Chip image registration method and device, equipment and storage medium
By combining images of different resolutions, low-resolution images are used for rapid preliminary registration, while high-resolution images are used for precise verification. This solves the problem of repetitive texture interference in chip image registration and achieves efficient and accurate chip image registration.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHENZHEN LIXIN SEMICON CO LTD
- Filing Date
- 2025-12-31
- Publication Date
- 2026-05-01
AI Technical Summary
Existing chip image registration methods tend to overlook key points when dealing with scenes with many repetitive textures, leading to a decrease in registration accuracy. Furthermore, existing technologies rely on phase information, resulting in insufficient accuracy during rapid registration.
Chip image registration is performed using image information at different resolutions. Low-resolution images are used for rapid preliminary registration, while high-resolution images are used for precise verification. Combining texture richness and geometric verification ensures registration accuracy.
While ensuring registration accuracy, the speed and efficiency of chip image registration are improved, the complexity of the registration algorithm is reduced, and the matching accuracy is enhanced.
Smart Images
Figure CN121962652A_ABST
Abstract
Description
Chip image registration methods, apparatus, devices and storage media Technical Field
[0001] This application relates to the field of image processing technology, and in particular to chip image registration methods, apparatus, devices and storage media. Background Technology
[0002] In the field of electronic design automation (EDA) for chip analysis, chip image registration is a crucial step. At multiple stages of chip design, manufacturing, and testing, chip images need to be accurately registered to ensure consistency between the design layout and the actual manufactured chip.
[0003] Chip image registration methods primarily rely on the phase information of chip images for registration, which is particularly suitable for scenarios with few repetitive textures. Because the repetitive textures between the images to be registered are minimal, rapid registration can be achieved using phase information. However, when repetitive cell designs appear in chip images, the registration of adjacent chip images often uses large areas of repetitive cells as the basis, thus ignoring crucial points that should be precisely aligned.
[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention
[0005] The main objective of this application is to provide a chip image registration method, apparatus, device, and storage medium, aiming to solve the technical problem that repeated textures in the image interfere with the registration accuracy during chip image registration.
[0006] To achieve the above objectives, this application proposes a chip image registration method, which includes: acquiring a chip image, the chip image including first resolution image information; downsampling the chip image to obtain second resolution image information corresponding to the chip image; the second resolution corresponding to the second resolution image information is less than the first resolution corresponding to the first resolution image information; performing a first registration verification on the chip image based on the second resolution image information to obtain a first verification value; and obtaining target registration information in response to the first verification value being greater than a first verification threshold; or, performing a second registration verification on the chip image based on the first resolution image information in response to the first verification value being less than the first verification threshold to obtain target registration information.
[0007] In one embodiment, acquiring a chip image includes: dividing the chip image into multiple sub-images to be processed; preprocessing each sub-image to be processed to obtain multiple chip sub-images; wherein the preprocessing includes image correction processing and image grayscale processing.
[0008] In one embodiment, a first registration verification is performed on the chip image based on the second resolution image information to obtain a first verification value. If the first verification value is greater than a verification threshold, target registration information is obtained. Alternatively, if the first verification value is less than the verification threshold, a second registration verification is performed on the chip image based on the first resolution image information to obtain target registration information. This includes: obtaining a first texture richness of the first resolution image information and a second texture richness of the second resolution image information; performing a first registration verification on the chip image based on the second texture richness to obtain a first verification value. If the first verification value is greater than the first verification threshold, target registration information is obtained. Alternatively, if the first verification value is less than the first verification threshold, performing a second registration verification on the chip image based on the first texture richness to obtain target registration information.
[0009] In one embodiment, obtaining the first texture richness of the first resolution image information and the second texture richness of the second resolution image information includes: obtaining the corresponding pixel variance in the first resolution image information and calculating the first texture richness; obtaining the corresponding pixel variance in the second resolution image information and calculating the second texture richness.
[0010] In one embodiment, a first registration verification is performed on the chip image based on a second texture richness to obtain a first verification value. If the first verification value is greater than a first verification threshold, target registration information is obtained. Alternatively, if the first verification value is less than the first verification threshold, a second registration verification is performed on the chip image based on the first texture richness to obtain target registration information. This includes: performing a first geometric verification based on the second texture richness and obtaining a first verification value; performing a second geometric verification based on the first texture richness and obtaining a second verification value if the first verification value is less than the first verification threshold; and outputting the corresponding registration relationship and obtaining target registration information if the second verification value is greater than the second verification threshold.
[0011] In one embodiment, performing a first geometric verification based on a second texture richness and obtaining a first verification value includes: in response to the second texture richness being greater than a first threshold, detecting feature points of the second resolution image information and obtaining a first feature value; performing a first geometric relationship verification based on the first feature value and obtaining a first verification value; or, in response to the second texture richness being less than the first threshold, performing phase matching on the second resolution image information and obtaining a first phase value; performing a first geometric verification based on the first phase value and obtaining a first verification value.
[0012] In one embodiment, performing a second geometric verification based on a first texture richness and obtaining a second verification value includes: in response to the first texture richness being greater than a second threshold, detecting feature points of the first resolution image information and obtaining a second feature value; performing a second geometric relationship verification based on the second feature value and obtaining a second verification value; or, in response to the first texture richness being less than the second threshold, performing phase matching on the first resolution image information and obtaining a second phase value; performing a second geometric relationship verification based on the second phase matching result and obtaining a second verification value.
[0013] Furthermore, to achieve the above objectives, this application also proposes an image registration device, which includes: an acquisition module for acquiring a chip image; a processing module for dividing the chip image to acquire multiple chip sub-images, each chip sub-image including second resolution image information; and downsampling each chip sub-image to acquire first resolution image information corresponding to each chip sub-image; wherein the second resolution corresponding to the second resolution image information is less than the first resolution corresponding to the first resolution image information; and an output module for performing a first registration verification on the chip image based on the second resolution image information to acquire a first verification value, and obtaining target registration information in response to the first verification value being greater than a first verification threshold; or, in response to the first verification value being less than the first verification threshold, performing a second registration verification on the chip image based on the first resolution image information to obtain target registration information.
[0014] In addition, to achieve the above objectives, this application also proposes an image registration apparatus, the apparatus comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the image registration apparatus method as described above.
[0015] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the chip image registration device method described above.
[0016] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the chip image registration apparatus method as described above.
[0017] The one or more technical solutions proposed in this application have at least the following technical effects: by using images of different resolutions, under the condition of meeting the registration accuracy, the lower resolution is used for fast registration, and under the condition that the registration accuracy cannot be met, the higher resolution image is used to ensure the registration accuracy. By combining images of different resolutions for registration, the complexity of the registration algorithm is reduced and the registration efficiency is improved while ensuring the registration accuracy. Attached Figure Description
[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0020] Figure 1 is a flowchart illustrating a first embodiment of the chip image registration method provided in this application; Figure 2 is a flowchart illustrating an embodiment of step S10 in the chip image registration method provided in this application; Figure 3 is a flowchart illustrating an embodiment of step S30 in the chip image registration method provided in this application; Figure 4 is a flowchart illustrating an embodiment of step A32 in the chip image registration method provided in this application; Figure 5 is a flowchart illustrating an embodiment of step B32 in the chip image registration method provided in this application; Figure 6 is a flowchart illustrating an embodiment of step B33 in the chip image registration method provided in this application; Figure 7 is a structural schematic diagram of an embodiment of the image registration apparatus provided in this application; Figure 8 is a structural schematic diagram of an embodiment of the image registration device provided in this application.
[0021] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0022] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.
[0023] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.
[0024] The main solution of this application embodiment is to provide a chip image registration method, which includes: acquiring a chip image, the chip image including first resolution image information; downsampling the chip image to obtain second resolution image information corresponding to the chip image; the second resolution corresponding to the second resolution image information is less than the first resolution corresponding to the first resolution image information; and performing chip image registration verification based on the second resolution image information and / or the first resolution image information to obtain target registration information.
[0025] In practical applications of electronic design automation (EDA) for chip analysis, chip image registration often faces numerous challenges due to various factors such as equipment precision, operational errors, and material deformation. These challenges not only affect the accuracy of chip design but may also lead to a decrease in yield during the manufacturing process, thereby increasing production costs and time. Therefore, achieving efficient and accurate chip image registration has become an urgent problem to be solved in the EDA field.
[0026] Current technologies primarily rely on phase information from chip images for registration. This approach is particularly suitable for scenarios with minimal repetitive textures, as the limited texture overlap between the images allows for rapid registration using phase information. However, when chip images contain repetitive cell designs, large areas of these repetitive cells are often used as the basis for registration when registering adjacent chip images, neglecting crucial points that should be precisely aligned. When registering two images, these repetitive texture cells severely interfere with registration accuracy, causing the crucial points that should be aligned below to fail to match correctly.
[0027] This application provides a chip image registration method, apparatus, device, and storage medium to solve the above-mentioned problems and improve the speed and efficiency of chip image registration while meeting the chip image registration accuracy requirements.
[0028] As can be seen from the above embodiments, this application improves the speed and efficiency of chip registration by using different resolutions of chip images and combining the first resolution with the second resolution, while meeting the accuracy of chip image registration.
[0029] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or apparatus capable of performing the above functions. The following description uses a chip image registration device as an example to illustrate this embodiment and the subsequent embodiments.
[0030] Based on this, the present application provides a chip image registration method. Referring to FIG1, FIG1 is a flowchart of the first embodiment of the chip image registration method provided in this application.
[0031] In this embodiment, the chip image registration method includes steps S10 to S40, and the specific steps are as follows: Step S10: Obtain the chip image, which includes first resolution image information.
[0032] It should be noted that acquiring chip images can be done using image acquisition methods or devices, including but not limited to microscopes, to capture images of the chip from multiple angles and positions. During the imaging process, it is essential to ensure that the image acquisition equipment has sufficiently high resolution and accuracy to capture subtle features on the chip surface. Simultaneously, by precisely controlling the shooting angle and position, image information from different areas of the chip can be obtained, providing rich data support for subsequent image registration.
[0033] In one embodiment, an automated shooting system can also be used during shooting to achieve rapid and accurate acquisition of chip images through preset shooting parameters and paths, thereby further improving acquisition efficiency and accuracy.
[0034] It is understandable that step S10 is used to obtain a chip image, thereby providing data support for the subsequent image stitching process.
[0035] In one feasible implementation, as shown in FIG2, FIG2 is a flowchart of an embodiment of step S10 in the chip image registration method provided in this application; step S10 may include steps A11 to A12, and the specific steps are as follows: step A11, dividing the chip image to obtain multiple sub-images to be processed.
[0036] In one embodiment, the chip image is divided according to a set step size. For example, the image block size is set to 64×64, and the step size is 8. The chip image is divided into blocks according to the set block parameters to obtain multiple sub-images to be processed.
[0037] In other embodiments, the chip sub-image is preprocessed to improve parameter accuracy, so as to reduce data processing during subsequent registration work and improve registration accuracy.
[0038] Step A12: Preprocess each sub-image to be processed to obtain multiple chip sub-images; wherein, the preprocessing includes image correction processing and image grayscale processing.
[0039] Understandably, preprocessing can improve the accuracy of subsequent parameters, thereby reducing data processing and increasing the accuracy of registration during the registration process.
[0040] In this embodiment, by dividing the chip image, multiple chip sub-images are obtained, which facilitates the connection of multiple chip sub-images in the subsequent image stitching process, thereby improving the stitching efficiency of the chip image and enhancing the accuracy of chip image registration.
[0041] The above are merely feasible implementations of step S10 provided in this embodiment. This embodiment does not specifically limit the specific implementation of step S10.
[0042] Step S20: Downsample the chip image to obtain the second resolution image information corresponding to the chip image; the second resolution corresponding to the second resolution image information is less than the first resolution corresponding to the first resolution image information.
[0043] Understandably, during the matching process of chip images, the resolution directly affects the amount of data that the computer needs to process. Higher resolution requires a large amount of data processing, which places specific demands on the computer's processing performance and requires the computer to run for a long time to process this amount of data. Therefore, the registration efficiency cannot be guaranteed, and it is difficult to process large amounts of data quickly in a short time.
[0044] Therefore, step S20 involves acquiring a lower resolution image so that subsequent calculations can be performed using the lower resolution image for registration, which effectively reduces computational complexity and improves data processing efficiency.
[0045] Step S30: Perform a first registration verification on the chip image based on the second resolution image information to obtain a first verification value. If the first verification value is greater than the first verification threshold, obtain target registration information; or, if the first verification value is less than the first verification threshold, perform a second registration verification on the chip image based on the first resolution image information to obtain target registration information.
[0046] In the chip image registration process, to ensure registration efficiency, lower-resolution images are selected for batch processing to improve efficiency and achieve large-area image registration. However, in some cases, some images may fail to meet registration requirements due to excessively low resolution or low registration accuracy. Therefore, for low-resolution images in such cases, they are converted into corresponding high-resolution images (i.e., the image before sampling, the first-resolution image information), thus completing the image registration while ensuring accuracy.
[0047] In one feasible implementation, as shown in FIG3, FIG3 is a schematic flowchart of an embodiment of step S30 in the chip image registration method provided in this application; step S30 may include steps A31 to A33, and the specific steps are as follows: step A31: obtain the first texture richness of the first resolution image information and the second texture richness of the second resolution image information.
[0048] It is understandable that in the above embodiment, the texture richness in the first resolution image information and the second resolution image information is acquired so that the image registration can be verified based on the texture richness in the subsequent process.
[0049] In one feasible implementation, step A31 may include step B31, the specific steps of which are as follows: Step B31: Obtain the pixel variance corresponding to the first resolution image information and calculate the first texture richness; obtain the pixel variance corresponding to the second resolution image information and calculate the second texture richness.
[0050] In one embodiment, the specific operation for obtaining the texture richness of a chip image through variance is as follows: First, obtain the grayscale value of each corresponding pixel in the chip image; second, calculate the variance of the grayscale values based on the grayscale value information, which can be used as an indicator to measure texture richness. It can be understood that the larger the variance, the more dispersed the distribution of the pixel's grayscale values, and the greater the texture richness of the image. Conversely, the smaller the variance, the more concentrated the pixel's grayscale values, and the relatively simpler the image texture.
[0051] By using the above method, the variance of the grayscale values of pixels in the image information is used as a standard to measure the texture richness. This allows for the accurate and efficient calculation of the texture richness of the first resolution image information and / or the second resolution image information, providing crucial basis and support for subsequent registration work.
[0052] Step A32: Perform a first registration verification on the chip image based on the second texture richness to obtain a first verification value. If the first verification value is greater than the first verification threshold, obtain target registration information; or, if the first verification value is less than the first verification threshold, perform a second registration verification on the chip image based on the first texture richness to obtain target registration information.
[0053] After obtaining the texture richness in the image information, the chip image can be registered based on the texture richness. After the first texture richness and / or the second texture richness meet certain judgment conditions, different registration methods are performed accordingly. This avoids ignoring key points that should be precisely aligned when there are many repeated textures due to different texture distributions in the chip image, such as some images having fewer repeated textures and some images having more repeated textures. This achieves accurate matching of the chip image.
[0054] In one feasible implementation, as shown in FIG4, FIG4 is a schematic flowchart of an embodiment of step A32 in the chip image registration method provided in this application; step A32 may include steps B32 to B34, and the specific steps are as follows: step B32: perform a first geometric verification based on the second texture richness and obtain a first verification value.
[0055] It should be noted that regarding geometric verification, during chip image registration, partial recognition errors may occur due to repetitive textures. For example, a sub-image of a certain block may be incorrectly identified due to a large number of repetitive textures, exceeding its original position and registering with another sub-image in a different area. Therefore, considering the above-mentioned possible situations, geometric verification is proposed, which verifies the image using its positional information. In other embodiments, geometric verification can also be performed by combining overlap rate and positional information to determine whether the images are registered.
[0056] Taking adjacent images as an example, during registration, it is essential to ensure that the right side of the left image is precisely aligned with the left side of the right image. If the right side of the left image fails to align accurately with the leftmost part of the right image, it indicates an error in the geometric relationship, resulting in incorrect registration of image edge information. This geometric relationship can be determined directly by calculating the horizontal coordinate of the image alignment position.
[0057] By using the above method, the situation where image stitching loses its original position due to repeated textures is eliminated, thus increasing the accuracy of image registration.
[0058] In another feasible implementation, as shown in FIG5, FIG5 is a flowchart of an embodiment of step B32 in the chip image registration method provided in this application; step B32 may include steps B321 to B324, and the specific steps are as follows: step B321: in response to the second texture richness being greater than the first threshold, feature points of the second resolution image information are detected to obtain the first feature value.
[0059] Step B322: Based on the first feature value, perform the first geometric relationship verification to obtain the first verification value.
[0060] It should be noted that feature point detection, which obtains the first feature value, refers to relying on local feature information in the image (such as corners, edges, textures, and other visual features that can be recognized by the algorithm). By extracting and matching these features in the overlapping area, it mainly relies on the texture / contour features of the image. The stitching accuracy can be controlled, and precise registration can be achieved.
[0061] Understandably, in the above scheme, when the second texture richness is greater than the first threshold, it indicates that there are many repeated textures. If phase information is used for registration at this time, these repeated texture units will seriously interfere with the registration accuracy during the registration process, causing the key points that should be aligned below to fail to match and align correctly.
[0062] Therefore, in the above scheme, feature points are used to accurately align the key points, avoiding interference caused by a large number of repeated textures and improving the accuracy of registration.
[0063] Alternatively, step B323: In response to the second texture richness being less than the first threshold, perform phase matching on the second resolution image information to obtain the first phase value.
[0064] Step B324: Perform the first geometric verification based on the first phase value to obtain the first verification value.
[0065] It should be noted that the phase matching mentioned above, obtaining the first phase value, refers to first transforming the image from the spatial domain to the frequency domain (usually through Fourier transform). The frequency domain information of the image can be divided into amplitude information and phase information. Among them, the phase information records the spatial structure and positional information of the image. This stitching method relies on the phase information of the overlapping areas to calculate the positional offset between the images and complete the stitching. This method does not rely on the texture features of the image, but the accuracy is generally low.
[0066] Understandably, in the above scheme, if the detected texture richness is less than the first threshold, that is, the texture repetition is less, then phase information is considered for registration, which can quickly achieve registration and improve the efficiency of chip image registration.
[0067] Step B33: In response to the first verification value being less than the first verification threshold, perform a second geometric verification based on the first texture richness and obtain the second verification value.
[0068] Understandably, when the first verification value is greater than the first verification threshold, it indicates that the current geometric relationship has passed verification, and the corresponding correct matching relationship can be directly output.
[0069] When the first verification value is less than the first verification threshold, it indicates that the current geometric relationship verification has failed. Therefore, the first texture richness is used for the second geometric verification. Since the first texture richness is calculated from the first resolution image information with higher resolution, the registration accuracy can be improved with the support of high resolution. However, high resolution means more data processing, which will increase the amount of computation.
[0070] In another feasible implementation, as shown in FIG6, FIG6 is a schematic flowchart of an embodiment of step B33 in the chip image registration method provided in this application; step B33 may include steps B331 to B334, and the specific steps are as follows: step B331: in response to the first texture richness being greater than the second threshold, feature points of the first resolution image information are detected to obtain the second feature value.
[0071] Step B332: Based on the second feature value, perform the second geometric relationship verification to obtain the second verification value.
[0072] Alternatively, step B333: In response to the first texture richness being less than the second threshold, phase matching is performed on the first resolution image information to obtain the second phase value.
[0073] Step B334: Based on the second phase matching result, perform the second geometric relationship verification and obtain the second verification value.
[0074] It is understood that steps B341 to B344 in this embodiment correspond to the verification process of the first resolution image. The scheme is roughly similar to the verification process of the second resolution image corresponding to steps B331 to B334. For content that is the same as or similar to the above embodiment, please refer to the above description, and it will not be repeated hereafter.
[0075] By combining the first-resolution image information and the second-resolution image information in the above manner, image stitching registration is completed at two different resolutions. When the registration accuracy is met, the lower-resolution image information is used to achieve fast registration processing. When the registration accuracy is not met, the higher-resolution image information is used to improve the registration accuracy. Thus, while ensuring the registration accuracy, the complexity of the registration algorithm can be reduced, the amount of data processed can be reduced, and the registration efficiency can be improved.
[0076] Step B34: In response to the second verification value being greater than the second verification threshold, output the corresponding registration relationship and obtain the target registration information.
[0077] As mentioned above, if the second verification value is greater than the second verification threshold, it indicates that the current matching relationship is correct.
[0078] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the chip image registration method of this application. Any simple transformations based on this technical concept are all within the protection scope of this application.
[0079] This application also provides an image registration device 100. Please refer to Figure 7, which is a structural schematic diagram of an embodiment of the image registration device provided in this application. The image registration device 100 includes: an acquisition module 10 for acquiring a chip image; a processing module 20 for dividing the chip image to acquire multiple chip sub-images, each chip sub-image including second resolution image information; and downsampling each chip sub-image to acquire first resolution image information corresponding to each chip sub-image; the second resolution corresponding to the second resolution image information is less than the first resolution corresponding to the first resolution image information; and an output module 30 for performing a first registration verification on the chip image based on the second resolution image information to acquire a first verification value, and obtaining target registration information in response to the first verification value being greater than a first verification threshold; or, in response to the first verification value being less than the first verification threshold, performing a second registration verification on the chip image based on the first resolution image information to obtain target registration information.
[0080] The image registration device 100 provided in this application employs the chip image registration method in the above embodiments, which can solve the technical problems of low matching accuracy and efficiency in chip image registration. Compared with the prior art, the beneficial effects of the image registration device 100 provided in this application are the same as those of the chip image registration method provided in the above embodiments, and other technical features in the image registration device 100 are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.
[0081] This application provides an image registration device 200, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the chip image registration method in the first embodiment described above.
[0082] Referring now to FIG8, FIG8 is a structural schematic diagram of an embodiment of the image registration device provided in this application; it shows a structural schematic diagram of the image registration device 200 suitable for implementing the embodiments of this application. The image registration device 200 in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle terminals (e.g., vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. The image registration device 200 shown in FIG8 is merely an example and should not impose any limitations on the function and scope of use of the embodiments of this application.
[0083] As shown in Figure 8, the image registration device 200 may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the image registration device 200. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows image registration device 200 to communicate wirelessly or wiredly with other devices to exchange data. Although an image registration device 200 with various systems is shown in the figure, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems may be implemented alternatively.
[0084] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.
[0085] The image registration device 200 provided in this application, employing the chip image registration method in the above embodiments, can solve the technical problems of low matching accuracy and efficiency in chip image registration. Compared with the prior art, the beneficial effects of the image registration device 200 provided in this application are the same as those of the chip image registration method provided in the above embodiments, and other technical features of the image registration device 200 are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.
[0086] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.
[0087] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
[0088] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the chip image registration method in the above embodiments.
[0089] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.
[0090] The aforementioned computer-readable storage medium may be included in the image registration device 200; or it may exist independently and not be assembled into the image registration device 200.
[0091] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the image registration device 200, enable the image registration device 200 to solve the technical problems of low matching accuracy and efficiency in chip image registration.
[0092] Computer program code for performing the operations of this application can be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, and C++, and 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, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0093] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0094] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.
[0095] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described chip image registration method, which can solve the technical problems of low matching accuracy and efficiency in chip image registration. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the chip image registration method provided in the above embodiments, and will not be repeated here.
[0096] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the chip image registration method described above.
[0097] The computer program product provided in this application can solve the technical problems of low matching accuracy and efficiency in chip image registration. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the image registration method provided in the above embodiments, and will not be repeated here.
[0098] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.
Claims
1. A chip image registration method, characterized in that, The chip image registration method includes: acquiring a chip image, the chip image including first resolution image information; downsampling the chip image to obtain second resolution image information corresponding to the chip image; the second resolution corresponding to the second resolution image information is less than the first resolution corresponding to the first resolution image information; performing a first registration verification on the chip image based on the second resolution image information to obtain a first verification value; and obtaining target registration information in response to the first verification value being greater than a first verification threshold; or, performing a second registration verification on the chip image based on the first resolution image information in response to the first verification value being less than the first verification threshold to obtain target registration information.
2. The chip image registration method as described in claim 1, characterized in that, The process of acquiring the chip image includes: dividing the chip image into multiple sub-images to be processed; preprocessing each sub-image to be processed to obtain multiple chip sub-images; wherein the preprocessing includes image correction processing and image grayscale processing.
3. The chip image registration method as described in claim 1, characterized in that, The chip image is first registered and verified according to the second resolution image information to obtain a first verification value. In response to the first verification value being greater than the verification threshold, target registration information is obtained. Alternatively, in response to the first verification value being less than the verification threshold, a second registration verification is performed on the chip image based on the first resolution image information to obtain target registration information, including: obtaining the first texture richness of the first resolution image information and the second texture richness of the second resolution image information; The chip image is subjected to a first registration verification based on the second texture richness to obtain the first verification value. If the first verification value is greater than the first verification threshold, target registration information is obtained; or, if the first verification value is less than the first verification threshold, the chip image is subjected to a second registration verification based on the first texture richness to obtain target registration information.
4. The chip image registration method as described in claim 3, characterized in that, The step of obtaining the first texture richness of the first resolution image information and the second texture richness of the second resolution image information includes: obtaining the corresponding pixel variance in the first resolution image information and calculating the first texture richness; obtaining the corresponding pixel variance in the second resolution image information and calculating the second texture richness.
5. The chip image registration method as described in claim 3, characterized in that, The chip image is first registered and verified according to the second texture richness to obtain the first verification value. In response to the first verification value being greater than the first verification threshold, target registration information is obtained. Alternatively, in response to the first verification value being less than the first verification threshold, a second registration verification is performed on the chip image based on the first texture richness to obtain target registration information, including: performing a first geometric verification based on the second texture richness and obtaining the first verification value; If the first verification value is less than the first verification threshold, a second geometric verification is performed based on the first texture richness, and a second verification value is obtained; if the second verification value is greater than the second verification threshold, the corresponding registration relationship is output, and the target registration information is obtained.
6. The chip image registration method as described in claim 5, characterized in that, The step of performing a first geometric verification based on the second texture richness and obtaining a first verification value includes: in response to the second texture richness being greater than a first threshold, detecting feature points of the second resolution image information and obtaining a first feature value; performing a first geometric relationship verification based on the first feature value and obtaining a first verification value; or, in response to the second texture richness being less than the first threshold, performing phase matching on the second resolution image information and obtaining a first phase value; performing a first geometric verification based on the first phase value and obtaining a first verification value.
7. The chip image registration method as described in claim 5, characterized in that, The step of performing a second geometric verification based on the first texture richness and obtaining a second verification value includes: in response to the first texture richness being greater than a second threshold, detecting feature points of the first resolution image information and obtaining a second feature value; performing a second geometric relationship verification based on the second feature value and obtaining a second verification value; or, in response to the first texture richness being less than the second threshold, performing phase matching on the first resolution image information and obtaining a second phase value; performing a second geometric relationship verification based on the second phase matching result and obtaining a second verification value.
8. An image registration device, characterized in that, The image registration device includes: an acquisition module for acquiring a chip image; a processing module for dividing the chip image to acquire multiple chip sub-images, each chip sub-image including second resolution image information; and downsampling each chip sub-image to acquire first resolution image information corresponding to each chip sub-image; wherein the second resolution corresponding to the second resolution image information is less than the first resolution corresponding to the first resolution image information; and an output module for performing a first registration verification on the chip image based on the second resolution image information to acquire a first verification value, and obtaining target registration information in response to the first verification value being greater than a first verification threshold; or, in response to the first verification value being less than the first verification threshold, performing a second registration verification on the chip image based on the first resolution image information to obtain target registration information.
9. An image registration device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the chip image registration method as described in any one of claims 1 to 7.
10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the chip image registration method as described in any one of claims 1 to 7.