve the matching speed while ensuring the matching accuracy.

In order to solve the above technical problems, this application provides an adaptive template matching method based on cross-entropy dissimilarity, including:

Determine the effective range of coordinates and the initial value of the coordinates of the matching starting point of the image to be recognized;

Within the effective range of the coordinates, adjust the coordinates of the matching starting point successively according to the preset translation direction and translation amount, and perform difference calculation with the template image of the matching target, so as to obtain the corresponding difference of each matching starting point degree value;

determining a minimum value among all said dissimilarity values;

determining the position of the matching target in the image to be recognized according to the coordinates of the matching starting point corresponding to each of the minimum values;

Wherein, each of the translation amounts has the same increase or decrease as the dissimilarity value corresponding to each matching starting point; the calculation expression of the dissimilarity is:

Wherein, the pixel size of the template image is a×b; p(i, j) is the gray value of the template image at point coordinates (i, j); a, b, i and j are all positive integers , and 1≤i≤a, 1≤j≤b; (x, y) is the coordinate of the matching starting point of the image to be recognized; q(x+i, y+j) is the image to be recognized Gray value at point coordinates (x+i, y+j); f(x, y) is the dissimilarity value corresponding to the matching starting point (x, y).

Optionally, the preset translation direction is column translation.

Optionally, the calculation expression of the translation amount is:

Wherein, h is the translation amount, and is a positive integer; δ is the mean value of the dissimilarity values obtained by matching a plurality of sample images containing the matching target with the template image; c is a preset coefficient, c ≥1; [t] is the integer part of t.

Optionally, the determining the position of the matching target in the image to be recognized according to the coordinates of the matching starting point corresponding to each of the minimum values includes:

judging whether the distance between the matching starting points corresponding to two adjacent minimum values is lower than a preset distance threshold;

If so, it is determined that the image to be recognized has a matching target at the matching starting point corresponding to the smaller value of the two adjacent minimum values;

If not, it is determined that there is one matching target in the image to be recognized at the matching starting points respectively corresponding to the two adjacent minimum values.

Optionally, the preset distance threshold includes a preset lateral distance threshold and a preset longitudinal distance threshold;

The judging whether the distance between the matching starting points corresponding to two adjacent minimum values is lower than the preset distance threshold includes:

Judging whether the lateral distance between the matching starting points corresponding to the two adjacent minimum values is lower than the preset lateral distance threshold, or the distance between the matching starting points corresponding to the two adjacent minimum values The longitudinal distance is lower than the preset longitudinal distance threshold.

The present application also provides an adaptive template matching device based on cross-entropy dissimilarity, including:

The first determining module: used to determine the effective range of coordinates and the initial value of the coordinates of the matching starting point of the image to be recognized;

Matching module: used to adjust the coordinates of the matching starting point successively according to the preset translation direction and translation amount within the effective range of the coordinates, and perform dissimilarity calculation with the template image of the matching target, so as to obtain each matching starting point The corresponding dissimilarity value;

The second determining module: used to determine the minimum value among all the dissimilarity values; and determine the position of the matching target in the image to be recognized according to the coordinates of the matching starting point corresponding to each of the minimum values;

Wherein, each of the translation amounts has the same increase or decrease as the dissimilarity value corresponding to each matching starting point; the calculation expression of the dissimilarity is:

Wherein, the pixel size of the template image is a×b; p(i, j) is the gray value of the template image at point coordinates (i, j); a, b, i and j are all positive integers , and 1≤i≤a, 1≤j≤b; (x, y) is the coordinate of the matching starting point of the image to be recognized; q(x+i, y+j) is the image to be recognized Gray value at point coordinates (x+i, y+j); f(x, y) is the dissimilarity value corresponding to the matching starting point (x, y).

Optionally, the preset translation direction is column translation.

Optionally, the calculation expression of the translation amount is:

Wherein, h is the translation amount, and is a positive integer; δ is the mean value of the dissimilarity values obtained by matching a plurality of sample images containing the matching target with the template image; c is a preset coefficient, c ≥1; [t] is the integer part of t.

The present application also provides an adaptive template matching device based on distance measure dissimilarity, including:

memory: used to store computer instructions;

Processor: for executing the computer instructions to implement the steps of any adaptive template matching method based on distance measure dissimilarity as described above.

The present application also provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any one of the distance-based dissimilarity measures described above can be realized. Steps of an adaptive template matching method.

