Character printing defect detection method

Abstract

The present application discloses a method for detecting character printing defects, which obtains a local image of a character printing defect, or a real-time character printing defect image, and imports the character printing defect image into a system to preview the effect of the character printing defect image; performs defect detection on the character printing defect image, and displays the character printing defect detection results, marks the defect area of the image defect, and calculates the defect area; records the character printing defect detection results, generates a character printing defect detection template, and views, switches, or edits the character printing defect detection template. Compared with the existing technology, the present application has a higher detection accuracy, supports accurate identification of character edge defects, quantifies defects, supports area measurement of character defects, and facilitates customers to determine whether the defect is qualified or not based on the degree of the defect. It has a fast deployment efficiency and does not require the collection of large quantities of training samples. It has high defect detection accuracy and a deformation tolerance mechanism to avoid misjudgment due to printing differences.

Description

Technical Field

[0001] The present disclosure generally relates to the field of image recognition technology, and more particularly to a method for detecting character printing defects. Background Art

[0002] Character printing defect detection is widely used in products such as watch engraving, electronic component identification, and label coding. Its quality is directly related to product appearance and brand reputation. Current detection methods mostly use traditional image processing methods such as deep learning recognition, OCR technology, or template matching.

[0003] Template matching is known for its stability and fast computational speed, making it suitable for scenarios with clearly arranged characters. However, existing technologies significantly reduce the accuracy of traditional methods when characters are arranged in a circular pattern, such as on watch dials or printed on the back, or when slight deformations occur during actual printing. Deep learning algorithms, on the other hand, require a large number of training samples and suffer from high deployment costs, long training cycles, difficulty interpreting information, and the inability to accurately quantify defect areas, primarily due to the following issues:

[0004] 1. Poor adaptability: Traditional template matching cannot adapt to slight rotation, scaling, or aspect ratio changes of characters, and often misclassifies qualified characters as unqualified;

[0005] 2. Difficulty in processing circular characters: Conventional algorithms have difficulty processing circularly arranged characters in a Cartesian coordinate system, such as the circular lettering on watches, and the extraction and comparison are highly complex.

[0006] 3. Slow launch of new products: Traditional algorithms usually require engineers to redesign or develop templates to launch new products, which is time-consuming and labor-intensive.

[0007] 4. Deep learning relies on training data: it requires a large number of defect samples for training, and the results lack interpretability, making it impossible to accurately quantify defects.

[0008] Therefore, the existing technology needs to be improved. Summary of the Invention

[0009] In view of the above-mentioned defects or deficiencies in the prior art, it is desired to provide a method for detecting character printing defects that can meet the current specific needs for character printing defect detection.

[0010] According to one aspect of an embodiment of the present invention, the present application provides a method for detecting character printing defects, comprising:

[0011] Acquire local images of character printing defects, or real-time character printing defect images acquired by image acquisition equipment, and import the character printing defect images into the system to preview the effects of the character printing defect images;

[0012] Perform defect detection on character printing defect images and display the character printing defect detection results, mark the defect area of the image defects, and calculate the defect area;

[0013] Record character printing defect detection results, generate character printing defect detection templates, and view, switch, or edit character printing defect detection templates.

[0014] In another embodiment of the present application, the defect detection on the character printing defect image includes:

[0015] Perform polar coordinate transformation and image straightening on character printing defect images;

[0016] The polar coordinate transformation and image straightening of the character printing defect image comprises:

[0017] When the character printing defect image is arranged in a circle, the character printing defect image is straightened into a horizontal character sequence through polar coordinate transformation;

[0018] The method of straightening the character printing defect image into a horizontal character sequence by polar coordinate transformation includes:

[0019] Obtaining a geometric center point of the character printing defect image, and using the geometric center point as the origin of polar coordinate transformation;

[0020] Performing edge detection and boundary fitting on the geometric center point to improve the alignment of the character printing defect image;

[0021] Setting a radius interval that needs to be expanded by polar coordinate transformation, wherein the radius interval that needs to be expanded by polar coordinate transformation is a character area range defined in the character printing defect image;

[0022] Taking the geometric center point as the pole, sampling each polar coordinate point within the radius interval that needs to be expanded for the polar coordinate transformation, and mapping each polar coordinate point to the original image coordinates of the character printing defect image;

[0023] Bilinear interpolation sampling is performed on the original image coordinates of the character printing defect image according to the set polar coordinate grid to obtain a straightened image matrix. The horizontal axis of the straightened image matrix represents the angle, and the vertical axis represents the radius direction. The character content within the radius range that needs to be expanded by the polar coordinate transformation changes from a curve to a horizontal arrangement.

[0024] In another embodiment of the present application, the defect detection on the character printing defect image further includes:

[0025] The character detection of character printing defect images is carried out by combining template matching with area analysis;

[0026] The method of combining template matching with area analysis to detect characters in a character printing defect image includes:

[0027] Preprocessing the character printing defect image to obtain a first processed image, wherein the preprocessing includes performing grayscale processing, filtering processing, edge enhancement processing, and binarization processing on the character printing defect image;

[0028] Extracting a character area in the first processed image and comparing it with a character printing defect detection template, and evaluating whether the character area in the first processed image has defects based on overlap, edge consistency, and area difference;

[0029] If the area deviation of a certain region of the character area of the first processed image exceeds a set threshold, it is determined to be a defective region and is highlighted.

[0030] In another embodiment of the present application, the defect detection on the character printing defect image further includes:

[0031] Fine-tuning and matching the character printing defect image with the character printing defect detection template;

[0032] The fine-tuning and matching of the character printing defect image with the character printing defect detection template includes:

[0033] The image sample in the character printing defect detection template is adjusted to a set angle and / or scale and / or a set ratio of the aspect ratio so as to match the character printing defect image to be detected.

[0034] In another embodiment of the present application, generating a character printing defect detection template includes:

[0035] Automatic template generation: by importing local images of character printing defects or real-time character printing defect images acquired by image acquisition equipment, the system automatically analyzes the character area and generates the basic template area;

[0036] Manual drawing and editing: Use automatically generated templates to freely draw areas on the interface, mark the outlines of characters of interest, and support scaling, rotation, and shape adjustment.

[0037] In another embodiment of the present application, the grayscale processing of the character printing defect image includes:

[0038] A grayscale image of the character printing defect image and a pixel value of each pixel in the grayscale image are obtained, where the pixel value of each pixel is the brightness intensity of the pixel.

[0039] In another embodiment of the present application, the filtering process on the character printing defect image includes:

[0040] Performing Gaussian filtering on the grayscale-processed character printing defect image to obtain a Gaussian-processed image, wherein the Gaussian filtering smoothes the character printing defect image and retains edge information of the character printing defect image;

[0041] Performing median filtering on the Gaussian processed image to obtain a median filtered image, wherein the median filtering suppresses salt and pepper noise on the Gaussian processed image;

[0042] Performing edge enhancement processing on the median filtered image to obtain an edge enhanced processed image, wherein the edge enhancement processing is used to enhance the edge contrast of characters in the median filtered image to facilitate binarization;

[0043] The edge-enhanced processed image is binarized to obtain a first processed image. The binarization is used to convert the edge-enhanced processed image into a black and white binary image, so that the character area is separated from the background with high contrast, which is convenient for contour extraction and area analysis.

[0044] In another embodiment of the present application, extracting the character area in the first processed image and comparing it with a character printing defect detection template, and evaluating whether the character area in the first processed image has defects based on overlap, edge consistency, and area difference, includes:

[0045] Extracting a character region in the first processed image to obtain a character outline of the first processed image;

[0046] aligning the character contour of the acquired first processed image with the character detection area of the character printing defect detection template;

[0047] Calculating the intersection area and the union area of the character outline of the first processed image and the character detection area of the character printing defect detection template;

[0048] Calculating an overlap index between the character outline of the first processed image and the character detection area of the character printing defect detection template based on the intersection area and the union area;

[0049] According to the relationship between the overlap index and the set threshold, it is determined whether there is a defect in the character area of the first processed image.

[0050] In another embodiment of the present application, extracting the character area in the first processed image and comparing it with a character printing defect detection template, and evaluating whether the character area in the first processed image has defects based on overlap, edge consistency, and area difference, further includes:

[0051] Extracting a character region in the first processed image to obtain a character outline of the first processed image;

[0052] Calculating the filling area of the character outline of the first processed image, and obtaining the standard area of the character detection area of the character printing defect detection template;

[0053] Calculating the area difference between the filled area and the standard area;

[0054] Based on the relationship between the area difference and a set threshold, it is determined whether there is a defect in the character area of the first processed image.

[0055] In the embodiment of the present application, by obtaining a local image of a character printing defect, or a real-time character printing defect image captured by an image acquisition device, and importing the character printing defect image into the system, the character printing defect image effect can be previewed; defect detection is performed on the character printing defect image, and the character printing defect detection results are displayed, the defect area of the image defect is marked, and the defect area is calculated; the character printing defect detection results are recorded, and a character printing defect detection template is generated, and the character printing defect detection template can be viewed, switched, or edited. Compared with the existing technology, the present application has a higher detection accuracy, supports accurate identification of character edge defects, and an area determination error of less than 5%; defects can be quantified, and support area measurement of character defects, which facilitates customers to determine whether they are qualified or not based on the degree of defects; deployment efficiency is fast, without the need to collect large quantities of training samples or secondary development, and it only takes about 10 minutes from importing images to launching detection templates; defect detection accuracy is high, and the deformation tolerance mechanism avoids misjudgment due to printing differences; computing resource usage is low: no GPU is required, and it can run stably with only an ordinary industrial PC, adapting to embedded deployment. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Other features, objects and advantages of the present application will become more apparent upon reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0057] Figure 1 This is a flowchart of a character printing defect detection method provided by an embodiment of the present application. DETAILED DESCRIPTION

[0058] The present application will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely for the purpose of explaining the relevant invention and are not intended to limit the invention. It should also be noted that, for ease of description, only portions relevant to the invention are shown in the accompanying drawings.

[0059] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0060] In one embodiment, Figure 1 As shown, a method for detecting character printing defects is provided.

[0061] Please refer to Figure 1 , which shows a flowchart of a character printing defect detection method that can be applied to an embodiment of the present application.

[0062] like Figure 1 As shown, the character printing defect detection method includes:

[0063] Step 101: obtaining a local image of a character printing defect, or a real-time character printing defect image acquired by an image acquisition device, and importing the character printing defect image into a system to preview the character printing defect image effect;

[0064] Step 102: perform defect detection on the character printing defect image, display the character printing defect detection results, mark the defect area of the image defect, and calculate the defect area;

[0065] Step 103 : Record the character printing defect detection result, generate a character printing defect detection template, and view, switch or edit the character printing defect detection template.

[0066] The defect detection of the character printing defect image includes:

[0067] Perform polar coordinate transformation and image straightening on character printing defect images;

[0068] The polar coordinate transformation and image straightening of the character printing defect image comprises:

[0069] When the character printing defect image is arranged in a circle, the character printing defect image is straightened into a horizontal character sequence through polar coordinate transformation;

[0070] The method of straightening the character printing defect image into a horizontal character sequence by polar coordinate transformation includes:

[0071] Obtaining a geometric center point of the character printing defect image, and using the geometric center point as the origin of polar coordinate transformation;

[0072] Performing edge detection and boundary fitting on the geometric center point to improve the alignment of the character printing defect image;

[0073] Setting a radius interval that needs to be expanded by polar coordinate transformation, wherein the radius interval that needs to be expanded by polar coordinate transformation is a character area range defined in the character printing defect image;

[0074] Taking the geometric center point as the pole, sampling each polar coordinate point within the radius interval that needs to be expanded for the polar coordinate transformation, and mapping each polar coordinate point to the original image coordinates of the character printing defect image;

[0075] Bilinear interpolation sampling is performed on the original image coordinates of the character printing defect image according to the set polar coordinate grid to obtain a straightened image matrix. The horizontal axis of the straightened image matrix represents the angle, and the vertical axis represents the radius direction. The character content within the radius range that needs to be expanded by the polar coordinate transformation changes from a curve to a horizontal arrangement.

[0076] Specifically, by using polar coordinate transformation to straighten the character printing defect image into a horizontal character sequence, the visibility and consistency of template drawing can be improved, the positional interference between characters can be reduced, the recognition speed can be increased, and subsequent defect detection and area comparison can be facilitated. The straightened image has a consistent character arrangement direction, making the template easier to define; operations such as regional template matching and area analysis of characters are more concise and accurate; it is particularly suitable for scenes with small character spacing and large circular curvature;

[0077] When the detection objects are arranged in a circular or semi-circular shape along a certain center point, the traditional linear template matching method is difficult to apply directly. This application uses polar coordinate transformation technology to expand the circular characters into a linear arrangement, which facilitates subsequent template production and defect detection.

[0078] The advantages of the above method are: adaptability, which can handle any circularly symmetrical character arrangement; intuitive operation, the expanded image is a linear image, which is easy for users to label and debug; improved detection accuracy, reducing misjudgments and missed detections caused by character bending; and improved template generalization ability. The same template can adapt to multiple circular character images with different diameters but similar structures.

[0079] The defect detection of the character printing defect image also includes:

[0080] The character detection of character printing defect images is carried out by combining template matching with area analysis;

[0081] The method of combining template matching with area analysis to detect characters in a character printing defect image includes:

[0082] Preprocessing the character printing defect image to obtain a first processed image, wherein the preprocessing includes performing grayscale processing, filtering processing, edge enhancement processing, and binarization processing on the character printing defect image;

[0083] Extracting a character area in the first processed image and comparing it with a character printing defect detection template, and evaluating whether the character area in the first processed image has defects based on overlap, edge consistency, and area difference;

[0084] If the area deviation of a certain region of the character area of the first processed image exceeds a set threshold, it is determined to be a defective region and is highlighted.

[0085] The defect detection of the character printing defect image also includes:

[0086] Fine-tuning and matching the character printing defect image with the character printing defect detection template;

[0087] The fine-tuning and matching of the character printing defect image with the character printing defect detection template includes:

[0088] The image sample in the character printing defect detection template is adjusted to a set angle and / or scale and / or a set ratio of the aspect ratio so as to match the character printing defect image to be detected.

[0089] Specifically, by fine-tuning and matching the character printing defect image with the character printing defect detection template, misjudgment caused by slight character deformation can be reduced.

[0090] The generating of the character printing defect detection template comprises:

[0091] Automatic template generation: by importing local images of character printing defects or real-time character printing defect images acquired by image acquisition equipment, the system automatically analyzes the character area and generates the basic template area;

[0092] Manual drawing and editing: Use automatically generated templates to freely draw areas on the interface, mark the outlines of characters of interest, and support scaling, rotation, and shape adjustment.

[0093] The grayscale processing of the character printing defect image includes:

[0094] A grayscale image of the character printing defect image and a pixel value of each pixel in the grayscale image are obtained, where the pixel value of each pixel is the brightness intensity of the pixel.

[0095] In another embodiment of the present application, the filtering process on the character printing defect image includes:

[0096] Performing Gaussian filtering on the grayscale-processed character printing defect image to obtain a Gaussian-processed image, wherein the Gaussian filtering smoothes the character printing defect image and retains edge information of the character printing defect image;

[0097] Performing median filtering on the Gaussian processed image to obtain a median filtered image, wherein the median filtering suppresses salt and pepper noise on the Gaussian processed image;

[0098] Performing edge enhancement processing on the median filtered image to obtain an edge enhanced processed image, wherein the edge enhancement processing is used to enhance the edge contrast of characters in the median filtered image to facilitate binarization;

[0099] The edge-enhanced processed image is binarized to obtain a first processed image. The binarization is used to convert the edge-enhanced processed image into a black and white binary image, so that the character area is separated from the background with high contrast, which is convenient for contour extraction and area analysis.

[0100] Specifically, the binarization processing of the edge enhanced image is to convert the image into a black and white binary image, so that the character area is separated from the background with high contrast, which is convenient for contour extraction and area analysis.

[0101] The step of extracting a character region from the first processed image and comparing it with a character printing defect detection template, and evaluating whether the character region in the first processed image has defects based on overlap, edge consistency, and area difference, includes:

[0102] Extracting a character region in the first processed image to obtain a character outline of the first processed image;

[0103] aligning the character contour of the acquired first processed image with the character detection area of the character printing defect detection template;

[0104] Calculating the intersection area and the union area of the character outline of the first processed image and the character detection area of the character printing defect detection template;

[0105] Calculating an overlap index between the character outline of the first processed image and the character detection area of the character printing defect detection template based on the intersection area and the union area;

[0106] According to the relationship between the overlap index and the set threshold, it is determined whether there is a defect in the character area of the first processed image.

[0107] The extracting of the character area in the first processed image and comparing it with a character printing defect detection template, and evaluating whether the character area in the first processed image has defects based on overlap, edge consistency, and area difference, further includes:

[0108] Extracting a character region in the first processed image to obtain a character outline of the first processed image;

[0109] Calculating the filling area of the character outline of the first processed image, and obtaining the standard area of the character detection area of the character printing defect detection template;

[0110] Calculating the area difference between the filled area and the standard area;

[0111] Based on the relationship between the area difference and a set threshold, it is determined whether there is a defect in the character area of the first processed image.

[0112] Specifically, the system allows users to define personalized templates for each character position, thereby quickly adapting to various product character layouts without the need for coding.

[0113] When the final inspection results are output, the system will mark the defect characters and highlight them with a red frame on the image; display the defect area, location and possible causes, such as breakage, offset, etc.; record the inspection log and support the export of inspection result images and reports.

[0114] This application converts circular characters into linear arrangements through polar coordinate conversion, greatly simplifying the character comparison process;

[0115] By combining automatic template generation with manual editing, it supports the rapid launch of new products and adapts to different character arrangement structures;

[0116] Through deformation tolerance mechanism: introducing adaptive template matching strategy of angle, scale and aspect ratio to improve system robustness;

[0117] Perform high-speed and accurate comparisons, and achieve fast and interpretable defect assessment through efficient image pre-processing and area quantification.

[0118] The above description is merely a preferred embodiment of the present application and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of the invention herein is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also encompasses other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the inventive concept. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features having similar functions disclosed in this application.

Claims

1. A method for detecting character printing defects, characterized in that: include: Acquire local images of character printing defects, or real-time character printing defect images acquired by image acquisition equipment, and import the character printing defect images into the system to preview the effects of the character printing defect images; Perform defect detection on character printing defect images and display the character printing defect detection results, mark the defect area of the image defects, and calculate the defect area; Record character printing defect detection results, generate character printing defect detection templates, and view, switch or edit character printing defect detection templates; The defect detection of the character printing defect image includes: Perform polar coordinate transformation and image straightening on character printing defect images; The polar coordinate transformation and image straightening of the character printing defect image comprises: When the character printing defect image is arranged in a circle, the character printing defect image is straightened into a horizontal character sequence through polar coordinate transformation; The method of straightening the character printing defect image into a horizontal character sequence by polar coordinate transformation includes: Obtaining a geometric center point of the character printing defect image, and using the geometric center point as the origin of polar coordinate transformation; Performing edge detection and boundary fitting on the geometric center point to improve the alignment of the character printing defect image; Setting a radius interval that needs to be expanded by polar coordinate transformation, wherein the radius interval that needs to be expanded by polar coordinate transformation is a character area range defined in the character printing defect image; Taking the geometric center point as the pole, sampling each polar coordinate point within the radius interval that needs to be expanded for the polar coordinate transformation, and mapping each polar coordinate point to the original image coordinates of the character printing defect image; Bilinear interpolation sampling is performed on the original image coordinates of the character printing defect image according to the set polar coordinate grid to obtain a straightened image matrix. The horizontal axis of the straightened image matrix represents the angle, and the vertical axis represents the radius direction. The character content within the radius range that needs to be expanded by the polar coordinate transformation changes from a curve to a horizontal arrangement.

2. The character printing defect detection method according to claim 1, characterized in that: The defect detection of the character printing defect image also includes: The character detection of character printing defect images is carried out by combining template matching with area analysis; The method of combining template matching with area analysis to detect characters in a character printing defect image includes: Preprocessing the character printing defect image to obtain a first processed image, wherein the preprocessing includes performing grayscale processing, filtering processing, edge enhancement processing, and binarization processing on the character printing defect image; Extracting a character area in the first processed image and comparing it with a character printing defect detection template, and evaluating whether the character area in the first processed image has defects based on overlap, edge consistency, and area difference; If the area deviation of a certain region of the character area of the first processed image exceeds a set threshold, it is determined to be a defective region and is highlighted.

3. The character printing defect detection method according to claim 2, characterized in that: The defect detection of the character printing defect image also includes: Fine-tuning and matching the character printing defect image with the character printing defect detection template; The fine-tuning and matching of the character printing defect image with the character printing defect detection template includes: The image sample in the character printing defect detection template is adjusted to a set angle and / or scale and / or a set ratio of the aspect ratio so as to match the character printing defect image to be detected.

4. The character printing defect detection method according to claim 1, wherein: The generating of the character printing defect detection template comprises: Automatic template generation: by importing local images of character printing defects or real-time character printing defect images acquired by image acquisition equipment, the system automatically analyzes the character area and generates the basic template area; Manual drawing and editing: Use automatically generated templates to freely draw areas on the interface, mark the outlines of characters of interest, and support scaling, rotation, and shape adjustment.

5. The character printing defect detection method according to claim 2, wherein: The grayscale processing of the character printing defect image includes: A grayscale image of the character printing defect image and a pixel value of each pixel in the grayscale image are obtained, where the pixel value of each pixel is the brightness intensity of the pixel.

6. The character printing defect detection method according to claim 2, wherein: The filtering process of the character printing defect image includes: Performing Gaussian filtering on the grayscale-processed character printing defect image to obtain a Gaussian-processed image, wherein the Gaussian filtering smoothes the character printing defect image and retains edge information of the character printing defect image; Performing median filtering on the Gaussian processed image to obtain a median filtered image, wherein the median filtering suppresses salt and pepper noise on the Gaussian processed image; Performing edge enhancement processing on the median filtered image to obtain an edge enhanced processed image, wherein the edge enhancement processing is used to enhance the edge contrast of characters in the median filtered image to facilitate binarization; The edge-enhanced processed image is binarized to obtain a first processed image. The binarization is used to convert the edge-enhanced processed image into a black and white binary image, so that the character area and the background are separated by high contrast, which is convenient for contour extraction and area analysis.

7. The character printing defect detection method according to claim 2, wherein: The extracting the character area in the first processed image and comparing it with a character printing defect detection template, and evaluating whether the character area in the first processed image has defects based on overlap, edge consistency, and area difference, includes: Extracting a character region in the first processed image to obtain a character outline of the first processed image; aligning the character contour of the acquired first processed image with the character detection area of the character printing defect detection template; Calculating the intersection area and the union area of the character outline of the first processed image and the character detection area of the character printing defect detection template; Calculating an overlap index between the character outline of the first processed image and the character detection area of the character printing defect detection template based on the intersection area and the union area; According to the relationship between the overlap index and the set threshold, it is determined whether there is a defect in the character area of the first processed image.

8. The character printing defect detection method according to claim 7, characterized in that: The extracting of the character area in the first processed image and comparing it with a character printing defect detection template, and evaluating whether the character area in the first processed image has defects based on overlap, edge consistency, and area difference, further includes: Extracting a character region in the first processed image to obtain a character outline of the first processed image; Calculating the filling area of the character outline of the first processed image, and obtaining the standard area of the character detection area of the character printing defect detection template; Calculating the area difference between the filled area and the standard area; Based on the relationship between the area difference and a set threshold, it is determined whether there is a defect in the character area of the first processed image.

Images