Wafer ocr recognition method and recognition device based on template matching

Abstract

This invention provides a wafer OCR recognition method and device based on template matching. The wafer OCR recognition method includes the following steps: creating an OCR character outline template and a target area outline template in a preset coordinate system; acquiring a wafer image; using template matching to find OCR character outlines on the wafer image in the preset coordinate system based on the created OCR character outline template, determining the scaling ratio and rotation angle, and determining the center of the rough OCR character outline; translating the wafer image so that the center of the rough OCR character outline coincides with the center of the OCR character outline template; scaling and rotating the target area outline template according to the scaling ratio and rotation angle to obtain the actual target area outline; extracting the image within the actual target area outline in the wafer image; extracting and recognizing each character within the wafer OCR character area. This invention greatly improves the recognition accuracy and applicability of wafer OCR.

Description

Technical Field

[0001] The present invention belongs to the technical field of wafer OCR recognition, and particularly relates to a wafer OCR recognition method and recognition device based on template matching. Background Art

[0002] Wafer processing is a very important part of the chip production process. Each wafer has a unique number (Wafer ID), which is the OCR (Chinese name: identification code) of the wafer. Through this OCR, the production information of the wafer can be queried. In the front-end process, the OCR of the wafer is usually on the back of the wafer; in the back-end packaging and testing stage, after the wafer is tested by probing, the corresponding Map image information will be written into the OCR of the wafer. Through the wafer OCR, it can be known which DIEs in the wafer are qualified, providing information assistance for subsequent packaging and testing.

[0003] The commonly used methods for reading wafer OCR mainly include manual recording and traditional camera recognition. The manual recognition method has high accuracy, but it takes a long time, and workers are prone to make mistakes when working for a long time. The camera recognition method has a high degree of automation and a relatively fast recognition time, but it has high requirements for wafer characters, lighting conditions, and camera fields of view. When the wafer has a large deflection angle or the wafer characters become larger or smaller, the recognition accuracy is low and unstable. Summary of the Invention

[0004] Therefore, the present invention provides a wafer OCR recognition method and recognition device based on template matching, which can solve the technical problem of low OCR recognition accuracy in the prior art when the wafer has a large deflection angle or the wafer characters become larger or smaller.

[0005] To solve the above problems, the present invention provides a wafer OCR recognition method based on template matching, which includes the following steps:

[0006] Create an OCR character contour template and a target area contour template corresponding to the OCR character contour template in a preset coordinate system; wherein, the OCR character contour is located within the target area contour;

[0007] Obtain a wafer image and place the wafer image in the preset coordinate system;

[0008] According to the created OCR character contour template, use the template matching method to find the OCR character contour on the wafer image in the preset coordinate system, obtain a rough OCR character contour, and determine the scaling ratio and rotation angle between the rough OCR character contour and the OCR character contour template, and determine the center of the rough OCR character contour;

[0009] The wafer image is translated within the preset coordinate system so that the center of the rough OCR character outline is aligned with the center of the OCR character outline template.

[0010] The target region contour template is scaled and rotated according to the scaling ratio and rotation angle to obtain the actual target region contour.

[0011] Extract the image within the actual target region outline of the wafer image to obtain the wafer OCR character region image;

[0012] Extract each character within the character area of ​​the wafer OCR;

[0013] Each character is identified sequentially.

[0014] In some embodiments, the extraction of each character within the wafer OCR character area specifically includes:

[0015] Threshold segmentation is performed on the OCR character region of the wafer to obtain different connected components;

[0016] Each of the connected components is subjected to structural filtering to filter out the character connected components, thus obtaining each character.

[0017] In some implementations, the structure screening includes: area comparison and / or length comparison and / or width comparison.

[0018] In some implementations, each character is identified sequentially, specifically including:

[0019] Each character in the wafer OCR is trained to obtain a recognition model for each character.

[0020] Each character is identified sequentially according to the recognition model.

[0021] The present invention also provides a wafer OCR recognition device based on template matching, which includes a template creation module, a wafer image acquisition module, a template matching module, a position compensation module, a scaling and rotation module, a wafer OCR extraction module, a character extraction module, and a recognition module;

[0022] The template creation module is used to create an OCR character outline template and a target area outline template corresponding to the OCR character outline template within a preset coordinate system; wherein, the OCR character outline is located within the target area outline; the wafer image acquisition module is used to acquire a wafer image and place the wafer image within the preset coordinate system; the template matching module is used to find the OCR character outline on the wafer image within the preset coordinate system using template matching based on the created OCR character outline template, to obtain a coarse OCR character outline, and to determine the scaling ratio and rotation angle between the coarse OCR character outline and the OCR character outline template, and to determine... The center of the rough OCR character outline; the position compensation module is used to translate the wafer image within the preset coordinate system so that the center of the rough OCR character outline is consistent with the center of the OCR character outline template; the scaling and rotation module is used to scale and rotate the target area outline template according to the scaling ratio and rotation angle to obtain the actual target area outline; the wafer OCR extraction module is used to extract the image within the actual target area outline of the wafer image to obtain the wafer OCR character area image; the character extraction module is used to extract each character within the wafer OCR character area; the recognition module is used to recognize each character sequentially.

[0023] The wafer OCR recognition method and device based on template matching provided by this invention have the following beneficial effects:

[0024] 1. The technical solution of the present invention sets a character template image corresponding to the wafer, and performs scaling and / or rotation processing on the acquired wafer image through the character template image, so that the wafer can match the character template image when the deflection angle is large and the characters are enlarged or reduced, so as to facilitate subsequent recognition. This greatly improves the recognition accuracy and applicability of wafer OCR, and maintains high recognition accuracy even when the wafer deflection angle is large and the characters are enlarged or reduced.

[0025] 2. By setting a target region contour template corresponding to the character contour template, and scaling and rotating the target region contour template according to the determined scaling ratio and rotation angle, the actual target region contour can be obtained. This can accurately extract the OCR character region within the wafer image and avoid the situation of incomplete OCR character region extraction. Attached Figure Description

[0026] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. The drawings described below are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.

[0027] Figure 1 This is a flowchart of a wafer OCR recognition method based on template matching according to the present invention;

[0028] Figure 2 This is a diagram illustrating the creation of a character template;

[0029] Figure 3 This is a diagram illustrating template matching and positioning;

[0030] Figure 4 This is a diagram illustrating the extraction of character regions;

[0031] Figure 5 This is a diagram illustrating the separator characters;

[0032] Figure 6 This is a schematic diagram of wafer OCR recognition;

[0033] Figure 7 A diagram showing the relationship between a rough OCR character outline and an OCR character outline template within a preset coordinate system is provided. Detailed Implementation

[0034] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the present invention or its application or use. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0035] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this application. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0036] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0037] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of the invention. It should also be understood that, for ease of description, the structures, proportions, sizes, etc., shown in the accompanying drawings are only for the purpose of illustrative purposes and to facilitate understanding and reading by those skilled in the art, and are not intended to limit the conditions under which the invention can be implemented. Any modifications to the structure, changes in proportions, or adjustments to size, without affecting the effects and objectives achieved by the invention, should still fall within the scope of the technical content disclosed in the invention. Techniques, methods, and devices known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and devices should be considered part of the specification. In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar reference numerals and letters in the following figures denote similar items; therefore, once an item is defined in one figure, it does not need to be further discussed in subsequent figures.

[0038] In the description of this invention, it should be understood that the orientation or positional relationship indicated by directional terms such as "front, back, up, down, left, right", "horizontal, vertical, horizontal" and "top, bottom" is generally based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing this invention and simplifying the description. Unless otherwise stated, these directional terms do not indicate or imply that the device or element referred to must have a specific orientation or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on the scope of protection of this invention; the directional terms "inner" and "outer" refer to the inner and outer contours relative to the outline of each component itself.

[0039] For ease of description, spatial relative terms such as "above," "on top of," "on the upper surface of," "above," etc., are used herein to describe the spatial positional relationship of a device or feature as shown in the figures to other devices or features. It should be understood that spatial relative terms are intended to encompass different orientations in use or operation beyond the orientation of the device as described in the figures. For example, if the device in the figures were inverted, a device described as "above" or "on top of" other devices or structures would subsequently be positioned as "below" or "under" other devices or structures. Thus, the exemplary term "above" can include both "above" and "below." The device may also be positioned in other different ways (rotated 90 degrees or in other orientations), and the spatial relative descriptions used herein will be interpreted accordingly.

[0040] Furthermore, it should be noted that the use of terms such as "first" and "second" to define components is merely for the purpose of distinguishing the corresponding components. Unless otherwise stated, the above terms have no special meaning and therefore should not be construed as limiting the scope of protection of this invention.

[0041] See also Figure 1-6 As shown in the embodiment of the present invention, a wafer OCR recognition method based on template matching is provided, which includes the following steps:

[0042] Step S1: Create an OCR character outline template and a target area outline template corresponding to the OCR character outline template within a preset coordinate system. The OCR character outline is located within the target area outline.

[0043] Among them, such as Figure 2 As shown, to ensure the recognition accuracy of subsequent wafer OCR, it is necessary to create qualified character template images to ensure that subsequent wafer OCR can match them. Specifically, the character template image should be clear, and the character template box should be as small as possible to reduce interference with character extraction.

[0044] In addition, the target area outline module mentioned above can be a rectangular outline. Within the preset coordinate system, the center coordinates of the OCR character outline template are (x0, y0).

[0045] Step S2: Obtain a wafer image and place the wafer image within the preset coordinate system.

[0046] One approach is to use an industrial camera, a zoom lens, and a bar light source to form a data acquisition module for acquiring wafer images. Using this module ensures high-quality images, and by adjusting the light source brightness, it can be applied to most wafer image acquisition scenarios.

[0047] It should be noted that wafer images captured by a camera need to be preprocessed to enhance image features and reduce noise.

[0048] Step S3: As Figure 3 As shown, based on the created OCR character outline template, the template matching method is used to find the OCR character outline on the wafer image within the preset coordinate system to obtain a rough OCR character outline. The scaling ratio and rotation angle between the rough OCR character outline and the OCR character outline template are determined, and the center of the rough OCR character outline is determined.

[0049] The template matching method used is an existing technology, which can find OCR character outlines on wafer images. However, due to the low accuracy of template matching, the found OCR character outlines may contain missing or incomplete characters. Further, more precise searching of the OCR character outlines is needed.

[0050] In step S3, the center of the rough OCR character outline is (x1, y1), the scaling ratio between the rough OCR character outline and the OCR character outline template is (Sx, Sy), and the rotation angle is θ. The two-dimensional transformation matrix Vector_2D of this rough OCR character outline is:

[0051]

[0052] Step S4: Translate the wafer image within the preset coordinate system so that the center of the rough OCR character outline is aligned with the center of the OCR character outline template.

[0053] It should be noted here that the translation distance along the X-axis in the preset coordinate system is ΔX, and the translation distance along the Y-axis is ΔY.

[0054]

[0055]

[0056] Step S5: Scale and rotate the target area contour template according to the scaling ratio and rotation angle to obtain the actual target area contour.

[0057] The actual target region contour transformation matrix Vector_2D' is:

[0058]

[0059] Step S6: As Figure 4As shown, the image within the actual target region outline in the wafer image is extracted to obtain the wafer OCR character region image.

[0060] Step S7: Extract each character from the OCR character area on the wafer.

[0061] Specifically, such as Figure 5 As shown, the extraction of each character within the wafer OCR character region can be achieved as follows: The wafer OCR character region is threshold-segmented to obtain different connected components. Each connected component is then subjected to structural filtering to identify the character connected components, thus obtaining each character.

[0062] Among these, some connected components are character connected components, while others are non-character connected components. By using structural filtering, the character connected components can be filtered out, thus obtaining the individual characters.

[0063] In a specific application example, the above structure filtering may include: area comparison and / or length comparison and / or width comparison. Specifically, by comparing the area of ​​each connected component with a preset area range value, and / or comparing the length of each connected component with a preset length range value, and / or comparing the width of each connected component with a preset width range value, if the area of ​​the connected component is within the preset area range value, and / or the length of the connected component is within the preset length range value, and / or the width of the connected component is within the preset width range value, then the connected component is the desired character connected component, that is, the connected component is filtered out.

[0064] Step S8: Recognize each character in turn.

[0065] Among them, such as Figure 6 As shown, the characters can be recognized sequentially in the following way: Each character in the wafer OCR is trained to obtain a recognition model for each character. Then, each character is recognized sequentially based on the recognition model.

[0066] It should be noted that character sets can be used to train the recognition model for each character. The specific training methods are existing technologies and will not be elaborated here. When recognizing unfamiliar characters, the character can be added to the character set for training, and the recognition model can be updated accordingly.

[0067] For ease of understanding, Figure 7 This diagram illustrates the relationship between a rough OCR character outline and an OCR character outline template within a preset coordinate system. In this example, the OCR character is AB. Figure 7 The top left corner is the OCR character outline template. The center point of the OCR character outline template is O1, and the coordinates of the center point O1 are (x0, y0). Figure 7The bottom right side shows a rough OCR character outline, with its center point O2 at coordinates (x1, y1). The distance between center points O2 and O1 along the X-axis is ΔX, and the distance between them along the Y-axis is ΔY. Figure 7 The rectangle outside the OCR character AB on the upper left is the outline template of the target area.

[0068] pass Figure 7 As can be seen, firstly, the wafer image within the preset coordinate system is moved so that the center points O2 and O1 coincide. Then, the target area contour template is scaled and rotated according to the determined scaling ratio and rotation angle to obtain the actual target area contour.

[0069] In the above example, the wafer OCR recognition method of the present invention sets a character outline template corresponding to the wafer and performs scaling and / or rotation processing on the acquired wafer image through the character outline template, so that the wafer can match the character template image when the deflection angle is large and the characters are enlarged or reduced, so as to facilitate subsequent recognition. This greatly improves the recognition accuracy and applicability of wafer OCR, and maintains high recognition accuracy even when the wafer deflection angle is large and the characters are enlarged or reduced.

[0070] In addition, by setting a target region contour template corresponding to the character contour template, and scaling and rotating the target region contour template according to the determined scaling ratio and rotation angle, the actual target region contour can be obtained. This can accurately extract the OCR character region within the wafer image and avoid the situation of incomplete OCR character region extraction.

[0071] This invention also provides a wafer OCR recognition device based on template matching, comprising a template creation module, a wafer image acquisition module, a template matching module, a position compensation module, a scaling and rotation module, a wafer OCR extraction module, a character extraction module, and a recognition module. The template creation module is used to create an OCR character outline template and a target region outline template corresponding to the OCR character outline template within a preset coordinate system; wherein the OCR character outline is located within the target region outline. The wafer image acquisition module is used to acquire a wafer image and place the wafer image within the preset coordinate system. The template matching module is used to find the OCR character outline on the wafer image within the preset coordinate system using template matching based on the created OCR character outline template, obtaining a coarse OCR character outline, determining the scaling ratio and rotation angle between the coarse OCR character outline and the OCR character outline template, and determining the center of the coarse OCR character outline. The position compensation module is used to translate the wafer image within the preset coordinate system so that the center of the coarse OCR character outline coincides with the center of the OCR character outline template. The scaling and rotation module is used to scale and rotate the target area contour template according to the scaling ratio and rotation angle to obtain the actual target area contour. The wafer OCR extraction module is used to extract the image within the actual target area contour of the wafer image to obtain the wafer OCR character area image. The character extraction module is used to extract each character within the wafer OCR character area. The recognition module is used to recognize each character sequentially.

[0072] In the above example, the wafer OCR recognition device sets a character template image corresponding to the wafer and performs scaling and / or rotation processing on the acquired wafer image using the character template image. This allows the wafer to match the character template image even when the wafer is rotated at a large angle and the characters are enlarged or reduced, facilitating subsequent recognition. This greatly improves the recognition accuracy and applicability of wafer OCR, and maintains high recognition accuracy even when the wafer is rotated at a large angle and the characters are enlarged or reduced.

[0073] It will be readily understood by those skilled in the art that, without conflict, the advantageous technical features of the above-mentioned methods can be freely combined and superimposed.

[0074] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention. The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the protection scope of the present invention.

Claims

1. A wafer OCR recognition method based on template matching, characterized in that: Includes the following steps: Create an OCR character outline template and a target area outline template corresponding to the OCR character outline template within a preset coordinate system; wherein, the OCR character outline is located within the target area outline; Acquire a wafer image and place the wafer image within the preset coordinate system; Based on the created OCR character outline template, the template matching method is used to find the OCR character outline on the wafer image in the preset coordinate system to obtain a rough OCR character outline. The scaling ratio and rotation angle between the rough OCR character outline and the OCR character outline template are determined, and the center of the rough OCR character outline is determined. The wafer image is translated within the preset coordinate system so that the center of the rough OCR character outline is aligned with the center of the OCR character outline template. The target region contour template is scaled and rotated according to the scaling ratio and rotation angle to obtain the actual target region contour. Extract the image within the actual target region outline of the wafer image to obtain the wafer OCR character region image; Extract each character within the character area of ​​the wafer OCR; Each character is identified sequentially.

2. The wafer OCR recognition method based on template matching according to claim 1, characterized in that: The extraction of each character within the wafer OCR character area specifically includes: Threshold segmentation is performed on the OCR character region of the wafer to obtain different connected components; Each of the connected components is subjected to structural filtering to filter out the character connected components, thus obtaining each character.

3. The wafer OCR recognition method based on template matching according to claim 2, characterized in that: The structural screening includes: area comparison and / or length comparison and / or width comparison.

4. The wafer OCR recognition method based on template matching according to claim 1, characterized in that: Each character is identified sequentially, specifically including: Each character in the wafer OCR is trained to obtain a recognition model for each character. Each character is identified sequentially according to the recognition model.

5. A wafer OCR recognition device based on template matching, characterized in that: It includes a template creation module, a wafer image acquisition module, a template matching module, a position compensation module, a scaling and rotation module, a wafer OCR extraction module, a character extraction module, and a recognition module; The template creation module is used to create an OCR character outline template and a target area outline template corresponding to the OCR character outline template within a preset coordinate system; wherein, the OCR character outline is located within the target area outline; The wafer image acquisition module is used to acquire a wafer image and place the wafer image within the preset coordinate system; The template matching module is used to find the OCR character outline on the wafer image in the preset coordinate system by using template matching based on the created OCR character outline template, to obtain a rough OCR character outline, and to determine the scaling ratio and rotation angle between the rough OCR character outline and the OCR character outline template, and to determine the center of the rough OCR character outline. The position compensation module is used to translate the wafer image within the preset coordinate system so that the center of the rough OCR character outline is consistent with the center of the OCR character outline template. The scaling and rotation module is used to scale and rotate the target area contour template according to the scaling ratio and rotation angle to obtain the actual target area contour. The wafer OCR extraction module is used to extract the image within the actual target region outline in the wafer image to obtain the wafer OCR character region image; The character extraction module is used to extract each character within the wafer OCR character area; The recognition module is used to recognize each character sequentially.

Images