CN112819746A

CN112819746A - Nut kernel worm-eating defect detection method and device

Info

Publication number: CN112819746A
Application number: CN201911054851.3A
Authority: CN
Inventors: 乐翠; 孙彪; 李建峰; 孙春泉
Original assignee: Hefei Meyer Optoelectronic Technology Inc
Current assignee: Hefei Meyer Optoelectronic Technology Inc
Priority date: 2019-10-31
Filing date: 2019-10-31
Publication date: 2021-05-18
Anticipated expiration: 2039-10-31
Also published as: CN112819746B

Abstract

The invention discloses a nut kernel wormhole defect detection method and a device, wherein the method comprises the following steps: acquiring an image to be detected, wherein the image to be detected is an external rectangular X-ray image of a material to be detected; according to wait to detect the image and wait to detect the material and carry out outside worm corrosion and detect, outside worm corrosion detects and includes: sequentially carrying out binarization processing and convex hull processing on an image to be detected to respectively obtain a binarization image and a convex hull image, and subtracting the binarization image from the convex hull image to obtain a concave region; and judging whether the material to be detected has the external wormhole defect or not according to the area of the sunken area. According to the method, an external rectangular X-ray image of a material to be detected is used as an image to be detected, binarization processing and convex hull processing are carried out on the image to be detected, a concave area in the image to be detected is obtained, and whether the material to be detected has an external wormhole defect or not is judged according to the area of the concave area. The method has the advantages of high detection efficiency, high accuracy, automatic detection and the like.

Description

Nut kernel worm-eating defect detection method and device

Technical Field

The invention relates to the technical field of X-ray detection, in particular to a nut and seed kernel wormhole defect detection method and device.

Background

In recent years, nuts have become popular and their sales have increased year by year. However, nut kernels (such as almonds, almonds and the like) are extremely easy to grow insects, and if the wormhead and damaged fruits of nuts cannot be effectively sorted before being sold, the wormhead and damaged fruits of the nuts can bring extremely bad experience to consumers, so that the reputation and the market of sellers are influenced.

The X-ray inspection is an inspection method which can penetrate materials by utilizing X-rays, and can obtain X-ray images according to different absorption and scattering effects of the materials on the X-rays so as to judge the internal defect conditions of the materials. At present, X-ray flaw detection is often applied to the fields of metal material flaw detection, rubber material flaw detection such as tires, timber flaw detection and the like. However, there is no accurate and reliable detection method for the wormhole defect of the nut seeds.

In the related art, the detection of the external worm damage defect of the nut kernels is mostly realized through manual detection. The manual detection can not guarantee the long-time efficient and stable separation, and the separation personnel are easy to have fatigue, so that the wrong separation or the missing separation can be caused, and the separation efficiency of the nut kernels is lower. Therefore, the existing nut kernel wormhole defect detection method still needs to be improved.

Disclosure of Invention

The present invention is directed to solving, at least to some extent, one of the technical problems in the related art. Therefore, the invention aims to provide a nut and seed kernel wormhole defect detection method and device. The method can be used for efficiently detecting the wormhole defect of the nut kernels, has high detection accuracy and can realize automatic detection.

In one aspect of the invention, the embodiment of the invention provides a nut kernel wormholing defect detection method, which comprises the following steps:

acquiring an image to be detected, wherein the image to be detected is an external rectangular X-ray image of a material to be detected;

carrying out external wormhole detection on the material to be detected according to the image to be detected, wherein the external wormhole detection comprises the following steps: sequentially carrying out binarization processing and convex hull processing on the image to be detected to respectively obtain a first binarized image and a first convex hull image, and subtracting the first binarized image from the first convex hull image to obtain a concave area; and judging whether the material to be detected has the external wormhole defect or not according to the area of the depressed area.

According to the method, an external rectangular X-ray image of a material to be detected is used as an image to be detected, binarization processing and convex hull processing are carried out on the image to be detected, a concave area in the image to be detected is obtained, and whether the material to be detected has an external wormhole defect or not is judged according to the area of the concave area. The method has the advantages of high detection efficiency, high accuracy, automatic detection and the like.

In addition, the nut kernel wormhole corrosion defect detection method according to the above embodiment of the invention may further have the following additional technical features:

in some embodiments of the present invention, before the step of performing external worm damage detection on the material to be detected according to the image to be detected, the method further includes:

carrying out central worm corrosion detection on the material to be detected according to the image to be detected, wherein the central worm corrosion detection comprises the following steps: carrying out sharpening, corrosion and binarization on the image to be detected to obtain a second binarized image, and judging whether the material to be detected has a central wormhole defect or not according to the area of an inner contour in the second binarized image;

the external wormhole corrosion detection of the material to be detected according to the image to be detected comprises the following steps:

and under the condition that the central wormhole defect does not exist, carrying out external wormhole detection on the material to be detected according to the image to be detected.

In some embodiments of the present invention, the step of determining whether the material to be detected has an external wormhole defect according to the area of the recessed area includes:

if the number of the sunken areas with the areas smaller than a first preset threshold and larger than a second preset threshold is a preset number, and the distance from the sunken areas to the image boundary is larger than a preset distance threshold, determining that the material to be detected has an external worm damage defect;

or the like, or, alternatively,

and if the number of the sunken areas with the areas smaller than the first preset threshold and larger than the second preset threshold is a preset number, determining that the material to be detected has the defect of external worm corrosion.

In some embodiments of the present invention, before the step of performing the central worm erosion detection on the material to be detected according to the image to be detected, the method further includes:

judging whether the materials to be detected in the image to be detected are adhered or not;

the step of performing central worm erosion detection on the material to be detected according to the image to be detected comprises the following steps of:

and under the condition that adhesion does not exist, carrying out central worm corrosion detection on the material to be detected according to the image to be detected.

acquiring a to-be-detected image of a to-be-detected material, wherein the to-be-detected image is an external rectangular X-ray image of the to-be-detected material;

if the adhesion exists, the material to be detected in the image to be detected is segmented, and the circumscribed rectangle X-ray image of the material to be detected is intercepted again to obtain the image to be detected;

judging whether the material to be detected is cut or not according to the image to be detected;

if the material to be detected is cut, carrying out external wormhole detection on the material to be detected according to the image to be detected, wherein the external wormhole detection comprises the following steps: sequentially carrying out binarization processing and convex hull processing on the image to be detected to respectively obtain a first binarized image and a first convex hull image, and subtracting the first binarized image from the first convex hull image to obtain a concave area; and judging whether the material to be detected has the external wormhole defect or not according to the area of the depressed area.