The adaptive template matching method based on cross-entropy dissimilarity provided by the present application includes: determining the effective range of coordinates and the initial value of the coordinates of the matching starting point of the image to be recognized; within the effective range of the coordinates, successively follow the preset translation direction Adjust the coordinates of the matching starting point and the translation amount, and perform dissimilarity calculation with the template image of the matching target, so as to obtain the corresponding dissimilarity value of each matching starting point; determine the extreme value of all the dissimilarity values A small value; determine the position of the matching target in the image to be recognized according to the coordinates of the matching starting points corresponding to each of the minimum values; wherein, each of the translation amounts and the corresponding degree of difference of each matching starting point The values have the same increase and decrease; the calculation expression of the dissimilarity is:

Wherein, the pixel size of the template image is a×b; p(i, j) is the gray value of the template image at point coordinates (i, j); a, b, i and j are all positive integers , and 1≤i≤a, 1≤j≤b; (x, y) is the coordinate of the matching starting point of the image to be recognized; q(x+i, y+j) is the image to be recognized Gray value at point coordinates (x+i, y+j); f(x, y) is the dissimilarity value corresponding to the matching starting point (x, y).

It can be seen that, compared with the prior art, in the self-adaptive template matching method based on cross-entropy dissimilarity provided by the present application, a simple and effective cross-entropy dissimilarity is used to judge the local area of the image to be recognized and the template image Then, according to the size of the dissimilarity value, the translation amount is adaptively adjusted when the matching starting point of the local area is translated, so that the translation amount can be increased in the area with high dissimilarity value, and the translation amount can be increased in the area with low dissimilarity value The area of the algorithm reduces the amount of translation, thereby effectively improving the matching speed while ensuring the matching accuracy. The cross-entropy dissimilarity-based adaptive template matching device, equipment, and computer-readable storage medium provided by the present application can realize the above-mentioned adaptive template matching method based on cross-entropy dissimilarity, and also have the above-mentioned beneficial effects.

Description of drawings

In order to illustrate the prior art and the technical solutions in the embodiments of the present application more clearly, the following briefly introduces the drawings that need to be used in the description of the prior art and the embodiments of the present application. Of course, the following drawings related to the embodiments of the application describe only a part of the embodiments of the application, and those of ordinary skill in the art can obtain other The accompanying drawings, and other obtained drawings also belong to the protection scope of the present application.

FIG. 1 is a flow chart of an adaptive template matching method based on cross-entropy dissimilarity provided by an embodiment of the present application;

FIG. 2 is a structural block diagram of an adaptive template matching device based on cross-entropy dissimilarity provided by an embodiment of the present application.

Detailed ways

The core of the present application is to provide an adaptive template matching method, device, equipment and computer-readable storage medium based on cross-entropy dissimilarity, so as to effectively improve the matching speed while ensuring the matching accuracy.

In order to describe the technical solutions in the embodiments of the present application more clearly and completely, the technical solutions in the embodiments of the present application will be introduced below in conjunction with the drawings in the embodiments of the present application. Apparently, the described embodiments are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

Please refer to FIG. 1. FIG. 1 is a flow chart of an adaptive template matching method based on cross-entropy dissimilarity provided by the embodiment of the present application, which mainly includes the following steps:

Step 1: Determine the effective range of coordinates and the initial value of the coordinates of the matching starting point of the image to be recognized.

Specifically, when the dissimilarity calculation is performed after a local area is selected, starting from the matching starting point of the local area, traversal is performed in the local area in units of 1 pixel, and according to all The difference between the gray value of the pixel and the gray value of the pixel of the template image is calculated. When performing template matching, in order to sequentially compare the local area selected from the image to be recognized with each pixel of the template image, it is necessary to set the origin and a unified coordinate axis direction for the image to be recognized and the template image respectively. Generally, the upper left vertices of the image to be recognized and the template image can be set as their respective origins, and then the horizontal to the right and vertical downward can be set to the abscissa direction and the ordinate direction respectively. Since the local area covers multiple pixel points, the matching starting point can generally be used to measure the position of the local area. Similarly, generally, the pixel point of the upper left vertex of the local area is used as the matching start point.

