Detecting apparatus, detecting method and computer readable storage medium
Patent Information
- Application Number
- PCT/CN2024/099290
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-06-15
- Filing Date
- 2024-06-14
- Publication Date
- 2024-12-19
Smart Images

Figure CN2024099290_19122024_PF_FP_ABST
Abstract
Description
DETECTING APPARATUS, DETECTING METHOD AND COMPUTER READABLE STORAGE MEDIUMTECHNICAL FIELD
[0001] At least one embodiment of the present disclosure relates to a detecting apparatus, a detecting method and a computer readable storage medium.BACKGROUND
[0002] At present, trade exchanges between countries and regions are very frequent. In order to facilitate storage, transportation and sales, it is usually necessary to package various products. For example, foods such as milk, beverages, and vegetable puree need to be packaged and sealed in various forms of containers such as package cartons and package bags.
[0003] A process for sealing a product into a container requires several detection processes and check at each level, to control yield and guarantee supply of a safe and reliable product for a user.
[0004] After sealing a product into a container, it is also necessary to detect the container containing the product. If there are defects in the sealed container, a series of problems may be caused, for example, quality deterioration of the product contained in the container, inability of a user to use normally, poor appearance of the container affecting sales, and so on.SUMMARY
[0005] According to an embodiment of the present disclosure, it is provided a detecting apparatus for detecting a defect of a package carton, the package carton having a slanted surface, and the slanted surface having a cap region for arranging a cap, wherein the detecting apparatus comprises: an image acquiring module, configured to acquire a to-be-processed image of the slanted surface; an extracting module, configured to provide a positioning window on the to-be-processed image, and extract a feature region to be analyzed from the positioning window; and a feature analyzing module, configured to extract a feature value of the feature region and compare the feature value of the feature region with a preset value, to determine whether the package carton has the defect.
[0006] For example, the detecting apparatus is configured to detect whether the package carton has a defect of cap lacking; the extracting module is configured to extract a feature region to be analyzed in a way below: providing a first positioning window on the to-be-processed image, the first positioning window comprising the cap region; segmenting a first initial region from the first positioning window based on a first grayscale value range; and fitting a graphic region as a first feature region, based on a boundary of the first initial region; the feature analyzing module is configured to determine whether the package carton has a defect of cap lacking in a way below: extracting a first feature value of the first feature region; comparing the first feature value with a first preset value, and determining that the package carton has the defect of cap lacking if the first feature value is less than the first preset value.
[0007] For example, the graphic region is an elliptical region or a rounded region; and the first feature value is an area of the first feature region.
[0008] For example, the package carton further comprises a strip-shaped sealing ridge arranged on the slanted surface and a side surface intersecting with the slanted surface; a connection edge is provided at the intersection of the slanted surface and the side surface; an angle between the slanted surface and the side surface is not a right angle; and the detecting apparatus is configured to detect whether the package carton has a defect of wrinkle located between the connection edge and the cap region; the extracting module is configured to extract a feature region to be analyzed in a way below: providing a second positioning window on the to-be-processed image, the second positioning window being located on a side of the cap region that is away from the strip-shaped sealing ridge and comprising a region located between the cap region and the connection edge; and extracting a second feature region from the second positioning window; the feature analyzing module is configured to determine whether the package carton has a defect of wrinkle in a way below: extracting a second feature value of the second feature region; comparing the second feature value with a second preset value, and determining that the package carton has the defect of wrinkle, if the second feature value is greater than or equal to the second preset value; the second feature value being a size of the second feature region in a direction parallel to the side surface; or extracting the second feature value and a third feature value of the second feature region; comparing the second feature value with the second preset value and comparing the third feature value with a third preset value simultaneously, and determining that the package carton has the defect of wrinkle, if the second feature value is greater than or equal to the second preset value, and the third feature value is greater than or equal to the third preset value simultaneously; the third feature value being a size of the second feature region in a direction parallel to the connection edge; or extracting the second feature value and a fourth feature value of the second feature region; comparing the second feature value with the second preset value and comparing the fourth feature value with a fourth preset value simultaneously; and determining that the package carton has the defect of wrinkle, if the second feature value is greater than or equal to the second preset value, and the fourth feature value is greater than or equal to the fourth preset value simultaneously; the fourth feature value being an area of the second feature region; or extracting the second feature value, the third feature value, and the fourth feature value of the second feature region; comparing the second feature value with the second preset value, comparing the third feature value with the third preset value, and comparing the fourth feature value with the fourth preset value simultaneously; and determining that the package carton has the defect of wrinkle, if the second feature value is greater than or equal to the second preset value, the third feature value is greater than or equal to the third preset value, and the fourth feature value is greater than or equal to the fourth preset value simultaneously.
[0009] For example, the extracting a second feature region from the second positioning window comprises: segmenting a second initial region from the second positioning window based on a second grayscale value range; selecting a continuous region with a largest area from the second initial region; and segmenting the second feature region from the continuous region based on a third grayscale value range.
[0010] For example, when detecting whether the packaging carton has a defect of a cap lacking and whether the packaging carton has a defect of wrinkle between the connecting edge and the cap region, the to-be-processed image is a side view of the slanted surface.
[0011] For example, the package carton further comprises a strip-shaped sealing ridge arranged on the slanted surface and a side surface intersecting with the slanted surface; a connection edge is provided at an intersection of the slanted surface and the side surface; an angle between the slanted surface and the side surface is not a right angle; the image acquiring module comprises a first image acquiring apparatus; the first image acquiring apparatus comprises a first lens, the first lens faces towards the slanted surface and the side surface, and a central axis of the first lens is perpendicular to the side surface.
[0012] For example, the package carton further comprises a strip-shaped sealing ridge arranged on the slanted surface and a side surface intersecting with the slanted surface; a connection edge is provided at an intersection of the slanted surface and the side surface; an angle between the slanted surface and the side surface is not a right angle; and the connection edge and the strip-shaped sealing ridge are located on two opposite sides of the cap region; the detecting apparatus is configured to detect whether the package carton has a defect of inner layer material exposure located at the strip-shaped sealing ridge; the extracting module is configured to extract a feature region in a way below: providing a third positioning window on the to-be-processed image; the third positioning window being located on a side of the cap region that is provided with the strip-shaped sealing ridge and comprising the strip-shaped sealing ridge; and extracting a third feature region from the third positioning window; the feature analyzing module is configured to determine whether the package carton has a defect of inner layer material exposure in a way below: extracting a fifth feature value of the third feature region; comparing the fifth feature value with a fifth preset value, and determining that the package carton has the defect of inner layer material exposure, if the fifth feature value is greater than or equal to the fifth preset value, and a region, where the fifth feature value is greater than or equal to the fifth preset value, is continuous and greater than or equal to a sixth preset value in the direction parallel to the strip-shaped sealing ridge; the fifth feature value being a size of the third feature region in a direction perpendicular to the strip-shaped sealing ridge.
[0013] For example, the extracting a third feature region from the third positioning window comprises: segmenting a third initial region from the third positioning window based on a fourth grayscale value range; and selecting a continuous region with a largest area from the third initial region as the third feature region.
[0014] For example, the detecting apparatus is configured to detect whether the package carton has a defect of cap offset, such as cap position offset; the extracting module is configured to extract a feature region in a way below: providing a fourth positioning window on the to-be-processed image, the fourth positioning window comprising the cap region; defining a boundary of the cap region from the fourth positioning window; and fitting a rounded region as the fourth feature region based on the boundary of the cap region; the feature analyzing module is configured to determine whether the package carton has a defect of cap position offset in a way below: extracting the sixth feature value of the fourth feature region; comparing the sixth feature value with a seventh preset value, and determining that the package carton has the defect of cap position offset, if the sixth feature value is greater than or equal to the seventh preset value; the sixth feature value being a distance between a center of the fourth feature region and a center of the cap.
[0015] For example, when detecting whether the packaging carton has a defect of inner layer material exposure located at the strip-shaped sealing ridge and whether the packaging carton has a defect of cap position offset, the to-be-processed image is a front view of the slanted surface.
[0016] For example, the image acquiring module comprises a second image acquiring apparatus; the second image acquiring apparatus comprises a second lens, the second lens faces towards the slanted surface, and a central axis of the second lens is perpendicular to the slanted surface.
[0017] According to an embodiment of the present disclosure, it is provided a detecting method for detecting a defect of a package carton; the package carton having a slanted surface, and the slanted surface having a cap region for arranging a cap, wherein the detecting method comprises: acquiring a to-be-processed image of the slanted surface; providing a positioning window on the to-be-processed image, and extracting a feature region to be analyzed from the positioning window; and extracting a feature value of the feature region and comparing a feature value of the feature region with a preset value to determine whether the package carton has the defect.
[0018] For example, the detecting method comprises: detecting whether the package carton has a defect of cap lacking; the extracting a feature region to be analyzed comprises: providing a first positioning window on the to-be-processed image, the first positioning window comprising the cap region; segmenting a first initial region from the first positioning window based on a first grayscale value range; and fitting a graphic region as the first feature region, based on a boundary of the first initial region; the determining whether the package carton has the defect comprises: extracting a first feature value of the first feature region; comparing the first feature value with a first preset value, and determining that the package carton has the defect of cap lacking if the first feature value is less than the first preset value.
[0019] For example, the graphic region is an elliptical region or a rounded region; and the first feature value is an area of the first feature region.