The method comprises the steps of using an external rectangular X-ray image of a material to be detected as an image to be detected, firstly judging whether the condition that nut kernels are adhered to each other exists in the material to be detected, when the material to be detected is adhered, segmenting the image, using the segmented image as the image to be detected, carrying out binarization processing and convex hull processing on the image to be detected to obtain a concave area in the image to be detected, and further judging whether the material to be detected has an external wormhole defect according to the area of the concave area. The method has the advantages of high detection efficiency, high accuracy and the like.

in some embodiments of the invention, the method further comprises:

if the materials to be detected are not cut apart, carrying out central worm corrosion detection on the materials to be detected according to the images to be detected, wherein the central worm corrosion detection comprises the following steps: and carrying out sharpening, corrosion and binarization on the image to be detected to obtain a second binarized image, and judging whether the material to be detected has a central wormhole defect or not according to the area of the inner contour in the second binarized image.

or the like, or, alternatively,

In some embodiments of the present invention, before the performing the central worm corrosion detection on the material to be detected according to the image to be detected, the method further includes:

sequentially carrying out binarization processing and convex hull processing on the image to be detected, respectively obtaining a third binarization image and a second convex hull image, and subtracting the third binarization image from the second convex hull image to obtain a first concave area;

and if the number of the first sunken areas with the areas larger than the second preset threshold is more than the preset number, performing line drawing on the image to be detected.

In some embodiments of the invention, the method further comprises:

and under the condition that the number of the first sunken areas with the areas larger than a second preset threshold is a preset number, if the distance from the first sunken areas to the image boundary is larger than a preset distance threshold and the areas are smaller than a first preset threshold, determining that the material to be detected has an external wormhole defect, otherwise, performing the central wormhole detection on the material to be detected according to the image to be detected.

In some embodiments of the invention, the method further comprises: if the adhesion does not exist, taking the image to be detected as an image to be detected, and carrying out external wormhole detection on the material to be detected according to the image to be detected, or carrying out central wormhole detection on the material to be detected according to the image to be detected, wherein the central wormhole detection comprises the following steps: and carrying out sharpening, corrosion and binarization on the image to be detected to obtain a second binarized image, and judging whether the material to be detected has a central wormhole defect or not according to the area of the inner contour in the second binarized image.

In some embodiments of the invention, the method further comprises: if the adhesion does not exist, taking the image to be detected as an image to be detected, performing the external wormhole corrosion detection on the material to be detected according to the image to be detected, and performing the central wormhole corrosion detection on the material to be detected according to the image to be detected, wherein one of the two detection modes is performed firstly, and the other detection mode is performed when the corresponding defect is not detected; wherein the central worm erosion detection comprises: and carrying out sharpening, corrosion and binarization on the image to be detected to obtain a second binarized image, and judging whether the material to be detected has a central wormhole defect or not according to the area of the inner contour in the second binarized image.

In some embodiments of the invention, the segmenting comprises: and sequentially carrying out binarization treatment, corrosion treatment and expansion treatment on the image to be detected so as to segment the material to be detected in the image to be detected.

In some embodiments of the invention, the line drawing process comprises: and drawing a line for the minimum distance between the first concave region with the largest area and the first concave region with the second largest area.

In some embodiments of the invention, the method further comprises:

acquiring a second sunken area after drawing a line;

and judging whether the line is drawn successfully or not according to the first sunken area and the second sunken area, if not, determining the distance between the vertexes of the second sunken areas with the area larger than a second preset threshold value, and drawing the line between the two vertexes corresponding to the minimum distance.

In one aspect of the invention, the embodiment of the invention provides a nut kernel wormhole defect detection device, which comprises:

the image acquisition module is used for acquiring an image to be detected, wherein the image to be detected is an external rectangular X-ray image of a material to be detected;

the external wormhole corrosion detection module is used for carrying out external wormhole corrosion detection on the material to be detected according to the image to be detected, and the external wormhole corrosion detection module comprises: sequentially carrying out binarization processing and convex hull processing on the image to be detected to respectively obtain a first binarized image and a first convex hull image, and subtracting the first binarized image from the first convex hull image to obtain a concave area; and judging whether the material to be detected has the external wormhole defect or not according to the area of the depressed area.

the device comprises an image acquisition module, a data acquisition module and a data processing module, wherein the image acquisition module is used for acquiring a to-be-detected image of a to-be-detected material, and the to-be-detected image is an external rectangular X-ray image of the to-be-detected material;

the first judgment module is used for judging whether the materials to be detected in the image to be detected are adhered or not;

the segmentation module is used for segmenting the material to be detected in the image to be detected when the judgment result of the first judgment module is that adhesion exists, and intercepting the circumscribed rectangle X-ray image of the material to be detected again to obtain the image to be detected;

the second judgment module is used for judging whether the material to be detected is cut according to the image to be detected;

the external wormhole corrosion detection module is used for carrying out external wormhole corrosion detection on the material to be detected according to the image to be detected when the judgment result of the second judgment module is that the material to be detected is divided, and the external wormhole corrosion detection comprises the following steps: sequentially carrying out binarization processing and convex hull processing on the image to be detected to respectively obtain a first binarized image and a first convex hull image, and subtracting the first binarized image from the first convex hull image to obtain a concave area; and judging whether the material to be detected has the external wormhole defect or not according to the area of the depressed area.

Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.

Drawings

The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:

FIG. 1 is a schematic flow diagram of a nut kernel wormhole defect detection method according to one embodiment of the present invention;

FIG. 2 is a diagram of various images involved in convex hull processing, according to one embodiment of the invention;

FIG. 3 is a diagram of various images involved in convex hull processing, according to one embodiment of the invention;

FIG. 4 is a schematic flow diagram of a nut-seed kernel wormhole defect detection method according to one embodiment of the present invention;

FIG. 5 is an image of various images involved in a central worm erosion detection process according to one embodiment of the present invention;

FIG. 6 is a schematic flow diagram of a nut-seed kernel wormhole defect detection method according to one embodiment of the present invention;

FIG. 7 is a schematic flow diagram of a nut-seed kernel wormhole defect detection method according to one embodiment of the present invention;

FIG. 8 is a schematic flow diagram of a nut-seed kernel wormhole defect detection method according to one embodiment of the present invention;

FIG. 9 is a schematic flow diagram of a nut-seed kernel wormhole defect detection method according to one embodiment of the present invention;

FIG. 10 is a depiction of various images involved in the segmentation process in accordance with one embodiment of the present invention;

FIG. 11 is an illustration of respective images involved in a line drawing process in accordance with one embodiment of the present invention;

FIG. 12 is a schematic diagram of a nut-kernel wormhole defect detection apparatus according to one embodiment of the present invention;

FIG. 13 is a schematic diagram of a nut-kernel wormhole defect detection apparatus according to one embodiment of the present invention.

Detailed Description

Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.

Furthermore, the terms "first," "second," "third," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicit to a number of indicated technical features. Thus, a feature defined as "first," "second," "third," etc. may explicitly or implicitly include at least one of the feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.

