Method and system for improving filtering surface metal of dewaxing cleaning machine

Abstract

The embodiment of the invention relates to the technical field of semiconductor cleaning, and discloses a method and system for improving filtering surface metal of a dewaxing cleaning machine. Comprising the steps that an industrial camera is adopted to collect a semiconductor overall image, image extraction is carried out, and a semiconductor image containing irregular impurities is obtained through extraction; performing image enhancement processing on the semiconductor image by adopting a multi-scale illumination compensation combined morphological enhancement method, and extracting the enhanced image to obtain fine impurity information on the surface of the semiconductor; and cleaning the semiconductor surface based on the extracted fine impurities on the semiconductor surface. The technical problem that surface metal cannot be effectively cleaned through an existing semiconductor cleaning method is at least solved.

Description

Technical Field

[0001] The present application relates to the field of semiconductor cleaning technology, and in particular to a method and system for improving the filtering of surface metals by a dewaxing cleaning machine. Background Art

[0002] In industrial production, dewaxing cleaning machines are widely used to remove wax and other contaminants from the polished surfaces of silicon wafers. With the continuous advancement of production technology, the requirements for cleaning performance and filtration precision of cleaning machines are becoming increasingly higher. Traditional dewaxing cleaning machines use NCW-1002 to remove wax residue after polishing, and SC1 (NH4OH+H2O2+H2O) to dissolve the oxide layer and remove particles from the silicon surface. However, because the dewaxing cleaning machine is only equipped with a particle filter element for the liquid tank, it is difficult to achieve ideal filtration results when filtering wax liquids or cleaning fluids containing metal impurities.

[0003] Therefore, there is an urgent need for a design solution that can effectively remove impurities including metal particles on the surface of semiconductors. Summary of the Invention

[0004] One purpose of the present application is to provide a method and system for improving the ability of a dewaxing cleaning machine to filter surface metal. By using an image recognition method to identify the surface metal of a semiconductor and using a cleaning device to clean it, it is at least used to solve the technical problem that existing semiconductor cleaning methods cannot effectively clean surface metal.

[0005] To achieve the above objectives, some embodiments of the present application provide the following aspects:

[0006] In a first aspect, some embodiments of the present application further provide a method for improving the ability of a dewaxing cleaning machine to filter surface metal, comprising the following steps:

[0007] An industrial camera is used to capture the overall image of the semiconductor and perform image extraction to obtain an image of the semiconductor containing irregular impurities;

[0008] Performing image enhancement processing on the semiconductor image using a multi-scale illumination compensation combined with a morphological enhancement method, and extracting the enhanced image to obtain information on subtle impurities on the semiconductor surface;

[0009] The semiconductor surface is cleaned based on the extracted fine impurities on the semiconductor surface.

[0010] In a second aspect, some embodiments of the present application further provide a system for improving the filtering of surface metals by a dewaxing cleaning machine, comprising: a semiconductor image acquisition device, a semiconductor impurity extraction device, and a cleaning device;

[0011] The semiconductor image acquisition device is used to acquire the overall image of the semiconductor by using an industrial camera, and perform image extraction to obtain a semiconductor image containing irregular impurities;

[0012] The semiconductor impurity extraction device is used to perform image enhancement processing on the semiconductor image, and extract the fine impurities on the semiconductor surface from the enhanced image;

[0013] The cleaning device is used to perform cleaning treatment on the semiconductor surface based on the fine impurities on the semiconductor surface obtained by the extraction.

[0014] Compared with the related technology, in the solution provided by the embodiment of the present application:

[0015] (1) The present invention adopts an edge-guided dynamic weight mechanism: by combining gradient magnitude analysis with multi-scale Retinex weight allocation, it breaks through the traditional fixed weight mode, and at the same time adopts a region constraint enhancement strategy. Through the combined operation of morphological dilation and top-hat transformation, precise spatial positioning of impurity signals is achieved;

[0016] (2) The cleaning device of the present invention adds a metal filter element in front of the particle filter element to preliminarily intercept and filter metal impurities, improve the filtration accuracy, effectively remove metal particles in the wax liquid and cleaning liquid, ensure the cleanliness of the workpiece surface, and meet the production requirements of high-end products; filtering out metal impurities in advance can reduce the wear and corrosion of the internal components of the washing machine by metal particles, reduce the incidence of equipment failures, extend the maintenance cycle and service life of the equipment, and reduce the equipment maintenance cost;

[0017] (3) The present invention effectively filters metal impurities, reduces the content of impurities in the cleaning liquid, extends the service life of the cleaning liquid, reduces the replacement frequency of the cleaning liquid, thereby saving the usage cost of the cleaning liquid, and at the same time reducing the downtime caused by frequent replacement of the cleaning liquid, and improving the production efficiency. Description of the Drawings

[0018] One or more embodiments are exemplarily illustrated by the pictures in the corresponding drawings. These exemplary illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are represented as similar elements, unless otherwise stated, the drawings in the drawings do not constitute a proportional limitation.