[0020] For example, the package carton further comprises a strip-shaped sealing ridge arranged on the slanted surface and a side surface intersecting with the slanted surface; a connection edge is provided at the intersection of the slanted surface and the side surface; and an angle between the slanted surface and the side surface is not a right angle; the detecting method comprises: detecting whether the package carton has a defect of wrinkle located between the connection edge and the cap region; the extracting a feature region to be analyzed, comprises: providing a second positioning window on the to-be-processed image, the second positioning window being located on a side of the cap region that is away from the strip-shaped sealing ridge and comprising a region located between the cap region and the connection edge; and extracting a second feature region from the second positioning window; the determining whether the package carton has the defect comprises: extracting a second feature value of the second feature region; comparing the second feature value with a second preset value, and determining that the package carton has the defect of wrinkle, if the second feature value is greater than or equal to the second preset value; the second feature value being a size of the second feature region in a direction parallel to the side surface; or, extracting the second feature value and a third feature value of the second feature region; comparing the second feature value with the second preset value and comparing the third feature value with a third preset value simultaneously; and determining that the package carton has the defect of wrinkle, if the second feature value is greater than or equal to the second preset value, and the third feature value is greater than or equal to the third preset value simultaneously; the third feature value being a size of the second feature region in a direction parallel to the connection edge; or, extracting the second feature value and a fourth feature value of the second feature region; comparing the second feature value with the second preset value and comparing the fourth feature value with a fourth preset value simultaneously; and determining that the package carton has the defect of wrinkle, if the second feature value is greater than or equal to the second preset value, and the fourth feature value is greater than or equal to the fourth preset value simultaneously; the fourth feature value being an area of the second feature region; or, extracting the second feature value, the third feature value, and the fourth feature value of the second feature region; comparing the second feature value with the second preset value, comparing the third feature value with the third preset value, and comparing the fourth feature value with the fourth preset value simultaneously; and determining that the package carton has the defect of wrinkle, if the second feature value is greater than or equal to the second preset value, the third feature value is greater than or equal to the third preset value, and the fourth feature value is greater than or equal to the fourth preset value simultaneously.
[0021] For example, the extracting a second feature region from the second positioning window comprises: segmenting a second initial region from the second positioning window based on a second grayscale value range; selecting a continuous region with a largest area from the second initial region; and segmenting the second feature region from the continuous region based on a third grayscale value range.
[0022] For example, when detecting whether the packaging carton has a defect of a cap lacking and whether the packaging carton has a defect of wrinkle between the connecting edge and the cap region, the to-be-processed image is a side view of the slanted surface.
[0023] For example, the package carton further comprises a strip-shaped sealing ridge arranged on the slanted surface and a side surface intersecting with the slanted surface; a connection edge is provided at the intersection of the slanted surface and the side surface; an angle between the slanted surface and the side surface is not a right angle; and the connection edge and the strip-shaped sealing ridge are located on two opposite sides of the cap region; the image acquiring module comprises a first image acquiring apparatus; the first image acquiring apparatus comprises a first lens; the detecting method comprises: arranging the first lens to face towards the slanted surface and the side surface; and arranging a central axis of the first lens to be perpendicular to the side surface.
[0024] For example, the package carton further comprises a strip-shaped sealing ridge arranged on the slanted surface and a side surface intersecting with the slanted surface; a connection edge is provided at the intersection of the slanted surface and the side surface; and an angle between the slanted surface and the side surface is not a right angle; the detecting method comprises: detecting whether the package carton has a defect of inner layer material exposure located at the strip-shaped sealing ridge; the extracting a feature region to be analyzed comprises: providing a third positioning window on the to-be-processed image, the third positioning window being located on a side of the cap region that is provided with the strip-shaped sealing ridge and comprising the strip-shaped sealing ridge; and extracting a third feature region from the third positioning window; the determining whether the package carton has the defect comprises: extracting a fifth feature value of the third feature region; comparing the fifth feature value with a fifth preset value; and determining that the package carton has the defect of inner layer material exposure, if the fifth feature value is greater than or equal to the fifth preset value and a region, where the fifth feature value is greater than or equal to the fifth preset value, is continuous and greater than or equal to a sixth preset value in the direction parallel to the strip-shaped sealing ridge; the fifth feature value being a size of the third feature region in the direction perpendicular to the strip-shaped sealing ridge.
[0025] For example, the extracting a third feature region from the third positioning window comprises: segmenting a third initial region from the third positioning window based on a fourth grayscale value range; and selecting a continuous region with a largest area from the third initial region as the third feature region.
[0026] For example, the detecting method comprises: detecting whether the package carton has a defect of cap position offset; the extracting a feature region to be analyzed comprises: providing a fourth positioning window on the to-be-processed image, the fourth positioning window comprising the cap region; defining a boundary of the cap region from the fourth positioning window; and fitting a rounded region as the fourth feature region based on the boundary of the cap region; the determining whether the package carton has the defect comprises: extracting a sixth feature value of the fourth feature region; comparing the sixth feature value with a seventh preset value, and determining that the package carton has the defect of cap position offset, if the sixth feature value is greater than or equal to the seventh preset value; the sixth feature value being a distance between a center of the fourth feature region and a center of the cap.
[0027] For example, when detecting whether the packaging carton has a defect of inner layer material exposure located at the strip-shaped sealing ridge and whether the packaging carton has a defect of cap position offset, the to-be-processed image is a front view of the slanted surface.
[0028] For example, the image acquiring module comprises a second image acquiring apparatus, and the second image acquiring apparatus comprises a second lens; the detecting method comprises: arranging the second lens to face towards the slanted surface, and arranging a central axis of the second lens to be perpendicular to the slanted surface.
[0029] According to an embodiment of the present disclosure, it is provided a detecting apparatus, comprising: a processor; and a memory, comprising one or more computer program modules; wherein, the one or more computer program modules are stored on the memory and are configured to be executed by the processor, and the one or more computer program modules comprise instructions for implementing the above-mentioned detecting method.
[0030] According to an embodiment of the present disclosure, it is provided a computer readable storage medium, configured to store non-transitory computer readable instructions; wherein, the non-transitory computer readable instructions, when executed by a computer, implements the above-mentioned detecting method.BRIEF DESCRIPTION OF DRAWINGS
[0031] In order to clearly illustrate technical solutions of the embodiments of the present disclosure, the drawings of the embodiments will be briefly described in the following; it is obvious that the described drawings are only related to some embodiments of the present disclosure, rather than limiting the present disclosure.
[0032] FIG. 1 is a schematic diagram of a sealed package carton;
[0033] FIG. 2 is a schematic diagram I of a detecting apparatus according to an embodiment of the present disclosure;
[0034] FIG. 3A to FIG. 3C are schematic diagrams of the detecting apparatus according to the embodiment of the present disclosure processing a to-be-processed image, to detect whether the package carton has a defect of cap lacking;
[0035] FIG. 4A to FIG. 4C are schematic diagrams of a procedure of the detecting apparatus according to the embodiment of the present disclosure detecting whether the package carton has a defect of cap lacking;
[0036] FIG. 5A to FIG. 5D are schematic diagrams of the detecting apparatus according to the embodiment of the present disclosure processing a to-be-processed image, to detect whether the package carton has a defect of wrinkle;
[0037] FIG. 6A to FIG. 6D are schematic diagrams of a procedure of the detecting apparatus according to the embodiment of the present disclosure detecting whether the package carton has a defect of wrinkle;
[0038] FIG. 6E is a schematic diagram of a defect of wrinkle;
[0039] FIG. 7A to FIG. 7C are schematic diagrams of the detecting apparatus according to the embodiment of the present disclosure processing a to-be-processed image, to detect whether the package carton has a defect of inner layer material exposure;
[0040] FIG. 8A to FIG. 8C are schematic diagrams of a procedure of the detecting apparatus according to the embodiment of the present disclosure detecting whether the package carton has a defect of inner layer material exposure;
[0041] FIG. 9A to FIG. 9C are schematic diagrams of the detecting apparatus according to the embodiment of the present disclosure processing a to-be-processed image, to detect whether the package carton has a defect of cap position offset;
[0042] FIG. 10A to FIG. 10C are schematic diagrams of a procedure of the detecting apparatus according to the embodiment of the present disclosure detecting whether the package carton has a defect of cap position offset;
[0043] FIG. 11A is a schematic diagram of a first image acquiring apparatus according to the embodiment of the present disclosure;
[0044] FIG. 11B is a schematic diagram of a second image acquiring apparatus according to the embodiment of the present disclosure;
[0045] FIG. 12 is a schematic flow chart of a detecting method according to an embodiment of the present disclosure;
[0046] FIG. 13 is another schematic diagram of a framework of the detecting apparatus according to the embodiment of the present disclosure;
[0047] FIG. 14 is a yet another schematic diagram of a framework of the detecting apparatus according to the embodiment of the present disclosure;
[0048] FIG. 15 is a schematic diagram of a computer readable storage medium according to an embodiment of the present disclosure; and
[0049] FIG. 16 is a detection result table according to the embodiment of the present disclosure.DETAILED DESCRIPTION
[0050] In order to make objects, technical details and advantages of the embodiments of the present disclosure apparent, the technical solutions of the embodiments of the present disclosure will be described in a clear and fully understandable way in connection with the accompanying drawings of the embodiments of the present disclosure. It is obvious that the described embodiments are just a part but not all of the embodiments of the present disclosure. Based on the embodiments described herein, those ordinarily skilled in the art may obtain other embodiment (s) , without any inventive work, which should be within the scope of the present disclosure.