In addition, the specific type of image processing software used in the detection method proposed by the present invention is not particularly limited, and MATLAB, OpenCV, or the like may be used, for example. In addition, in the present invention, the term "binarization processing" refers to setting, using image processing software, a pixel gradation value larger than a preset threshold value in an image to be processed as a gradation maximum value (i.e., black), and a pixel gradation value in the image to be processed, which gradation value is smaller than or equal to the preset threshold value, as a gradation minimum value (i.e., white).

In embodiments of the present invention, the nut kernels may include almonds, peanut kernels, melon seeds, macadamia nuts, pistachio nuts, and the like, and are not particularly limited herein. The present invention will be described in detail below using a almond kernel as an example.

In one aspect of the invention, the invention provides a nut kernel wormhole defect detection method for detecting whether the almond kernels have wormhole defects. According to an embodiment of the invention, with reference to fig. 1, the method comprises:

s11: and acquiring an image to be detected of the material to be detected, wherein the image to be detected is an external rectangular X-ray image of the material to be detected.

In the step, an X-ray image of the material to be detected is obtained through an imaging device of the X-ray detection equipment, the material to be detected is intercepted in the X-ray image by utilizing an external rectangle, and the image to be detected, such as the image to be detected shown in figures 2a and 3a, is obtained, wherein the material to be detected is almond. According to some embodiments of the invention, a method for intercepting a material to be detected by using a circumscribed rectangle comprises: firstly, carrying out binarization processing on an obtained X-ray image, then extracting the outline of a material to be detected, obtaining a rectangle along the edge of the outline, and then carrying out amplification processing on each side of the rectangle (for example, each side is widened by 2-8 pixels) to obtain the external rectangle, and intercepting the material to be detected from the X-ray image by using the external rectangle. By adopting the method, the image to be detected of the material to be detected is obtained by intercepting the image to be detected by the external rectangle, so that the interference of other materials can be effectively eliminated, and the misjudgment caused by adhesion of the materials is reduced.

S12: according to wait to detect the image and wait to detect the material and carry out outside worm corrosion and detect, outside worm corrosion detects and includes: sequentially carrying out binarization processing and convex hull processing on an image to be detected to respectively obtain a first binarized image and a first convex hull image, and subtracting the first binarized image from the first convex hull image to obtain a concave area; and judging whether the material to be detected has the external wormhole defect or not according to the area of the sunken area.

According to an embodiment of the present invention, referring to fig. 2 and 3, fig. 2a and 3a are respectively the images to be detected of the material badam kernel to be detected obtained according to S11. And (3) sequentially performing binarization processing and convex hull processing on the almond kernels in the graph 2a to obtain a graph 2b and a graph 2c respectively, and subtracting the graph 2b from the graph 2c to obtain a graph 2d, namely the concave regions on the outer parts of the almond kernels in the graph 2. And (3) sequentially carrying out binarization processing and convex hull processing on the almond kernels in the graph of fig. 3a to obtain a graph of fig. 3b and a graph of fig. 3c, and subtracting the graph of fig. 3b from the graph of fig. 3c to obtain a graph of fig. 3d, namely the concave regions outside the almond kernels in the graph of fig. 3. From the resulting depressed regions, it can be determined whether the almonds of figures 2 and 3, respectively, have external wormhole defects.

According to an implementation manner of the embodiment of the present invention, the step of determining whether the material to be detected has the external wormhole defect according to the area of the recessed area may include: and if the number of the sunken areas with the areas smaller than the first preset threshold and larger than the second preset threshold is a preset number, and the distance from the sunken areas to the image boundary is larger than a preset distance threshold, determining that the material to be detected has the defect of external worm corrosion. The inventor finds in research that if the number of the obtained concave regions is too large, such as more than 2, the number may be caused by adhesion of the materials to be detected; if the obtained area of the concave area is too large, namely the area of the obtained concave area is larger than or equal to a first preset threshold value, the situation may be caused by adhesion of the materials to be detected and non-separation; if the distance between the acquired concave region and the image boundary is too small, that is, smaller than or equal to a preset distance threshold, the boundary region may be misjudged. Therefore, whether the material to be detected has the external wormhole defect or not is judged according to the area and the number of the concave regions and the distance from the concave regions to the image boundary, so that the condition that the external wormhole defect possibly exists can be eliminated, and the accuracy of detecting the external wormhole defect is improved.

According to another implementation manner of the embodiment of the present invention, the step of determining whether the material to be detected has the external wormhole defect according to the area of the recessed area may include: and if the number of the sunken areas with the areas smaller than the first preset threshold and larger than the second preset threshold is a preset number, determining that the material to be detected has the defect of external worm corrosion. Whether the material to be detected has the external wormhole defect or not is judged according to the area and the number of the sunken areas, so that the condition that misjudgment possibly exists can be partially eliminated, and the accuracy of external wormhole defect detection is improved.

It should be noted that by setting the first preset threshold, a recessed region with a smaller area may be excluded, and such a similar recessed region may not constitute an insect erosion defect, for example, a surface damage of the seed kernel due to scratch.

In another aspect of the invention, the invention also provides a nut kernel wormhole defect detection method. According to an embodiment of the present invention, referring to fig. 4, the nut-seed kernel wormholing defect detection method comprises:

s41: and acquiring an image to be detected of the material to be detected, wherein the image to be detected is an external rectangular X-ray image of the material to be detected.

S42: carrying out central worm corrosion detection on the material to be detected according to the image to be detected, wherein the central worm corrosion detection comprises the following steps: and carrying out sharpening, corrosion and binarization on the image to be detected to obtain a second binarized image, and judging whether the material to be detected has a central wormhole defect or not according to the area of the inner contour in the second binarized image.

In the step, the central wormhole corrosion detection is carried out on the material to be detected according to the image to be detected, if the central wormhole corrosion defect exists in the material to be detected, the wormhole corrosion defect exists in the material to be detected, and the detection aiming at the image to be detected can be finished. In the case where there is no central worm damage defect, S43 is performed.

It should be noted that the detected central worm damage defect may be an external worm damage defect of the nut kernel or an internal worm damage defect of the nut kernel.

According to an implementation manner of the embodiment of the invention, after the material contour is obtained from the sharpened image, the inside of the contour can be filled with black, and the black part is eroded, wherein the material contour is a contour corresponding to the largest connected domain in the image. In addition, after the material contour is obtained from the sharpened image, the inside of the contour can be filled with white, and the white part can be corroded. And (5) the outline of the corroded material becomes small, and a central area image corresponding to the corroded outline of the material is taken from the sharpened image to be detected. And (4) carrying out binarization processing on the central region image, extracting the inner contour of the central region, and judging the central worm damage according to the area of the inner contour. Specifically, referring to fig. 5, fig. 5a is an image to be detected, fig. 5b is a sharpened image obtained by sharpening the image to be detected, fig. 5c is a corroded image obtained by corroding a black part after filling black in the outline of the sharpened image, and fig. 5d is a binarized image obtained by binarizing the sharpened image according to the corroded material outline.

