WO2021195873A1

WO2021195873A1 - Method and device for identifying region of interest in sfr test chart image, and medium

Info

Publication number: WO2021195873A1
Application number: PCT/CN2020/082153
Authority: WO
Inventors: 胡友华
Original assignee: 南昌欧菲光电技术有限公司
Priority date: 2020-03-30
Filing date: 2020-03-30
Publication date: 2021-10-07

Abstract

The present application relates to a method and device for identifying a region of interest in an SFR test chart image, and a medium. The method comprises: acquiring an SFR test chart image; calculating edge contours of a black test block in the SFR test chart image; calculating the coordinates of the centroid of the edge contours; determining, according to distances between contour points on the edge contours and the centroid, the vertex coordinates of the black test block; and determining a region of interest according to the vertex coordinates of the black test block and a preset region-of-interest constraint value.

Description

Method, device and medium for identifying region of interest in SFR test card image

Technical field

The present invention relates to the field of image technology, in particular to a method for recognizing a region of interest in an image of an SFR test card, a device for recognizing a region of interest in an image of an SFR test card, and a non-temporary computer storage medium.

Background technique

With the rapid development of digital images, cameras have been widely used in people's lives. Camera performance testing has become very important in design and production. Testing the resolution of the camera is a necessary part of the camera performance test.

The spatial frequency response SFR (Spatial Frequency Response) test card has a white background, as shown in Figure 1, which includes a number of obliquely distributed black blocks, and the area of interest is centered on a certain hypotenuse of the designated black block Determine the spatial frequency response SFR of the designated black block according to the region of interest, so as to evaluate the resolution of the camera under test according to the spatial frequency response SFR of the designated black block.

In related technologies, for determining the region of interest in an image, some solutions require the user to manually mark the region of interest, but the application of this method has limitations and the operation is more troublesome. Or, some solutions determine the area of interest of the SFR test card through a preset configuration file. However, when the position of the field of view changes with this method, the coordinates of the determined area of interest may not meet the requirements of the spatial frequency response SFR algorithm. Regional requirements affect the accuracy of the spatial frequency response SFR algorithm.

Summary of the invention

The present invention aims to solve at least one of the technical problems existing in the prior art.

One of the objectives of this application is to propose a method for recognizing the region of interest in the image of the SFR test card, which can realize the automatic recognition of the region of interest and improve the accuracy of the results of the SFR algorithm.

The second purpose of this application is to propose a non-temporary computer storage medium.

The third purpose of this application is to provide a device for identifying the region of interest in the image of the SFR test card.

In order to solve the above-mentioned problems, the method for identifying the region of interest in the SFR test card image provided by the embodiment of the first aspect of the present application includes: acquiring an SFR test card image; calculating the edge contour of the test black block in the SFR test card image; Calculate the centroid coordinates of the edge contour; determine the vertex coordinates of the test black block according to the distance between the contour point of the edge contour and the centroid; according to the vertex coordinates of the test black block and the set constraint value of the region of interest Determine the region of interest.

According to the method of identifying the region of interest in the SFR test card image according to the embodiment of the present application, the edge contour of the test black block in the SFR test card image and the centroid coordinates of the edge contour are calculated, and the distance between the contour point of the edge contour and the centroid is used to determine The vertex coordinates of the test black block are combined with the set constraint value of the region of interest to calculate the vertex coordinates of the region of interest, so as to realize the automatic recognition of the region of interest in the SFR test card image, without manual alignment, saving time and effort , The accuracy is high, and, compared with the method of determining the region of interest of the SFR test card by using a preset configuration file, the method of the embodiment of the present application uses the distance between the contour point of the edge contour and the centroid to determine the test black block Vertex coordinates, based on the vertex coordinates of the test black block to identify the region of interest, where the determination of the test black block position is not affected by the change of the field of view and the field of view, that is, it can be determined when the field of view or the field of view changes. The location of the black block is tested, so as to realize self-adaptive automatic recognition, avoid the problem of inaccurate calculation values due to fixed coordinates of the region of interest, and improve the accuracy of the SFR algorithm results.

In some embodiments, before calculating the edge contour of the test black block in the SFR test card image, the method further includes: graying and binarizing the SFR test card image to remove the image The color in the middle and black and white are helpful to test the recognition of the edge contour of the black block.

In some embodiments, after calculating the edge contour of the test black block in the SFR test card image, the method further includes: calculating the area enclosed by the edge contour; obtaining the first area whose area is greater than the first preset area threshold. A type of contour and a second type of contour whose area is smaller than a second preset area threshold; the first type of contour and the second type of contour are removed from all the calculated edge contours to reduce non-test black The interference of block edge contours improves the accuracy of the SFR algorithm results.

In some embodiments, after calculating the edge contour of the test black block in the SFR test card image, the method further includes: calculating the maximum x coordinate and the minimum x coordinate of the edge contour point of each test black block. Coordinates, the maximum y coordinate and the minimum y coordinate; calculate the x coordinate difference between the maximum x coordinate and the minimum x coordinate, and obtain the first type contour and all the contours whose x coordinate difference is greater than the first preset difference threshold The second-type contour whose x-coordinate difference is less than a second preset difference threshold, remove the first-type contour and the second-type contour from all the calculated edge contours; calculate the maximum y-coordinate The difference between the y-coordinate and the minimum y-coordinate to obtain the first-type contour whose y-coordinate difference is greater than the first preset difference threshold and the second-type contour whose y-coordinate difference is less than the second preset difference threshold Class contour, removing the first class contour and the second class contour from all the calculated edge contours.

In some embodiments, determining the vertex coordinates of the test black block according to the distance between the contour point of the edge contour and the centroid includes the steps of: calculating the distance between two contour points in the edge contour; The two contour points with the smallest distance are selected from the contour, and the distance between the two contour points and the centroid is calculated, and the two contour points with the smallest distance from the centroid are removed from the contour points of the edge contour Repeat this step until there are four remaining contour points in the edge contour; use the coordinates of the remaining four contour points as the coordinates of the four vertices of the test black block, so that it is not affected by the field of view and the view The influence of field angle changes is conducive to the automatic identification and adaptation of black blocks.

In some embodiments, before determining the vertex coordinates of the test black block according to the distance between the contour point of the edge contour and the centroid, the method further includes: simplifying the edge contour to obtain the pre-defined edge contour. Setting a number of contour points is beneficial to reduce the amount of calculation and improve the calculation efficiency of the vertex coordinates of the black block.

In some embodiments, determining the region of interest according to the vertex coordinates of the test black block and the set constraint value of the region of interest includes the step of: calculating the test according to the four vertex coordinates of the test black block The coordinates of the center point of each side of the black block; taking the coordinates of the center point as the diagonal center point of the region of interest, calculate the area of interest according to the set length and width pixel values of the region of interest Vertex coordinates to realize automatic recognition of the region of interest.

In some embodiments, determining the region of interest according to the vertex coordinates of the test black block and the set constraint value of the region of interest includes the step of: calculating the test according to the four vertex coordinates of the test black block The coordinates of the center point of each side of the black block and the length of the contour side; calculate the length of the region of interest according to the side length of the contour and the ratio of the length and width of the region of interest to the length of the contour side. Width pixel value; taking the center point coordinates as the diagonal center point of the region of interest, calculate the vertex coordinates of the region of interest according to the set length and width pixel values of the region of interest to realize automatic recognition Region of interest.

In some embodiments, determining the region of interest according to the vertex coordinates of the test black block and the set constraint value of the region of interest includes the step of: calculating the coordinates of every two points according to the four vertex coordinates of the test black block. The slope of the straight line where the vertices are located and the inclination angle of the straight line and the coordinate axis; find the inclination angle of the straight line and the coordinate axis as the preset inclination angle and the straight line equation passing through the midpoint of the two vertices; The midpoint of the two vertices is taken as the intersection of the diagonals of the rectangle, and the straight line obtained by the straight line equation is taken as a diagonal bisector of the rectangle, and the four pixels of the rectangle are calculated according to the preset length and width pixel values of the region of interest. Vertex coordinates; the image content is intercepted according to the coordinates of the vertices of the rectangle, and the image content is rotated as a whole by a preset angle as the image content of the region of interest.

A non-transitory computer storage medium according to an embodiment of the second aspect of the present application has a computer program stored thereon, and when the computer program is executed, the method for identifying a region of interest in an image of an SFR test card described in the foregoing embodiment is implemented.

An apparatus for identifying a region of interest in an image of an SFR test card according to an embodiment of the third aspect of the present application includes: a display for displaying the image of the SFR test card; a processor and a memory connected in communication with the processor; The memory stores instructions that can be executed by the processor, and when the instructions are executed by the processor, the processor executes the method for identifying the region of interest in the SFR test card image described in the foregoing embodiment.

According to the device for recognizing the region of interest in the image of the SFR test card according to the embodiment of the present application, the method for recognizing the region of interest in the image of the SFR test card provided by the above-mentioned embodiment is executed by the processor to realize the detection of the region of interest in the image of the SFR test card. Automatic recognition, no manual alignment is required, and the problem of inaccurate calculation of the coordinates of the region of interest can be avoided, and the accuracy of the results of the SFR algorithm can be improved.

The additional aspects and advantages of the present invention will be partly given in the following description, and partly will become obvious from the following description, or be understood through the practice of the present invention.

Description of the drawings

The above and/or additional aspects and advantages of the present invention will become obvious and easy to understand from the description of the embodiments in conjunction with the following drawings, in which:

Fig. 1 is a schematic diagram of black blocks in an image of an SFR test card according to an embodiment of the present application;

Fig. 2 is a flowchart of a method for identifying a region of interest in an image of an SFR test card according to an embodiment of the present application;

Fig. 3 is a schematic diagram of a region of interest in an image of an SFR test card according to an embodiment of the present application;

4 is a schematic diagram of a region of interest in an image of an SFR test card according to another embodiment of the present application;

Fig. 5 is a structural block diagram of a device for identifying a region of interest in an image of an SFR test card according to an embodiment of the present application.

Reference signs:

Device 1 for identifying the region of interest in the image of the SFR test card; display 2; processor 3; memory 4.

Detailed ways

The embodiments of the present invention are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals indicate the same or similar elements or elements with the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary, and are only used to explain the present invention, but should not be understood as limiting the present invention.

In order to have a more detailed understanding of the features and technical content of the embodiments of the present disclosure,

The implementation of the embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. The attached drawings are for reference and description purposes only, and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a number of details are used to provide a sufficient understanding of the disclosed embodiments. However, without these details, one or more embodiments can still be implemented. In other cases, in order to simplify the drawings, well-known structures and devices may be simplified for display.

The following describes a method for identifying a region of interest in an image of an SFR test card according to an embodiment of the present application with reference to the accompanying drawings. This method can realize automatic identification of the region of interest and improve the accuracy of the SFR algorithm result.

Fig. 2 shows a flowchart of a method for identifying a region of interest in an image of an SFR test card provided by an embodiment of the application. As shown in FIG. 2, the method for identifying the region of interest in the image of the SFR test card in the embodiment of the present application at least includes steps S1-S5.

Step S1: Obtain an image of the SFR test card.

Among them, the SFR test card is a card with a white background and multiple black test blocks as shown in Figure 1. In actual operation, the image of the SFR test card can be captured by an imaging device such as a camera to determine the sense of the image. The region of interest, the region of interest is used as the image area for analysis, used to calculate the MTF value and other purposes.

Step S2: Calculate the edge contour of the test black block in the SFR test card image.

The method of the embodiment of the present application realizes the automatic recognition of the region of interest by determining the position of the test black block in the SFR test card image. Therefore, the edge of the test black block needs to be defined, that is, the edge contour of the test black block needs to be extracted. The edge contour refers to the boundary line between the black block and the white background in the SFR test card image.

Specifically, it can be achieved by extracting the edge of the image and then extracting the corresponding boundary, in which edge detection algorithms such as Scharr operator, Sobels operator, Canny operator, Laplacian operator, etc. can be used to extract the edge of the image, and then through edge tracking Algorithms, such as the Square tracking algorithm, realize the extraction of the corresponding boundary of the image to generate the edge contour of the test black block. Or adopt the image gradient algorithm to form the edge contour by calculating and statistics the gradient direction histogram of the local area of the image, or adopt other algorithms to obtain the edge contour of the test black block, which is not limited.

Step S3: Calculate the centroid coordinates of the edge contour.

In the embodiment, calculation can be performed by using a method such as a sub-pixel centroid positioning algorithm, a binarized centroid positioning algorithm, or a weighted binarized centroid positioning algorithm, etc., to obtain the centroid coordinates of the edge contour. Specifically, an appropriate selection can be made according to the actual situation. The algorithm of this embodiment is not limited and fixed here.

Step S4: Determine the vertex coordinates of the test black block according to the distance between the contour point of the edge contour and the centroid.

In an embodiment, the test black block may be a square, and the vertex coordinates of the test black block are the contour points with the largest distance from the center of mass. Obtaining the vertex coordinates of the test black block is to calculate the distance between each contour point and the center of mass, and determine the distance between each contour point and the center of mass. The four contour points with the largest distance are the vertex coordinates of the test black block.

In an embodiment, by calculating the distance between the two contour points in the edge contour, the two contour points with the smallest distance can be selected from the edge contour, and the distance between the two contour points and the centroid can be calculated, from the two contour points Remove a contour point with a small distance from the center of mass and keep a contour point with a large distance from the center of mass. Repeat this step until there are four remaining contour points in the edge contour, so that the coordinates of the remaining four contour points are used as the four points of the test black block. Vertex coordinates.

Therefore, by adopting the method of determining the vertex coordinates of the test black block in the SFR test card image of the embodiment of the present application, the position of the test black block can still be determined when the field of view is changed, such as when part of the image is cropped. It is not affected by the range of the field of view, and when the field of view of several consecutive photos changes due to autofocus, the vertex coordinates of the test black block can also be automatically recognized, so that the changes in the coordinates of the region of interest can also be automatically recognized and adapted. This avoids the problem of inaccurate calculated values caused by the fixed coordinates of the region of interest, which is beneficial to improve the accuracy of the SFR algorithm.

Step S5: Determine the region of interest according to the vertex coordinates of the test black block and the set constraint value of the region of interest.

Among them, the SFR algorithm has certain requirements for the region of interest. For example, the width of the region of interest is 40-120 pixels, and the height is 80-300 pixels. The width B is greater than 5 pixels. Therefore, in the embodiment of the present application, the constraint value of the region of interest can be set. For example, the set constraint value of the region of interest can include a preset length and width pixel value or a preset length and width. The ratio of the side length of the silhouette, etc.

Specifically, calculate the center point coordinates of each side of the test black block according to the coordinates of the four vertices of the test black block; take the center point coordinates as the diagonal center point of the area of interest, and calculate according to the set constraint value of the area of interest The vertex coordinates of the region of interest are used to determine the region of interest and realize the automatic recognition of the region of interest.

According to the method for identifying the region of interest in the SFR test card image according to the embodiment of the present application, the edge contour of the test black block in the SFR test card image and the centroid coordinates of the edge contour are calculated, and the distance between the contour point of the edge contour and the centroid is used to determine the test The vertex coordinates of the black block are combined with the set constraint values of the region of interest to calculate the vertex coordinates of the region of interest, so as to realize the automatic recognition of the region of interest in the SFR test card image, without the need for manual and precise alignment. At the same time, compared with the method of determining the region of interest of the SFR test card by using a preset configuration file, the method of the embodiment of the present application uses the distance between the contour point of the edge contour and the centroid to determine the vertex coordinates of the test black block, based on the test The vertex coordinates of the black block identify the region of interest, where the determination of the test black block position is not affected by the field of view range and field angle changes, that is, the test black block position can also be determined when the field of view range or field angle changes. In this way, adaptive automatic recognition can be realized, the problem of inaccurate calculated values caused by fixed coordinates of the region of interest can be avoided, and the accuracy of the results of the SFR algorithm can be improved.

In the embodiment, before calculating the edge contour of the test black block in the SFR test card image, the method in the embodiment of the present application further includes performing grayscale and binarization processing on the SFR test card image. Specifically, grayscale processing is performed on the acquired SFR test card image to generate a corresponding grayscale image. In the grayscale processing process, the component method, maximum value method, average method, or weighted average method can be used. Furthermore, the 256 brightness levels of the grayscale image are selected by selecting appropriate thresholds to obtain a binarized image that can still reflect the overall and local characteristics of the image, that is, through grayscale processing, the image loses color, and then the binarization process , Make the image appear black and white, which is more conducive to the recognition of the edge contour of the black block in the SFR image.

In the embodiment, in order to reduce the interference of other edge contours except the test black block, the method of the embodiment of the present application, after calculating the edge contour of the test black block in the SFR test card image, further includes: Area, to obtain the first type contour whose area is larger than the first preset area threshold and the second type contour whose area is smaller than the second preset area threshold, and then remove the first type contour and the second type contour from all the edge contours calculated , That is, remove the edge contours of the SFR test card image except for the test black block.

Or, in an embodiment, the method of the present application further includes calculating the maximum x-coordinate, the minimum x-coordinate, the maximum y-coordinate, and the minimum y-coordinate of the edge contour point of each test black block, and then the maximum x-coordinate and the minimum x-coordinate are calculated. The x coordinate difference of the coordinates, the first type of contour whose x coordinate difference is greater than the first preset difference threshold and the second type of contour whose x coordinate difference is less than the second preset difference threshold are obtained in all the calculated edges Remove the first-type contour and the second-type contour from the contour, and calculate the y-coordinate difference between the maximum y-coordinate and the minimum y-coordinate to obtain the first-type contour and the y-coordinate difference whose y-coordinate difference is greater than the first preset difference threshold For contours of the second type whose value is less than the second preset difference threshold, the contours of the first type and the second type are removed from all the calculated edge contours. That is, by comparing the side length of the edge contour with the preset threshold, remove the other edge contours except the test black block in the SFR test card image. For example, the edge contour can be a square, and calculate the maximum x coordinate, minimum x coordinate, and The maximum y coordinate and the minimum y coordinate are obtained, and the difference between the x coordinate and the y coordinate is obtained, which is the length of the side of the square, and the first type of contour with the larger side length and the second type of contour with the smaller side length are obtained. Remove the first type contour and the second type contour in all the edge contours, so as to remove the other edge contours in the SFR image except the test black block. In short, the method of the embodiment of the present application compares the area and/or side length of the edge contour with a preset threshold to remove the excessively large and small edge contours in the SFR test card image, which can be retained to the greatest extent Test the edge contour of the black block, so as to avoid the interference of the edge contour of the non-test black block.

In the embodiment, before determining the vertex coordinates of the test black block according to the distance between the contour point of the edge contour and the centroid, the method of the embodiment of the present application further includes simplifying the edge contour to obtain a preset number of contour points in the edge contour. That is, the number of contour points included in the edge contour is smaller than a certain threshold to simplify the edge contour, thereby facilitating rapid calculation of the vertex coordinates of the test black block, reducing the amount of calculation, and improving the calculation efficiency.

In the embodiment, the area of interest corresponding to the test black block includes two types, one is the area parallel to the edge of the SFR test card image, as shown in Figure 3; the other is the sense of a certain angle with the test black block. The region of interest, for example, an area where one side is substantially parallel to the hypotenuse of the edge contour of the test black block, and the other side is substantially perpendicular to the hypotenuse of the edge contour of the test black block, as shown in FIG. 4. Among them, rectangle a represents the test black block, rectangle b represents the region of interest

Specifically, for the region of interest shown in FIG. 3, the embodiment of the present application can calculate the center point coordinates of each side of the test black block according to the coordinates of the four vertices of the test black block, and then use the center point coordinates as the pair of the region of interest. For the center point of the corner line, the vertex coordinates of the area of interest are calculated according to the set length and width pixel values of the area of interest to determine the area of interest.

Or, you can calculate the center point coordinates and silhouette side length of each side of the test black block according to the four vertices coordinates of the test black block, and according to the silhouette side length and the ratio of the length and width of the set area of interest to the silhouette side length , Calculate the length and width pixel values of the region of interest, and then take the center point coordinates as the diagonal center point of the region of interest, and calculate the vertex coordinates of the region of interest according to the set length and width pixel values of the region of interest to determine the feeling Area of interest.

And for the region of interest shown in FIG. 4, the embodiment of the present application can determine the tilt angle of the region of interest according to the coordinates of the apex of the region of interest, and adjust the coordinates of the apex of the region of interest to make the tilt angle of the region of interest at The preset angle range is, for example, 6°-8°, to meet the requirements of the region of interest in the SFR algorithm. Specifically, the slope of the line where each two vertices are located and the inclination angle of the line and the coordinate axis are calculated according to the coordinates of the four vertices of the test black block; the inclination angle of the line and the coordinate axis is calculated as the preset tilt angle and passed The straight line equation of the midpoint of the two vertices; the midpoint of the two vertices is taken as the intersection of the diagonals of the rectangle, and the straight line obtained by the straight line equation is taken as the diagonal bisector of the rectangle, according to the preset length and width pixel values of the region of interest, Find the coordinates of the four vertices of the rectangle; intercept the image content according to the coordinates of the vertices of the rectangle, and rotate the entire image content by a preset angle as the image content of the region of interest. That is, after calculating the vertex coordinates of the region of interest, determine the region of interest parallel to the SFR test card image shown in Figure 3, and then adjust the region of interest through rotation to obtain the black block with the test shown in Figure 4 A region of interest at a certain angle, and the region of interest is within a preset angle range, which meets the requirements of the SFR algorithm.

Or, if one side of the region of interest needs to be substantially parallel to the hypotenuse of the edge contour of the test black block, and the other side is substantially perpendicular to the hypotenuse of the edge contour of the test black block, that is, the slope of each side of the region of interest is known. The application embodiment can also calculate the region of interest based on the coordinates of the center point of each side of the test black block, the set constraint value of the region of interest, and the known slope of each side of the region of interest. The vertex coordinates to determine the area of interest.

It should be noted that the constraint value for the set region of interest, that is, the preset length and width pixel value or the ratio value of the given length and width to the contour side length, is preset by the program and should be finalized The region of interest can meet the requirements of the region of interest in the SFR algorithm as much as possible.

The non-temporary computer storage medium provided by the embodiment of the second aspect of the present application has a computer program stored thereon, wherein the computer program is executed to implement the method for identifying the region of interest in the SFR test card image provided by the above embodiment.

The device for identifying the region of interest in the image of the SFR test card provided by the embodiment of the third aspect of the present application is shown in FIG. .

Wherein, the display 2 is used to display the image of the SFR test card, and the memory 4 stores instructions that can be executed by the processor 3. When the instructions are executed by the processor 3, the processor 3 executes the identification of the SFR test card image provided by the above-mentioned embodiment. Method of interest area.

According to the device 1 for recognizing the region of interest in the image of the SFR test card according to the embodiment of the present application, the processor 3 executes the method for recognizing the region of interest in the image of the SFR test card provided in the above embodiment, so that the interest in the image of the SFR test card can be realized. The automatic recognition of the region does not require manual and precise alignment, and can avoid the problem of inaccurate calculation of the coordinates of the region of interest, and improve the accuracy of the SFR algorithm.

In the description of this specification, any process or method description in the flowchart or described in other ways herein can be understood as meaning that includes one or more executable instructions for implementing custom logic functions or steps of the process. Modules, fragments, or parts of code, and the scope of the preferred embodiments of the present application includes additional implementations, which may not be in the order shown or discussed, including in a substantially simultaneous manner or in the reverse order according to the functions involved , To perform functions, which should be understood by those skilled in the art to which the embodiments of this application belong.

The logic and/or steps represented in the flowchart or described in other ways herein, for example, can be considered as a sequenced list of executable instructions for realizing logic functions, and can be embodied in any computer-readable medium, For use by instruction execution systems, devices, or equipment (such as computer-based systems, systems including processors, or other systems that can fetch and execute instructions from instruction execution systems, devices, or equipment), or combine these instruction execution systems, devices Or equipment. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by an instruction execution system, device, or device or in combination with these instruction execution systems, devices, or devices. More specific examples (non-exhaustive list) of computer readable media include the following: electrical connections (electronic devices) with one or more wiring, portable computer disk cases (magnetic devices), random access memory (RAM), Read only memory (ROM), erasable and editable read only memory (EPROM or flash memory), fiber optic devices, and portable compact disk read only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program can be printed, because it can be used, for example, by optically scanning the paper or other medium, followed by editing, interpretation, or other suitable media if necessary. The program is processed in a manner to obtain the program electronically, and then stored in the computer memory.

It should be understood that each part of this application can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if it is implemented by hardware as in another embodiment, it can be implemented by any one or a combination of the following technologies known in the art: Discrete logic gate circuits with logic functions for data signals Logic circuits, application specific integrated circuits with suitable combinational logic gates, programmable gate array (PGA), field programmable gate array (FPGA), etc.

A person of ordinary skill in the art can understand that all or part of the steps carried in the method of the foregoing embodiments can be implemented by a program instructing relevant hardware to complete. The program can be stored in a computer-readable storage medium. When executed, it includes one of the steps of the method embodiment or a combination thereof.

In addition, the functional units in the various embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or software functional modules. If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

The aforementioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above-mentioned embodiments are exemplary and should not be construed as limiting the present application. A person of ordinary skill in the art can comment on the foregoing within the scope of the present application. The embodiment undergoes changes, modifications, substitutions, and modifications.

In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "exemplary embodiments", "examples", "specific examples", or "some examples" etc. means to incorporate the implementation The specific features, structures, materials or characteristics described by the examples or examples are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above-mentioned terms do not necessarily refer to the same embodiment or example. Moreover, the described specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and modifications can be made to these embodiments without departing from the principle and purpose of the present invention. The scope of the present invention is defined by the claims and their equivalents.

Claims

A method for identifying a region of interest in an image of an SFR test card, which is characterized in that it includes:

Obtain the image of the SFR test card;

Calculate the edge contour of the test black block in the SFR test card image;

Calculating the centroid coordinates of the edge contour;

Determine the vertex coordinates of the test black block according to the distance between the contour point of the edge contour and the center of mass;

The region of interest is determined according to the vertex coordinates of the test black block and the set constraint value of the region of interest.
The method for identifying the region of interest in the SFR test card image according to claim 1, wherein before calculating the edge contour of the test black block in the SFR test card image, the method further comprises: checking the The SFR test card image is grayed and binarized.
The method for identifying the region of interest in the SFR test card image according to claim 1 or 2, wherein after calculating the edge contour of the test black block in the SFR test card image, the method further comprises:

Calculating the area enclosed by the edge contour;

Obtaining a first-type contour with an area larger than a first preset area threshold and a second-type contour with an area smaller than a second preset area threshold;

Remove the first-type contour and the second-type contour from all the calculated edge contours.
The method for identifying the region of interest in the SFR test card image according to claim 1 or 2, wherein after calculating the edge contour of the test black block in the SFR test card image, the method further comprises:

Calculating the maximum x coordinate, the minimum x coordinate, the maximum y coordinate and the minimum y coordinate among the edge contour points of each test black block;

Calculate the x coordinate difference between the maximum x coordinate and the minimum x coordinate to obtain a first type of contour whose x coordinate difference is greater than a first preset difference threshold and the x coordinate difference is less than a second preset A second-type contour of a difference threshold, removing the first-type contour and the second-type contour from all the calculated edge contours;

Calculate the y-coordinate difference between the maximum y-coordinate and the minimum y-coordinate to obtain a first type of contour whose y-coordinate difference is greater than a first preset difference threshold and the y-coordinate difference is less than a second preset The second-type contour of the difference threshold is used to remove the first-type contour and the second-type contour from all the calculated edge contours.
The method for recognizing a region of interest in an image of an SFR test card according to claim 1, wherein determining the vertex coordinates of the test black block according to the distance between the contour point of the edge contour and the center of mass comprises the steps of:

Calculating the distance between two contour points in the edge contour;

Select the two contour points with the smallest distance from the edge contour, calculate the distance between the two contour points and the centroid, and remove the two contour points from the contour points of the edge contour. For a contour point with a smaller centroid distance, repeat this step until there are four contour points remaining in the edge contour;

The coordinates of the remaining four contour points are used as the coordinates of the four vertices of the test black block.
The method for identifying the region of interest in the SFR test card image according to claim 5, characterized in that, before determining the vertex coordinates of the test black block according to the distance between the contour point of the edge contour and the centroid, the method It also includes: simplifying the edge contour to obtain a preset number of contour points in the edge contour.
The method for identifying a region of interest in an image of an SFR test card according to claim 5, wherein determining the region of interest according to the vertex coordinates of the test black block and the set constraint value of the region of interest includes step:

Calculating the coordinates of the center point of each side of the test black block according to the coordinates of the four vertices of the test black block;

Using the center point coordinates as the diagonal center point of the region of interest, the vertex coordinates of the region of interest are calculated according to the set length and width pixel values of the region of interest.
The method for identifying a region of interest in an image of an SFR test card according to claim 5, wherein determining the region of interest according to the vertex coordinates of the test black block and the set constraint value of the region of interest includes step:

Calculating the coordinates of the center point and the contour side length of each side of the test black block according to the coordinates of the four vertices of the test black block;

Calculating the pixel value of the length and width of the region of interest according to the side length of the contour and the set ratio of the length and width of the region of interest to the side length of the contour;

Using the center point coordinates as the diagonal center point of the region of interest, the vertex coordinates of the region of interest are calculated according to the set length and width pixel values of the region of interest.
The method for identifying a region of interest in an image of an SFR test card according to claim 5, wherein determining the region of interest according to the vertex coordinates of the test black block and the set constraint value of the region of interest includes step:

Calculating the slope of the line where each two vertices are located and the inclination angle of the line and the coordinate axis according to the coordinates of the four vertices of the test black block;

Finding a straight line equation that is a preset inclination angle and passes through the midpoint of the two vertices;

The midpoint of the two vertices is taken as the intersection of the diagonals of the rectangle, and the straight line obtained by the straight line equation is taken as a diagonal bisector of the rectangle, and the rectangle is obtained according to the preset length and width pixel values of the region of interest. The coordinates of the four vertices;

The image content is intercepted according to the coordinates of the vertices of the rectangle, and the image content is rotated as a whole by a preset angle as the image content of the region of interest.
A non-temporary computer storage medium with a computer program stored thereon, wherein the computer program implements the method for identifying a region of interest in an image of an SFR test card according to any one of claims 1-9 when the computer program is executed .
A device for identifying a region of interest in an image of an SFR test card, which is characterized in that it comprises:

Display, used to display SFR test card image;

A processor and a memory communicatively connected with the processor; wherein,

The memory stores instructions that can be executed by the processor, and when the instructions are executed by the processor, the processor executes the recognition of the SFR test card image according to any one of claims 1-9. Method of interest area.