[0051] Unless otherwise specified, the technical terms or scientific terms here should be of general meaning as understood by those ordinarily skilled in the art. In the specification and the claims of the present disclosure of patent application, words such as “first” , “second” and the like do not denote any order, quantity, or importance, but rather are used for distinguishing different components. Words such as “include” or “comprise” and the like denote that elements or objects appearing before the words of “include” or “comprise” cover the elements or the objects enumerated after the words of “include” or “comprise” or equivalents thereof, not exclusive of other elements or objects. Words such as “inner” , “outer” , “upper” , “lower” and the like are only used for expressing relative positional relationship, when the absolute position of the described object is changed, the relative positional relationship may also be correspondingly changed.
[0052] The drawings in the present disclosure are not strictly drawn to actual proportions, and specific sizes and quantities of respective structures may be determined according to actual needs. The drawings described in the present disclosure are only schematic structural diagrams.
[0053] After sealing a product into a container, it is necessary to detect the container containing the product. If the container has defects, a series of problems may be caused, for example, quality deterioration of the product contained in the container, inability of a user to use normally, poor appearance of the container affecting sales, and so on. There is an urgent requirement of a solution that may efficiently and accurately detect whether a sealed container has a defect and detect a variety of defects.
[0054] FIG. 1 is a schematic diagram of a sealed package carton. For example, after products such as milk, beverages, vegetable puree, etc. are filled into a package carton through a filling port, the filling port of the package carton is sealed so as to obtain a sealed package carton 1 as shown in FIG. 1. For example, referring to FIG. 1, the package carton 1 has a slanted surface 11; the slanted surface 11 has a cap region 12 for arranging a cap. For example, the surface 11 being slanted refers to: an angle between the surface 11 and at least one of surfaces intersecting therewith being not a right angle. For example, the cap region 12 is used for arranging a cap; the cap region 12 includes an opening 13; the opening 13 is selectively covered by an aluminum foil; the cap is adhered to the cap region 12 and completely covers the opening 13; a user may unscrew the cap to acquire a product contained in package carton 1, for example, milk, a beverage, vegetable puree, etc., through the opening 13. For example, the cap 13 is provided with a protruding spine; in a case where the opening 13 is covered by the aluminum foil, while the user unscrews the cap, the protruding spine punctures the aluminum foil, allowing the user to acquire the product contained in package carton 1 through the opening 13. For example, the cap region 12 is concentric and conformal to the opening 13, and the cap region 12 has an area larger than an area of the opening 13 but less than or equal to twice the area of the opening 13; further, for example, the area of the cap region 12 is larger than the area of the opening 13 and less than or equal to 1.5 times the area of the opening 13. For example, the cap region 12 is a blank region including the opening 13 and no pattern is printed thereon. In FIG. 1, in order to show the opening 13, the cap is not shown; a cap 18 shown in FIG. 4A, FIG. 6A, FIG. 8A, FIG. 10A, as well as FIG. 11A and FIG. 11B may be referred to for the cap, which is arranged in the cap region 12.
[0055] For example, referring to FIG. 1, the package carton 1 further includes a strip-shaped sealing ridge 14 arranged on the slanted surface 11. After the product is filled into the package carton 1 through the filling port and the filling port is sealed, the strip-shaped sealing ridge 14 is formed. For example, the strip-shaped sealing ridge 14 is bent to adhere to the slanted surface 11. For example, the strip-shaped sealing ridge 14 is not bent and stands upright on the slanted surface 11. For example, referring to FIG. 1, the package carton 1 further includes earing 17 connected with the slanted surface 11; the strip-shaped sealing ridge 14 extends from one earing 17 across the slanted surface 11 to the other earing 17;and the above-described two earings 17 are arranged opposite to each other across the slanted surface 11.
[0056] For example, referring to FIG. 1, the package carton 1 further includes a side surface 15 intersecting with the slanted surface 11; a connection edge 16 is provided at the intersection of the slanted surface 11 and the side surface 15; and an angle between the slanted surface 11 and the side surface 15 is not a right angle. It should be noted that the package carton 1 in FIG. 1 has four side surfaces 15; however, the embodiment of the present disclosure is not limited thereto; and the package carton 1 may include other quantities of surfaces 15 as needed which is different from four. It should be noted that with respect to the package carton 1 in FIG. 1, corners each have a vertex; however, the embodiment of the present disclosure is not limited thereto; and a corner of the package carton 1 may appear in a chamfered form without the vertex, referring to FIG. 4A, FIG. 6A, FIG. 8A and FIG. 10A below.
[0057] The package carton 1 shown in FIG. 1 may be prone to have defects below. (1) A defect of cap lacking: if the cap region that should have been arranged with a cap is not arranged with a cap, various problems will be caused, for example, inability to sell, product leakage inside the package carton, etc. (2) A defect of wrinkle: during the process of adhering the cap to the cap region, an external force is inevitably applied to press the cap towards the package carton; and due to lack of support inside the package carton, the operation of applying the external force to press may cause wrinkle in a region located in the vicinity of the cap on the slanted surface 11, especially between the connection edge 16 and the cap region 12; the wrinkle may cause failure of the cap to fit tightly with the slanted surface 11, resulting in a gap, which increases a risk of product leakage, and even directly causes product leakage. (3) A defect of exposing inner layer material: the package carton is formed by folding and sealing sheet-like materials; the sheet-like materials usually includes an inner layer and an outer layer; the inner layer is in direct contact with the product, and the outer layer corresponds to an appearance layer of the package carton; when sealing the filling port of the package carton, sheet-like materials on both sides of the filling port are aligned and bonded together to form a strip-shaped sealing ridge 14 (i.e., the strip-shaped sealing ridge 14 includes two layers of sheet-like materials bonded together) ; if the sheet-like materials located on both sides of the filling port fail to be aligned well, an inner layer of a sheet will be exposed, causing the user to clearly see the inner layer material of the package carton at the strip-shaped sealing ridge 14, which results in poor appearance and even seriously reduces purchase intention of a user. (4) A defect of cap position offset: it is usually hoped that the cap is arranged concentrically in the cap region 12, which is both aesthetically pleasing and may effectively protect the opening 13 or cover aluminum foil of the opening 13; if the cap has position offset and cannot be arranged concentrically in the cap region 12, it will affect aesthetics and reduce willingness of the user to purchase, and in serious cases, it may even expose the opening 13 or the aluminum foil, thereby increasing the risk of product leakage.
[0058] According to the embodiments of the present disclosure, there are provided a detecting apparatus, a detecting method and a computer readable storage medium that efficiently and accurately detect each of the above-described various defects. According to the embodiments of the present disclosure, if no defects are found in the package carton, the package carton will pass the detection and be transported and sold on the market; if any defect is found in the package carton during detection, the package carton will be removed and destroyed.
[0059] It should be noted that the package carton in FIG. 1 is only exemplary and should not be viewed as a limitation on the embodiments of the present disclosure; and the detecting apparatus, the detecting method and the computer readable storage medium according to the embodiments of the present disclosure may be applied to package cartons different from that in FIG. 1 as needed.
[0060] FIG. 2 is a schematic diagram of a detecting apparatus according to an embodiment of the present disclosure. Referring to FIG. 2, the detecting apparatus according to the embodiment of the present disclosure is used for detecting defects in a package carton 1; the package carton 1 has a slanted surface 11; the slanted surface 1 has a cap region 12 for arranging a cap; the detecting apparatus includes: an image acquiring module, configured to acquire a to-be-processed image of the slanted surface 11; an extracting module, configured to provide a positioning window on the to-be-processed image and extract a feature region to be analyzed from the positioning window; and a feature analyzing module, configured to extract a feature value of the feature region and compare the feature value of the feature region with a preset value to determine whether the package carton 1 has a defect. The detecting apparatus according to the embodiment of the present disclosure can efficiently and accurately detect each type of a variety of defects. The detecting apparatus according to the embodiment of the present disclosure adopts an integrated design, which has a variety of functional modules integrated into one, so that the apparatus occupies less space and can be applied to and installed on any operation site. According to the embodiment of the present disclosure, the image acquiring module, the extracting module, and the feature analyzing module are designed in a modular manner, making maintenance and repair very convenient. The detecting apparatus according to the embodiment of the present disclosure has high detection accuracy, which may be up to 1 mm.
[0061] For example, according to the embodiment of the present disclosure, the image acquiring module may be an imaging apparatus such as a still camera, a video camera, etc.; the extracting module may be an extracting circuit; and the feature analyzing module may be a feature analyzing circuit.
[0062] FIG. 3A to FIG. 3C are schematic diagrams of processing a to-be-processed image by using a detecting apparatus according to an embodiment of the present disclosure for detecting whether the package carton has a defect of cap lacking; and FIG. 4A to FIG. 4C are procedure schematic diagrams of detecting whether the package carton has a defect of cap lacking by using a detecting apparatus according to an embodiment of the present disclosure. It should be noted that FIG. 3A to FIG. 3C are real images acquired by the image acquiring module, which only have necessary reference signs marked thereon; in order to help understanding, the lines drawn in FIG. 4A to FIG. 4C are in correspondence with those shown in FIG. 3A to FIG. 3C.