Therefore, by adopting corrosion treatment in the central wormhole corrosion detection, the interference of external wormhole corrosion defects possibly existing in the material to be detected can be effectively avoided. Further, a sharpened image of a central area is taken out according to the sharpened image and the contour of the corroded material, binarization processing is carried out on the sharpened image, all images outside the central area are filled into colors different from the inner contour in the central area, if the area in the inner contour is white and the rest is black, or the area in the inner contour is black and the rest is white, the area of the internal communication area is obtained for the image of the binarized central area, namely the area closest to the central worm erosion part, namely the area of the inner contour, and if the area is within the preset area threshold range of the central worm erosion defect, the area is determined to be the central worm erosion defect.

S43: according to wait to detect the image and wait to detect the material and carry out outside worm corrosion and detect, outside worm corrosion detects and includes: sequentially carrying out binarization processing and convex hull processing on an image to be detected to respectively obtain a first binarized image and a first convex hull image, and subtracting the first binarized image from the first convex hull image to obtain a concave area; and judging whether the material to be detected has the external wormhole defect or not according to the area of the sunken area.

S41 is the same as S11, S43 is the same as S12, and explanation of S41 and S43 can refer to the corresponding parts, which are not repeated herein.

The method comprises the steps of firstly carrying out central worm erosion detection, detecting the internal worm erosion defect and the external worm erosion defect of the nut kernels, and carrying out external worm erosion defect detection when the central worm erosion detection result shows that the worm erosion defect does not exist. The combination of the two can effectively detect the internal worm-eating defect and the external worm-eating defect of the nut kernels, the detection is more comprehensive, and the detection accuracy is higher.

In another aspect of the invention, the invention also provides a nut kernel wormhole defect detection method. Referring to fig. 6, the method includes:

s61: and acquiring an image to be detected of the material to be detected, wherein the image to be detected is an external rectangular X-ray image of the material to be detected.

S62: and judging whether the materials to be detected in the image to be detected are adhered or not, and if not, executing S63.

Specifically, the step of judging whether the material to be detected in the image to be detected has adhesion comprises the following steps: if the size of the circumscribed rectangular X-ray image of the material to be detected exceeds a preset size threshold, judging that the material to be detected is adhered; otherwise, judging that the materials to be detected are not adhered. The above-mentioned size refers to at least one of the length, width and area of the circumscribed rectangular X-ray image, i.e., the image to be detected. For example, the size for judging adhesion includes length, width and area, if the length, width and area of the circumscribed rectangle X-ray image exceed the corresponding length threshold, width threshold and area threshold, it is determined that the material to be detected has adhesion, otherwise, it is determined that the material to be detected does not have adhesion. The preset size threshold is set according to the size of the material to be detected, for example, for the badam kernel, the length and the width of the badam kernel in imaging can be set according to the free placement of the badam kernel.

S63: carrying out central worm corrosion detection on the material to be detected according to the image to be detected, wherein the central worm corrosion detection comprises the following steps: and carrying out sharpening, corrosion and binarization on the image to be detected to obtain a second binarized image, and judging whether the material to be detected has a central wormhole defect or not according to the area of the inner contour in the second binarized image. In the case where there is no central worm damage defect, S64 is performed.

S64: according to wait to detect the image and wait to detect the material and carry out outside worm corrosion and detect, outside worm corrosion detects and includes: sequentially carrying out binarization processing and convex hull processing on an image to be detected to respectively obtain a first binarized image and a first convex hull image, and subtracting the first binarized image from the first convex hull image to obtain a concave area; and judging whether the material to be detected has the external wormhole defect or not according to the area of the sunken area.

S61 is the same as S11, S63 is the same as S42, S64 is the same as S12, and explanation of S61, S63, and S64 can refer to the corresponding parts, which are not repeated herein.

According to the method, the intercepted materials are subjected to adhesion judgment, central worm erosion detection is firstly carried out on the materials to be detected without adhesion, the internal worm erosion defect and the external worm erosion defect of the nut kernels can be detected, and the external worm erosion defect detection is carried out when the central worm erosion detection result shows that the worm erosion defect does not exist. Set up like this and not only can reduce the erroneous judgement because of the material adhesion leads to, adopt the mode that central worm erodees and detects both combinations with outside worm erode, can effectually detect out the inside worm erode defect and the outside worm erode defect of nut seed benevolence, detect more comprehensively and detect that the accuracy is higher.

In another aspect of the invention, the invention also provides a nut kernel wormhole defect detection method. Referring to fig. 7, the method includes, according to an embodiment of the present invention:

s71: and acquiring a to-be-detected image of the to-be-detected material, wherein the to-be-detected image is an external rectangular X-ray image of the to-be-detected material.

In the step, an X-ray image of the material to be detected is obtained through an imaging device of the X-ray detection equipment, the material to be detected is targeted in the X-ray image, and the material to be detected is intercepted by utilizing an external rectangle, so that the image to be detected is obtained. According to some embodiments of the invention, a method for intercepting a material to be detected by using a circumscribed rectangle comprises: firstly, carrying out binarization processing on an obtained X-ray image, then extracting the outline of a material to be detected, obtaining a rectangle along the edge of the outline, and then carrying out amplification processing on each side of the rectangle (for example, each side is widened by 2-8 pixels) to obtain the external rectangle, and intercepting the material to be detected from the X-ray image by using the external rectangle. By adopting the method, the image to be detected of the material to be detected is obtained by intercepting the image to be detected by the external rectangle, so that the interference of other materials can be effectively eliminated, and the misjudgment caused by adhesion of the materials is reduced.

S72: and judging whether the materials to be detected in the image to be detected are adhered or not, and if so, executing the subsequent step S73.

Specifically, the step of judging whether the material to be detected in the image to be detected has adhesion comprises the following steps: if the size of the circumscribed rectangular X-ray image of the material to be detected exceeds a preset size threshold, judging that the material to be detected is adhered; otherwise, judging that the materials to be detected are not adhered. The above-mentioned size refers to at least one of the length, width and area of the circumscribed rectangular X-ray image, i.e., the image to be detected. For example, the size for judging adhesion includes length, width and area, if the length, width and area of the circumscribed rectangle X-ray image exceed the corresponding length threshold, width threshold and area threshold, it is determined that the material to be detected has adhesion, otherwise, it is determined that the material to be detected does not have adhesion.