The coordinates of the matching starting point represent the range of the corresponding local area, that is, when the pixel size of the template image is a×b and the coordinates of the matching starting point of the image to be recognized are (x, y), the local area corresponding to the matching starting point The area is the area with the pixel point (x, y) as the upper left vertex, the vertical length is a, and the horizontal length is b. Moreover, in order to prevent the local area from exceeding the scope of the image to be recognized, the coordinates of the matching starting point should have a valid range of coordinates. When the matching starting point is translated within the effective range of the coordinates, the corresponding local area will not exceed the range of the image to be identified, and the image to be identified can be covered after multiple translations along the preset translation direction.

For example, if the pixel size of the image to be recognized is A×B, in order to prevent the local area from exceeding the range of the image to be recognized, the matching starting point can be made within the effective range of the coordinates of (A-a)×(B-b) in the image to be recognized. order translation; and the initial coordinates of the corresponding coordinate starting point are (1,1).

Step 2: Within the valid range of coordinates, adjust the coordinates of the matching starting point successively according to the preset translation direction and translation amount, and according to the formula

Calculate the dissimilarity with the template image of the matching target to obtain the dissimilarity corresponding to each matching starting point, and each translation amount has the same increase or decrease as the dissimilarity value corresponding to each matching starting point.

Among them, the pixel size of the template image is a×b; p(i, j) is the gray value of the template image at point coordinates (i, j); a, b, i and j are all positive integers, and 1≤ i≤a, 1≤j≤b; (x, y) is the coordinate of the matching starting point of the image to be recognized; q(x+i, y+j) is the point coordinate of the image to be recognized at (x+i, y+ The gray value at j); f(x, y) is the dissimilarity value corresponding to the matching starting point (x, y).

The adaptive template matching algorithm provided by the embodiment of the present application calculates the degree of dissimilarity based on cross entropy. Cross-entropy is an important concept in Shannon's information theory. It is mainly used to measure the difference information between two probability distributions. In feature engineering, it can be used to measure the difference between two random variables. The dissimilarity calculated based on cross-entropy is not only simple but also effective, and is especially suitable for image recognition applications with significant cross-entropy characteristics of pixel gray values.

Specifically, the preset translation direction can be selected and set by those skilled in the art according to actual application conditions. For example, when the upper left vertex is taken as the coordinate origin, the matching start point can be shifted row by row from the coordinate start point, or it can be shifted column by column. Column-to-column translation means to translate the matching starting point in the column from top to bottom (with the upper left vertex as the origin), and when it reaches the bottom of the column, switch to the top of the next column and continue to pan down; row-to-row translation Specifically, it means that the matching starting point is translated from left to right in the row (when the upper left vertex is used as the origin), and when the translation reaches the right end of the column, then switch to the next row and continue to translate to the right. Then when the matching start point is translated within the effective range of coordinates of (A-a)×(B-b), the coordinates after it is translated again must fall outside the valid range of the coordinates. Therefore, the matching starting point can be specifically The coordinate is not within the valid range of the coordinate as the default termination condition.

In addition, the translation amount of the matching starting point is specifically adaptive to the same increase or decrease as the value of the dissimilarity. When the dissimilarity value corresponding to the current matching starting point is large, it means that the local area selected at this time has a large difference from the template image, and the possibility of matching the target is low. The amount of translation in order to increase the matching speed appropriately. When the dissimilarity value corresponding to the current matching starting point is small, it means that the local area selected at this time is not much different from the template image, and the possibility of saving the matching target is high. Therefore, each translation can be appropriately reduced In order to ensure the recognition accuracy of matching targets.

Step 3: Determine the minimum value among all dissimilarity values.

Step 4: Determine the position of the matching target in the image to be recognized according to the coordinates of the matching starting point corresponding to each minimum value.

Specifically, after step 3 determines that the preset termination condition is met, the position of the matching target in the image to be recognized can be determined according to the historically stored dissimilarity values. The embodiment of the present application specifically determines the position of the matching target based on the minimum value: according to the physical meaning of the minimum value, the image to be recognized is likely to exist at the matching start point corresponding to the minimum value or in the area between to match the target.

It can be seen that in the self-adaptive template matching method based on cross-entropy dissimilarity provided by the embodiment of the present application, a simple and effective cross-entropy dissimilarity is used to judge the degree of matching between the local area of the image to be recognized and the template image, and then Adaptively adjust the translation amount when translating the matching starting point of the local area according to the size of the dissimilarity value, so that the translation amount is increased in the area with a high dissimilarity value, and the translation is decreased in an area with a low dissimilarity value Therefore, the matching speed can be effectively improved while ensuring the matching accuracy.