[0063] For example, according to the embodiment of the present disclosure, the detecting apparatus is configured to detect whether the package carton 1 has a defect of cap lacking. In this case, the extracting module is configured to extract a feature region to be analyzed in a way below: providing a first positioning window 101 on the to-be-processed image, the first positioning window 101 including the cap region 12, referring to FIG. 3A and FIG. 4A; segmenting a first initial region 100I from the first positioning window 101 based on a first grayscale value range, referring to FIG. 3B and FIG. 4B; and fitting a graphic region as a first feature region 102, based on a boundary of the first initial region 100I, referring to FIG. 3C and FIG. 4C. For example, the first grayscale value range is from 50 to 75. Further, the feature analyzing module is configured to determine whether the package carton 1 has a defect of cap lacking in a way below: extracting a first feature value of the first feature region 102; comparing the first feature value with a first preset value; and determining that the package carton 1 has a defect of cap lacking if the first feature value is less than the first preset value. For example, the graphic region is an elliptical region or a rounded region; and the first feature value is an area of the first feature region 102. For example, the first preset value is 20, 000pixel points. For example, according to the embodiment of the present disclosure, the image acquiring apparatus has 1.3 million pixels. It should be noted that, the first feature value is not limited to the area of the first feature region 102, and may also be a maximum size of the first feature region, and so on.
[0064] FIG. 5A to FIG. 5D are schematic diagrams of processing a to-be-processed image by using a detecting apparatus according to an embodiment of the present disclosure for detecting whether the package carton has a defect of wrinkle; FIG. 6A to FIG. 6D are procedure schematic diagrams of detecting whether the package carton has a defect of wrinkle by using a detecting apparatus according to an embodiment of the present disclosure; and FIG. 6E is a schematic diagram of a defect of wrinkle. It should be noted that FIG. 5A to FIG. 5D are real images acquired by the image acquiring module, which only have necessary reference signs marked thereon; in order to help understanding, the lines drawn in FIG. 6A to FIG. 6D are in correspondence with those shown in FIG. 5A to FIG. 5D.
[0065] For example, according to the embodiment of the present disclosure, the package carton 1 further includes a strip-shaped sealing ridge 14 arranged on the slanted surface 11 and a side surface 15 intersecting with the slanted surface 11; a connection edge 16 is provided at the intersection of the slanted surface 11 and the side surface 15; an angle between the slanted surface 11 and the side surface 15 is not a right angle; and the detecting apparatus is configured to detect whether the package carton 1 has a defect of wrinkle located between the connection edge 16 and the cap region 12. In this case, the extracting module is configured to extract a feature region to be analyzed in a way below: providing a second positioning window 201 on the to-be-processed image, the second positioning window 201 being located on a side of the cap region 12 that is away from the strip-shaped sealing ridge 14 and including a region between the cap region 12 and the connection edge 16, referring to FIG. 5A and FIG. 6A; and extracting a second feature region 202 from the second positioning window 201, referring to FIG. 5D and FIG. 6D. Further, the feature analyzing module is configured to determine whether the package carton 1 has a defect of wrinkle in a way below: extracting a second feature value of the second feature region 202; comparing the second feature value with a second preset value; and determining that the package carton 1 has a defect of wrinkle, if the second feature value is greater than or equal to the second preset value, herein, the second feature value is a size of the second feature region 202 in a direction D1 parallel to the side surface 15, referring to FIG. 6A and FIG. 6E. Alternatively, the feature analyzing module is configured to determine whether the package carton 1 has a defect of wrinkle in a way below: extracting the second feature value and a third feature value of the second feature region 202; comparing the second feature value with the second preset value and comparing the third feature value with a third preset value simultaneously; and determining that the package carton 1 has a defect of wrinkle, if the second feature value is greater than or equal to the second preset value, and simultaneously, the third feature value being greater than or equal to the third preset value, herein, the third feature value is a size of the second feature region 202 in a direction D2 parallel to the connection edge 16, referring to FIG. 6A and FIG. 6E. Alternatively, the feature analyzing module is configured to determine whether the package carton 1 has a defect of wrinkle in a way below: extracting the second feature value and a fourth feature value of the second feature region 202; comparing the second feature value with the second preset value and comparing the fourth feature value with a fourth preset value simultaneously; and determining that the package carton 1 has a defect of wrinkle, if the second feature value is greater than or equal to the second preset value, and the fourth feature value is greater than or equal to the fourth preset value simultaneously, herein, the fourth feature value is an area of the second feature region 202, referring to FIG. 6E. Alternatively, the feature analyzing module is configured to determine whether the package carton 1 has a defect of wrinkle in a way below: extracting the second feature value, the third feature value, and the fourth feature value of the second feature region 202; comparing the second feature value with the second preset value, comparing the third feature value with the third preset value, and comparing the fourth feature value with the fourth preset value, simultaneously; and determining that the package carton 1 has a defect of wrinkle, if the second feature value is greater than or equal to the second preset value, the third feature value being greater than or equal to the third preset value, and the fourth feature value being greater than or equal to the fourth preset value simultaneously. For example, the second preset value is 50pixel points. For example, the third preset value is 200pixel points. For example, the fourth preset value is 20, 000pixel points. Among the second feature value, the third feature value, and the fourth feature value as described above, the second feature value is the most critical, which directly affects tightness of the adherence between the cap 18 and the slanted surface 11, as well as a risk of product leakage. Therefore, it is a fast and efficient way to determine whether there is a defect of wrinkle by determining only the relationship between the second feature value and the second preset value. By combining the relationship between the second feature value and the second preset value, as well as the relationship between the third feature value and the third preset value, the accuracy of determining the defect of wrinkle can be improved. By combining the relationship between the second feature value and the second preset value, as well as the relationship between the fourth feature value and the fourth preset value, the accuracy of determining the defect of wrinkle can be improved. Comparatively speaking, the accuracy of determining while combining the relationship between the second feature value and the second preset value, as well as the relationship between the third feature value and the third preset value, is higher than the accuracy of determining while combining the relationship between the second feature value and the second preset value, as well as the relationship between the fourth feature value and the fourth preset value. By combining the relationship between the second feature value and the second preset value, the relationship between the third feature value and the third preset value, and the relationship between the fourth feature value and the fourth preset value, the accuracy of determining the defect of wrinkle can be further improved. For example, according to the embodiment of the present disclosure, the extracting the second feature region 202 from the second positioning window 201 includes: segmenting a second initial region 200I from the second positioning window 201 based on a second grayscale value range, referring to FIG. 5B and FIG. 6B; selecting a continuous region 200C with the largest area from the second initial region 200I, referring to FIG. 5C and FIG. 6C; and segmenting the second feature region 202 from the continuous region 200C based on a third grayscale value range, referring to FIG. 5D and FIG. 6D. For example, the second grayscale value range is from 60 to 70. For example, the third grayscale value range is from 70 to 255.
[0066] For example, according to the embodiment of the present disclosure, in FIG. 3A to FIG. 3C and FIG. 5A to FIG. 5D, the to-be-processed image is a side view of the slanted surface 11. By processing and analyzing the side view of the slanted surface 11, the fact that whether the package carton 1 has a defect of cap lacking or whether the package carton 1 has a defect of wrinkle can be efficiently and accurately determined. That is, by using an image at an appropriate angle, for example, a side view of the slanted surface 11, presence or absence of the two types of defects can be determined, which greatly simplifies the defect detection process.
[0067] FIG. 11A is a schematic diagram of a first image acquiring apparatus according to an embodiment of the present disclosure. For example, the package carton 1 includes a strip-shaped sealing ridge 14 arranged on the slanted surface 11 and a side surface 15 intersecting with the slanted surface 11; a connection edge 16 is provided at the intersection of the slanted surface 11 and the side surface 15; an angle between the slanted surface 11 and the side surface 15 is not a right angle; and the connection edge 16 and the strip-shaped sealing ridge 14 are located on two opposite sides of the cap region 12. Referring to FIG. 11A, the image acquiring module includes a first image acquiring apparatus 20; the first image acquiring apparatus 20 includes a first lens 21; the first lens 21 faces towards the slanted surface 11 and the side surface 15; and a central axis 21X of the first lens 21 is perpendicular to the side surface 15. By arranging the first image acquiring apparatus 20 in the above-described manner, the above-described desired side view of the slanted surface 11 can be acquired. For example, according to the embodiment of the present disclosure, the first image acquiring apparatus 20 has 1.3 million pixels.
[0068] FIG. 7A to FIG. 7C are procedure schematic diagrams of processing a to-be-processed image by using a detecting apparatus according to an embodiment of the present disclosure for detecting whether the package carton has a defect of inner layer material exposure; and FIG. 8A to FIG. 8C are schematic diagrams of detecting whether the package carton has a defect of inner layer material exposure by using the detecting apparatus according to the embodiment of the present disclosure. It should be noted that FIG. 7A to FIG. 7C are real images acquired by the image acquiring module, which only have necessary reference signs marked thereon; in order to help understanding, lines drawn in FIG. 8A to FIG. 8C are in correspondence with those shown in FIG. 7A to FIG. 7C.
[0069] For example, according to the embodiment of the present disclosure, the package carton 1 includes a strip-shaped sealing ridge 14 arranged on a slanted surface 11 and a side surface 15 intersecting with the slanted surface 11; a connection edge 16 is provided at the intersection of the slanted surface 11 and the side surface 15; an angle between the slanted surface 11 and the side surface 15 is not a right angle; and the detecting apparatus is configured to detect whether the package carton 1 has a defect of inner layer material exposure located at the strip-shaped sealing ridge 14. In this case, the extracting module is configured to extract a feature region in a way below: providing a third positioning window 301 on the to-be-processed image, the third positioning window 301 being located on a side of the cap region 12 that is provided with a strip-shaped sealing ridge 14 and including the strip-shaped sealing ridge 14, referring to FIG. 7A and FIG. 8A; and extracting a third feature region 302 from the third positioning window 301, referring to FIG. 7C and FIG. 8C. Further, the feature analyzing module is configured to determine whether the package carton 1 has a defect of inner layer material exposure in a way below: extracting a fifth feature value of the third feature region 302; comparing the fifth feature value with a fifth preset value; and determining that the package carton 1 has a defect of inner layer material exposure, if the fifth feature value is greater than or equal to the fifth preset value and a region, where the fifth feature value is greater than or equal to the fifth preset value, is continuous and greater than or equal to a sixth preset value in the direction D2 parallel to the strip-shaped sealing ridge 14, herein, the fifth feature value is a size of the third feature region 302 in a direction D3 perpendicular to the strip-shaped sealing ridge 14, referring to FIG. 8A. For example, the directions D1, D2 and D3 are perpendicular to each other. For example, the fifth preset value is 65pixel points. For example, the sixth preset value is 20pixel points. For example, the strip-shaped sealing ridge 14 includes two layers of sheet-like materials bonded together; and the third feature region 302 is an inner layer of one layer of sheet-like materials and exposed by the other layer of sheet. For example, referring to FIG. 8A to FIG. 8C, the strip-shaped sealing ridge 14 includes two layers of sheet-like materials bonded together, and the strip-shaped sealing ridge 14 is bent to adhere to the slanted surface 11; and the third feature region 302 belongs to the inner layer of the lower sheet-like material and is exposed by the upper sheet-like material. For example, according to the embodiment of the present disclosure, the extracting the third feature region 302 from the third positioning window 301 includes: segmenting a third initial region 300I from the third positioning window 301 based on a fourth grayscale value range, referring to FIG. 7B and FIG. 8B; and selecting a continuous region with the largest area from the third initial region 300I as the third feature region 302, referring to FIG. 7C and FIG. 8C. For example, the fourth grayscale value range is 165 to 255.
[0070] FIG. 9A to FIG. 9C are schematic diagrams of processing a to-be-processed image by using a detecting apparatus according to an embodiment of the present disclosure for detecting whether the package carton has a defect of cap position offset; and FIG. 10A to FIG. 10C are schematic diagrams of a procedure of detecting whether the package carton has a defect of cap position offset by using the detecting apparatus according to an embodiment of the present disclosure. It should be noted that FIG. 9A to FIG. 9C are real images acquired by the image acquiring module, which only have necessary reference signs marked thereon; in order to help understanding, lines drawn in FIG. 10A to FIG. 10C are in correspondence with those shown in FIG. 9A to FIG. 9C.
[0071] For example, according to the embodiment of the present disclosure, the detecting apparatus is configured to detect whether the package carton 1 has a defect of cap position offset. In this case, the extracting module is configured to extract a feature region in a way below: providing a fourth positioning window 401 on the to-be-processed image, the fourth positioning window 401 including a cap region 12, referring to FIG. 9A and FIG. 10A; defining a boundary 400B of the cap region 12 from the fourth positioning window 401, referring to FIG. 9B and FIG. 10B; and fitting a rounded region as the fourth feature region 402 based on the boundary of the cap region 12, referring to FIG. 9C and FIG. 10C. Further, the feature analyzing module is configured to determine whether the package carton 1 has a defect of cap position offset in a way below: extracting a sixth feature value of the fourth feature region 402 and comparing the sixth feature value with a seventh preset value; and determining that the package carton 1 has a defect of cap position offset, if the sixth feature value is greater than or equal to the seventh preset value, herein, the sixth feature value is a distance between a center O’ of the fourth feature region 402 and a center O of the cap 18, referring to FIG. 9C and FIG. 10C. For example, the seventh preset value is 700pixel points. For example, the detecting apparatus detects whether the package carton 1 has a defect of cap position offset after detecting whether the package carton 1 has a defect of cap lacking. For example, a boundary of a white region surrounding the cap 18 is taken as the boundary 400B of the cap region 12.
[0072] For example, according to the embodiment of the present disclosure, in FIG. 7A to FIG. 7C and FIG. 9A to FIG. 9C, the to-be-processed image is a front view of the slanted surface 11. By processing and analyzing the front view of the slanted surface 11, the fact that whether the package carton 1 has a defect of inner layer material exposure or whether the package carton 1 has a defect of cap position offset can be efficiently and accurately determined. That is, by using an image at an appropriate angle, for example, a front view of the slanted surface 11, presence or absence of the two types of defects can be determined, which greatly simplifies the defect detection process.
[0073] FIG. 11B is a schematic diagram of a second image acquiring apparatus according to an embodiment of the present disclosure. Referring to FIG. 11B, the image acquiring module includes a second image acquiring apparatus 30; the second image acquiring apparatus 30 includes a second lens 31; the second lens 31 faces towards the slanted surface 11; and a central axis 31X of the second lens is perpendicular to the slanted surface 11. By arranging the second image acquiring apparatus 30 in the above-described manner, the desired front view of the slanted surface 11 can be acquired. For example, according to the embodiment of the present disclosure, the second image acquiring apparatus 30 has 1.3 million pixels.
[0074] According to the embodiment of the present disclosure, there is further provided a detecting method for detecting defects in a package carton 1; the package carton 1 has a slanted surface 11; and the slanted surface 1 has a cap region 12 for arranging a cap. FIG. 12 is a schematic flow chart of a detecting method according to an embodiment of the present disclosure. Referring to FIG. 12, the detecting method according to the embodiment of the present disclosure includes: acquiring a to-be-processed image of the slanted surface 11; providing a positioning window on the to-be-processed image, and extracting a feature region to be analyzed from the positioning window; and extracting a feature value of the feature region and comparing the feature value of the feature region with a preset value to determine whether the package carton 1 has a defect. The procedures and effects of the detecting method according to the embodiment of the present disclosure can refer to those described in the detecting apparatus according to the embodiment of the present disclosure as described above, and no details will be repeated here.
[0075] For example, according to the embodiment of the present disclosure, the detecting method includes: detecting whether the package carton 1 has a defect of cap lacking. In this case, the extracting a feature region to be analyzed includes: providing a first positioning window 101 on the to-be-processed image, the first positioning window 101 including a cap region 12; segmenting a first initial region 100I from the first positioning window 101 based on a first grayscale value range; and fitting a graphic region as the first feature region 102, based on a boundary of the first initial region 100I. For example, the first grayscale value range is from 50 to 75. Further, the determine whether the package carton 1 has a defect includes: extracting a first feature value of the first feature region 102; comparing the first feature value with a first preset value; and determining that the package carton 1 has a defect of cap lacking if the first feature value is less than the first preset value. For example, the graphic region is an elliptical region or a rounded region; the first feature value is an area of the first feature region 102. For example, the first preset value is 20,000pixel points. For example, according to the embodiment of the present disclosure, the image acquiring apparatus has 1.3 million pixels. For example, FIG. 3A to FIG. 3C, FIG. 4A to FIG. 4C as well as the corresponding description above may be referred to for the detecting whether the package carton 1 has a defect of cap lacking, and no details will be repeated here.
[0076] For example, according to the embodiment of the present disclosure, the package carton 1 includes a strip-shaped sealing ridge 14 arranged on a slanted surface 11 and a side surface 15 intersecting with the slanted surface 11; a connection edge 16 is provided at the intersection of the slanted surface 11 and the side surface 15; and an angle between the slanted surface 11 and the side surface 15 is not a right angle. For example, according to the embodiment of the present disclosure, the detecting method includes: detecting whether the package carton 1 has a defect of wrinkle located between the connection edge 16 and the cap region 12. In this case, the extracting a feature region to be analyzed, includes: providing a second positioning window 201 on the to-be-processed image, the second positioning window 201 being located on a side of the cap region 12 that is away from the strip-shaped sealing ridge 14 and including a region located between the cap region 12 and the connection edge 16; and extracting a second feature region 202 from the second positioning window 201. Further, the determining whether the package carton 1 has a defect includes: extracting a second feature value of the second feature region 202; comparing the second feature value with a second preset value; and determining that the package carton 1 has a defect of wrinkle, if the second feature value is greater than or equal to the second preset value, herein, the second feature value is a size of the second feature region 202 in a direction D1 parallel to the side surface 15. Alternatively, the determining whether the package carton 1 has a defect includes: extracting the second feature value and a third feature value of the second feature region 202; comparing the second feature value with the second preset value and comparing the third feature value with a third preset value simultaneously; and determining that the package carton 1 has a defect of wrinkle, if the second feature value is greater than or equal to the second preset value and the third feature value is greater than or equal to the third preset value simultaneously, herein, the third feature value is a size of the second feature region 202 in a direction D2 parallel to the connection edge 16. Alternatively, the determining whether the package carton 1 has a defect includes: extracting the second feature value and a fourth feature value of the second feature region 202; comparing the second feature value with the second preset value and comparing the fourth feature value with a fourth preset value simultaneously; and determining that the package carton 1 has a defect of wrinkle, if the second feature value is greater than or equal to the second preset value and the fourth feature value is greater than or equal to the fourth preset value simultaneously, herein, the fourth feature value is an area of the second feature region 202. Alternatively, the determining whether the package carton 1 has a defect includes: extracting the second feature value, the third feature value, and the fourth feature value of the second feature region 202; comparing the second feature value with the second preset value, comparing the third feature value with the third preset value, and comparing the fourth feature value with the fourth preset value simultaneously; and determining that the package carton 1 has a defect of wrinkle, if the second feature value is greater than or equal to the second preset value, and the third feature value is greater than or equal to the third preset value, as well as the fourth feature value is greater than or equal to the fourth preset value simultaneously. For example, the second preset value is 50pixel points. For example, the third preset value is 200pixel points. For example, the fourth preset value is 20, 000pixel points. Among the second feature value, the third feature value, and the fourth feature value as described above, the second feature value is the most critical, which directly affects tightness of the adherence between the cap 18 and the slanted surface 11, as well as the risk of product leakage. Therefore, it is fast and efficient to determine whether there is a defect of wrinkle by determining only a relationship between the second feature value and the second preset value. By combining the relationship between the second feature value and the second preset value, as well as the relationship between the third feature value and the third preset value, the accuracy of determining the defect of wrinkle can be improved. By combining the relationship between the second feature value and the second preset value, as well as the relationship between the fourth feature value and the fourth preset value, the accuracy of determining the defect of wrinkle can be improved. Comparatively speaking, the accuracy of determining while combining the relationship between the second feature value and the second preset value, as well as the relationship between the third feature value and the third preset value, is higher than the accuracy of determining while combining the relationship between the second feature value and the second preset value, as well as the relationship between the fourth feature value and the fourth preset value. By combining the relationship between the second feature value and the second preset value, the relationship between the third feature value and the third preset value, and the relationship between the fourth feature value and the fourth preset value, the accuracy of determining the defect of wrinkle can be further improved. For example, the extracting a second feature region 202 from the second positioning window 201 includes: segmenting a second initial region 200I from the second positioning window 201 based on a second grayscale value range; selecting a continuous region 200C with the largest area from the second initial region 200I; and segmenting the second feature region 202 from the continuous region 200C based on a third grayscale value range. For example, the second grayscale value range is from 60 to 70. For example, the third grayscale value range is from 70 to 255. For example, for the detecting whether the package carton 1 has a defect of wrinkle, please refer to FIG. 5A to FIG. 5D, FIG. 6A to FIG. 6D, FIG. 6E as well as the corresponding description above, and no details will be repeated here.
[0077] For example, a side view of the slanted surface 11 may be used as the to-be-processed image for detecting whether the package carton 1 has a defect of cap lacking or detecting whether the package carton 1 has a defect of wrinkle. By processing and analyzing the side view of the slanted surface 11, the fact that whether the package carton 1 has a defect of cap lacking or whether the package carton 1 has a defect of wrinkle can be efficiently and accurately determined. That is, by using an image at an appropriate angle, for example, a side view of the slanted surface 11, presence or absence of the two types of defects can be determined, which greatly simplifies the defect detection process.
[0078] For example, the package carton 1 further includes a strip-shaped sealing ridge 14 arranged on the slanted surface 11 and a side surface 15 intersecting with the slanted surface 11; a connection edge 16 is provided at the intersection of the slanted surface 11 and the side surface 15; an angle between the slanted surface 11 and the side surface 15 is not a right angle; and the connection edge 16 and the strip-shaped sealing ridge 14 are located on two opposite sides of the cap region 12. Referring to FIG. 11A, the image acquiring module includes a first image acquiring apparatus 20; the first image acquiring apparatus 20 includes a first lens 21; and the detecting method according to the embodiment of the present disclosure includes: arranging the first lens to face towards the slanted surface 11 and the side surface 15; and arranging a central axis 21X of the first lens 21 to be perpendicular to the side surface 15. By arranging the first image acquiring apparatus 20 in the above-described manner, the above-described desired side view of the slanted surface 11 can be acquired. For example, according to the embodiment of the present disclosure, the first image acquiring apparatus 20 has 1.3 million pixels.
[0079] For example, according to the embodiment of the present disclosure, the package carton 1 includes a strip-shaped sealing ridge 14 arranged on the slanted surface 11 and a side surface 15 intersecting with the slanted surface 11; a connection edge 16 is provided at the intersection of the slanted surface 11 and the side surface 15; and an angle between the slanted surface 11 and the side surface 15 is not a right angle. For example, the detecting method according to the embodiment of the present disclosure includes detecting whether the package carton 1 has a defect of inner layer material exposure located at the strip-shaped sealing ridge 14. In this case, the extracting a feature region to be analyzed includes: providing a third positioning window 301 on the to-be-processed image, the third positioning window 301 being located on a side of the cap region 12 that is provided with a strip-shaped sealing ridge 14 and including the strip-shaped sealing ridge 14; and extracting a third feature region 302 from the third positioning window 301. Further, the determining whether the package carton 1 has a defect includes: extracting a fifth feature value of the third feature region 302; comparing the fifth feature value with a fifth preset value; and determining that the package carton 1 has a defect of inner layer material exposure, if the fifth feature value is greater than or equal to the fifth preset value and a region, where the fifth feature value is greater than or equal to the fifth preset value, is continuous and greater than or equal to a sixth preset value in the direction D2 parallel to the strip-shaped sealing ridge 14, herein, the fifth feature value is a size of the third feature region 302 in the direction D3 perpendicular to the strip-shaped sealing ridge 14. For example, the directions D1, D2 and D3 are perpendicular to each other. For example, the fifth preset value is 65pixel points. For example, the sixth preset value is 20 pixels. For example, according to the embodiment of the present disclosure, the extracting a third feature region 302 from the third positioning window 301 includes: segmenting a third initial region 300I from the third positioning window 301 based on a fourth grayscale value range; and selecting a continuous region with the largest area from the third initial region 300I as the third feature region 302. For example, the fourth grayscale value range is 165 to 255. For example, for the detecting whether package carton 1 has a defect of inner layer material exposure, please refer to FIG. 7A to 7C, FIG. 8A to FIG. 8C as well as the corresponding description above, and no details will be repeated here.
[0080] For example, according to the embodiment of the present disclosure, the detecting method includes: detecting whether the package carton 1 has a defect of cap position offset. In this case, the extracting a feature region to be analyzed includes: providing a fourth positioning window 401 on the to-be-processed image, the fourth positioning window 401 including a cap region 12; defining a boundary of the cap region 12 from the fourth positioning window 401; fitting a rounded region as the fourth feature region 402 based on the boundary of the cap region 12. Further, the determining whether the package carton 1 has a defect includes: extracting the sixth feature value of the fourth feature region 402 and comparing the sixth feature value with a seventh preset value; and determining that the package carton 1 has a defect of cap position offset, if the sixth feature value is greater than or equal to the seventh preset value, herein, the sixth feature value is a distance between a center O’ of the fourth feature region 402 and a center O of the cap 18. For example, the seventh preset value is 700pixel points. For example, the detecting apparatus detects whether the package carton 1 has a defect of cap position offset after detecting whether the package carton 1 has a defect of cap lacking. For example, a boundary of a white region surrounding the cap 18 is taken as the boundary 400B of the cap region 12. For example, for the detecting whether the package carton 1 has a defect of cap position offset, please refer to FIG. 9A to FIG. 9C, FIG. 10A to FIG. 10C as well as the corresponding description, and no details will be repeated here.
[0081] For example, a front view of the slanted surface 11 may be used as the to-be-processed image for detecting whether the package carton 1 has a defect of inner layer material exposure and detecting whether the package carton 1 has a defect of cap position offset. By processing and analyzing the front view of the slanted surface 11, the fact that whether the package carton 1 has a defect of inner layer material exposure or whether the package carton 1 has a defect of cap position offset can be efficiently and accurately determined. That is, by using an image at an appropriate angle, for example, a front view of the slanted surface 11, presence or absence of the two types of defects may be determined, which greatly simplifies the defect detection process.
[0082] For example, referring to FIG. 11B, the image acquiring module includes a second image acquiring apparatus 30; and the detecting method according to the embodiment of the present disclosure includes: arranging the second lens 31 to face towards the slanted surface 11, and arranging a central axis 31X of the second lens 31 to be perpendicular to the slanted surface 11. By arranging the second image acquiring apparatus 30 in the above-described manner, the above-described desired front view of the slanted surface 11 may be acquired. For example, according to the embodiment of the present disclosure, the second image acquiring apparatus 30 has 1.3 million pixels.
[0083] According to the embodiment of the present disclosure, there is further provided a detecting apparatus. FIG. 13 is another schematic diagram of a framework of the detecting apparatus according to the embodiment of the present disclosure. Referring to FIG. 13, the detecting apparatus according to the embodiment of the present disclosure includes: a processor; and a memory, including one or more computer program modules; herein, the one or more computer program modules are stored on the memory and are configured to be executed by the processor, and the one or more computer program modules include instructions for implementing the detecting method as described above. For the operation principle and technical effects of the detecting apparatus, please refer to the detecting apparatus and the detecting method according to the embodiments of the present disclosure as described above, and no details will be repeated here.
[0084] For example, the memory is configured to store non-transitory computer readable instructions (e.g., one or more computer program modules) . The processor is configured to execute the non-transitory computer readable instructions; and when executed by the processor, the non-transitory computer readable instructions may execute one or more steps in the detecting method as described above. The memory and the processor may be interconnected through a bus system and / or other form of connection mechanism (not shown) .
[0085] For example, the processor is a central processing unit (CPU) , a graphics processing unit (GPU) , or other form of processing unit having a data processing capability and / or a program execution capability. For example, the central processing unit (CPU) may be an X86 or ARM architecture. The processor may be a general-purpose processor or a special purpose processor, and may control other components in the detecting apparatus to execute desired functions.
[0086] For example, the memory may include any combination of one or more computer program products; and the computer program products may include various forms of computer readable storage media, for example, a volatile memory and / or a non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory, or the like. The non-volatile memory may include, for example, a read only memory (ROM) , a hard disk, an erasable programmable read only memory (EPROM) , a portable compact disk read only memory (CD-ROM) , a USB memory, a flash memory, or the like. One or more computer program modules may be stored on the computer readable storage medium, and the processor may execute the one or more computer program modules, to implement various functions of the detecting apparatus. Various applications and various data, as well as various data used and / or generated by the applications may also be stored on the computer readable storage medium.
[0087] FIG. 14 is a yet another schematic diagram of a framework of the detecting apparatus according to the embodiment of the present disclosure. Referring to FIG. 14, the detecting apparatus 800, for example, is suitable for implementing the detecting method provided by the embodiment of the present disclosure. The detecting apparatus 800 may be a terminal device, etc. It should be noted that the detecting apparatus 800 shown in FIG. 14 is only an example, and doesn’ t impose any limitation on the function and application scope of the embodiments of the present disclosure.
[0088] Referring to FIG. 14, the detecting apparatus 800 may include a processing apparatus 810 (e.g., a central processing unit, a graphics processor, etc. ) ; and the processing apparatus 810 may execute various appropriate actions or processing according to a program stored on a read-only memory 820 (ROM) or a program loaded from a storage apparatus 880 into a random access memory 830 (RAM) . The random access memory 830 (RAM) further stores various programs and data required for operation of the detecting apparatus 800. The processing apparatus 810, the ROM 820, and the RAM 830 are connected with each other through a bus 840. An input / output (I / O) interface 850 is also connected to the bus 840.
[0089] Usually, apparatuses below may be connected to the I / O interface 850: an input apparatus 860 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc. ; an output apparatus 870 including, for example, a liquid crystal display (LCD) , a speaker, a vibrator, etc. ; a storage apparatus 880 including, for example, a magnetic tape, a hard disk, etc. ; and a communication apparatus 890. The communication apparatus 890 allows the detecting apparatus 800 to perform wireless or wired communication with other device so as to exchange data. Although FIG. 14 shows that the detecting apparatus 800 includes various apparatuses, it should be understood that, it is not required to implement or have all the apparatuses as shown, and the detecting apparatus 800 may be alternatively implemented or have more or fewer apparatuses.
[0090] For example, according to the embodiment of the present disclosure, the above-described detecting method may be implemented as computer software programs. For example, the embodiments of the present disclosure include a computer program product, including a computer program carried on a computer readable medium, the computer program including program codes for executing the above-described detecting method. In such embodiments, the computer program may be downloaded and installed from the network via the communication apparatus 890, or installed from the storage apparatus 880, or installed from the ROM 820. When the computer program is executed by the processing apparatus 810, the detecting method according to the embodiments of the present disclosure is implemented.
[0091] According to an embodiment of the present disclosure, there is further provided a computer readable storage medium. FIG. 15 is a schematic diagram of a computer readable storage medium according to an embodiment of the present disclosure. Referring to FIG. 15, the computer readable storage medium 900 provided by the embodiment of the present disclosure is configured to store non-transitory computer readable instructions 910; and the non-transitory computer readable instructions 910, when executed by the computer, may implement the above-described detecting method. For the operation principle and technical effects of the computer readable storage medium 900, please refer to the detecting apparatus and the detecting method as described above, and no details will be repeated here. For example, the storage medium 900 may be applied to the above-described detecting apparatus. For example, the storage medium 900 may be a memory in the detecting apparatus shown in FIG. 13.
[0092] For example, the storage medium 900 may include a memory card of a smart phone, a storage component of a tablet personal computer, a hard disk of a personal computer, a random access memory (RAM) , a read-only memory (ROM) , an erasable programmable read-only memory (EPROM) , a portable compact disc read-only memory (CD-ROM) , a flash memory, or any combination of the above-described storage media, or other applicable storage media.
[0093] FIG. 16 is a detection result table according to an embodiment of the present disclosure. In the embodiment of the present disclosure, a large number of samples are acquired and detected, and detection results are summarized in the table in FIG. 16. It can be seen from FIG. 16 that the detecting apparatus, the detecting method, and the computer readable storage medium according to the embodiments of the present disclosure have 100%accuracy in detecting the presence or absence of defects. Moreover, it can be seen from FIG. 16 that the detecting apparatus, the detecting method, and the computer readable storage medium according to the embodiments of the present disclosure also have 100%accuracy in detecting various defects. According to the embodiment of the present disclosure, by arranging only two image acquiring apparatuses, i.e., the first image acquiring apparatus and the second image acquiring apparatus, the side view and the front view as described above can be acquired, the four types of defects can be accurately determined.
[0094] What is described above is related to only the illustrative embodiments of the present disclosure and not limitative to the protection scope of the present application. The protection scope of the present application shall be defined by the accompanying claims.
Claims
1.A detecting apparatus for detecting a defect of a package carton, the package carton having a slanted surface, and the slanted surface having a cap region for arranging a cap, wherein the detecting apparatus comprises:an image acquiring module, configured to acquire a to-be-processed image of the slanted surface;an extracting module, configured to provide a positioning window on the to-be-processed image, and extract a feature region to be analyzed from the positioning window; anda feature analyzing module, configured to extract a feature value of the feature region and compare the feature value of the feature region with a preset value, to determine whether the package carton has the defect.2.The detecting apparatus according to claim 1, wherein,the detecting apparatus is configured to detect whether the package carton has a defect of cap lacking;the extracting module is configured to extract a feature region to be analyzed in a way below:providing a first positioning window on the to-be-processed image, the first positioning window comprising the cap region;segmenting a first initial region from the first positioning window based on a first grayscale value range; andfitting a graphic region as a first feature region, based on a boundary of the first initial region;the feature analyzing module is configured to determine whether the package carton has a defect of cap lacking in a way below:extracting a first feature value of the first feature region;comparing the first feature value with a first preset value, and determining that the package carton has the defect of cap lacking if the first feature value is less than the first preset value.3.The detecting apparatus according to claim 2, wherein,the graphic region is an elliptical region or a rounded region; andthe first feature value is an area of the first feature region.4.The detecting apparatus according to claim 1, wherein,the package carton further comprises a strip-shaped sealing ridge arranged on the slanted surface and a side surface intersecting with the slanted surface; a connection edge is provided at the intersection of the slanted surface and the side surface; an angle between the slanted surface and the side surface is not a right angle; andthe detecting apparatus is configured to detect whether the package carton has a defect of wrinkle located between the connection edge and the cap region;the extracting module is configured to extract a feature region to be analyzed in a way below:providing a second positioning window on the to-be-processed image, the second positioning window being located on a side of the cap region that is away from the strip-shaped sealing ridge and comprising a region located between the cap region and the connection edge; andextracting a second feature region from the second positioning window;the feature analyzing module is configured to determine whether the package carton has a defect of wrinkle in a way below:extracting a second feature value of the second feature region; comparing the second feature value with a second preset value, and determining that the package carton has the defect of wrinkle, if the second feature value is greater than or equal to the second preset value; the second feature value being a size of the second feature region in a direction parallel to the side surface; orextracting the second feature value and a third feature value of the second feature region; comparing the second feature value with the second preset value and comparing the third feature value with a third preset value simultaneously, and determining that the package carton has the defect of wrinkle, if the second feature value is greater than or equal to the second preset value, and the third feature value is greater than or equal to the third preset value simultaneously; the third feature value being a size of the second feature region in a direction parallel to the connection edge; orextracting the second feature value and a fourth feature value of the second feature region; comparing the second feature value with the second preset value and comparing the fourth feature value with a fourth preset value simultaneously; and determining that the package carton has the defect of wrinkle, if the second feature value is greater than or equal to the second preset value, and the fourth feature value is greater than or equal to the fourth preset value simultaneously; the fourth feature value being an area of the second feature region; orextracting the second feature value, the third feature value, and the fourth feature value of the second feature region; comparing the second feature value with the second preset value, comparing the third feature value with the third preset value, and comparing the fourth feature value with the fourth preset value simultaneously; and determining that the package carton has the defect of wrinkle, if the second feature value is greater than or equal to the second preset value, the third feature value is greater than or equal to the third preset value, and the fourth feature value is greater than or equal to the fourth preset value simultaneously.5.The detecting apparatus according to claim 4, wherein, the extracting a second feature region from the second positioning window comprises:segmenting a second initial region from the second positioning window based on a second grayscale value range;selecting a continuous region with a largest area from the second initial region; andsegmenting the second feature region from the continuous region based on a third grayscale value range.6.The detecting apparatus according to any one of claims 2 to 5, wherein,the to-be-processed image is a side view of the slanted surface.7.The detecting apparatus according to claim 6, wherein,the package carton further comprises a strip-shaped sealing ridge arranged on the slanted surface and a side surface intersecting with the slanted surface; a connection edge is provided at an intersection of the slanted surface and the side surface; an angle between the slanted surface and the side surface is not a right angle;the image acquiring module comprises a first image acquiring apparatus; the first image acquiring apparatus comprises a first lens, the first lens faces towards the slanted surface and the side surface, and a central axis of the first lens is perpendicular to the side surface.8.The detecting apparatus according to claim 1, wherein,the package carton further comprises a strip-shaped sealing ridge arranged on the slanted surface and a side surface intersecting with the slanted surface; a connection edge is provided at an intersection of the slanted surface and the side surface; an angle between the slanted surface and the side surface is not a right angle; and the connection edge and the strip-shaped sealing ridge are located on two opposite sides of the cap region;the detecting apparatus is configured to detect whether the package carton has a defect of inner layer material exposure located at the strip-shaped sealing ridge;the extracting module is configured to extract a feature region in a way below:providing a third positioning window on the to-be-processed image; the third positioning window being located on a side of the cap region that is provided with the strip-shaped sealing ridge and comprising the strip-shaped sealing ridge; andextracting a third feature region from the third positioning window;the feature analyzing module is configured to determine whether the package carton has a defect of inner layer material exposure in a way below:extracting a fifth feature value of the third feature