JP7435840B2 - Image processing method, device and storage medium - Google Patents

Description

TECHNICAL FIELD The present invention relates generally to the field of image processing, and more particularly to an image processing method, an image processing apparatus, and a computer-readable storage medium for extending line segments in an image.

In recent years, defect detection technology based on computer vision processing has already been widely applied in various industries. It is possible to determine the presence or absence. For example, defect detection has very important applications in industries such as production and manufacturing, and by performing defect detection on manufactured workpieces, it is possible to select workpieces whose external contour meets requirements and to identify defects in the external contour. A certain product acceptance rate is achieved by removing existing workpieces.

However, traditional defect detection techniques are adversely affected by undesirable conditions such as image background disturbance, nonlinear illumination, and contrast inversion, leading to situations where defect features such as cracks, chips, etc. in the image become discontinuous or blurred. There is a fear.

Therefore, there is a need for techniques that can effectively detect defects in objects, especially image processing techniques that are robust to background noise, nonlinear illumination, and contrast inversion situations.

In view of the above problems, an object of the present invention is to provide an image processing method, an image processing device, and a computer-readable storage medium for extending line segments in an image.

In order to solve the above problems, one aspect of the present invention includes the steps of: acquiring a target image including defect features; identifying (identifying) at least one line segment from the target image; performing an extension process on the line segment, and the extension process on a specific (predetermined) line segment in the at least one line segment is based on the main direction and tangential direction of the specific line segment, determining an extension direction for extending the specific line segment; determining an extension length for extending the specific line segment based on the length of the specific line segment; and determining the extension direction and the extension length. An image processing method is provided, which includes extending the specific line segment using a method and obtaining an extended line segment related to a defect feature in the target image.

According to an embodiment of the present invention, before identifying the at least one line segment, preprocessing is performed on the target image based on an adaptive histogram equalization method, and the target image after preprocessing is The at least one line segment is identified from .

According to an embodiment of the present invention, in the step of identifying at least one line segment from the target image, processing based on frequency domain filtering is performed on the target image, and a first Obtaining a result image, performing processing based on spatial bilateral filtering on the target image, obtaining a second result image, fusing the first result image with the second result image, and after enhancement. obtain a final result image, perform binarization processing on the final result image after enhancement to obtain at least one line segment area, and thin the line segment area using a skeleton extraction algorithm. , obtaining the at least one line segment of the target image.

According to an embodiment of the present invention, the steps include setting weighting coefficients for each of the first resultant image and the second resultant image, and determining the first resultant image and the second resultant image based on the set weighting coefficients. The method further includes the step of fusing the second resultant image.

According to one embodiment of the present invention, in the step of determining an extension direction for extending the specific line segment, the specific determining the main direction of the line segment, and determining the tangential direction of the specific line segment based on the tangential directions of a second number of points smaller than the first number near the end points in the specific line segment; is determined, weighting coefficients are set in each of the main direction and the tangential direction, and the extension direction of the specific line segment is determined based on the set weighting coefficients.

According to an embodiment of the present invention, the set weighting coefficient is adjusted based on the curvature of the particular line segment, or the set weighting coefficient is adjusted based on the curvature of the particular line segment, or the set weighting coefficient is adjusted based on the curvature of the particular line segment, or the set weighting coefficient is There is a positive correlation with the number of (positive correlation).

According to one embodiment of the present invention, in the extension process, a line segment that satisfies a condition is selected from among the identified at least one line segment, and the line segment that satisfies the condition is selected as a candidate line segment. Extending processing is performed, and the condition includes that the length of the line segment is greater than a first threshold, and/or the distance between the line segment and the nearest line segment is less than a second threshold. .

According to another aspect of the present invention, there is provided an acquisition unit that acquires a target image including a defect feature, an identification unit that identifies at least one line segment from the target image, and an extension process for the at least one line segment. and a processing unit for extending the specific line segment based on the main direction and the tangential direction of the specific line segment. determining an extension direction, determining an extension length to extend the specific line segment based on the length of the specific line segment, and using the extension direction and the extension length to extend the specific line segment; An image processing apparatus is provided that includes extending the line segment and obtaining an extended line segment associated with a defect feature in the target image.

According to yet another aspect of the invention, the invention comprises a processor and a memory having computer program instructions stored therein, the computer program instructions, when executed by the processor, causing the processor to include a defective feature. Acquiring a target image, identifying at least one line segment from the target image, and performing extension processing on at least one line segment, and identifying the at least one line segment. The extension process for the line segment determines an extension direction for extending the specific line segment based on the main direction and tangential direction of the specific line segment, and determines an extension direction for extending the specific line segment based on the length of the specific line segment. , determining an extension length for extending the specific line segment, extending the specific line segment using the extension direction and the extension length, and determining an extended line segment related to the defect feature in the target image. An image processing apparatus is provided, the image processing apparatus comprising: obtaining an image.