According to some embodiments of the present invention, the threshold value for the length of the circumscribed rectangular X-ray image may be 60-70 pixels, and the threshold value for the width of the circumscribed rectangular X-ray image may be 60-70 pixels.

S73: and segmenting the material to be detected in the image to be detected, and intercepting the external rectangular X-ray image of the material to be detected again to obtain the image to be detected.

To wait that it detects in the image to wait to detect and detect material cut apart, include: and carrying out binarization processing, corrosion processing and expansion processing on the image to be detected. Specifically, binarization processing is carried out on a pre-detected image to obtain a binarization image; the method comprises the steps of obtaining the outline of the maximum connected domain in a binary image, filling white or black in the outline area, carrying out corrosion treatment on the black area or the white area, obtaining the corroded outline, carrying out expansion treatment on the corroded outline, obtaining the expanded outline, obtaining a circumscribed rectangle of the expanded outline, and intercepting the area corresponding to the expanded outline in a pre-detection image by using the circumscribed rectangle, namely the re-intercepted image to be detected. Referring to fig. 10, fig. 10a is a predicted image to be detected with material adhesion, fig. 10b is an image obtained by performing corrosion expansion processing on the predicted image to be detected, and a small frame in fig. 10c is a rectangle obtained by cutting again, wherein the frame is selected as the image to be detected.

According to some embodiments of the present invention, the erosion radius used in the erosion image may be 0 to 30, the parameter used in the dilation includes a dilation radius, i.e. how many circles of dilation, and the operation is to obtain a rectangular frame after segmentation, and the value is about 40.

S74: and judging whether the material to be detected is cut off or not according to the image to be detected, and executing S75 if the material to be detected is cut off.

The step of judging whether the material to be detected is cut off comprises the following steps: if the size of the circumscribed rectangular X-ray image of the material to be detected exceeds a preset size threshold, judging that the material to be detected is not cut, namely, the material to be detected in the image to be detected is still adhered; otherwise, judging that the material to be detected is cut, namely the material to be detected in the image to be detected does not adhere. The above-mentioned size refers to at least one of the length, width and area of the circumscribed rectangular X-ray image, i.e., the image to be detected. For example, the size for judging adhesion comprises length, width and area, if the length, width and area of the circumscribed rectangular X-ray image exceed the corresponding length threshold, width threshold and area threshold, the material to be detected is judged not to be separated, otherwise, the material to be detected in the image to be detected is judged to be separated.

S75: according to wait to detect the image and wait to detect the material and carry out outside worm corrosion and detect, outside worm corrosion detects and includes: sequentially carrying out binarization processing and convex hull processing on an image to be detected to respectively obtain a first binarized image and a first convex hull image, and subtracting the first binarized image from the first convex hull image to obtain a concave area; and judging whether the material to be detected has the external wormhole defect or not according to the area of the sunken area.

S75 is the same as S12, and is not described herein, and for the detailed explanation, reference may be made to the corresponding parts. .

According to the method, the intercepted materials are subjected to adhesion judgment, the adhered materials to be detected are subjected to cutting treatment, and external wormhole defect detection is carried out on the cut materials. Set up like this and not only can reduce the erroneous judgement that leads to because of the material adhesion, will treat the external rectangle X-ray image of material as treating the detection image, at first judge and treat whether there is the mutual adhesion's of nut seed benevolence the condition in treating the detection material, when treating the detection material and have the adhesion, cut apart the image, and regard as the image of waiting to detect with the image of cutting apart, through will waiting to detect the image and carry out binarization processing, the convex closure is handled, obtain and wait to detect the sunken region in the image, and then judge according to the area of sunken region and wait to detect whether there is outside wormhole defect in the material. The method has the advantages of high detection efficiency, high accuracy and the like.

In an implementation manner of the embodiment shown in fig. 7, the step of determining whether the material to be detected has the external wormhole defect according to the area of the recessed area may include: and if the number of the sunken areas with the areas smaller than the first preset threshold and larger than the second preset threshold is a preset number, and the distance from the sunken areas to the image boundary is larger than a preset distance threshold, determining that the material to be detected has the defect of external worm corrosion.

The inventor finds in research that if the number of the obtained concave regions is too large, such as more than 2, the number may be caused by adhesion of the materials to be detected; if the obtained area of the concave area is too large, namely the area of the obtained concave area is larger than or equal to a first preset threshold value, the situation may be caused by adhesion of the materials to be detected and non-separation; if the distance between the acquired concave region and the image boundary is too small, that is, smaller than or equal to a preset distance threshold, the boundary region may be misjudged. Therefore, whether the material to be detected has the external wormhole defect or not is judged according to the area and the number of the concave regions and the distance from the concave regions to the image boundary, so that the condition that the external wormhole defect possibly exists can be eliminated, and the accuracy of detecting the external wormhole defect is improved.

In another implementation manner of the embodiment shown in fig. 7, the step of determining whether the material to be detected has the external wormhole defect according to the area of the recessed area may include: and if the number of the sunken areas with the areas smaller than the first preset threshold and larger than the second preset threshold is a preset number, determining that the material to be detected has the defect of external worm corrosion.

Whether the material to be detected has the external wormhole defect or not is judged according to the area and the number of the sunken areas, so that the condition that misjudgment possibly exists can be partially eliminated, and the accuracy of external wormhole defect detection is improved.

According to the embodiment of the present invention, if the determination result in the step S74 is that the material to be detected in the image to be detected is not divided, the image to be detected is directly used as the image to be detected for central worm erosion detection, and the method for performing central worm erosion detection on the image to be detected in this step is the same as that in the step S42, which is not described herein again, and reference may be made to the above corresponding contents.

In another aspect of the invention, the invention also provides a nut kernel wormhole defect detection method. Referring to fig. 8, the method includes, according to an embodiment of the present invention:

s81: and acquiring a to-be-detected image of the to-be-detected material, wherein the to-be-detected image is an external rectangular X-ray image of the to-be-detected material. S81 is the same as S71, and details thereof are not repeated herein, and reference may be made to the corresponding contents.

S82: and judging whether the materials to be detected in the image to be detected are adhered or not. Judging whether the materials to be detected in the image to be detected are adhered or not; if there is sticking, the subsequent step S83 is performed. S82 is the same as S72, and details thereof are not repeated herein, and reference may be made to the corresponding contents.

S83: and segmenting the material to be detected in the image to be detected, and intercepting the external rectangular X-ray image of the material to be detected again to obtain the image to be detected. S83 is the same as S73, and details thereof are not repeated herein, and reference may be made to the corresponding contents.

S84: and judging whether the material to be detected is cut off or not according to the image to be detected, and executing S85 if the material to be detected is cut off. S84 is the same as S74, and details thereof are not repeated herein, and reference may be made to the corresponding contents.