The adaptive template matching method based on cross-entropy dissimilarity provided by this application, on the basis of the above-mentioned embodiments:

As a preferred embodiment, the preset translation direction is column translation.

Specifically, the column-oriented translation method commonly used in the computer field can generally be selected to update the matching starting point. Certainly, those skilled in the art may also adopt other manners, which are not limited in this embodiment of the present application.

As a preferred embodiment, the calculation expression of translation amount is:

Among them, h is the translation amount, and it is a positive integer; δ is the average value of the dissimilarity value obtained by matching multiple sample images containing matching targets with the template image; c is the preset coefficient, c≥1; [t] is to take the integer part of t.

As mentioned above, specifically, a column-wise translation method can be used. Specifically, the translation amount h can be made to change proportionally with the ratio of the dissimilarity value f(x, y) to δ, and the proportional coefficient, ie, the preset coefficient c, can be preset by those skilled in the art. Since generally at least one pixel point should be translated, c should be at least greater than or equal to 1. δ represents the general average level of the matching results between the sample image containing the matching object and the template image, wherein the sample image is an image containing the matching object randomly selected.

Certainly, those skilled in the art may also use other methods to calculate the translation amount h, which is not limited in the present application.

When the column-oriented translation method is used, the translation amount h after each update can be limited in size to prevent the translation amount h from being too large and skipping some regions containing the matching target, which affects the matching accuracy. Specifically, the translation amount h can be set to be not greater than the vertical length a of the template image, that is, 1≤h≤a. When ensuring the magnitude of the translation amount h, specifically, a saturation function can be used for processing.

As a preferred embodiment, determining the position of the matching target in the image to be recognized according to the coordinates of the matching starting point corresponding to each minimum value includes:

Judging whether the distance between the matching starting points corresponding to two adjacent minimum values is lower than the preset distance threshold;

If so, it is determined that there is a matching target at the matching starting point corresponding to the smaller value of the adjacent two minimum values in the image to be recognized;

If not, it is determined that there is a matching target in the image to be recognized at the matching start points corresponding to the two adjacent minimum values respectively.

Specifically, in the adaptive template matching method based on cross-entropy dissimilarity provided in the embodiment of the present application, when determining the matching target according to each dissimilarity value, the determination is specifically based on the minimum value. In order to distinguish whether the image to be recognized has a matching target at the matching starting point (local area) corresponding to a certain minimum value, or in the area between matching starting points corresponding to multiple minimum values, the present application In this embodiment, the distance between matching starting points corresponding to two adjacent minimum values is judged.

If the distance is less than the preset distance threshold, it means that the two matching starting points are very close to each other, which should belong to the above-mentioned second situation. The specific position of the matching target described by these two minimum values can be determined by the smaller value of the two adjacent minimum values, that is, there is a matching target at the matching starting point corresponding to the smaller value . Assuming that the coordinates of the matching start point corresponding to the smaller value are (x1, y1), the position coordinates of the center of the matching target can be regarded as (x1+a/2, y1+b/2).

If the distance between the matching starting points corresponding to the two adjacent minimum values is not less than the preset distance threshold, it means that the two matching starting points are far apart, which should belong to the first case above. Therefore, it can be determined that there is a matching target at the matching start points corresponding to the two minimum values in the image to be recognized.

As a preferred embodiment, the preset distance threshold includes a preset horizontal distance threshold and a preset longitudinal distance threshold;

Judging whether the distance between the matching start points corresponding to two adjacent minimum values is lower than the preset distance threshold includes:

Judging whether the horizontal distance between the matching start points corresponding to two adjacent minimum values is lower than the preset horizontal distance threshold, or whether the vertical distance between the matching starting points corresponding to two adjacent minimum values is lower than the preset Set the vertical distance threshold.

Specifically, the preset distance thresholds used in the embodiment of the present application include two preset horizontal distance thresholds and preset vertical distance thresholds, which are respectively used to judge the horizontal distance and vertical distance corresponding to the matching starting point of two minimum values. And, specifically, the preset horizontal distance threshold and the preset vertical distance threshold may be respectively set as the horizontal length b and the vertical length a of the template image. Certainly, those skilled in the art may also select and set other thresholds by themselves, which is not limited in the embodiments of the present application.

The following is an introduction to the adaptive template matching device based on the cross-entropy dissimilarity provided by the embodiment of the present application.