According to yet another aspect of the invention, there is provided a computer-readable storage medium having computer program instructions stored thereon, the computer program instructions, when executed by a processor, for obtaining a target image including defective features. , identifying at least one line segment from the target image, and performing an extension process on the at least one line segment, and performing the extension process on a specific line segment in the at least one line segment. The processing includes determining an extension direction for extending the specific line segment based on the main direction and tangential direction of the specific line segment, and determining an extension direction for extending the specific line segment based on the length of the specific line segment. determining an extension length to extend, extending the specific line segment using the extension direction and the extension length, and obtaining an extended line segment related to a defect feature in the target image. , a computer readable storage medium is provided.

According to the present invention, the line segment is extended based on the partial (local) information and the entire (global) information of the line segment identified from the image so as to eliminate the discontinuity of defect features. It can be performed. Furthermore, according to the present invention, it is possible to eliminate the adverse effects of uneven illumination, background noise, etc., and to retain edge information of defect characteristics. Therefore, the image processing method and image processing apparatus of the present invention can effectively process complex backgrounds, nonlinear illumination, and contrast inversion.

The above and other objects, features, and advantages of the present invention will become more apparent from the following detailed description of embodiments of the invention in conjunction with the accompanying drawings. These drawings are intended to provide a further understanding of embodiments of the invention, and constitute a part of the specification and, together with the embodiments of the invention, serve to explain the invention; It should be understood that the invention is not limited. Additionally, in the drawings, like reference numbers generally represent similar parts or steps.
1 is a flowchart showing an image processing method according to an embodiment of the present invention. It is a figure which shows the target image which is an image of the ring-shaped workpiece|work containing a crack based on embodiment of this invention. FIG. 3 is a schematic diagram showing a specific line segment extension process according to an embodiment of the present invention. It is a schematic diagram which shows the line segment after the extension process based on embodiment of this invention. 3 is a flowchart showing a line segment identification method according to an embodiment of the present invention. 1 is a schematic diagram illustrating image enhancement by a combination of frequency domain filtering and spatial domain filtering, according to an embodiment of the invention; FIG. FIG. 1 is a block diagram showing an example of an image processing device according to an embodiment of the present invention. FIG. 2 is a block diagram showing another example of an image processing device according to an embodiment of the present invention.

Embodiments of an image processing method, an image processing apparatus, and a computer-readable recording medium according to the present invention will be described below with reference to the drawings. All other embodiments that a person skilled in the art can derive from the embodiments described in the present invention without any creative effort should be included within the protection scope of the present invention and are not included in the present specification. The examples are only some examples of the invention, not all examples of the invention, and these examples are only illustrative and illustrative, and therefore do not limit the scope of the invention. It should be understood that it should not be construed as Further, for clarity and conciseness of the description of the present invention, detailed descriptions of functions and structures well known in the art are omitted, and redundant descriptions of steps and components are also omitted.

First, with reference to FIG. 1, a basic flow of an image processing method according to an embodiment of the present invention will be described in detail. As shown in FIG. 1, the image processing method can include the following processes.

In step S101, a target image including defect features is acquired.

According to embodiments of the invention, the target images may be acquired by means of receiving one or more target images via, but not limited to, wired or wireless means. Further, the step of acquiring the target image may include the step of acquiring from the memory a pre-stored image or a continuous frame image captured by an imaging device such as a camera. Here, the target image may be an original image captured by an image capturing device, the original image may be a grayscale or color image, and various image preprocessing is performed on the original image. It may also be a processed image obtained after processing. Here, such image pre-processing includes, for example, processing such as trimming, scaling, or deformation, but is not limited thereto.

Further, according to embodiments of the invention, the defect features included in the target image may be defects such as cracks, crevices, gaps, or stains on the surface of a product or building. Furthermore, depending on the particular application scenario of the image processing method of the present invention, defect features in the image are not limited to defects appearing on the surface of the object, but any type of interest in the image, such as texture or lines. Note that a portion of a straight line or curve can be broadly included.

Here, an example will be described in which an image of a ring-shaped work is used as the target image. Figure 2 shows an image of such a ring-shaped workpiece, and there are two cracks on the surface of the ring-shaped workpiece, which are characteristics of defects, but external factors such as uneven illumination and the image sensor Due to internal factors, as shown in FIG. 2, originally complete cracks appear as blurred or discontinuous images in the target image, which adversely affects processes such as defect detection.