[0019] Figure 1 It is a schematic flowchart of a method for improving the filtration of surface metals of a wax-removing washing machine according to the first embodiment of the present application;

[0020] Figure 2 It is a schematic structural diagram of a system for improving the filtration of surface metals of a wax-removing washing machine according to the second embodiment of the present application;

[0021] Figure 3 Schematic structural diagram of a system cleaning device for enhancing the filtering of surface metals of a dewaxing washing machine according to the second embodiment of the present application;

[0022] Figure 4 Exemplary structural diagram of an electronic device according to the third embodiment of the present application. Detailed implementation manners

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Apparently, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0024] First embodiment

[0025] The first embodiment of the present application relates to a method for enhancing the filtering of surface metals of a dewaxing washing machine. As Figure 1 shown, the method may include the following steps:

[0026] S101. Use an industrial camera to collect an overall image of the semiconductor, and perform image extraction to obtain a semiconductor image containing irregular impurities.

[0027] In this embodiment, during the semiconductor manufacturing process, due to reasons such as processes and operations, fine impurities are likely to be generated on the semiconductor surface. Since the distribution of the fine impurities is irregular, it is difficult to detect the impurities at the edge of the semiconductor image. Since the gray scale and texture saliency of some impurities have a low distinguishability from the normal part, and the region edges are blurred, direct visual saliency detection cannot obtain accurate dimensions, which further increases the detection difficulty. Therefore, in this embodiment, an industrial camera is used to collect an overall image of the semiconductor, and a semiconductor image containing fine impurity information such as wax residues and metal particles is obtained.

[0028] S102. Perform image enhancement processing on the semiconductor image, and extract fine impurities on the semiconductor surface from the enhanced image.

[0029] Use an improved multi-scale Retinex and ROI edge extraction method to perform image processing on the image, and extract enhanced impurity information.

[0030] Therefore, in this embodiment, by using the ROI edge extraction method and combining with the specific content of the image, the fine impurities existing on the semiconductor surface can be detected. The specific process is as follows:

[0031] First, perform multi-scale enhancement on the overall semiconductor image obtained by acquisition. In this embodiment, an improved image enhancement method is formed by constructing a method based on ROI edge extraction and multi-scale Retinex method to achieve the effect of image enhancement. Specifically:

[0032] First, calculate the gradient magnitude of the original image S(x, y), specifically:

[0033]

[0034] Among them, respectively represent the gradients of the image in the horizontal and vertical directions, is the gradient magnitude, representing the edge intensity of the image at (x, y).

[0035] Subsequently, perform multi-scale Gaussian smoothing on the gradient magnitude to generate an edge energy map with the same scale as Retinex:

[0036]

[0037] Among them, σk is the Gaussian kernel scale parameter, is a two-dimensional Gaussian kernel with a standard deviation of σk, used for multi-scale smoothing.

[0038] Allocate local weights for each scale according to the generated edge energy map:

[0039]

[0040] Among them, ∈ is a minimum value to prevent division by zero.

[0041] Specifically, in the strong edge region ( large), the small-scale weight ω1 dominates; in the flat region, the large-scale weight ω3 dominates.

[0042] After calculating the local weights, calculate the enhanced output result based on the improved multi-scale Retinex formula, specifically:

[0043]

[0044] Among them, log(S(x, y)) is the logarithmic domain representation of the original image, is the Gaussian blur result of the k-th scale, representing the illumination estimation of this scale.

[0045] It can be seen that through the improved multi-scale Retinex formula, on the one hand, spatial self-adaptability can be achieved, that is, the weight ω k (x, y) changes dynamically with the position, replacing the traditional fixed weight; on the other hand, edge protection can be achieved, that is, small-scale details are retained in the edge region (such as the scratch boundary) to avoid over-smoothing.