Please refer to FIG. 2. FIG. 2 is a structural block diagram of an adaptive template matching device based on cross-entropy dissimilarity provided by the present application; it includes a first determination module 1, a matching module 2 and a second determination module 3;

The first determination module 1 is used to determine the effective range of coordinates and the initial value of the coordinates of the matching starting point of the image to be recognized;

The matching module 2 is used to adjust the coordinates of the matching starting point successively according to the preset translation direction and translation amount within the effective range of the coordinates, and perform difference calculation with the template image of the matching target, so as to obtain the corresponding matching starting point. Differential value;

The second determination module 3 is used to determine the minimum value in all dissimilarity values; and determine the position of the matching target in the image to be recognized according to the coordinates of the matching starting point corresponding to each minimum value;

Among them, each translation amount has the same increase or decrease as the dissimilarity value corresponding to each matching starting point; the calculation expression of the dissimilarity is:

Among them, the pixel size of the template image is a×b; p(i, j) is the gray value of the template image at point coordinates (i, j); a, b, i and j are all positive integers, and 1≤ i≤a, 1≤j≤b; (x, y) is the coordinate of the matching starting point of the image to be recognized; q(x+i, y+j) is the point coordinate of the image to be recognized at (x+i, y+ The gray value at j); f(x, y) is the dissimilarity value corresponding to the matching starting point (x, y).

It can be seen that the self-adaptive template matching device based on cross-entropy dissimilarity provided by the present application uses simple and effective cross-entropy dissimilarity to judge the degree of matching between the local area of the image to be recognized and the template image, and then according to the dissimilarity The size of the degree value is adapted to adjust the translation amount when the matching starting point of the local area is translated, so that the translation amount is increased in the area with a high dissimilarity value, and the translation amount is decreased in the area with a low dissimilarity value. This can effectively improve the matching speed while ensuring the matching accuracy.

The adaptive template matching device based on cross-entropy dissimilarity provided by this application, on the basis of the above-mentioned embodiments:

As a preferred embodiment, the preset translation direction is column translation.

As a preferred embodiment, the calculation expression of translation amount is:

Among them, h is the translation amount, and it is a positive integer; δ is the average value of the dissimilarity value obtained by matching multiple sample images containing matching targets with the template image; c is the preset coefficient, c≥1; [t] is to take the integer part of t.

The present application also provides an adaptive template matching device based on distance measure dissimilarity, including:

memory: used to store computer instructions;

Processor: used to execute the computer instructions to implement the steps of any one of the above-mentioned adaptive template matching methods based on distance measure dissimilarity.

The present application also provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any one of the above-mentioned methods based on distance measure dissimilarity can be realized. Steps of an adaptive template matching method.

The specific implementations of the adaptive template matching device, device, and computer-readable storage medium based on distance measure dissimilarity provided in this application may correspond to the above-described adaptive template matching method based on distance measure dissimilarity For reference, I won’t go into details here.

The specific implementations of the cross-entropy dissimilarity-based adaptive template matching device, equipment, and computer-readable storage medium provided in this application may correspond to the cross-entropy dissimilarity-based adaptive template matching method described above. Reference here will not repeat them.

Each embodiment in the present application is described in a progressive manner, each embodiment focuses on the differences from other embodiments, and the same and similar parts of the various embodiments can be referred to each other. As for the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and for the related part, please refer to the description of the method part.

It should also be noted that in this application, relative terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between such entities or operations. Furthermore, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or apparatus comprising a set of elements includes not only those elements, but also includes elements not expressly listed. other elements of or also include elements inherent in such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising said element.

The technical solution provided by the present application has been introduced in detail above. In this paper, specific examples are used to illustrate the principles and implementation methods of the present application, and the descriptions of the above embodiments are only used to help understand the methods and core ideas of the present application. It should be pointed out that those skilled in the art can make some improvements and modifications to the application without departing from the principles of the application, and these improvements and modifications also fall within the protection scope of the claims of the application.

Claims (10)

1. a kind of adaptive masterplate matching process based on cross entropy distinctiveness ratio, which is characterized in that including：

Determine the coordinate effective range of the matching starting point of images to be recognized and coordinate initial value；

In the coordinate effective range, gradually according to default translation direction and the seat of the translational movement adjustment matching starting point Mark, and the template image with matching target carries out distinctiveness ratio calculating, to obtain the distinctiveness ratio corresponding to each matching starting point Value；

Determine the minimum in all different angle value；

It determines to match target in the images to be recognized according to the corresponding coordinate for matching starting point of each minimum Position；

Wherein, each translational movement has identical monotonicity with the different angle value corresponding to each matching starting point； The calculation expression of the distinctiveness ratio is：

Wherein, the pixel size of the template image is a × b；P (i, j) is ash of the template image at point coordinates (i, j) Angle value；A, b, i and j are positive integer, and 1≤i≤a, 1≤j≤b；(x, y) is that the matching of the images to be recognized originates The coordinate of point；Q (x+i, y+j) is gray value of the images to be recognized at point coordinates (x+i, y+j)；F (x, y) be with it is described Match the corresponding different angle value of starting point (x, y).

2. adaptive masterplate matching process according to claim 1, which is characterized in that the default translation direction for row to Translation.

3. adaptive masterplate matching process according to claim 2, which is characterized in that the calculation expression of the translational movement For：

Wherein, h is the translational movement, and is positive integer；δ is multiple sample images containing the matching target and the template Image match the mean value of obtained different angle value；C is predetermined coefficient, c >=1；[t] is the integer part for taking t.

4. adaptive masterplate matching process according to any one of claims 1 to 3, which is characterized in that described according to each The position that the corresponding coordinate for matching starting point of the minimum determines to match target in the images to be recognized includes：

Judge the distance between matching starting point corresponding to the two neighboring minimum whether less than pre-determined distance threshold value；

If so, judge the matching starting point corresponding to smaller value of the images to be recognized in the two neighboring minimum There are a matching targets at place；

If it is not, then judge that the images to be recognized is deposited respectively in the two neighboring corresponding matching starting point of minimum In a matching target.

5. adaptive template matching process according to claim 4, which is characterized in that the pre-determined distance threshold value includes pre- If lateral distance threshold value and default fore-and-aft distance threshold value；

Whether the distance between described matching starting point judged corresponding to two neighboring minimum is less than pre-determined distance threshold value packet It includes：

Judge whether that the lateral distance between the matching starting point corresponding to the two neighboring minimum is less than the default horizontal stroke It is default less than described to the fore-and-aft distance between the matching starting point corresponding to distance threshold or the two neighboring minimum Fore-and-aft distance threshold value.

6. a kind of adaptive masterplate coalignment based on cross entropy distinctiveness ratio, which is characterized in that including：

First determining module：For determining the coordinate effective range of the matching starting point of images to be recognized and coordinate initial value；

Matching module：For in the coordinate effective range, gradually adjusting described according to default translation direction and translational movement Coordinate with starting point, and the template image with matching target carries out distinctiveness ratio calculating, to obtain each matching starting point institute Corresponding different angle value；

Second determining module：For determining the minimum in all different angle value；And distinguished according to each minimum The coordinate of corresponding matching starting point determines to match the position of target in the images to be recognized；

Wherein, each translational movement has identical monotonicity with the different angle value corresponding to each matching starting point； The calculation expression of the distinctiveness ratio is：

Wherein, the pixel size of the template image is a × b；P (i, j) is ash of the template image at point coordinates (i, j) Angle value；A, b, i and j are positive integer, and 1≤i≤a, 1≤j≤b；(x, y) is that the matching of the images to be recognized originates The coordinate of point；Q (x+i, y+j) is gray value of the images to be recognized at point coordinates (x+i, y+j)；F (x, y) be with it is described Match the corresponding different angle value of starting point (x, y).

7. adaptive masterplate coalignment according to claim 6, which is characterized in that the default translation direction for row to Translation.

8. adaptive masterplate coalignment according to claim 7, which is characterized in that the calculation expression of the translational movement For：

Wherein, h is the translational movement, and is positive integer；δ is multiple sample images containing the matching target and the template Image match the mean value of obtained different angle value；C is predetermined coefficient, c >=1；[t] is the integer part for taking t.

9. a kind of adaptive masterplate matching unit based on cross entropy distinctiveness ratio, which is characterized in that including：

Memory：For storing computer instruction；

Processor：For performing the computer instruction cross entropy phase is based on as described in any one of claim 1 to 5 to realize The step of adaptive masterplate matching process of different degree.

10. a kind of computer readable storage medium, which is characterized in that be stored with computer in the computer readable storage medium Program is realized when the computer program is executed by processor as described in any one of claim 1 to 5 different based on cross entropy The step of adaptive masterplate matching process of degree.