S85: sequentially carrying out binarization processing and convex hull processing on an image to be detected, respectively obtaining a third binarization image and a second convex hull image, and subtracting the obtained second convex hull image from the third binarization image to obtain a first concave region; and if the number of the first sunken areas with the areas larger than the second preset threshold is more than the preset number, performing line drawing on the image to be detected, and performing S86.

Therefore, the central worm damage defect detection and the external worm damage defect detection of the image to be detected are carried out on the maximum connected domain in the image to be detected, the plurality of first sunken areas in the image are further divided into the plurality of areas through line drawing, the subsequent detection result can be influenced through line drawing processing, and the accuracy of the detection result can be further improved. As shown in fig. 11, fig. 11a is an image to be detected after being divided, fig. 11b is a material image after being subjected to line changing, and when central worm corrosion detection and/or external worm corrosion detection are/is subsequently performed, the largest connected domain in the material image after being subjected to line drawing is processed.

According to an embodiment of the present invention, the line drawing process includes: the minimum distance between the first depressed region having the largest area and the first depressed region having the second largest area is drawn.

Further, a second concave area after line drawing is obtained; and judging whether the line is drawn successfully or not according to the first sunken area and the second sunken area, if not, determining the distance between the vertexes of the second sunken areas with the area larger than a second preset threshold value, and drawing the line between the two vertexes corresponding to the minimum distance. Specifically, a plurality of second recessed areas are obtained after line drawing; and if the area of the second recessed region is obviously changed relative to the first recessed region, the line drawing is considered to be successful, and the line drawing is finished, for example, the area reduction amplitude of the second recessed region relative to the first recessed region exceeds a preset area proportion, or the number of the second recessed regions exceeds a preset number proportion, the line drawing is considered to be successful. And if the line drawing is unsuccessful, determining the distances between the vertexes of the plurality of second sunken areas with the areas larger than a second preset threshold value, and drawing the line between the two vertexes corresponding to the minimum distance.

S86: carrying out central worm corrosion detection on the material to be detected according to the image to be detected, wherein the central worm corrosion detection comprises the following steps: and carrying out sharpening, corrosion and binarization on the image to be detected to obtain a second binarized image, and judging whether the material to be detected has a central wormhole defect or not according to the area of the inner contour in the second binarized image. In the case where there is no central worm damage defect, S87 is further performed. The method for detecting central worm damage of the image to be detected in this step is the same as that of S42, and details thereof are not repeated herein, and reference may be made to the above contents.

S87: according to wait to detect the image and wait to detect the material and carry out outside worm corrosion and detect, outside worm corrosion detects and includes: sequentially carrying out binarization processing and convex hull processing on an image to be detected to respectively obtain a first binarized image and a first convex hull image, and subtracting the first binarized image from the first convex hull image to obtain a concave area; and judging whether the material to be detected has the external wormhole defect or not according to the area of the sunken area. The method for detecting external worm damage of the image to be detected in this step is the same as that of S12, and details thereof are not repeated herein, and reference may be made to the above contents.

According to the embodiment of the present invention, under the condition that the number of the first depressed regions having the areas smaller than the first preset threshold and larger than the second preset threshold is a preset number, if the distance from the first depressed region to the image boundary is larger than the preset distance threshold (i.e. it does not belong to the boundary region misjudgment), it is determined that the first depressed region is an external wormhole defect, and it is determined that the material to be detected has the external wormhole defect, otherwise, the central wormhole detection is performed on the material to be detected according to the image to be detected, and the manner of performing the central wormhole detection in this step is the same as that in the above S42, which is not described herein again.

According to an embodiment of the present invention, the method may further include: by executing the step S82, if it is predicted that the material to be detected in the image to be detected does not adhere, the image to be detected is taken as the image to be detected, and external worm damage detection is performed on the material to be detected according to the image to be detected. The manner of performing the external worm damage detection in this step is the same as that in S12, and is not described herein again.

According to an embodiment of the present invention, the method may further include: by executing the step S82, if it is predicted that the material to be detected in the image to be detected is not adhered, the image to be detected is taken as the image to be detected, and the material to be detected is subjected to central worm corrosion detection according to the image to be detected. The manner of performing the central worm damage detection in this step is the same as that in S42, and is not described herein again.

According to an embodiment of the present invention, the method may further include: by executing the step S82, if it is predicted that the material to be detected in the image to be detected does not adhere, the image to be detected is used as the image to be detected, and in two detection modes, external wormhole detection is performed on the material to be detected according to the image to be detected, and central wormhole detection is performed on the material to be detected according to the image to be detected, one of the two detection modes is executed first, and when the corresponding defect is not detected, the other detection mode is executed. Specifically, external wormhole corrosion detection can be performed on the material to be detected according to the image to be detected, and when the external wormhole corrosion defect is detected, the detection is finished, and the existence of the external wormhole corrosion defect in the material to be detected is judged; and when the external wormhole defect is not detected, further carrying out central wormhole detection on the material to be detected according to the image to be detected. Or carrying out central worm erosion detection on the material to be detected according to the image to be detected, and judging that the material to be detected has the central worm erosion defect after the detection is finished when the central worm erosion defect is detected; and when the central wormhole defect is not detected, further carrying out external wormhole detection on the material to be detected according to the image to be detected. The specific operation methods of the external worm damage detection and the central worm damage detection are as described above, and are not described herein again.

According to the method, the intercepted materials are subjected to adhesion judgment, the adhered materials to be detected are subjected to segmentation treatment, whether line drawing treatment is carried out or not is determined according to the number and the area of the obtained first concave areas aiming at the segmented materials, and then central worm corrosion detection and external worm corrosion detection are sequentially carried out on the basis. Set up like this and not only can reduce the erroneous judgement because of the material adhesion leads to, adopt the mode that central worm erodees and detects both combinations with outside worm erode, can effectually detect out the inside worm erode defect and the outside worm erode defect of nut seed benevolence, detect more comprehensively and detect that the accuracy is higher.

For ease of understanding, a nut-seed kernel worm damage defect detection method according to one specific example of the invention is described below with reference to FIG. 9:

s91: acquiring a to-be-detected image of a to-be-detected material, wherein the to-be-detected image is an external rectangular X-ray image of the to-be-detected material;

s92: judging whether the materials to be detected in the images to be detected are adhered or not, if not, executing S93 to detect the central worm erosion defect of the materials to be detected, and if not, executing S94 to detect the external worm erosion defect of the materials to be detected; if sticking exists, S95 is executed.

S93: taking the image to be detected as the image to be detected, and carrying out central worm corrosion detection on the material to be detected according to the image to be detected, wherein the central worm corrosion detection comprises the following steps: and carrying out sharpening, corrosion and binarization on the image to be detected to obtain a second binarized image, and judging whether the material to be detected has a central wormhole defect or not according to the area of the inner contour in the second binarized image.