[0046] After completing the image enhancement, this embodiment combines the ROI edge extraction method for impurity separation. The specific process is as follows:

[0047] First, perform image edge thinning. In this embodiment, non-maximum suppression is used to thin the Canny edge detection result to obtain a sub-pixel edge E thin (x, y),

[0048] Subsequently, perform morphological dilation on the thinned edge, i.e., the sub-pixel edge, to compensate for the edge positioning error. Specifically:

[0049]

[0050] where B 3×3 is a 3×3 rectangular structuring element, and E dilated (x, y) is the dilation result.

[0051] Through Equation 5, the edge region is expanded outward by 1-2 pixels to cover the possible positions where impurities may adhere.

[0052] At the same time, perform a top-hat transform on the Retinex output image to extract bright regions smaller than the structuring element. Specifically:

[0053]

[0054] where B 5×5 is a 5×5 rectangular structuring element, is a morphological opening operation.

[0055] Finally, this embodiment performs a region intersection operation based on the bright region and the dilation result to complete the final impurity mask. The specific process is as follows:

[0056] M defect (x, y) = T(x, y) ∩ E dilated (x, y) (7)

[0057] where M defect (x, y) is the final impurity mask, which locates the defects near the edge.

[0058] Through the intersection operation, only the enhanced signals within the edge expansion region are retained, thereby excluding false detections far from the edge.

[0059] where S(x, y) is the original image, is the Gaussian kernel function, and ω k is the weight coefficient, usually taking equal weights or decreasing according to the scale.

[0060] Implement multi-scale illumination compensation through an enhancement process to enhance the contrast of impurities in dark areas.

[0061] Subsequently, perform non-local means denoising on the enhanced image. The specific process is as follows:

[0062]

[0063] Among them, P(x, y) is a 7×7 neighborhood pixel block centered at (x, y), Ω is the search window, h is the smoothing parameter, and Z(x, y) is the normalization factor.

[0064] Subsequently, perform frequency-domain detail enhancement on the enhanced image. This embodiment is achieved by using Fourier transform and ideal high-pass filtering. Specifically:

[0065]

[0066] Among them, (u0, v0) is the spectrum center, r is the cut-off radius, and M, N are the Fourier transform sizes.

[0067] At the same time, perform the inverse transform after filtering. Specifically:

[0068] g(x, y) = F -1 {F(u, v)·H(u, v)} (11)

[0069] Finally, perform morphological top-hat reconstruction to extract small-scale regions of the structure element (realize the extraction of impurity signals). Specifically:

[0070]

[0071] Among them, is the opening operation operator, defined as B is the structure element.

[0072] Therefore, through the above operations, the extraction of the image is realized. The finally extracted image is as follows:

[0073] I output = T(F -1 [H(u, v)·F(NLM(R(S)))]) (13)

[0074] Among them, R(S) is the enhanced image, NLM() is non-local means denoising, F, F -1 are the Fourier transform and inverse transform, H(u, v) is the high-pass filter, and T() is the top-hat transform.

[0075] The step division of the above various methods is only for clear description. When implemented, they can be combined into one step or some steps can be split into multiple steps. As long as the same logical relationship is included, they are all within the protection scope of this patent; adding insignificant modifications to the algorithm or process or introducing insignificant designs, but not changing the core design of the algorithm and process, are all within the protection scope of this patent.

[0076] Second Embodiment

[0077] The second embodiment of this application relates to a system for enhancing the filtration of surface metals of a dewaxing and cleaning machine, as Figure 2 shown, including: a semiconductor image acquisition device 1, a semiconductor impurity extraction device 2, and a cleaning device 3;

[0078] The semiconductor image acquisition device 1 is used to collect the overall image of the semiconductor using an industrial camera and perform image extraction to obtain a semiconductor image containing irregular impurities;

[0079] The semiconductor impurity extraction device 2 is used to perform image enhancement processing on the semiconductor image and extract the fine impurities on the semiconductor surface from the enhanced image;

[0080] The cleaning device 3 is used to clean the semiconductor surface based on the fine impurities on the semiconductor surface extracted.

