An adaptive light source system for dark field tack impression imaging
By adaptively adjusting the luminous intensity of the LED light source array through an adaptive light source system, the difficulty of identifying adhesive residues is solved, clear imaging of adhesive residues is achieved, and the accuracy of identification is improved.
Patent Information
- Application Number
- CN202310636274.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-31
- Publication Date
- 2025-11-21
- Estimated Expiration
- 2043-05-31
AI Technical Summary
Existing technologies are insufficient to effectively distinguish between counterfeit and genuine cigarettes, especially when using glue marks for identification, which is prone to misjudgment. The counterfeit cigarette manufacturing industry cannot replicate the glue coating machines used for genuine cigarettes, making glue mark identification difficult.
An adaptive light source system, including an LED light source array and an image analysis platform, is adopted. By adaptively adjusting the luminous intensity of the LED light source, a complete and clear outline of the adhesive trace is obtained. The purple LED light source array is arranged in three concentric circles to achieve efficient imaging of the adhesive trace.
It achieves clear imaging of glue marks, improves the accuracy of glue mark identification, and reduces the possibility of misjudging counterfeit cigarettes.
Smart Images

Figure CN116773529B_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The application belongs to the technical field of cigarette identification, and particularly relates to a self-adaptive light source system for dark-field glue mark imaging. BACKGROUND
[0002] There are serious quality problems in fake cigarettes, and harmful bacteria exceed the standard, which not only harms the health of residents in China, but also has adverse effects on the social economy. Cigarette identification technology can be divided into four categories: trademark identification, cigarette box identification, tobacco identification and glue mark identification.
[0003] Trademark identification: some fake cigarette samples with high simulation degree can completely reproduce the image and texture of the real trademark, which leads to misjudgment when using trademarks to identify the authenticity of cigarettes;
[0004] Cigarette box identification: some fake cigarette samples with high simulation degree can completely reproduce the outer packaging material and form of the genuine cigarette, which leads to misjudgment when using the cigarette box to identify the authenticity of the cigarette;
[0005] Tobacco identification: relies on component analysis testing equipment;
[0006] Glue mark identification: the glue used for cigarette packaging is applied by a glue applicator, and the shape of the glue mark is closely related to the type of the machine. At present, the fake cigarette manufacturing industry cannot imitate the glue applicator used in China's tobacco manufacturing, and basically uses manual glue application. Therefore, the application provides a self-adaptive light source system for dark-field glue mark imaging. SUMMARY
[0007] The application aims to provide a self-adaptive light source system for dark-field glue mark imaging, which can collect complete and clear glue mark contours for subsequent identification by technicians.
[0008] To solve the above technical problems, the application adopts the following technical solutions:
[0009] A self-adaptive light source system for dark-field glue mark imaging includes a shooting device, an LED light source array and an image analysis platform, and further includes a dark field without external light source, a cigarette packaging box is placed at the bottom of the dark field without external light source, the LED light source array and the shooting device are placed inside the dark field without external light source, and the image analysis platform is placed outside the dark field without external light source.
[0010] The photographing device is connected with the image analysis platform, and is used for transmitting the photographed transparent adhesive mark image back to the image analysis platform; the image analysis platform is connected with the LED light source array, and the light emitting intensity of the LED light source array is adjusted adaptively according to the analysis result of the image analysis platform; the LED light source array is arranged around the photographing device, after the light emitting intensity of the LED light source array is adjusted, the photographing device re-photographs the image and transmits the image back to the image analysis platform until the complete transparent adhesive mark contour is acquired, and each LED lamp can be controlled individually; and the image analysis platform, the LED light source array and the photographing device are all powered by an external power supply.
[0011] Further, the LED light source array is composed of 20 purple LED lights arranged in three concentric circles.
[0012] Further, the three concentric circles include the innermost circle, the second circle and the third circle of lamps, the innermost circle has 4 purple LED lamps, each purple LED lamp has a power of P1; the second circle has 8 purple LED lamps, each purple LED lamp has a power of P2; the third circle has 8 purple LED lamps, each purple LED lamp has a power of P3.
[0013] Further, the powers of the three circles of LED lamps are P1
[0014] Further, the LED lamps of the innermost circle are spaced 90°, the LED lamps of the second circle are spaced 45°, and the LED lamps of the third circle are spaced 45°.
[0015] Further, the photographing device, the LED light source array and the image analysis platform are all prior art, and the internal structure, circuit connection relationship and working principle thereof are all known to the skilled in the art.
[0016] Compared with the prior art, the present application has at least one of the following beneficial effects:
[0017] The present application proposes a self-adaptive light source system for dark field adhesive mark imaging. The disassembled cigarette outer packaging box is placed as a sample in a dark field without external light source, the LED light source array is used to irradiate the packaging box to the transparent adhesive mark on the surface thereof, the light source parameters are adaptively adjusted according to the contour integrity of the adhesive mark until the adhesive mark contour is clearly visible; the light source parameters can be adaptively adjusted to realize complete and clear photographing of the transparent adhesive mark on the cigarette outer packaging box. BRIEF DESCRIPTION OF DRAWINGS
[0018] Figure 1 The present application is a whole flow chart.
[0019] Figure 2 The present application is a structure block diagram.
[0020] Figure 3 The present application is a schematic diagram of the LED light source array.
[0021] Figure 4 The light field schematic diagram of the LED point light source of the present application;
[0022] Figure 5 The light field superposition schematic diagram top view of the LED light source array of the present application;
[0023] Figure 6 The schematic diagram of the contour pixel point determination method of the present application.
[0024] In the figure, 1 is a shooting device; 2 is an LED light source array; 3 is an image analysis platform; and 4 is a dark field without external light source. DETAILED DESCRIPTION
[0025] As Figures 1-6 shown, in order to make the purpose, technical scheme and advantages of the present application more clear and explicit, the present application is further described in detail below in combination with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and do not limit the present application.
[0026] EMBODIMENT
[0027] An adaptive light source system for dark field adhesive mark imaging, comprising a shooting device 1, an LED light source array 2 and an image analysis platform 3, further comprising a dark field 4 without external light source, the dark field 4 without external light source is placed with a cigarette packaging box at the bottom, the LED light source array 2 and the shooting device 1 are placed inside the dark field 4 without external light source, and the image analysis platform 3 is placed outside the dark field 4 without external light source,
[0028] The shooting device 1 is connected with the image analysis platform 3; the image analysis platform 3 is connected with the LED light source array 2; the LED light source array 2 is arranged and set around the shooting device 1, and each LED lamp can be controlled individually; the image analysis platform 3, the LED light source array 2 and the shooting device 1 are all powered by an external power supply, and the present application proposes an adaptive light source system for dark field adhesive mark imaging. The disassembled cigarette outer packaging box is placed as a sample in the dark field without external light source, the LED light source array is used to irradiate the packaging box to show the transparent adhesive mark on it, the light source parameters are adaptively adjusted according to the contour integrity of the adhesive mark, and the adhesive mark contour is clearly visible; the light source parameters can be adaptively adjusted to realize complete and clear shooting of the transparent adhesive mark on the cigarette outer packaging box.
[0029] As a preferred, the LED light source array 2 is composed of 20 purple LED lights arranged in the form of three concentric circles.
[0030] As preferred, the three concentric circles include the innermost circle, the second circle and the third circle of the lamps, the innermost circle has 4 purple LED lamps, each purple LED lamp has a power of P1; the second circle has 8 purple LED lamps, each purple LED lamp has a power of P2; the third circle has 8 purple LED lamps, each purple LED lamp has a power of P3.
[0031] As preferred, the power of the three circles of LED lamps is P1
[0032] As preferred, the LED lamps of the innermost circle are spaced 90°, the LED lamps of the second circle are spaced 45°, and the LED lamps of the third circle are spaced 45°.
[0033] The working process of the device is as follows:
[0034] Step 1: As shown in the accompanying Figure 2 , carefully disassemble the part of the cigarette outer packaging box adhered by glue, avoid tearing, and lay it flat into the dark field, make the transparent glue mark face the LED light source array and the shooting device;
[0035] Step 2: Start the LED light source array, the arrangement of the LED light source array is as shown in the accompanying Figure Three .
[0036] Considering that the purple light has a good imaging effect on the transparent glue mark, the LED light source array is composed of 20 purple LED lights arranged in three concentric circles, the innermost circle has 4 purple LED lamps (spaced 90°), the power of which is P1; the second circle has 8 purple LED lamps (spaced 45°), the power of which is P2; the third circle has 8 purple LED lamps (spaced 45°), the power of which is P3.
[0037] As a point light source, the light field distribution of a single LED lamp is as shown in the accompanying Figure Four ; and the light field distribution of the LED light source array proposed by the present application is as shown in the accompanying Figure Five . In order to make the light field distribution uniform, the power of the three circles of LED lamps needs to satisfy P1
[0038] Step 3: Use the shooting device to collect the transparent glue mark image, and transmit the imaging result to the image analysis platform.
[0039] Step 4: Under the irradiation of the purple LED light source array, the imaging color depth of the transparent glue mark is higher than that of the white packaging box. The glue mark threshold T th The imaging result of the transparent glue mark is binarized:
[0040] If the pixel value T>T th, Let T=1, indicating that the imaging result of the transparent glue mark is black;
[0041] If the pixel value T≤Tth, Let T = 0, indicating that the imaging result of the white packaging box is white.
[0042] Wherein, the adhesive mark threshold T th Determined by the previous adhesive mark imaging experiment.
[0043] Step 5: Extract the contour line at the black-white junction in the binary image of the transparent adhesive mark as the contour of the transparent adhesive mark.
[0044] Step 6: Define any pixel point on the transparent adhesive mark contour as the current contour pixel point, and set its coordinates as x, y. Determine whether there is a pixel value = 1 point in the 3x3 neighborhood of the current contour pixel point:
[0045] As shown in the accompanying Figure Six If there is no pixel value = 1 point, it means that the current contour is missing, and the spatial coordinates of the missing contour are recorded. The point with the shortest Euclidean distance from the current contour pixel point is taken as the next contour pixel point x', y'; wherein, the calculation method of the Euclidean distance d between two points is:
[0046]
[0047] As shown in the accompanying Figure Six If there is a pixel value = 1 point, it means that the current contour is continuous, and this pixel value = 1 point is taken as the next contour pixel point.
[0048] As shown in the accompanying Figure Six If there are multiple pixel value = 1 points, it means that the current contour is continuous, and these pixel value = 1 points are taken as the next contour pixel points respectively.
[0049] Step 7: Take the next contour pixel point as the current contour pixel point, and repeat step 6 until the entire contour imaging result of the transparent adhesive mark is traversed, and all spatial coordinates of the missing contour are recorded.
[0050] Step 8: Since the weaker the light is, the better the imaging effect of the transparent adhesive mark is. According to the light field distribution of the LED light source array and all spatial coordinates of the missing contour, the power of the LED light source corresponding to the missing contour position is adaptively reduced.
[0051] Step 9: Repeat steps 3 to 8 until the complete and clear transparent adhesive mark contour is successfully extracted.
[0052] Step 10: End.
[0053] While the application has been described with reference to numerous exemplary embodiments, it will be understood that various other modifications can be made within the scope of the application as disclosed herein. More particularly, many modifications can be made to the components and / or arrangements of the subject combinations within the scope and spirit of the disclosure, and applicants will not be limited to the specific recitations of the figures and the claims. Other aspects, features and advantages of the application will become apparent to those skilled in the art from the following description.
Claims
1. An adaptive light source system for dark-field adhesive residue imaging, comprising an imaging device (1), an LED light source array (2), and an image analysis platform (3), characterized in that: It also includes a dark field (4) with and without external light sources. A cigarette packaging box is placed at the bottom of the dark field (4). An LED light source array (2) and a shooting device (1) are placed inside the dark field (4). An image analysis platform (3) is placed outside the dark field (4). The shooting device (1) is connected to the image analysis platform (3); the image analysis platform (3) is connected to the LED light source array (2); the LED light source array (2) is arranged around the shooting device (1), and each LED can be controlled individually; the image analysis platform (3), the LED light source array (2) and the shooting device (1) are all powered by an external power source; The LED light source array (2) consists of 20 purple LEDs arranged in three concentric circles; The three concentric circles consist of the innermost, second, and third circles of lights. The innermost circle has 4 purple LEDs, each with a power of P1; the second circle has 8 purple LEDs, each with a power of P2; and the third circle has 8 purple LEDs, each with a power of P3. The power of the three-ring LED light is P1 < P2 < P3; The innermost ring of LED lights is spaced 90° apart, the second ring of LED lights is spaced 45° apart, and the third ring of LED lights is spaced 45° apart.
2. The adaptive light source system for dark-field adhesive residue imaging according to claim 1, characterized in that: The work process is as follows: Step 1: Carefully remove the glued parts of the cigarette outer packaging box, avoiding tearing, and lay it flat in the dark field, so that the transparent glue marks face the LED light source array (2) and the shooting device (1); Step 2: Start the LED light source array (2); Step 3: Use the imaging device (1) to capture images of transparent adhesive residue and transmit the imaging results to the image analysis platform (3); Step 4: Under the illumination of a purple LED light source array, the color depth of the transparent adhesive residue is higher than that of the white packaging box. The imaging result of the transparent adhesive residue is binarized using the adhesive residue threshold Tth. If pixel value T > Tth, let T = 1, indicating that the image result of the transparent adhesive residue is black; If the pixel value T ≤ T th, let T = 0, which means that the image of the white packaging box is white; The adhesive residue threshold Tth was determined through a prior adhesive residue imaging experiment. Step 5: Extract the outline at the black-and-white boundary from the binary image of the transparent adhesive residue as the outline of the transparent adhesive residue. Step 6: Define any pixel on the outline of the transparent adhesive residue as the current outline pixel. Let its coordinates be x, y. Determine whether there exists a pixel with a value of 1 in the 3×3 neighborhood of the current outline pixel. If there is no point with pixel value = 1, it means that the current contour is missing. Record the spatial coordinates of the missing contour, and take the point with the shortest Euclidean distance to the current contour pixel as the next contour pixel x',y'; where the Euclidean distance d between the two points is calculated as follows; If there exists a pixel with a value of 1, it means that the current contour is continuous, and this pixel with a value of 1 is used as the next contour pixel. If there are multiple points with a pixel value of 1, it means that the current contour is continuous, and these points with a pixel value of 1 are used as the next contour pixel points respectively. Step 7: Take the next contour pixel as the current contour pixel, repeat step 6, until the entire contour imaging result of the transparent glue trace is traversed and all spatial coordinates of the missing contour are recorded. Step 8: Since the weaker the light, the better the imaging effect of the transparent adhesive marks; based on the light field distribution of the LED light source array and all spatial coordinates of the missing outline, adaptively reduce the power of the LED light source corresponding to the missing outline position; Step 9: Repeat steps 3 to 8 until a complete and clear outline of the transparent adhesive residue is successfully extracted; Step 10: End.
Citation Information
Patent Citations
Automatic identification and input system for cigarette code spraying
CN214540787U
Illuminating apparatus used for automated optical inspection device, and imaging system
WO2021129283A1