region; comparing the fifth feature value with a fifth preset value, and determining that the package carton has the defect of inner layer material exposure, if the fifth feature value is greater than or equal to the fifth preset value, and a region, where the fifth feature value is greater than or equal to the fifth preset value, is continuous and greater than or equal to a sixth preset value in the direction parallel to the strip-shaped sealing ridge; the fifth feature value being a size of the third feature region in a direction perpendicular to the strip-shaped sealing ridge.9.The detecting apparatus according to claim 8, wherein,the extracting a third feature region from the third positioning window comprises:segmenting a third initial region from the third positioning window based on a fourth grayscale value range; andselecting a continuous region with a largest area from the third initial region as the third feature region.10.The detecting apparatus according to claim 1, wherein,the detecting apparatus is configured to detect whether the package carton has a defect of cap position offset;the extracting module is configured to extract a feature region in a way below:providing a fourth positioning window on the to-be-processed image, the fourth positioning window comprising the cap region;defining a boundary of the cap region from the fourth positioning window; andfitting a rounded region as the fourth feature region based on the boundary of the cap region;the feature analyzing module is configured to determine whether the package carton has a defect of cap position offset in a way below:extracting the sixth feature value of the fourth feature region; comparing the sixth feature value with a seventh preset value, and determining that the package carton has the defect of cap position offset, if the sixth feature value is greater than or equal to the seventh preset value; the sixth feature value being a distance between a center of the fourth feature region and a center of the cap.11.The detecting apparatus according to any one of claims 8 to 10, wherein,the to-be-processed image is a front view of the slanted surface.12.The detecting apparatus according to claim 11, wherein,the image acquiring module comprises a second image acquiring apparatus; the second image acquiring apparatus comprises a second lens, the second lens faces towards the slanted surface, and a central axis of the second lens is perpendicular to the slanted surface.13.A detecting method for detecting a defect of a package carton; the package carton having a slanted surface, and the slanted surface having a cap region for arranging a cap, wherein the detecting method comprises:acquiring a to-be-processed image of the slanted surface;providing a positioning window on the to-be-processed image, and extracting a feature region to be analyzed from the positioning window; andextracting a feature value of the feature region and comparing a feature value of the feature region with a preset value to determine whether the package carton has the defect.14.The detecting method according to claim 13, wherein,the detecting method comprises: detecting whether the package carton has a defect of cap lacking;the extracting a feature region to be analyzed comprises:providing a first positioning window on the to-be-processed image, the first positioning window comprising the cap region;segmenting a first initial region from the first positioning window based on a first grayscale value range; andfitting a graphic region as the first feature region, based on a boundary of the first initial region;the determining whether the package carton has the defect comprises:extracting a first feature value of the first feature region;comparing the first feature value with a first preset value, and determining that the package carton has the defect of cap lacking if the first feature value is less than the first preset value.15.The detecting method according to claim 14, wherein,the graphic region is an elliptical region or a rounded region; andthe first feature value is an area of the first feature region.16.The detecting method according to claim 13, wherein,the package carton further comprises a strip-shaped sealing ridge arranged on the slanted surface and a side surface intersecting with the slanted surface; a connection edge is provided at the intersection of the slanted surface and the side surface; and an angle between the slanted surface and the side surface is not a right angle;the detecting method comprises: detecting whether the package carton has a defect of wrinkle located between the connection edge and the cap region;the extracting a feature region to be analyzed, comprises:providing a second positioning window on the to-be-processed image, the second positioning window being located on a side of the cap region that is away from the strip-shaped sealing ridge and comprising a region located between the cap region and the connection edge; andextracting a second feature region from the second positioning window;the determining whether the package carton has the defect comprises:extracting a second feature value of the second feature region; comparing the second feature value with a second preset value, and determining that the package carton has the defect of wrinkle, if the second feature value is greater than or equal to the second preset value; the second feature value being a size of the second feature region in a direction parallel to the side surface; or,extracting the second feature value and a third feature value of the second feature region; comparing the second feature value with the second preset value and comparing the third feature value with a third preset value simultaneously; and determining that the package carton has the defect of wrinkle, if the second feature value is greater than or equal to the second preset value, and the third feature value is greater than or equal to the third preset value simultaneously; the third feature value being a size of the second feature region in a direction parallel to the connection edge; or,extracting the second feature value and a fourth feature value of the second feature region; comparing the second feature value with the second preset value and comparing the fourth feature value with a fourth preset value simultaneously; and determining that the package carton has the defect of wrinkle, if the second feature value is greater than or equal to the second preset value, and the fourth feature value is greater than or equal to the fourth preset value simultaneously; the fourth feature value being an area of the second feature region; or,extracting the second feature value, the third feature value, and the fourth feature value of the second feature region; comparing the second feature value with the second preset value, comparing the third feature value with the third preset value, and comparing the fourth feature value with the fourth preset value simultaneously; and determining that the package carton has the defect of wrinkle, if the second feature value is greater than or equal to the second preset value, the third feature value is greater than or equal to the third preset value, and the fourth feature value is greater than or equal to the fourth preset value simultaneously.17.The detecting method according to claim 16, wherein, the extracting a second feature region from the second positioning window comprises:segmenting a second initial region from the second positioning window based on a second grayscale value range;selecting a continuous region with a largest area from the second initial region; andsegmenting the second feature region from the continuous region based on a third grayscale value range.18.The detecting method according to any one of claims 14 to 17, wherein,the to-be-processed image is a side view of the slanted surface.19.The detecting method according to claim 18, wherein,the package carton further comprises a strip-shaped sealing ridge arranged on the slanted surface and a side surface intersecting with the slanted surface; a connection edge is provided at the intersection of the slanted surface and the side surface; an angle between the slanted surface and the side surface is not a right angle; and the connection edge and the strip-shaped sealing ridge are located on two opposite sides of the cap region;the image acquiring module comprises a first image acquiring apparatus; the first image acquiring apparatus comprises a first lens;the detecting method comprises: arranging the first lens to face towards the slanted surface and the side surface; and arranging a central axis of the first lens to be perpendicular to the side surface.20.The detecting method according to claim 13, wherein,the package carton further comprises a strip-shaped sealing ridge arranged on the slanted surface and a side surface intersecting with the slanted surface; a connection edge is provided at the intersection of the slanted surface and the side surface; and an angle between the slanted surface and the side surface is not a right angle;the detecting method comprises: detecting whether the package carton has a defect of inner layer material exposure located at the strip-shaped sealing ridge;the extracting a feature region to be analyzed comprises:providing a third positioning window on the to-be-processed image, the third positioning window being located on a side of the cap region that is provided with the strip-shaped sealing ridge and comprising the strip-shaped sealing ridge; andextracting a third feature region from the third positioning window;the determining whether the package carton has the defect comprises:extracting a fifth feature value of the third feature region; comparing the fifth feature value with a fifth preset value; and determining that the package carton has the defect of inner layer material exposure, if the fifth feature value is greater than or equal to the fifth preset value and a region, where the fifth feature value is greater than or equal to the fifth preset value, is continuous and greater than or equal to a sixth preset value in the direction parallel to the strip-shaped sealing ridge; the fifth feature value being a size of the third feature region in the direction perpendicular to the strip-shaped sealing ridge.21.The detecting method according to claim 20, wherein,the extracting a third feature region from the third positioning window comprises:segmenting a third initial region from the third positioning window based on a fourth grayscale value range; andselecting a continuous region with a largest area from the third initial region as the third feature region.22.The detecting method according to claim 13, wherein,the detecting method comprises: detecting whether the package carton has a defect of cap position offset;the extracting a feature region to be analyzed comprises:providing a fourth positioning window on the to-be-processed image, the fourth positioning window comprising the cap region;defining a boundary of the cap region from the fourth positioning window; andfitting a rounded region as the fourth feature region based on the boundary of the cap region;the determining whether the package carton has the defect comprises:extracting a sixth feature value of the fourth feature region; comparing the sixth feature value with a seventh preset value, and determining that the package carton has the defect of cap position offset, if the sixth feature value is greater than or equal to the seventh preset value; the sixth feature value being a distance between a center of the fourth feature region and a center of the cap.23.The detecting method according to any one of claims 20 to 22, wherein,the to-be-processed image is a front view of the slanted surface.24.The detecting method according to claim 23, wherein,the image acquiring module comprises a second image acquiring apparatus, and the second image acquiring apparatus comprises a second lens;the detecting method comprises: arranging the second lens to face towards the slanted surface, and arranging a central axis of the second lens to be perpendicular to the slanted surface.25.A detecting apparatus, comprising:a processor; anda memory, comprising one or more computer program modules;wherein, the one or more computer program modules are stored on the memory and are configured to be executed by the processor, and the one or more computer program modules comprise instructions for implementing the detecting method according to any one of claims 13 to 24.26.A computer readable storage medium, configured to store non-transitory computer readable instructions; wherein, the non-transitory computer readable instructions, when executed by a computer, implements the detecting method according to any one of claims 13 to 24.
Citation Information
Patent Citations
Visual inspection method for bottle packaging quality
CN106370659A
OpenCV-based high-reflection bottle cap defect detection method
CN114018946A
Sealing detection method and device, electronic equipment and storage medium
CN115661054A
A method for quality assessment of a food package and a packaging system
EP4095519A1
Cited By
Intelligent milk powder packaging bag sorting method based on deep learning
CN120388025A