In step S102, at least one line segment is identified from the target image.

As shown in FIG. 2, the cracks in the target image appear as multiple line segments, and in this step, these line segments are identified from the target image, and in step S103, an extension process is performed on the identified line segments. give

Next, with reference to FIG. 3, the specific line segment extension process according to the embodiment of the present invention will be described in detail.

Specifically, for a specific line segment that has not been subjected to extension processing among at least one line segment identified from the image, in order to perform extension processing on that line segment, the extension direction for that specific line segment is determined. It is necessary to determine the length and extension length.

According to an embodiment of the present invention, an extension direction for extending a specific line segment is determined based on the main direction and tangential direction of the specific line segment. Here, the main direction of a line segment refers to the average direction of most or all points in the line segment. For example, as shown in FIG. According to embodiments of the present invention, the direction of most points (e.g., greater than 50% of the total number) or all points in the line segment may be global information reflecting the overall direction and trend of the line segment. The main direction of the line segment can be determined by calculating the average direction of the line segment or by selecting the direction that can represent the maximum number of points. The tangential direction of a line segment is obtained by the direction of a small number of points (e.g., smaller than 50% of the total number) near the endpoints in the line segment, for example, by finding the average direction or by can be the tangential direction of the line segment by choosing the direction of We can obtain the tangential direction. In the embodiment described above, since the tangential direction is only local information that reflects the direction and tendency at the end of the line segment, the number of points that specify the tangential direction of the line segment is the same as the number of points that specify the main direction of the line segment. must be less than the number of

Alternatively, after determining the main direction and tangential direction of a specific line segment, weighting coefficients may be set for each of the main direction and tangential direction, and the extension direction of the specific line segment may be determined based on the set weighting coefficients. , for example, can be expressed by the following equation (1).

である。各線分は両端を有し、必要に応じて線分の一端又は両端に対して対応する延長方向を決定してもよいことは理解すべきである。 In the above formula, D _t represents the tangential direction of the end of the line segment, D _p represents the main direction of the line segment, D _E represents the extension direction of the line segment, and c _t and c _p are the tangents, respectively. The weighting factor for the direction and main direction, the default setting is

It is. It should be understood that each line segment has opposite ends, and a corresponding direction of extension may be determined for one or both ends of the line segment, as desired.

Also, a line segment can be considered as part of a curve that actually has a curvature, i.e. each line segment has a corresponding curvature, and according to a preferred embodiment of the invention, the tangential direction and The weighting coefficient in the main direction can be adjusted based on the curvature of the specific line segment; for example, the larger the curvature of the specific line segment, the more the weighting coefficient is set in the tangential direction of the specific line segment. becomes larger, and accordingly, the weighting factor set in the main direction of that particular line segment becomes smaller, and vice versa. Alternatively, the weighting factors for the tangential and principal directions of a particular line segment can be positively correlated with the number of orientation points. In this way, the determined extension direction will be more accurate in the desired application scene.

On the other hand, according to an embodiment of the present invention, an extension length for extending a specific line segment is determined based on the length of the specific line segment. As shown in FIG. 3(b), the extended length of the line segment may be one quarter of the length of the line segment itself, or may be any proportion. For example, it can be expressed by the following equation (2).

In the above formula, L _c represents the length of the line segment. L _E indicates the extended length of the line segment. c _curve indicates the extension coefficient. According to a preferred embodiment of the invention, the extension factor can be adjusted depending on the distance between the line segments or the distance to the edge. In this way, the extended line segment is better adapted to the true defect features.

When the extension direction and extension length of the specific line segment are determined through the above process, the specific line segment is extended using the determined extension direction and extension length, and the extended line segment is obtained. Figure 4 shows the schematic diagram of the line segment after the extension process, each line segment after the extension process forms a continuous complete line segment, overcomes the situation where the crack is discontinuous, and the formed complete Since the line segment corresponds to a pattern formed by a crack in the ring-shaped workpiece, the defect characteristics in the target image can be strengthened by extending the at least one line segment.

Furthermore, according to a preferred embodiment of the invention, before identifying the at least one line segment, the target image is preprocessed based on an adaptive histogram equalization method, and the at least one line segment is extracted from the preprocessed target image. It is also possible to specify

Specifically, the gradation (grayscale) histogram of an image is a function related to the image gradation value distribution, and can be regarded as a statistical graph of the gradation value distribution in the image. The probability that a pixel having a value appears can be reflected by a function of the image tone value distribution. In general, the distribution of the tone histogram of a dark image appears to be concentrated on the side with low tone values, and conversely, the distribution of the tone histogram of a bright image appears to be concentrated on the side with high tone values. . When the tone histogram of an image covers almost the entire tone value range, ie, the total tone value distribution approaches a uniform distribution, the image has a large tone dynamic range and high contrast. As described above, one of the causes of the blurring and discontinuity of cracks, which are defect characteristics in the target image, is that the gradation dynamic range of the image becomes narrow due to illumination unevenness, and details of the image are lost.