S94: according to wait to detect the image and wait to detect the material and carry out outside worm corrosion and detect, outside worm corrosion detects and includes: sequentially carrying out binarization processing and convex hull processing on an image to be detected to respectively obtain a first binarized image and a first convex hull image, and subtracting the first binarized image from the first convex hull image to obtain a concave area; and judging whether the material to be detected has the external wormhole defect or not according to the area of the sunken area.

S95: and segmenting the material to be detected in the image to be detected, and intercepting the external rectangular X-ray image of the material to be detected again to obtain the image to be detected.

S96: and judging whether the material to be detected is divided or not according to the image to be detected, if not, executing S97, and if so, executing S98.

S97: carrying out central worm corrosion detection on the material to be detected according to the image to be detected, wherein the central worm corrosion detection comprises the following steps: and carrying out sharpening, corrosion and binarization on the image to be detected to obtain a second binarized image, and judging whether the material to be detected has a central wormhole defect or not according to the area of the inner contour in the second binarized image.

S98: sequentially carrying out binarization processing and convex hull processing on an image to be detected to respectively obtain a third binarization image and a second convex hull image, and subtracting the second convex hull image from the binarization image to obtain a second concave area;

if the number of the second concave regions having areas larger than the second predetermined threshold is greater than the predetermined number, S99 is executed, and if the number of the second concave regions having areas larger than the second predetermined threshold is greater than the predetermined number, S913 is executed.

S99: and performing line drawing processing on the image to be detected.

S910: carrying out central worm corrosion detection on the material to be detected according to the image to be detected, wherein the central worm corrosion detection comprises the following steps: and carrying out sharpening, corrosion and binarization on the image to be detected to obtain a second binarized image, and judging whether the material to be detected has a central wormhole defect or not according to the area of the inner contour in the second binarized image. In the absence of a central worm defect, S911 is performed.

S911: according to wait to detect the image and wait to detect the material and carry out outside worm corrosion and detect, outside worm corrosion detects and includes: sequentially carrying out binarization processing and convex hull processing on an image to be detected to respectively obtain a first binarized image and a first convex hull image, and subtracting the first binarized image from the first convex hull image to obtain a concave area; and judging whether the material to be detected has the external wormhole defect or not according to the area of the sunken area.

S912: and judging whether the material to be detected has an external wormhole defect or not according to the area of the first recessed area, and executing S913 under the condition that the external wormhole defect does not exist.

S913: carrying out central worm corrosion detection on the material to be detected according to the image to be detected, wherein the central worm corrosion detection comprises the following steps: and carrying out sharpening, corrosion and binarization on the image to be detected to obtain a second binarized image, and judging whether the material to be detected has a central wormhole defect or not according to the area of the inner contour in the second binarized image.

According to the method, adhesion judgment is carried out on intercepted materials, the materials to be detected which are adhered are subjected to segmentation treatment, whether line drawing treatment is carried out or not is determined according to the number and the area of the obtained first concave areas aiming at the segmented materials, and then how to judge the selection is determined based on the line drawing treatment. Aiming at the condition that adhesion does not exist, at least one of two modes of detecting the external worm corrosion of the central worm corrosion detection box can be only carried out, so that misjudgment caused by material adhesion can be reduced, the detection is more comprehensive, and the accuracy is higher.

It should be noted that the threshold range adopted in the binarization processing in any of the above embodiments may be 180-200, the preset area threshold of the central worm damage defect may be 15-20, the preset distance threshold may be 1-2 pixels, the preset number may be 1, the number greater than the preset number may be greater than 1, that is, not less than 2, and the remaining thresholds and preset values may be set according to actual expectations for results or according to feedback results.

In addition, it should be noted that each detection method, determination method, step, and the like described in the above specific examples are all as described above, and are not described herein again.

Based on the same inventive concept as the method embodiment, the embodiment of the invention also provides a nut kernel wormhole defect detection device, and with reference to fig. 12, the device comprises:

the image acquisition module 121 is configured to acquire an image to be detected, where the image to be detected is an external rectangular X-ray image of a material to be detected;

an external wormhole detection module 122, configured to perform external wormhole detection on the material to be detected according to the image to be detected, where the external wormhole detection includes: sequentially carrying out binarization processing and convex hull processing on the image to be detected to respectively obtain a first binarized image and a convex hull image, and subtracting the first binarized image from the convex hull image to obtain a concave area; and judging whether the material to be detected has the external wormhole defect or not according to the area of the depressed area.

In an implementation manner of this embodiment, the apparatus further includes a central worm erosion detection module.

The central worm corrosion detection module is used for carrying out central worm corrosion detection on the material to be detected according to the image to be detected, and the central worm corrosion detection comprises the following steps: carrying out sharpening, corrosion and binarization on the image to be detected to obtain a second binarized image, and judging whether the material to be detected has a central wormhole defect or not according to the area of an inner contour in the second binarized image;

the external wormhole corrosion detection module 122 is specifically configured to perform external wormhole corrosion detection on the material to be detected according to the image to be detected, when the detection result of the central wormhole corrosion detection module indicates that the central wormhole corrosion defect does not exist.

In an implementation manner of this embodiment, the external wormhole detection module 122 is configured to determine whether the material to be detected has an external wormhole defect according to an area of the concave region, and includes:

if the number of the sunken areas with the areas smaller than a first preset threshold and larger than a second preset threshold is a preset number, and the distance from the sunken areas to the image boundary is larger than a preset distance threshold, determining that the material to be detected has an external worm damage defect; or if the number of the sunken areas with the areas smaller than the first preset threshold and larger than the second preset threshold is a preset number, determining that the material to be detected has the defect of external worm corrosion.

In an implementation manner of this embodiment, the apparatus further includes an adhesion determination module;

before the step of performing the central worm erosion detection on the material to be detected according to the image to be detected, the method further comprises:

the adhesion judging module is used for judging whether the materials to be detected in the image to be detected are adhered or not;

the central worm corrosion detection module is used for carrying out central worm corrosion detection on the material to be detected according to the image to be detected, and comprises: and under the condition that adhesion does not exist, carrying out central worm corrosion detection on the material to be detected according to the image to be detected.

Based on the same inventive concept as the method embodiment, the embodiment of the invention also provides a nut kernel wormhole defect detection device, and with reference to fig. 13, the device comprises:

the image acquisition module 131 is used for acquiring a to-be-detected image of the to-be-detected material, wherein the to-be-detected image is an external rectangular X-ray image of the to-be-detected material;

the first judging module 132 is configured to judge whether the material to be detected in the image to be detected is adhered;

the segmentation module 133 is configured to segment the material to be detected in the image to be detected when the first determination module determines that adhesion exists, and re-intercept the external rectangular X-ray image of the material to be detected to obtain an image to be detected;

the second judging module 134 is configured to judge whether the material to be detected is cut according to the image to be detected;

an external wormhole detection module 135, configured to perform, according to the image to be detected, external wormhole detection on the material to be detected when the determination result of the second determination module is that the material to be detected is cut, where the external wormhole detection includes: sequentially carrying out binarization processing and convex hull processing on the image to be detected to respectively obtain a first binarized image and a convex hull image, and subtracting the first binarized image from the convex hull image to obtain a concave area; and judging whether the material to be detected has the external wormhole defect or not according to the area of the depressed area.