[0081] As Figure 3 shown, specifically, in this embodiment, the cleaning device 3 includes: a particle filter 31, a metal filter 32, a concentration meter 33, an exhaust valve, and a water pump;

[0082] The particle filter 31 is connected to the metal filter 32, the metal filter 32 is connected to the exhaust valve, and the water pump is connected to the inlet and outlet of the metal filter through a water inlet pipe;

[0083] Two drain pipes at the lower part of the metal filter 32 are respectively connected with ball valves to form a pipeline, which is connected to the main PPH alkali drainage pipe.

[0084] The thermometer 33 is installed on the bracket of the cleaning device 3.

[0085] In the prior art, the cleaning device generally has the following defects: (1) Limitation of particle filter element filtration: The particle filter element is mainly used to filter impurities with larger particles. For some tiny metal particles, especially metal particles at the micron level or even smaller, its interception ability is limited. These metal particles may circulate with the cleaning liquid and reattach to the surface of the workpiece, affecting the cleaning effect and reducing the product quality. (2) Influence of metal impurities in the cleaning liquid: During the cleaning process, the cleaning liquid often mixes with impurities such as metal chips and metal oxides. These metal impurities will not only affect the performance of the liquid medicine but also may cause wear and corrosion to the internal components of the cleaning machine, such as pumps and pipelines, shortening the service life of the equipment. (3) Pollution of cleaning liquid circulation: Since the particle filter element cannot effectively filter metal impurities, during the recycling process of the cleaning liquid, metal impurities accumulate continuously, and the pollution degree of the cleaning liquid gradually increases, thereby affecting the cleaning effect.

[0086] In this embodiment, the content of metal on the surface of the silicon wafer in different states is measured and compared by ICMPS, as specifically shown in Table 1:

[0087] Table 1 Comparison of metal cleaning between the present invention and the prior art

[0088]

[0089] According to the measurement results of ICMPS, a metal filter element is installed in front of the particle filter element of the dewaxing cleaning machine to preliminarily intercept and filter metal impurity elements such as AL, ZN, and PB, improve the filtration accuracy, and effectively remove metal particles in the wax liquid and the cleaning liquid.

[0090] In this embodiment, by effectively filtering metal impurities, the content of impurities in the cleaning liquid is reduced, the service life of the cleaning liquid is prolonged, the replacement frequency of the cleaning liquid is reduced, thereby saving the usage cost of the cleaning liquid. At the same time, the downtime caused by frequent replacement of the cleaning liquid is also reduced, improving the production efficiency.

[0091] It is not difficult to find that this embodiment is a system embodiment corresponding to the first embodiment, and this embodiment can be implemented in cooperation with the first embodiment. The relevant technical details mentioned in the first embodiment are still valid in this embodiment. To avoid repetition, they are not elaborated here. Correspondingly, the relevant technical details mentioned in this embodiment can also be applied to the first embodiment.

[0092] It is worth mentioning that each module involved in this embodiment is a logical module. In practical applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, to highlight the innovative part of this application, units that are not closely related to solving the technical problems proposed in this application are not introduced in this embodiment, but this does not mean that there are no other units in this embodiment.

[0093] In addition, some embodiments of this application also provide an electronic device. The electronic device can be various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and so on. The electronic device can also be various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices.

[0094] The electronic device includes: one or more processors; and a memory storing computer program instructions, which when executed cause the processor to execute the steps of the method provided in any one or more of the above embodiments. Figure 4 An exemplary structural diagram of the electronic device is disclosed. As Figure 4 shown, the electronic device includes: one or more processors 1101, a memory 1102, and interfaces for connecting various components, including a high-speed interface and a low-speed interface. Each component is interconnected using different buses and can be installed on a common motherboard or in other ways as needed. The processor can process instructions executed within the electronic device, including instructions stored in the memory or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some other embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a set of blade servers, or a multi-processor system). Among them, the components, their connections and relationships, and their functions shown herein are only examples and are not intended to limit the implementation of this application described and / or claimed herein.

[0095] The electronic device may further include: an input device 1103 and an output device 1104. The processor 1101, the memory 1102, the input device 1103, and the output device 1104 can be connected by a bus or other means, Figure 4 taking connection by bus as an example.

[0096] The input device 1103 can receive input digital or character information and generate key signal inputs related to the user settings and function controls of the electronic device, such as input devices like touchscreens, keypads, mice, trackpads, touchpads, pointing sticks, one or more mouse buttons, trackballs, joysticks, etc. The output device 1104 can include display devices, auxiliary lighting devices (e.g., LEDs), and tactile feedback devices (e.g., vibration motors), etc. The display device can include, but is not limited to, liquid crystal displays (LCDs), light-emitting diode (LED) displays, and plasma displays. In some embodiments, the display device can be a touchscreen.

[0097] To provide interaction with the user, the electronic device can be a computer. The computer has: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball), through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and the input from the user can be received in any form (including voice input, speech input, or tactile input).

[0098] In the embodiments of the present application, a computer program / instructions is stored on a computer-readable medium. When the computer program / instructions are executed by a processor, the steps of the method provided by any one or more of the above embodiments are implemented. The computer-readable medium can be included in the electronic device described in the above embodiments; or it can exist separately without being assembled into the device. The above computer-readable medium carries one or more computer-readable instructions.

[0099] The memory 1102 can be used as a non-transitory computer-readable storage medium and can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules. The processor 1101 executes various functional applications and data processing of the server by running the non-transitory software programs, instructions, and modules stored in the memory 1102, so as to implement the program instructions / modules corresponding to the method provided by any one or more of the above embodiments in the embodiments of the present application.

[0100] The memory 1102 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 1102 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory 1102 may optionally include a memory remotely provided with respect to the processor 1101, and these remote memories may be connected to the electronic device through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0101] It should be noted that the computer-readable medium described in this application may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the above two. The computer-readable medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this application, the computer-readable medium may be any tangible medium that contains or stores a program, and this program may be used by or in combination with an instruction execution system, apparatus, or device.

[0102] The computer-readable medium includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information may be computer-readable instructions, data structures, program modules, or other data. Examples of the computer's storage medium include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassette tapes, magnetic tape disk storage, or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0103] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0104] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. For example, an application-specific integrated circuit (ASIC), a general-purpose computer, or any other similar hardware device can be used. In some embodiments, the software program of this application can be executed by a processor to implement the above steps or functions. Similarly, the software program of this application (including related data structures) can be stored in a computer-readable recording medium, for example, a RAM memory, a magnetic or optical drive, or a floppy disk and similar devices. In addition, some steps or functions of this application can be implemented by hardware, for example, as a circuit that cooperates with a processor to execute each step or function.

[0105] The computer program product provided by the embodiments of this application includes one or more computer programs / instructions. When the computer programs / instructions are executed by a processor, they entirely or partially generate the processes or functions described in the embodiments of this application. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more integrated available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)), etc.

[0106] The flowcharts or block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of devices, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code, which contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the block may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0107] The scope of the present application is defined by the appended claims rather than the above description. Therefore, all changes that fall within the meaning and scope of the equivalent elements of the claims are intended to be included in the present application. Any reference numerals in the claims should not be construed as limiting the claims involved. In addition, it is obvious that the term "including" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units or devices stated in the apparatus claims may also be implemented by one unit or device through software or hardware. The terms "first", "second", etc. are only used for distinguishing descriptions and do not represent any specific order, nor can they be construed as indicating or implying relative importance.

[0108] As described above, the above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily mention changes or substitutions, which should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims, and the above embodiments should be regarded as exemplary and non-limiting.

Claims

1. A method for improving the filtering of surface metal of a dewaxing and cleaning machine, characterized in that, Including the following steps: Using an industrial camera to collect the overall image of the semiconductor, and performing image extraction to obtain a semiconductor image containing irregular impurities; Performing image enhancement processing on the semiconductor image by using multi-scale illumination compensation combined with morphological enhancement method, and extracting the enhanced image to obtain the fine impurity information on the semiconductor surface; Based on the fine impurities extracted from the semiconductor surface, cleaning the semiconductor surface.

2. The method for filtering surface metal of the lifting dewaxing and cleaning machine according to claim 1, characterized in that, The process of performing image enhancement processing on the semiconductor image by using multi-scale illumination compensation combined with morphological enhancement method, and extracting the enhanced image to obtain the fine impurity information on the semiconductor surface is as follows: Processing the semiconductor image by using an improved multi-scale Retinex and ROI edge extraction method, enhancing the contrast of impurities in the dark area of the semiconductor image to obtain impurity image information; Selecting the neighborhood pixels in the impurity image, setting a search window and a smoothing parameter, and suppressing the noise of the impurity image by using the non-local means denoising method; Performing frequency-domain detail enhancement on the suppressed impurity image to obtain image impurity prominent information; Performing morphological top-hat reconstruction on the image impurity prominent information, extracting the bright regions smaller than the structural element to obtain semiconductor impurity information.

3. The method for filtering surface metal of the lifting dewaxing and cleaning machine according to claim 2, characterized in that, The process of performing frequency-domain detail enhancement on the suppressed impurity image to obtain image impurity prominent information is as follows: Performing Fourier transform processing on the suppressed impurity image to obtain a processed impurity image; Performing ideal high-pass filtering processing on the processed impurity image and performing inverse transformation to amplify the impurity features in the image to obtain image impurity prominent information.

4. The method for filtering surface metal of the lifting dewaxing and cleaning machine according to claim 2, wherein The process of processing the semiconductor image by using an improved multi-scale Retinex and ROI edge extraction method, enhancing the contrast of impurities in the dark area of the semiconductor image to obtain impurity image information is as follows: Calculating the dynamic weight of the semiconductor image by using an edge-guided multi-scale weight allocation method, and calculating the enhanced output image by using an improved multi-scale Retinex method; Extracting the edge features of the enhanced output image based on the ROI edge-impurity separation method, and retaining the edge enhancement signal in the edge expansion region; Forming impurity image information based on the enhanced output image and the edge enhancement signal.

5. The method for filtering surface metal of the lifting dewaxing and cleaning machine according to claim 4, characterized in that, The process of calculating the dynamic weight of the semiconductor image by using an edge-guided multi-scale weight allocation method, and calculating the enhanced output image by using an improved multi-scale Retinex method is as follows: Processing the extracted semiconductor image to calculate the gradient magnitude of the semiconductor image; Performing multi-scale Gaussian smoothing on the gradient magnitude to generate an edge energy map with the same scale as Retinex; Performing local weight allocation at each scale according to the generated edge energy map to calculate the local weight; Calculating the enhanced output of the improved multi-scale Retinex based on the local weight.

6. The method for filtering surface metal of the lifting dewaxing and washing machine according to claim 4, characterized in that, The improved multi-scale Retinex method is: Among them, R edge (x, y) is the output image, ω k (x, y) is the local weight, log(S(x, y)) is the logarithmic domain representation of the original image, G σk (x, y)*S(x, y) is the Gaussian blur result of the k-th scale, indicating the illumination estimation at that scale.

7. The method for filtering surface metal of the lifting dewaxing and cleaning machine according to claim 4, characterized in that, The process of extracting edge features of the enhanced output image based on the ROI edge-impurity separation method and retaining edge enhancement signals in the edge extension area is as follows: Processing the semiconductor image using a Canny edge detection method to obtain an edge detection result, and refining the Canny edge detection result using non-maximum suppression to obtain a sub-pixel edge; Performing morphological dilation on the sub-pixel edge to compensate for edge positioning errors and obtain a dilation result; Performing top-hat edge processing on the enhanced image to extract bright areas that are smaller than the structural element; A regional intersection operation is performed based on the bright area and the dilation result to obtain a final impurity mask, that is, an edge enhancement signal.

8. A system for enhancing the filtration of surface metals in a dewaxing and cleaning machine, which is implemented by using the method for enhancing the filtration of surface metals in a dewaxing and cleaning machine according to any one of claims 1-7, characterized in that, include: Semiconductor image acquisition device (1), semiconductor impurity extraction device (2), cleaning device (3); The semiconductor image acquisition device (1) is used to acquire an overall semiconductor image using an industrial camera and perform image extraction to obtain a semiconductor image containing irregular impurities; The semiconductor impurity extraction device (2) is used to perform image enhancement processing on the semiconductor image and extract the enhanced image to obtain fine impurities on the semiconductor surface; The cleaning device (3) is used to clean the semiconductor surface based on the extracted fine impurities on the semiconductor surface.

9. The system for lifting and dewaxing cleaning machine to filter surface metal according to claim 8, characterized in that: The cleaning device (3) comprises: a particle filter (31), a metal filter (32), a concentration meter (33), an exhaust valve, and a water pump; The particle filter (31) is connected to the metal filter (32), the metal filter (32) is connected to the exhaust valve, and the water pump is connected to the inlet and outlet of the metal filter (32) via a water inlet pipe; The two drainage pipes at the lower part of the metal filter (32) are respectively connected with ball valves to form a pipeline, which is connected to the PPH alkali drainage main pipe; The thermometer (33) is mounted on a bracket of the cleaning device (3).

Images