Therefore, before identifying line segments to be used for extension processing, the target image is processed in advance by an adaptive histogram equalization method, such as adaptive histogram equalization, limited contrast adaptive histogram Methods such as Contrast Limited Adaptive Histogram Equalization and Adaptive Local Region Stretch histogram equalization make image details more noticeable and aid in subsequent specific processing of at least one line segment. and, accordingly, the definition after the extension process will be more complete and accurate.

Further, according to a preferred embodiment of the present invention, the image is enhanced using a method combining frequency domain filtering and spatial domain filtering, and at least one line segment is extracted from the enhanced image for subsequent extension processing. It can be used for. A method for specifying the line segment will be specifically explained with reference to FIGS. 5 and 6.

FIG. 5 is a flowchart showing a line segment identification method according to an embodiment of the present invention. As shown in FIG. 5, the method for identifying the line segment can include the following process.

In step S501, the target image is processed by frequency domain filtering to obtain a first resultant image that retains high frequency information.

Specifically, as shown in the schematic diagram of processing based on frequency domain filtering shown in Fig. 6, a frequency domain image of the target image is first obtained by Fourier transform or a similar frequency domain transformation method, and then a frequency domain image is obtained using a high-pass filter. A filtering process is performed on the frequency domain image to retain high frequency components in the image, and then an inverse transformation process is performed on the filtered image to finally obtain a first resultant image. In this way, low frequency information can be filtered from the first resultant image while preserving high frequency information corresponding to potential defect features, as well as eliminating the negative effects of non-uniform illumination in the image.

On the other hand, in step S502, the target image is processed by a spatial bilateral filter to obtain a second resultant image.

Specifically, a process based on spatial bilateral filtering is a spatial (spatial domain) filtering process realized by a bilateral filter, and such a bilateral filter uses the geometric proximity of pixels. In addition, by considering the luminance/color difference between pixels, it is possible to effectively remove noise on an image using a bilateral filter and preserve edge information on an image. Such a bilateral filter is composed of, for example, a Euclidean distance function for pixels and a tone difference function for pixels. A second resultant image is obtained after performing spatial domain bilateral filtering, as shown in the schematic diagram of the process based on spatial bilateral filtering shown in FIG.

Note that the processing by the frequency domain filter and the processing by the spatial bilateral filter in steps S501 and S502 may be performed synchronously or sequentially.

However, both the processing based on frequency domain filtering and the processing based on spatial bilateral filtering have their respective advantages and limitations. For example, spatial domain filtering has a remarkable sharpening effect, and This filtering method has the advantage of simple algorithms and fast processing speed, but it also reduces noise while at the same time causing image blurring, especially at edges and details. ,The frequency domain filtering algorithm is relatively complex, has a slow calculation speed, and at the same time removes noise, it causes loss of edge information and blurs the image edges.

Therefore, in the present invention, the final result image after enhancement is obtained by further fusing the frequency domain filter processing result image and the spatial domain filter processing result image, that is, in the next step S503, the first result The image and the second resultant image are fused to obtain an enhanced resultant image. As shown in FIG. 6, the resultant image after frequency domain filtering and the resultant image after spatial domain bilateral filtering are fused to obtain an enhanced image.

Further, according to a preferred embodiment of the present invention, in the fusion process, weighting coefficients are set for each of the first result image and the second result image, and the first result image and the second result image are determined based on the set weight coefficients. It is also possible to fuse the resulting images, and for example, it can be expressed by the following equation (3).

は、強化された最終結果画像を表し、
（外２）

は、周波数領域フィルタリング処理に対応する第１の結果マップを示す。
（外３）

は、空間領域フィルタ処理に対応する第２の結果マップを示す。c_f及びc_sは、それぞれ該第１の結果画像及び該第２の結果画像の重み係数であり、デフォルト設定は、

となる。さらに、本発明の好ましい実施形態によれば、より細部の多い複雑な画像、例えば、欠陥特徴の数が多い画像に対して、周波数領域フィルタ処理の第１の結果画像の重み係数を増加し、それに応じて、空間領域フィルタ処理の第２の結果画像の重み係数を減少し、逆もまた同様である。 In the above formula,
(Outside 1)

represents the enhanced final result image,
(Outside 2)

shows a first result map corresponding to the frequency domain filtering process.
(Outer 3)

shows a second result map corresponding to spatial domain filtering. c _f and c _s are weighting factors of the first result image and the second result image, respectively, and the default setting is

becomes. Furthermore, according to a preferred embodiment of the invention, for complex images with more details, e.g. images with a larger number of defective features, the weighting factors of the first resultant image of the frequency domain filtering are increased; Correspondingly, the weighting factors of the second resultant image of the spatial domain filtering are decreased, and vice versa.

Returning to the flow of the line segment identification method shown in FIG. 5, after acquiring the enhanced result image in step S503, in step S504, at least One rough line segment area is obtained, and the line segment area is thinned using a skeleton extraction algorithm to obtain at least one line segment of the target image.

Specifically, by converting the fused resultant image into a black and white image consisting only of pixels with a gradation value of 0 or 255 through binarization processing, a line segment having a relatively large width, In other words, after obtaining a line segment region, use a skeleton extraction algorithm (for example, Skeletonize function and medial_axis function) to extract these line segment regions until a line segment of a desired width (for example, about 1 pixel) is obtained from the region. By peeling off the pixels and maintaining the original shape, the line segment area is thinned. In this way, redundant information in the image can be removed and structural and shape information of interest can be enhanced, further enhancing the image.

Furthermore, in the method for identifying line segments in the above embodiments, the image may be enhanced by directly using a method that combines frequency domain filtering and spatial domain filtering on the target image; After performing preprocessing such as the adaptive histogram equalization method described in , a method combining frequency domain filtering and spatial domain filtering may be used on the preprocessed target image to enhance the image.

Through the above processing, at least one line segment can be identified and extracted from the target image, and an extension process can be performed to obtain an extended line segment related to the defect feature in the target image.

However, as can be seen from Fig. 4, some of the line segments identified from the target image may be noise unrelated to the defect features; Therefore, according to a preferred embodiment of the present invention, the above-mentioned extension process further includes selecting a line segment that satisfies the condition from at least one specified line segment as a candidate line segment. The selected line segment is extended only to the candidate line segment, and the conditions that must be met are that the length of the line segment is greater than the first threshold, or the distance between the line segment and the nearest line segment. is less than the second threshold, or both. In this way, a line segment having a length greater than the threshold value is selected from among the identified at least one line segment, a line segment having a distance from other line segments smaller than the threshold value is selected, or By selecting a line segment that simultaneously satisfies two conditions as a candidate line segment, noise in the image is removed and only the line segment related to the defect feature is extended, thereby reducing the amount of calculation required by the image processing method. At the same time, the accuracy of defect detection can be improved.

As explained above, according to the image processing method according to the embodiment of the present invention, defect characteristics are can resolve the discontinuous case. Further, it is possible to remove the adverse effects caused by uneven illumination, background noise, etc., and to retain edge information of defect characteristics.

Next, with reference to FIG. 7, an image processing apparatus according to an embodiment of the present invention will be described.

FIG. 7 is a block diagram of an image processing device 700 according to an embodiment of the present invention. As shown in FIG. 7, the image processing device 700 includes an acquisition section 710, a specification section 720, and a processing section 730. The illustrated configuration is merely exemplary and not limiting, and the image processing device 700 may include other components in addition to these units; however, these components are not limited to the present invention. It should be understood that illustrations and descriptions are omitted in this specification because they are unrelated to the content of the embodiments.

Further, since the specific details of the following operations by the image processing apparatus 700 according to the embodiment of the present invention are almost the same as the details described above with reference to FIGS. 1 to 6, similar details will be omitted. Some explanations are omitted for the sake of clarity. Each module and member of the image processing device 700 will be explained one by one below.

The acquisition unit 710 is configured to acquire a target image including defect features. The specific process executed by the acquisition unit 710 corresponds to the corresponding content of step S101 described above in connection with FIG.

Specifically, according to an embodiment of the present invention, the acquisition unit 710 may be an image capturing device such as a mobile phone, a camera, a video camera, etc., or may receive a captured image from such an image capturing device. It may also be a device for Further, the acquisition unit 710 is physically separated from other modules in the image processing device 700, and the acquisition unit 710 transmits captured images to other modules in the image processing device 700 by wire or wirelessly. Good too. Alternatively, the acquisition unit 710 may be located at the same physical location as other modules and components within the image processing apparatus 700, or may be located within the same housing. Other modules and components within the image processing device 700 receive the images acquired by the acquisition unit 710 via the internal bus.

The identification unit 720 is configured to identify at least one line segment from the target image. The specific process executed by the specifying unit 720 matches the corresponding content of step S102 described above in connection with FIG.

Specifically, according to the embodiment of the present invention, the identifying unit 720 identifies a line segment from the target image acquired by the acquiring unit 710, and the processing unit 730 performs an extension process on the identified line segment. I do.

Further, according to a preferred embodiment of the present invention, before identifying the at least one line segment, the identifying unit 720 preprocesses the target image using an adaptive histogram equalization method, and includes at least one line segment from the preprocessed target image. It is also possible to specify one line segment.

Further, according to a preferred embodiment of the present invention, the identification unit 720 enhances the image by a combination of frequency domain filtering and spatial domain filtering, and extracts at least one line segment from the enhanced image for subsequent extension processing. be able to. This is the method specifically explained with reference to FIGS. 5 and 6 above.

The processing unit 730 is configured to perform an extension process on at least one line segment, and here, the extension process on a specific line segment among the at least one line segment is performed in the main direction and direction of the specific line segment. Based on the tangential direction, determine the extension direction for extending the specific line segment; Based on the length of the specific line segment, determine the extension length for extending the specific line segment; A specific line segment is extended using the extension length, and an extended line segment related to the defect feature in the target image is obtained. The specific process executed by the processing unit 730 corresponds to the corresponding content of step S103 described above in connection with FIG.

Further, according to an embodiment of the present invention, the processing unit 730 determines an extension direction for extending a specific line segment based on the main direction and tangential direction of the specific line segment. Further, after determining the main direction and tangential direction of a specific line segment, the processing unit 730 sets weighting coefficients in the main direction and tangential direction, respectively, as shown in the above equation (1), and uses the set weighting coefficients. The extension direction of a specific line segment may be determined based on this. On the other hand, according to the embodiment of the present invention, the processing unit 730 calculates the extension length for extending the specific line segment based on the length of the specific line segment, as shown in equation (2) above. decide.

Further, according to the embodiment of the present invention, in the above-mentioned extension process by the processing unit 730, a line segment that satisfies the condition from at least one specified line segment is further selected as a candidate line segment, and only a candidate line segment is selected. The length of the line segment is greater than the first threshold, or the distance between the line segment and the nearest line segment is less than the second threshold, or It can include both.

Next, with reference to FIG. 8, an image processing apparatus according to an embodiment of the present invention will be described.

FIG. 8 is a block diagram of an image processing device 800 according to an embodiment of the present invention. As shown in FIG. 8, the image processing device 800 includes a processor 810 and a memory 820. Note that the image processing device 800 may be a computer or a server. The illustrated configuration is merely exemplary and not limiting, and the image processing device 800 may include other components in addition to these units; however, these components are not limited to the present invention. It should be understood that illustrations and descriptions are omitted in this specification because they are unrelated to the content of the embodiments.

Further, since the specific details of the following operations by the image processing apparatus 800 according to the embodiment of the present invention are almost the same as the details described above with reference to FIGS. 1 to 6, similar details will not be explained. Omitted. Each block of the image processing device 800 will be explained one by one below.

Processor 810 may be a central processing unit (CPU) or other form of processing device that has data processing and/or instruction execution capabilities and uses computer program instructions stored in memory 820 to perform desired functions. may be executed, and when the computer program instructions are executed by processor 810, the following steps are performed. That is, a target image including a defect feature is acquired, at least one line segment is identified from the target image, an extension process is performed on the at least one line segment, and a specific line of the at least one line segment is In the extension process for minutes, the extension direction for extending the specific line segment is determined based on the main direction and tangential direction of the specific line segment, and the extension direction for extending the specific line segment is determined based on the length of the specific line segment. By determining the extension length and extending the specific line segment using the extension direction and extension length, an extended line segment related to the defect feature in the target image is obtained. The above-described steps performed by processor 810 correspond to the contents of each of steps S101-S103 described above. Furthermore, processor 810 may also perform processing corresponding to each of the embodiments described above in connection with FIGS. 1-6.

Memory 820 may include one or more computer program products, which may include various forms of computer readable storage media, such as volatile memory and/or nonvolatile memory. The computer-readable storage medium is configured to cause the processor 810 to execute the program instructions to realize the functions of the image processing apparatus according to the embodiment of the present invention and/or other desired functions, and/or Alternatively, one or more computer program instructions may be stored to enable execution of image processing methods according to embodiments of the present invention. The computer readable recording medium may store various application programs and various data.

Next, a computer-readable storage medium according to an embodiment of the present invention will be described. The present invention, when executed by a processor, includes the steps of obtaining a target image including defective features, identifying at least one line segment from the target image, and performing an extension process on the at least one line segment. The extending process for a specific line segment among the at least one line segment includes a step of determining an extension direction for extending the specific line segment based on a main direction and a tangential direction of the specific line segment. , determining an extension length to extend a specific line segment based on the length of the specific line segment, and extending the specific line segment using the extension direction and extension length to A computer readable storage medium having computer program instructions stored thereon is provided that includes the step of obtaining an extended line segment associated with a defect feature. The above steps correspond to steps S101 to S103 described above. Additionally, the computer program instructions, when executed by a processor, may perform operations corresponding to the embodiments described above in connection with FIGS. 1-6.

It should be understood that each component or module in the image processing apparatus described above may be implemented in hardware, software, or a combination of hardware and software.

The embodiments described above are merely illustrative and not restrictive, and those skilled in the art may combine several steps and devices from the separately described embodiments above based on the concepts of the present invention. The effects of the present invention can be realized by using the present invention, and such combinations and combined embodiments are also included in the present invention, and such combinations and combinations will not be explained in detail here. Note that the advantages, effects, etc. described in the present invention are illustrative and not limiting, and are not essential to each embodiment of the present invention. Further, the specific details of the invention described above are merely illustrative and for ease of understanding, and are not limiting, and the above details do not realize the present invention with the specific details described above. It does not limit what you have to do.

Block diagrams of modules, apparatus, devices, systems referred to in this disclosure are exemplary only and require that they be connected, arranged, configured in the manner illustrated by the block diagrams, or It's not meant to be implied. These modules, apparatus, devices, and systems may be connected, arranged, and configured in any manner as can be understood by those skilled in the art. Additionally, words such as "comprises," "includes," and "having" are non-limiting words meaning "including, but not limited to," and are used interchangeably. As used herein, the words "or" and "and" refer to the words "and/or" and are used interchangeably unless the context clearly indicates otherwise. As used herein, the term "etc." refers to phrases such as "without limitation," and is used interchangeably.

The step flowcharts herein and the method descriptions above are exemplary only and do not require or imply that the steps of each embodiment must be performed in the order presented. . As will be understood by those skilled in the art, the order of steps in the embodiments described above can be performed in any order. Terms such as "thereafter," "subsequently," and "next" are not intended to limit the order of steps; they are used only to guide the reader through the description of these methods. be done. Furthermore, any reference to the article "an," "one," or "the" or "said" to an element in the singular is not to be construed as limiting that element to the singular.

Further, the steps and apparatuses of each embodiment herein are not limited to a certain embodiment, and in fact, the steps and apparatuses of each embodiment herein are performed in accordance with the concept of the present invention. New embodiments can be envisioned by combining some of the steps and some of the devices, and these new embodiments are also within the scope of the invention. The methods and features disclosed herein also include one or more acts for implementing the methods described above. The methods and/or acts may be interchangeable without departing from the scope of the claims. In other words, unless a particular order of acts is specified, the order and/or use of the particular acts may be modified without departing from the scope of the claims.

The various operations of the methods described above may be performed by any suitable means capable of performing the corresponding functions. The means may include various hardware and/or software components and/or modules, including, but not limited to, circuits, application specific integrated circuits (ASICs), or processors. The various exemplary logic blocks, modules, and circuits described above may include general purpose processors, digital signal processors (DSPs), ASICs, field programmable gate array signals (FPGAs) designed to perform the functions described herein. ) or other programmable logic devices (PLDs), discrete gate or transistor logic, discrete hardware components, or any combination thereof. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any commercially available processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. can be done.

The steps of the method or algorithm described in connection with the present invention may be implemented directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in any form of tangible storage medium. Some examples of storage media that may be used include random access memory (RAM), read only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, hard disks, removable disks, CD-ROM, and the like. A storage medium may be coupled to a processor such that the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. A software module may be a single instruction or many instructions, and may be distributed across different code segments, between different programs, and across multiple storage media.

Accordingly, the computer program product is capable of performing the operations presented herein. For example, such a computer program product may be a computer-readable tangible medium having instructions tangibly stored (and/or encoded thereon) for performing the operations described herein. Executable by one or more processors. The computer program product can include packaged materials. Software or instructions may also be transmitted via a transmission medium. For example, the software may be transmitted to a website, server, or other site using a transmission medium such as coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, or microwave. May be sent from a remote source.

Additionally, modules and/or other suitable means for performing the methods and techniques described herein may be downloaded and/or otherwise obtained by the user terminal and/or base station, as appropriate. can be done. For example, such a device may be coupled to a server to facilitate delivery of means for performing the methods described herein. Alternatively, the methods described herein may be stored in storage means (e.g. , a physical storage medium such as a ROM, a CD, or a floppy disk). Additionally, any other suitable technique for providing a device with the methods and techniques described herein may be utilized.

Other examples and embodiments are within the scope and spirit of the invention and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hardwired, or any combination thereof. Features implementing functionality may also be physically located at various locations, such as distributed such that portions of the functionality are implemented at different physical locations. Additionally, as used herein, including in the claims, "or" used in a listing of items beginning with "at least one" indicates a separate listing, e.g., "A, B, The recitation "at least one of or C" means A or B or C, or AB or AC or BC, or ABC (ie, A and B and C). Furthermore, the word "exemplary" does not imply that the described example is preferred or better than other examples.

Various changes, substitutions, and modifications to the technology described herein can be made without departing from the teachings defined by the appended claims. Furthermore, the claims are not limited to the particular aspects of the process, machine, manufacture, arrangement of events, means, methods, and operations described above. Any existing or later developed process, machine, manufacture, arrangement of events, means or method that performs substantially the same function or achieves substantially the same results as corresponding aspects described herein. , or an action is used. Accordingly, the appended claims include within their scope such processes, machines, manufacture, arrangements of events, means, methods, or acts.

The previous description of aspects of the invention is provided to enable any person skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments without departing from the scope of the invention. Therefore, this invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention.

The above description has been presented for purposes of illustration and description. Further, this description does not limit the embodiments of the present invention to the form of the present invention. Although several exemplary aspects and embodiments have been described above, those skilled in the art will recognize several variations, modifications, changes, additions, and subcombinations thereof.

Claims (11)

An image processing method performed by a computer, the method comprising:
obtaining a target image including defect features;
identifying at least one line segment from the target image;
performing an extension process on the at least one line segment,
The extension process for a specific line segment in the at least one line segment includes:
determining an extension direction for extending the specific line segment based on the main direction and tangential direction of the specific line segment;
determining an extension length for extending the specific line segment based on the length of the specific line segment; and extending the specific line segment using the extension direction and the extension length; An image processing method comprising obtaining an extended line segment related to a defect feature in the target image. Before identifying the at least one line segment, preprocessing the target image based on an adaptive histogram equalization method, and identifying the at least one line segment from the preprocessed target image. The image processing method according to claim 1. The step of identifying at least one line segment from the target image includes:
performing processing based on frequency domain filtering on the target image to obtain a first resultant image that retains high frequency information;
performing processing based on spatial bilateral filtering on the target image to obtain a second resultant image;
fusing the first resultant image with the second resultant image to obtain a final resultant image after enhancement; and performing a binarization process on the final resultant image after enhancement to create at least one line. 2. The image processing method according to claim 1, further comprising obtaining a line segment region and thinning the line segment region using a skeleton extraction algorithm to obtain the at least one line segment of the target image. setting a first weighting coefficient for each of the first result image and the second result image;
The image processing method according to claim 3, further comprising the step of fusing the first result image and the second result image based on the set first weighting coefficient. The step of determining an extension direction for extending the specific line segment includes:
determining the main direction of the specific line segment based on the direction of a first number of points in the specific line segment;
determining the tangential direction of the specific line segment based on the tangential directions of a second number of points smaller than the first number near the end points of the specific line segment;
2. The method according to claim 1, further comprising: setting second weighting coefficients in each of the main direction and the tangential direction, and determining the extension direction of the specific line segment based on the set second weighting coefficients. Image processing method described. The second weighting coefficient after the setting is adjusted based on the curvature of the specific line segment, or
The image processing method according to claim 5, wherein the set second weighting coefficients have a positive correlation with the first number and the second number, respectively. The extension process is
selecting a line segment that satisfies a condition from among the identified at least one line segment, and performing the extension process only on the candidate line segment;
The above conditions are:
The image according to claim 1, wherein the length of the line segment is greater than a first threshold and/or the distance between the line segment and the nearest line segment is less than a second threshold. Processing method. an acquisition unit that acquires a target image including defect characteristics;
a specifying unit that specifies at least one line segment from the target image;
a processing unit that performs an extension process on the at least one line segment,
The extension process for a specific line segment in the at least one line segment includes:
determining an extension direction for extending the specific line segment based on the main direction and tangential direction of the specific line segment;
determining an extension length for extending the specific line segment based on the length of the specific line segment; and extending the specific line segment using the extension direction and the extension length; An image processing device comprising: acquiring an extended line segment related to a defect feature in the target image. a processor;
a memory connected to the processor;
The memory stores a computer program,
An image processing apparatus, wherein the processor is configured to implement the image processing method according to any one of claims 1 to 7 by executing the computer program. A program for causing a computer to execute the image processing method according to claim 1. A computer-readable storage medium storing the program according to claim 10.

Images