The central worm corrosion detection module is configured to perform central worm corrosion detection on the to-be-detected material according to the to-be-detected image when the segmentation result of the segmentation module 133 is that the to-be-detected material is not segmented, where the central worm corrosion detection includes: and carrying out sharpening, corrosion and binarization on the image to be detected to obtain a second binarized image, and judging whether the material to be detected has a central wormhole defect or not according to the area of the inner contour in the second binarized image.

In an implementation manner of this embodiment, the external wormhole detection module 135 is configured to determine whether the material to be detected has an external wormhole defect according to an area of the concave region, and includes:

the external wormhole corrosion detection module 135 is configured to perform external wormhole corrosion detection on the material to be detected according to the image to be detected, and specifically, when the central wormhole corrosion detection module detects that the central wormhole corrosion defect does not exist, perform external wormhole corrosion detection on the material to be detected according to the image to be detected.

Further, the device also comprises a first processing module, which is used for sequentially carrying out binarization processing and convex hull processing on the image to be detected under the condition that the material to be detected is divided, respectively obtaining a third binarization image and a second convex hull image, and subtracting the third binarization image from the second convex hull image to obtain a first concave area;

Furthermore, the first processing module is further configured to, when the number of the first depressed regions having areas larger than a second preset threshold is a preset number, determine that the material to be detected has an external wormhole defect if the distance from the first depressed region to the image boundary is larger than a preset distance threshold and the area is smaller than a first preset threshold, and otherwise, perform the central wormhole detection on the material to be detected according to the image to be detected.

In an implementation manner of this embodiment, under the condition that there is no adhesion, the external wormhole corrosion detection module 135 is configured to use an image to be detected as an image to be detected, and perform the external wormhole corrosion detection on the material to be detected according to the image to be detected, or perform the central wormhole corrosion detection on the material to be detected according to the image to be detected, where the central wormhole corrosion detection includes: and carrying out sharpening, corrosion and binarization on the image to be detected to obtain a second binarized image, and judging whether the material to be detected has a central wormhole defect or not according to the area of the inner contour in the second binarized image.

Alternatively, the first and second electrodes may be,

in the absence of sticking, the external and central worm

erosion detection modules

135 and 135, respectively, are executed as follows: taking an image to be detected as an image to be detected, performing the external wormhole corrosion detection on the material to be detected according to the image to be detected, and performing the central wormhole corrosion detection on the material to be detected according to the image to be detected, wherein one of the two detection modes is performed firstly, and the other detection mode is performed when the corresponding defect is not detected; wherein the central worm erosion detection comprises: and carrying out sharpening, corrosion and binarization on the image to be detected to obtain a second binarized image, and judging whether the material to be detected has a central wormhole defect or not according to the area of the inner contour in the second binarized image.

In an implementation manner of the embodiment of the present invention, the segmentation module 133 is specifically configured to sequentially perform binarization processing, corrosion processing, and expansion processing on the image to be detected, so as to segment the material to be detected in the image to be detected.

In an implementation manner of the embodiment of the present invention, the first processing module is specifically configured to draw a line for a minimum distance between the first recessed region with a largest area and the first recessed region with a second largest area.

In an implementation manner of the embodiment of the present invention, the first processing module is further configured to: acquiring a second sunken area after drawing a line;

In the embodiment of the present invention, the apparatus portion corresponds to the method portion, and for the related technical explanation of this portion, reference may be made to the method embodiment portion, which is not described herein again.

In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.

Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.

Claims

1. A nut kernel wormhole defect detection method is characterized by comprising the following steps:

2. The method of claim 1, further comprising, prior to the step of performing external worm damage detection on the material to be detected from the image to be detected:

3. The method according to claim 1 or 2, wherein the step of judging whether the material to be detected has the external wormhole defect according to the area of the depressed area comprises the following steps:

or the like, or, alternatively,

4. The method according to claim 2, characterized in that before the step of performing the central worm erosion detection on the material to be detected on the basis of the image to be detected, the method further comprises:

5. A nut kernel wormhole defect detection method is characterized by comprising the following steps:

6. The method of claim 5, further comprising:

7. The method according to claim 5, wherein the step of judging whether the material to be detected has the external wormhole defect or not according to the area of the depressed area comprises the following steps:

or the like, or, alternatively,

8. The method according to claim 5, characterized in that before the step of external wormhole detection of the material to be detected from the image to be detected, the method further comprises:

9. The method according to claim 8, wherein before the central wormhole detection of the material to be detected from the image to be detected, the method further comprises:

10. The method of claim 9, further comprising:

11. The method of claim 5, further comprising: if the adhesion does not exist, taking the image to be detected as an image to be detected, and carrying out external wormhole detection on the material to be detected according to the image to be detected, or carrying out central wormhole detection on the material to be detected according to the image to be detected, wherein the central wormhole detection comprises the following steps: and carrying out sharpening, corrosion and binarization on the image to be detected to obtain a second binarized image, and judging whether the material to be detected has a central wormhole defect or not according to the area of the inner contour in the second binarized image.

12. The method of claim 5, further comprising: if the adhesion does not exist, taking the image to be detected as an image to be detected, performing the external wormhole corrosion detection on the material to be detected according to the image to be detected, and performing the central wormhole corrosion detection on the material to be detected according to the image to be detected, wherein one of the two detection modes is performed firstly, and the other detection mode is performed when the corresponding defect is not detected; wherein the central worm erosion detection comprises: and carrying out sharpening, corrosion and binarization on the image to be detected to obtain a second binarized image, and judging whether the material to be detected has a central wormhole defect or not according to the area of the inner contour in the second binarized image.

13. The method of claim 5, wherein the segmenting comprises: and sequentially carrying out binarization treatment, corrosion treatment and expansion treatment on the image to be detected so as to segment the material to be detected in the image to be detected.

14. The method of claim 9, wherein the line marking process comprises: and drawing a line for the minimum distance between the first concave region with the largest area and the first concave region with the second largest area.

15. The method of claim 14, further comprising:

acquiring a second sunken area after drawing a line;

16. The utility model provides a nut seed benevolence worm loses defect detecting device which characterized in that includes:

17. The utility model provides a nut seed benevolence worm loses defect detecting device which characterized in that includes: