CN118297810A - Luminance weighted self-adaptive paint defect image enhancement method and device - Google Patents

Abstract

The invention provides a brightness weighted self-adaptive paint defect image enhancement method and a device, which belong to the technical field of robot vision, and the method comprises the following steps: obtaining a Tiansi operator of a target image, obtaining weights of zero elements and adjacent elements of the target image, performing zero element replacement calculation on the Tiansi operator based on the weights of the zero elements and the adjacent elements to obtain a fractional differential operator, obtaining an image gradient, an information entropy, roughness and pixel brightness of the target image, obtaining an optimal differential order based on the fractional differential operator, the image gradient, the information entropy, the roughness and the pixel brightness of the target image, and performing feature enhancement on the target image based on the optimal differential order to obtain feature enhancement information of the target image. The invention improves the detection efficiency and accuracy of the vehicle body paint surface defect image.

Description

Brightness-weighted adaptive paint defect image enhancement method and device

Technical Field

The present invention relates to the field of robot vision technology, and in particular to a brightness-weighted adaptive paint surface defect image enhancement method and device.

Background technique

High-speed rail body paint defect detection is an important means to achieve zero-defect manufacturing. When it comes to body paint defect detection in an industrial environment, the presence of reflective noise and weak defect features on the paint surface exacerbates the difficulty of defect detection, resulting in poor detection rate and accuracy of existing detection methods. If there are defects on the paint surface and the defects are not detected when leaving the factory, it will not only reduce the economic benefits of the car, but also lead to more waste of resources when it is returned to the factory for spraying. Therefore, in order to ensure the quality of the paint surface, automobile paint defect detection has great research value. The texture features of body paint defects are not strong, and it is difficult to improve the accuracy and recall rate of body paint defect detection. There are technical problems in the prior art that the detection of body paint image defects is inefficient and the accuracy is not high.

Summary of the invention

In view of this, it is necessary to provide a brightness-weighted adaptive paint defect image enhancement method and device to solve the technical problems of low efficiency and low accuracy in detecting paint defect images of vehicle bodies.

In order to solve the above technical problems, on the one hand, the present invention provides a brightness-weighted adaptive paint defect image enhancement method, comprising:

In order to achieve the above object, the present invention provides a method comprising:

Get the Tiansi operator of the target image;

Obtaining weights of zero elements and adjacent elements of the target image, performing zero element replacement calculation on the Tiansi operator based on the weights of the zero elements and the adjacent elements, and obtaining a fractional differential operator;

Acquire the image gradient, information entropy, roughness and pixel brightness of the target image, and obtain the optimal differential order based on the fractional differential operator, the image gradient, information entropy, roughness and pixel brightness of the target image;

The target image is feature enhanced based on the optimal differential order to obtain feature enhancement information of the target image.

In a possible implementation, obtaining the Tiansi operator of the target image includes:

A partial fractional order differential of a target image is obtained, and a Tiansi operator of the target image is obtained based on the partial fractional order differential of the target image.

In a possible implementation, the zero element replacement calculation formula is as follows:

Wherein: _A3 is the fractional-order differential operator and _A2 is the difference approximation expression.

In a possible implementation, obtaining the optimal differential order based on the fractional differential operator, the image gradient of the target image, the information entropy, the roughness, and the pixel brightness includes:

A differential order function model is constructed based on the image gradient, the information entropy, the roughness and the pixel brightness of the target image to obtain a differential order function model, and the fractional-order differential operator is input into the differential order function model to obtain an optimal differential order.

In a possible implementation, the step of inputting the fractional-order differential operator into the differential order function model to obtain an optimal differential order includes:

The fractional-order differential operator is input into the differential order function model for adaptive optimization to obtain the optimal differential order.

In a possible implementation manner, the performing feature enhancement on the target image based on the optimal differential order to obtain feature enhancement information of the target image includes:

A differential order function model is constructed based on the optimal differential order to obtain a differential order function model, and the target image is input into the differential order function model to obtain feature enhancement information of the target image.

In a possible implementation, the differential order function model is expressed as follows:

Among them, v(x,y) is the differential order function model, x is the horizontal coordinate of the pixel point of the target image, y is the vertical coordinate of the pixel point of the target image, f _(x,y) (gray,L) is the optimal differential order, gray is the gray value of the pixel point and L is the gray level of the target image.

On the other hand, the present invention also provides a brightness-weighted adaptive paint surface defect image enhancement device, comprising:

Tiansi operator acquisition module, used to obtain the Tiansi operator of the target image;

A zero element calculation module, used to obtain the weights of the zero element and the adjacent elements of the target image, and perform zero element replacement calculation on the Tiansi operator based on the weights of the zero element and the adjacent elements to obtain a fractional differential operator;

An optimal differential order calculation module, used to obtain the image gradient, information entropy, roughness and pixel brightness of the target image, and obtain the optimal differential order based on the fractional differential operator, the image gradient, information entropy, roughness and pixel brightness of the target image;

The feature enhancement module is used to perform feature enhancement on the target image based on the optimal differential order to obtain feature enhancement information of the target image.

On the other hand, the present invention also provides an electronic device, including a memory and a processor, wherein:

The memory is used to store programs;

The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the brightness-weighted adaptive paint defect image enhancement method as described in any of the above implementations.

On the other hand, the present invention also provides a computer-readable storage medium for storing computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the brightness-weighted adaptive paint defect image enhancement method described in any of the above-mentioned implementation methods.

The beneficial effects of the present invention are as follows: the brightness-weighted adaptive paint defect image enhancement method provided by the present invention mainly obtains the Tiansi operator of the target image, obtains the weights of the zero elements and adjacent elements of the target image, performs zero element replacement calculation on the Tiansi operator based on the weights of the zero elements and the adjacent elements, obtains the fractional differential operator, obtains the image gradient, information entropy, roughness and pixel brightness of the target image, obtains the optimal differential order based on the fractional differential operator, the image gradient, information entropy, roughness and pixel brightness of the target image, performs feature enhancement on the target image based on the optimal differential order, and obtains feature enhancement information of the target image. Further, the present application mainly achieves the purpose of improving the detection efficiency and accuracy of the paint defect image of the vehicle body through the four steps of establishing the Tiansi operator, zero element replacement, constructing a function model about the differential order and realizing feature enhancement of the paint image, wherein the fractional differential theory is mainly introduced into the image gradient, information entropy, roughness and brightness information for defect image enhancement, which will effectively enhance the edge information of the defect area and make the texture of the defect area more obvious.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

FIG1 is a schematic flow chart of an embodiment of a brightness-weighted adaptive paint defect image enhancement method provided by the present invention;

FIG2 is a schematic diagram of an embodiment of a brightness-weighted adaptive paint defect image enhancement method provided by the present invention;

FIG3 is a schematic diagram of a Tiansi operator according to an embodiment of a brightness-weighted adaptive paint defect image enhancement method provided by the present invention;

FIG4 is a schematic diagram of a fractional differential operator of an embodiment of a brightness-weighted adaptive paint defect image enhancement method provided by the present invention;

FIG5 is a schematic structural diagram of an embodiment of a brightness-weighted adaptive paint surface defect image enhancement device provided by the present invention;

FIG. 6 is a schematic diagram of the structure of an embodiment of an electronic device provided by the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

In the description of the embodiments of the present invention, unless otherwise specified, "multiple" means two or more. "And/or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, "A and/or B" may mean: A exists alone, A and B exist at the same time, and B exists alone.

The descriptions of "first", "second", etc. involved in the embodiments of the present invention are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the technical features defined as "first" or "second" may explicitly or implicitly include at least one of the features.

Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive of other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

The present invention provides a brightness-weighted adaptive paint defect image enhancement method and device, which are described below respectively.

FIG1 is a schematic flow chart of an embodiment of a brightness weighted adaptive paint surface defect image enhancement method provided by the present invention, and FIG2 is a schematic diagram of an embodiment of a brightness weighted adaptive paint surface defect image enhancement method provided by the present invention, including:

S101, obtaining the Tiansi operator of the target image;

S102, obtaining the weights of the zero elements and the adjacent elements of the target image, performing a zero element replacement calculation on the Tiansi operator based on the weights of the zero elements and the adjacent elements, and obtaining a fractional differential operator;

S103, obtaining the image gradient, information entropy, roughness and pixel brightness of the target image, and obtaining the optimal differential order based on the fractional differential operator, the image gradient, information entropy, roughness and pixel brightness of the target image;

S104, performing feature enhancement on the target image based on the optimal differential order to obtain feature enhancement information of the target image.

It should be noted that in the prior art, when enhancing defects, most methods in the prior art may enhance reflective noise, which will affect the subsequent paint defect detection, or an improved GAN generative adversarial network will be used to directly generate new defect data based on the adversarial network. This method often leads to problems such as poor authenticity and pattern collapse of the generated images. The present invention mainly applies the fractional differential theory to the field of defect image enhancement, which can effectively enhance the edge information of the defect area and make the texture of the defect area more obvious.

It can be understood that the present invention mainly includes the following steps:

Step 1: According to the order of differentiation, the order is expanded from integer order to fractional order and applied to the image signal f(x, y), and the differential approximate expression of partial fractional differential is obtained; the first three coefficients of the fractional differential approximate expression are taken to obtain the Tiansi operator of size 5×5;

Step 2: According to the reciprocal of the distance from the central pixel as the zero element and the weight of its adjacent elements, zero element replacement is achieved to construct fractional differential operators in 16 directions;

Step 3: Based on the local information of three images, namely image gradient, information entropy and roughness, and the brightness information of the pixel points, a differential order function model is constructed as a weighted number to realize adaptive search for the optimal differential order;

Step 4: Based on the adaptive differential order v(x, y), feature enhancement is performed on the three components of the image to be enhanced on three channels respectively, and finally the RGB image is synthesized to achieve feature enhancement of the paint surface image.

FIG3 is a schematic diagram of a Tiansi operator according to an embodiment of a brightness-weighted adaptive paint defect image enhancement method provided by the present invention, comprising:

The partial fractional differential of the target image is obtained, and the Tiansi operator of the target image is obtained based on the partial fractional differential of the target image.

It should be noted that the specific steps for obtaining the Tiansi operator of the target image are as follows:

Step 1: According to the expanded fractional differential, it can be defined as:

Where: v is the fractional order v>0, h is the differential step size, for , a is the lower limit of fractional differential, is the Gamma function.

Step 2: Through the target image f(x,y), the differential approximate expression of the partial fractional differential in the positive direction of x and y can be obtained:

Where: x is the horizontal coordinate of the pixel point of the target image, y is the vertical coordinate of the pixel point of the target image, v is the fractional order v>0, and k represents the weight coefficient.

Step 3: The approximate fractional differential expressions in six directions, including the negative directions of x and y, and the left and right diagonal directions, can be obtained through the target image f(y,x).

Step 4: Take the first three coefficients of the fractional differential approximation expression to obtain the Tiansi operator of size 5×5.

In some embodiments of the present invention, the zero element replacement calculation formula is as follows:

Where: _A3 is the fractional differential operator and _A2 is the difference approximation expression.

It should be noted that, according to the reciprocal of the distance from the center pixel as the zero element and the weight of its adjacent elements, the zero element replacement is implemented according to the above formula, which can further enhance the algorithm accuracy and the anti-rotation ability of the operator, and construct a fractional-order differential operator in 16 directions.

FIG4 is a schematic diagram of a fractional differential operator of an embodiment of a brightness-weighted adaptive paint defect image enhancement method provided by the present invention, comprising:

A differential order function model is constructed based on the image gradient, information entropy, roughness and pixel brightness of the target image to obtain the differential order function model, and the fractional order differential operator is input into the differential order function model to obtain the optimal differential order.

It should be noted that the steps to obtain the optimal differential order are as follows:

Step 1: Extract image gradient to determine the spatial change rate. According to the image gradient change, determine whether the image texture information is rich. The normalized image gradient defined as:

Where: G _gray (x, y) is the gray value of the pixel point (x, y), x, y represent the horizontal and vertical coordinates of the pixel point respectively;

further,

Where: f _{gray (x, y)} is the gray value of the pixel (x, y).

Step 2: Extract image information entropy to determine the size of the average amount of information. The larger the entropy value, the more information it contains. It can be seen that the value of information entropy is relatively large in the edge area of the image. The normalized image information entropy defined as:

further,

Where: j is the gray mean of the pixel (x, y) in the N neighborhoods, g _gray (i, j) is the feature binary of the pixel (x, y) and the neighborhood information of the point, P _gtay (i, j) is the frequency of g _gray (i, j) occurring in the neighborhood, and NBL is the gray level of the image.

Step 3: Extract image roughness to determine the fineness of texture features. The image roughness is small in smooth areas and large in areas with rich details. Image roughness R _gray (x, y) is defined as:

further,

Where M _{gray (x, y)} is the gray mean in the local window with the pixel point (x, y) as the center and N as the side length, and σ (f _{gray (x, y)} (x, y)) ² is the gray value variance of the local window.

Step 4: Extract the image brightness information and use the brightness information value as the weight (1-I _L ).

Step 5: Introduce the local information of the above three images and the weighted number of pixel brightness information to construct a differential order function model to achieve adaptive search for the optimal differential order. The corresponding mathematical model f _{(x, y)} (gray, L) is:

Where: The pixel point (x, y) R _gray (x, y) and I _L (x, y) are abbreviated as R _gray , _IL and (1- _IL ) are the weights of brightness information.

In some embodiments of the present invention, a fractional differential operator is input into a differential order function model to obtain an optimal differential order, including:

The fractional-order differential operator is input into the differential order function model for adaptive optimization to obtain the optimal differential order.

It should be noted that the fractional-order differential operator is input into the differential order function model for adaptive optimization to obtain the optimal differential order.

In some embodiments of the present invention, feature enhancement is performed on a target image based on an optimal differential order to obtain feature enhancement information of the target image, including:

A differential order function model is constructed based on the optimal differential order to obtain a differential order function model, and a target image is input into the differential order function model to obtain feature enhancement information of the target image.

It should be noted that a differential order function model is constructed based on the optimal differential order to obtain a differential order function model, and the target image is input into the differential order function model to obtain feature enhancement information of the target image.

In some embodiments of the present invention, the expression of the differential order function model is as follows:

Among them, v(x,y) is the differential order function model, x is the horizontal coordinate of the pixel point of the target image, y is the vertical coordinate of the pixel point of the target image, f _(x,y) (gray,L) is the optimal differential order, gray is the gray value of the pixel point and L is the gray level of the target image.

It should be noted that in order to further highlight the increase in the differential order as f _{(x, y)} (gray, L) increases, a differential order v(x, y) function model as described above is constructed.

It should be further explained that the range of the differential order is between 0<v(x,y)<1. At the same time, f _(x,y) (gray,L)∈(0,1), with the gradual increase of frequency, the differential order is significantly enhanced nonlinearly. From the above analysis, it can be seen that the adaptive function to be characterized is a nonlinear monotonically increasing function.

FIG5 is a schematic structural diagram of an embodiment of a brightness-weighted adaptive paint surface defect image enhancement device provided by the present invention, comprising:

Tiansi operator acquisition module 501, used to acquire the Tiansi operator of the target image;

A zero element calculation module 502 is used to obtain the weights of the zero elements and adjacent elements of the target image, and perform zero element replacement calculation on the Tiansi operator based on the weights of the zero elements and adjacent elements to obtain a fractional differential operator;

The optimal differential order calculation module 503 is used to obtain the image gradient, information entropy, roughness and pixel brightness of the target image, and obtain the optimal differential order based on the fractional differential operator, the image gradient, information entropy, roughness and pixel brightness of the target image;

The feature enhancement module 504 is used to perform feature enhancement on the target image based on the optimal differential order to obtain feature enhancement information of the target image.

The brightness-weighted adaptive paint defect image enhancement device 700 provided in the above embodiment can implement the technical solution described in the above brightness-weighted adaptive paint defect image enhancement method embodiment. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above brightness-weighted adaptive paint defect image enhancement method embodiment, which will not be repeated here.

As shown in FIG6 , the present invention also provides an electronic device 600. The electronic device 600 includes a processor 601, a memory 602, and a display 603. FIG6 shows only some components of the electronic device 600, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

In some embodiments, the processor 601 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 602, such as the brightness-weighted adaptive paint defect image enhancement method of the present invention.

In some embodiments, the processor 601 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 601 may be local or remote. In some embodiments, the processor 601 may be implemented in a cloud platform. In one embodiment, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.

In some embodiments, the memory 602 may be an internal storage unit of the electronic device 600, such as a hard disk or memory of the electronic device 600. In other embodiments, the memory 602 may also be an external storage device of the electronic device 600, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 600.

Furthermore, the memory 602 may include both an internal storage unit of the electronic device 600 and an external storage device. The memory 602 is used to store application software installed in the electronic device 600 and various data.

In some embodiments, the display 603 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 603 is used to display information on the electronic device 600 and to display a visual user interface. The components 601-603 of the electronic device 600 communicate with each other via a system bus.

In one embodiment, when the processor 601 executes the brightness-weighted adaptive paint defect image enhancement program in the memory 602, the following steps may be implemented:

Get the Tiansi operator of the target image;

Obtain the weights of the zero elements and adjacent elements of the target image, perform zero element replacement calculation on the Tiansi operator based on the weights of the zero elements and adjacent elements, and obtain a fractional differential operator;

Obtain the image gradient, information entropy, roughness and pixel brightness of the target image, and obtain the optimal differential order based on the fractional differential operator, the image gradient, information entropy, roughness and pixel brightness of the target image;

The target image is feature enhanced based on the optimal differential order to obtain feature enhancement information of the target image.

It should be understood that: when the processor 601 executes the brightness-weighted adaptive paint defect image enhancement program in the memory 602, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.

Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 600 mentioned, and the electronic device 600 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic device may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 600 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

Accordingly, an embodiment of the present application also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, it can implement the steps or functions of the brightness-weighted adaptive paint defect image enhancement method provided in the above-mentioned method embodiments.

Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

The brightness-weighted adaptive paint defect image enhancement method and device provided by the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims (10)

1. A method for enhancing a luminance weighted adaptive paint defect image, comprising:

acquiring a tiandi operator of a target image;

Acquiring weights of zero elements and adjacent elements of a target image, and performing zero element replacement calculation on the Tiansi operator based on the weights of the zero elements and the adjacent elements to obtain a fractional differential operator;

Acquiring an image gradient, an information entropy, roughness and pixel brightness of a target image, and obtaining an optimal differential order based on the fractional differential operator, the image gradient, the information entropy, the roughness and the pixel brightness of the target image;

and carrying out feature enhancement on the target image based on the optimal differential order to obtain feature enhancement information of the target image.

2. The luminance weighted adaptive paint defect image enhancement method according to claim 1, wherein the tiarsi operator for acquiring the target image comprises:

And obtaining partial fractional differentiation of the target image, and obtaining a tiassi operator of the target image based on the partial fractional differentiation of the target image.

3. The luminance weighted adaptive paint defect image enhancement method according to claim 1, wherein the zero element substitution calculation formula is as follows:

Wherein: a ₃ is the fractional differential operator and A ₂ is a differential approximation expression.

4. The method for enhancing a luminance weighted adaptive paint defect image according to claim 1, wherein said deriving an optimal differential order based on said fractional differential operator, said image gradient of said target image, said information entropy, said roughness, and said pixel luminance comprises:

And constructing a differential order function model based on the image gradient, the information entropy, the roughness and the pixel brightness of the target image to obtain a differential order function model, and inputting the differential operator of the differential order to the differential order function model to obtain the optimal differential order.

5. The method for enhancing a luminance weighted adaptive paint defect image according to claim 4, wherein said inputting the fractional order differential operator to the differential order function model to obtain an optimal differential order comprises:

and the fractional order differential operator is input to the differential order function model to perform self-adaptive optimization, so that the optimal differential order is obtained.

6. The method for enhancing a luminance weighted adaptive paint defect image according to claim 1, wherein the performing feature enhancement on the target image based on the optimal differential order to obtain feature enhancement information of the target image comprises:

And constructing a differential order function model based on the optimal differential order to obtain a differential order function model, and inputting the target image into the differential order function model to obtain the characteristic enhancement information of the target image.

7. The luminance weighted adaptive paint defect image enhancement method according to claim 1, wherein the expression of the differential order function model is as follows:

Wherein v (x, y) is the differential order function model, x is the abscissa of the pixel point of the target image, y is the ordinate of the pixel point of the target image, f _(x,y) (gray, L) is the optimal differential order, gray is the pixel point gray value and L is the gray level of the target image.

8. A brightness weighted adaptive paint defect image enhancement device, comprising:

the Tiansi operator acquisition module is used for acquiring the Tiansi operator of the target image;

the zero element calculation module is used for acquiring weights of zero elements and adjacent elements of the target image, and performing zero element replacement calculation on the Tiansi operator based on the weights of the zero elements and the adjacent elements to obtain a fractional differential operator;

The optimal differential order calculation module is used for obtaining the image gradient, the information entropy, the roughness and the pixel brightness of the target image and obtaining the optimal differential order based on the fractional differential operator, the image gradient, the information entropy, the roughness and the pixel brightness of the target image;

and the characteristic enhancement module is used for carrying out characteristic enhancement on the target image based on the optimal differential order to obtain characteristic enhancement information of the target image.

9. An electronic device comprising a memory and a processor, wherein,

The memory is used for storing programs;

the processor, coupled to the memory, is configured to execute the program stored in the memory to implement the steps in a brightness weighted adaptive paint defect image enhancement method as claimed in any one of claims 1 to 7.

10. A computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements a brightness weighted adaptive paint defect image enhancement method according to any of claims 1 to 7.