Method, equipment and medium for distinguishing old and new paper sheet articles
By using a dual-polarization camera system and multi-scale linear feature detection, the crease damage, stain damage, and texture degradation characteristics of paper sheet items are determined, and a new/old evaluation index is calculated. This solves the problems of easily damaged paper playing cards and low efficiency of manual sorting, and achieves efficient identification of new and old paper sheet items.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-01-28
- Publication Date
- 2026-04-21
AI Technical Summary
In the existing technology, paper playing cards are difficult to use repeatedly, are easily damaged and cracked, have poor wear resistance, and the efficiency of manually sorting new and old playing cards is low, making it difficult to meet the needs of recycling and reuse.
A dual-polarization camera system is used to acquire parallel polarization images and vertical polarization images. Combined with multi-scale linear feature detection, the feature values of crease loss, stain loss and texture degradation are determined, and the newness evaluation index of paper sheet items is calculated.
It improves the accuracy and reliability of assessing the age of paper-based sheet items, solves the problem of image acquisition information loss, and achieves efficient differentiation between old and new paper-based sheet items.
Smart Images
Figure CN121904028A_ABST
Abstract
Description
Technical Field
[0001] This disclosure generally relates to the field of data analysis technology, and specifically to a method, apparatus and medium for distinguishing between new and old paper sheet-like items. Background Technology
[0002] Playing cards are a popular form of entertainment. China is a major consumer of playing cards. Currently, most playing cards circulating in the market are paper cards, which are prone to damage, tearing, and abrasion, and are usually discarded after only a few uses. Related technologies often rely on the user's personal experience for inspection. In environments requiring the recycling and reuse of large quantities of playing cards, manual sorting is insufficient to meet the accuracy and efficiency of distinguishing between new and used cards. Summary of the Invention
[0003] In view of the above-mentioned defects or deficiencies in the prior art, it is desirable to provide a method, device and medium for distinguishing the newness and oldness of paper sheet-like items, which can determine the newness and oldness assessment index of the target paper sheet-like items based on the parallel polarization image and vertical polarization image acquired by the dual polarization camera system, and provide reliable data support for the evaluation of the newness and oldness of paper sheet-like items.
[0004] In a first aspect, embodiments of this application provide a method for distinguishing between new and old paper sheet-like articles, including:
[0005] The system uses a camera to acquire images of the target paper-like object.
[0006] Multi-scale linear feature detection is performed on the acquired image to obtain crease loss feature values;
[0007] Based on the acquired images, determine the stain wear characteristic value and texture degradation characteristic value;
[0008] The newness assessment index of the target paper sheet is determined based on the crease damage characteristic value, the stain damage characteristic value, and the texture degradation characteristic value.
[0009] Secondly, embodiments of this application provide a device for distinguishing between new and old paper sheet-like articles, including:
[0010] The image acquisition module is used to acquire images of the target paper sheet based on the camera system;
[0011] The first loss feature acquisition module is used to perform multi-scale linear feature detection on the acquired image to obtain crease loss feature values;
[0012] The second loss feature acquisition module is used to determine the stain loss feature value and texture degradation feature value based on the acquired image;
[0013] The evaluation module is used to determine the newness evaluation index of the target paper sheet based on the crease damage characteristic value, the stain damage characteristic value and the texture degradation characteristic value.
[0014] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method described in embodiments of this application.
[0015] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in embodiments of this application.
[0016] Fifthly, embodiments of this application provide a computer program product, including a computer program, characterized in that, when the computer program is executed by a processor, it implements the method described in embodiments of this application.
[0017] The method, apparatus, and medium proposed in this application for distinguishing the newness and oldness of paper sheet-like items are based on a camera system to acquire images of the target paper sheet-like items. Then, by calculating crease damage characteristics, stain damage characteristics, and texture degradation characteristics, a comprehensive assessment index of the newness and oldness of the target paper sheet-like items can be determined. On the basis of solving the problem of severe loss of image acquisition information of target paper sheet-like items, the comprehensive assessment of multiple damage characteristics further effectively improves the accuracy and reliability of the assessment index of the newness and oldness of target paper sheet-like items.
[0018] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description
[0019] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:
[0020] Figure 1 A flowchart illustrating a method for distinguishing between new and old paper sheet articles according to an embodiment of this application is shown.
[0021] Figure 2 A schematic diagram of a device for distinguishing between new and old paper sheet articles according to an embodiment of this application is shown;
[0022] Figure 3 A schematic diagram of the structure of a computer system suitable for implementing an electronic device or server according to embodiments of this application is shown. Detailed Implementation
[0023] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.
[0024] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.
[0025] To further illustrate the technical solutions provided in the embodiments of this application, a detailed description is provided below in conjunction with the accompanying drawings and specific implementation methods. Although the embodiments of this application provide method operation instruction steps as shown in the following embodiments or drawings, the method may include more or fewer operation instruction steps based on conventional or non-creative effort. In steps where there is no logically necessary causal relationship, the execution order of these steps is not limited to the execution order provided in the embodiments of this application. In actual processing or when the device executes the method, it may be executed sequentially or in parallel according to the method shown in the embodiments or drawings.
[0026] It should be noted that the acquisition or use of data in the embodiments of this application requires the user's consent. The relevant data can only be obtained after the user's authorization and permission, and the acquisition or use of the data complies with the laws and regulations of the relevant regions.
[0027] Please refer to Figure 1 , Figure 1 A flowchart illustrating a method for distinguishing between new and old paper sheet-like articles according to an embodiment of this application is shown. Figure 1 As shown, the method includes:
[0028] Step 101: Acquire images of the target paper sheet based on the camera system.
[0029] It should be noted that the detection system used to distinguish between new and old paper-like items includes a camera system capable of capturing images of the target paper-like item. These images contain information reflecting the degree of newness or age of the target paper-like item.
[0030] Step 102: Perform multi-scale linear feature detection on the acquired image to obtain crease loss feature values.
[0031] Step 103: Determine the stain damage characteristic value and texture degradation characteristic value based on the acquired image.
[0032] In one feasible embodiment, a preset image recognition algorithm or a trained convolutional neural network can be used to perform image recognition on the acquired image to obtain crease damage feature values, stain damage feature values, and texture degradation feature values.
[0033] For example, a pre-trained ConvNeXt-Tiny model can be used. ConvNeXt-Tiny is a lightweight convolutional neural network model that maintains high performance while requiring fewer parameters, meeting the iterative needs of identifying the newness of paper-based sheet items in express delivery. The trained ConvNeXt-Tiny model uses weights pre-trained on the ImageNet-1k dataset, retaining only the backbone parameters, and re-initializing the classification head to adapt to the task of classifying the newness of paper-based sheet items. The training parameters can be set to: 8 samples per training session (batch_size=8); 10 training iterations (epochs=10); and a learning rate of 5e-4 (lr=5e-4).
[0034] Therefore, the trained ConvNeXt-Tiny model can be used to obtain the crease damage feature value, stain damage feature value and texture degradation feature value of paper sheet items, and thus be able to evaluate the age of paper sheet items.
[0035] In one feasible embodiment, to ensure that playing cards can withstand long-term and frequent use, existing technologies typically involve special treatments on dyed playing cards to enhance their durability and water resistance. For example, advanced lamination technology is used to cover the surface of the playing cards with a transparent plastic film. This film not only effectively prevents ink fading and paper wear, but also gives the playing cards a certain degree of water resistance, so they will not be easily damaged even if accidentally splashed with water.
[0036] However, laminated playing cards exhibit characteristics such as strong specular reflection on smooth surfaces of new cards and increased diffuse reflection on worn surfaces of older cards. For new cards with creases, the increased specular reflection can lead to severe image contamination by reflected light, resulting in the loss of crucial information for identifying the age of paper-like items, such as texture and fine creases. While pressing textures to improve the card's appearance can reduce the impact of specular reflection to some extent, the problem of information loss still exists. Therefore, this application proposes using a dual-polarization camera system for image acquisition.
[0037] Specifically, a dual-polarization camera system is used to acquire parallel polarization images and vertical polarization images of the target paper sheet at a preset polarization angle, and a reflection suppression image is determined based on the parallel polarization images and vertical polarization images.
[0038] The dual-polarization camera system includes two image acquisition devices, each equipped with a polarizer at a specific angle to the coaxial polarization light source. The preset polarization angle used to set the coaxial polarization light source can be determined based on the coating type of the target paper sheet, and this application does not impose specific limitations. For example, the refractive index and polarization correction change corresponding to the coating material of the target paper sheet can be obtained. Then, an initial polarization angle can be determined based on the coating refractive index and the air refractive index. The initial polarization angle is then corrected using the polarization correction change to obtain the optimal polarization angle, i.e., the preset polarization angle of the coaxial polarization light source.
[0039] In some embodiments, the preset polarization angle of the coaxial polarized light source can be determined using the following formula:
[0040]
[0041] in, The preset polarization angle for a coaxial polarized light source. For the coating refractive index, The refractive index of air, This represents the polarization correction change.
[0042] Furthermore, the dual-polarization camera is equipped with polarizers at 0° and 90° respectively to acquire parallel polarized images and vertical polarized images. The parallel polarized images are acquired by an image acquisition device equipped with a 0° polarizer, and the vertical polarized images are acquired by an image acquisition device equipped with a 90° polarizer.
[0043] It should be noted that the target paper sheet has a greater thickness than banknotes. In the process of use, in addition to being prone to bending and other creases that can cause obvious changes in shape, the target paper sheet is also prone to shallow creases, i.e. scratches, caused by sharp objects such as fingernails. When there are many scratches or they are concentrated, they can also accelerate the depreciation of the target paper sheet.
[0044] It should be understood that, due to the acquisition method of vertically polarized images, most of the specular reflection information has been eliminated. Therefore, it has a strong reflection suppression effect and can directly use the texture information of vertically polarized images for crease detection, that is, to detect shallow creases such as fingernail scratches that do not cause deformation of the target paper sheet.
[0045] Specifically, multi-scale linear feature detection is performed on the vertically polarized image to obtain the multi-scale gradient response corresponding to each pixel; the multi-scale gradient responses are fused to obtain the crease response corresponding to each pixel; regions with crease responses greater than a preset crease response threshold are used as crease candidate regions; and crease loss features corresponding to the crease candidate regions are obtained.
[0046] In other words, in this embodiment, since the usage status of the target paper sheet is unknown, multi-scale linear feature detection is employed. Specifically, in this embodiment, the gradient operator is used to calculate the gray-level change rate of the vertically polarized image to determine the gradient response. That is, the crease on the surface of the target paper sheet is prone to produce a long, continuous texture with symmetrical gray-level changes on both sides and a narrow and uniform width. Feature detection is performed on the gradient response at each scale, the gradient responses at each scale are fused, and candidate crease regions are determined based on threshold filtering. Finally, crease loss features are determined based on the candidate crease regions.
[0047] For example, the multi-scale gradient response can be calculated using the following formula:
[0048]
[0049] in, For scale 2D image crease response, For gradient operators, This is a vertically polarized image. Let the standard deviation be a Gaussian kernel. For scale parameters, For convolution calculation, This is an edge saliency mask.
[0050] It should be understood that, in the embodiments of this application, the edge saliency mask is used to suppress non-linear edges. Specifically, the edge saliency mask can be designed using a Frangi filter based on the Hessian matrix to enhance linear structures. Specifically, it can be expressed as:
[0051]
[0052] in, Based on the saliency mask of the basic edge, Linearity is used to distinguish between linear and speckled patterns. ( ), spotted ( ), For structural strength, For control parameters, , This represents the intensity characteristic of grayscale changes.
[0053] It should be understood that, Edge saliency masks may also include color suppression factors and symmetry suppression factors to prevent lines in printed images from being mistaken for creases.
[0054] For example, The mask body for edge saliency is as follows:
[0055]
[0056] in, For edge saliency mask, Based on the saliency mask of the basic edge, It is a symmetric repressor. It is a color suppression factor.
[0057] Furthermore, after obtaining the multi-scale gradient response, the multi-scale gradient response values are fused to obtain the crease response. If the crease response is greater than a preset crease response threshold, the crease response area is determined to be a candidate crease area; if the crease response is less than or equal to the preset crease response threshold, the crease response area is determined not to be a candidate crease area. The preset crease response threshold can be set according to the requirements for identifying the newness or oldness of the target paper sheet, and this application does not impose specific limitations on it.
[0058] Furthermore, after obtaining the candidate crease regions, the contrast of the candidate crease regions is extracted. As a crease loss feature. Preferably, the crease loss feature may further include the length of the crease candidate region. Straightness The specific settings can be configured according to the needs of identifying the newness or oldness of the target paper-like items; this application does not impose any specific limitations.
[0059] It should be understood that the depreciation of the target paper sheet may also include staining caused by liquid contamination and texture degradation caused by repeated use.
[0060] On the one hand, it should be noted that when identifying stain damage, due to the film coating on the surface of the target paper sheet, the surface of the target paper sheet usually only retains the outline of the stain damage or the light reflectivity of the attached film is reduced due to stains. Based on this, this application determines a reflectance map based on parallel polarization images and vertical polarization images; determines the reflectance difference value based on the reflectance map and a preset reflectance map; identifies areas with reflectance differences greater than the preset reflectance difference value as stain damage areas; extracts the texture features of the stain damage areas and obtains the texture feature difference value of each stain damage area; and determines the stain damage characteristics of the stain damage areas based on the reflectance difference value and the texture feature difference value.
[0061] Specifically, the diffuse reflection component and specular reflection component are obtained from the parallel polarization image and the vertical polarization image. Specifically:
[0062] in, This is a parallel polarization image. This is a vertically polarized image. For diffuse reflection component, For the specular reflection component, To preset the polarization angle, The polarizer angle refers to the angle of the polarizer in a polarizing camera, which can be either 0° or 90°.
[0063] Then, using the diffuse reflection component and the specular reflection component, the reflectance diagram is determined:
[0064]
[0065] in, The local reflectance at that location, For diffuse reflection component, For the specular reflection component, This is a constant term.
[0066] Then, the local reflectance is compared with the preset reflectance to obtain the reflectance difference. It should be understood that the local reflectance of each pixel can form a reflectance map, and the preset reflectances can form a preset reflectance difference. Simultaneously, local texture features are extracted from the vertically polarized image, and the extracted texture features are compared with preset texture feature values to obtain a texture feature difference value. The texture feature difference value can be calculated using LBP feature distance, and this application does not impose specific limitations on it.
[0067] By fusing the reflectance difference and texture feature difference values, we obtain:
[0068]
[0069] in, The stain wear characteristic is represented by N, where N is the number of stain wear areas. Let i be the reflectance difference of the i-th region. The difference in texture features for the i-th region. Let i be the area of the i-th region. This is the reflectance weight.
[0070] On the other hand, based on the parallel polarization image and the vertical polarization image, the texture degradation features are determined, including: determining the diffuse reflection component of the target paper sheet based on the parallel polarization image and the vertical polarization image; performing a four-level wavelet decomposition on the diffuse reflection component to obtain the wavelet coefficient matrix corresponding to each level of decomposition; and determining the texture degradation features of the target paper sheet based on the wavelet coefficient matrix and the corresponding preset wavelet coefficient matrix.
[0071] Specifically, the following formula can be used:
[0072]
[0073] in, This is a texture degradation feature. Let j be the wavelet coefficient matrix of the current target paper sheet. To pre-define the wavelet coefficient matrix of the j-th layer, Let the scale weight be the weight of the j-th layer. This represents the wavelet decomposition level.
[0074] Specifically, texture degradation features are used to characterize the overall wear degree of the target paper sheet surface. By performing a four-level wavelet decomposition on the diffuse reflection component, approximate components reflecting low-frequency information are obtained. Detail components that reflect high-frequency information Texture degradation differences are determined by comparing the j-th layer wavelet coefficient matrix with preset wavelet coefficients. The preset wavelet coefficient matrix is the wavelet coefficient matrix of the target paper sheet when it is in a new item state.
[0075] Step 104: Determine the newness assessment index of the target paper sheet based on the crease damage characteristic value, stain damage characteristic value, and texture degradation characteristic value.
[0076] Specifically, for any target paper sheet, the crease damage characteristic value, stain damage characteristic value, and texture degradation characteristic value can be normalized separately, and then the newness evaluation index of the target paper sheet can be determined by calculating the weight sum.
[0077] In some embodiments, the newness or oldness of the target paper sheet can be determined based on the threshold range corresponding to the newness or oldness assessment index. Then, the target paper sheet is alarmed and eliminated if it is greater than or equal to the elimination threshold. Other target paper sheet is classified according to the same newness or oldness for regrouping and packaging for later use. This application does not make any specific limitations.
[0078] In a preferred embodiment, the target paper sheet is also prone to bending at a large angle, such as being folded at a corner, or being bent entirely, such as curling the target paper sheet. Based on this, this application also proposes to use a laser scanning system to collect three-dimensional information data of the target paper sheet, so as to obtain depreciation information that cannot be obtained in two-dimensional images through laser scanning.
[0079] Specifically, the three-dimensional information data of the surface of the target paper sheet is acquired based on a laser scanning system; the surface height deviation of the target paper sheet is determined based on the three-dimensional information data; and the newness assessment index of the target paper sheet is determined based on the surface height deviation.
[0080] For example, after acquiring the three-dimensional information data, a surface fitting technique is used to fit the three-dimensional information data to obtain a height reference surface for the target paper sheet, thereby eliminating deviations caused by different paper thicknesses in the production of the target paper sheet. Then, based on the three-dimensional information data and the surface height reference surface, the surface height deviation is determined, and then the newness / oldness assessment index of the target paper sheet is determined based on the surface height deviation. For example, target paper sheets with a surface height deviation greater than a height threshold are directly identified as obsolete target paper sheets, or the newness / oldness assessment index of the target paper sheet can be determined based on the normalized weights of the surface height deviation, crease loss characteristic value, stain loss characteristic value, and texture degradation characteristic value. This application does not impose specific limitations.
[0081] In summary, the method for distinguishing the newness and oldness of paper sheet-like items proposed in this application acquires parallel polarized images and vertical polarized images of the target paper sheet-like item at a preset polarization angle based on a dual polarization camera system. Then, by calculating crease loss characteristics, stain loss characteristics, and texture degradation characteristics, the method can comprehensively determine the newness and oldness assessment index of the target paper sheet-like item. On the basis of solving the problem of severe loss of image acquisition information of the target paper sheet-like item, the method further improves the accuracy and reliability of the newness and oldness assessment index of the target paper sheet-like item through the comprehensive evaluation of multiple loss characteristics.
[0082] It should be noted that although the operation of the method of the present invention is described in a specific order in the accompanying drawings, this does not require or imply that the operations must be performed in that specific order, or that all of the operations shown must be performed in order to achieve the desired result.
[0083] Figure 2 A schematic diagram of a device for distinguishing between new and old paper sheet items according to an embodiment of this application is shown.
[0084] like Figure 2 As shown, the device 10 for distinguishing between new and old paper sheet items includes:
[0085] Image acquisition module 11 is used to acquire images of the target paper sheet based on the camera system;
[0086] The first loss feature acquisition module 12 is used to perform multi-scale linear feature detection on the acquired image to obtain crease loss feature values.
[0087] The second loss feature acquisition module 13 is used to determine the stain loss feature value and texture degradation feature value based on the acquired image;
[0088] Evaluation module 14 is used to determine the newness evaluation index of the target paper sheet based on the crease damage characteristic value, the stain damage characteristic value and the texture degradation characteristic value.
[0089] In some embodiments, the acquired image includes a vertically polarized image first loss feature acquisition module 12, specifically used for:
[0090] Multi-scale linear feature detection is performed on the vertically polarized image to obtain the multi-scale gradient response corresponding to each pixel.
[0091] The multi-scale gradient responses are fused to obtain the crease response corresponding to each pixel.
[0092] The region whose crease response is greater than a preset crease response threshold is designated as a crease candidate region.
[0093] Obtain the crease loss characteristics corresponding to the crease candidate region.
[0094] In some embodiments, the acquired image includes a vertically polarized image, and the second loss feature acquisition module 13 is specifically used for:
[0095] Based on the parallel polarization image and the vertical polarization image, determine the reflectance map;
[0096] The reflectance difference is determined based on the reflectance diagram and the preset reflectance diagram;
[0097] The area where the reflectance difference is greater than the preset reflectance difference is defined as the stain damage area;
[0098] Extract the texture features of the stained areas and obtain the texture feature difference values of each stained area;
[0099] The stain wear characteristics of the stain wear region are determined based on the reflectance difference and the texture feature difference.
[0100] In some embodiments, the acquired image includes a vertically polarized image, and the second loss feature acquisition module 13 is specifically used for:
[0101] The diffuse reflection component of the target paper sheet is determined based on the parallel polarization image and the vertical polarization image.
[0102] The diffuse reflection component is decomposed into four layers of wavelet coefficients to obtain the wavelet coefficient matrix corresponding to each layer of decomposition.
[0103] The texture degradation features of the target paper sheet are determined based on the wavelet coefficient matrix and the corresponding preset wavelet coefficient matrix.
[0104] In some embodiments, the image acquisition module 11 is further configured to:
[0105] The three-dimensional information data of the surface of the target paper sheet is obtained based on a laser scanning system;
[0106] Evaluation module 14 is also used for:
[0107] Based on the three-dimensional information data, determine the surface height deviation of the target paper sheet;
[0108] The newness / oldness assessment index of the target paper sheet is determined based on the surface height deviation.
[0109] In some embodiments, the image acquisition module 11 is further configured to:
[0110] Obtain the coating refractive index and polarization correction change of the target paper sheet;
[0111] The initial polarization angle is determined based on the refractive index of the coating and the refractive index of air;
[0112] The initial polarization angle is corrected using the polarization correction change to obtain the preset polarization angle.
[0113] It should be understood that the modules or modules described in device 10 for distinguishing between new and old paper sheet articles are related to the reference. Figure 1 The steps in the described method correspond accordingly. Therefore, the operations and features described above for the method are also applicable to the device 10 for distinguishing the newness of paper sheet items and the modules contained therein, and will not be repeated here. The device 10 for distinguishing the newness of paper sheet items can be pre-implemented in the browser or other security applications of an electronic device, or it can be loaded into the browser or its security applications of an electronic device through download or other means. The corresponding modules in the device 10 for distinguishing the newness of paper sheet items can cooperate with the modules in the electronic device to implement the solution of the embodiments of this application.
[0114] The division of modules or units mentioned in the detailed description above is not mandatory. In fact, according to the embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.
[0115] The following is for reference. Figure 3 , Figure 3 A schematic diagram of the structure of a computer system suitable for implementing the embodiments of this application is shown.
[0116] like Figure 3As shown, the computer system 300 includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 302 or programs loaded from storage section 308 into random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the system's operating instructions. The CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.
[0117] The following components are connected to I / O interface 305: an input section 306 including a keyboard, mouse, etc.; an output section 307 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN card, modem, etc. The communication section 309 performs communication processing via a network such as the Internet. Drive 310 is also connected to I / O interface 305 as needed. Removable media 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 310 as needed so that computer programs read from them can be installed into storage section 308 as needed.
[0118] Specifically, according to embodiments of this application, the flowchart above refers to... Figure 2 The described process can be implemented as a computer software program. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowchart. In such an embodiment, the computer program contains program code for performing the methods shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by central processing unit (CPU) 301, it performs the functions defined in the system of this application.
[0119] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.
[0120] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operational instructions of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two connected blocks may actually be executed substantially in parallel, or they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified functions or operational instructions, or using a combination of dedicated hardware and computer instructions.
[0121] The units or modules described in the embodiments of this application can be implemented in software or hardware. The described units or modules can also be housed in a processor; for example, a processor can be described as including an image acquisition module, a first loss feature acquisition module, a second loss feature acquisition module, and an evaluation module. The names of these units or modules do not necessarily limit the specific unit or module itself; for example, an image acquisition module can also be described as "acquiring images of a target paper sheet based on a camera system."
[0122] In another aspect, this application also provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments, or may exist independently and not assembled into the electronic device. The aforementioned computer-readable storage medium stores one or more programs that, when used by one or more processors, execute the method described in this application for distinguishing the newness of paper sheet-like articles.
[0123] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.
Claims
1. A method for distinguishing between new and old paper sheet-like items, characterized in that, include: The system uses a camera to acquire images of the target paper-like object. Multi-scale linear feature detection is performed on the acquired image to obtain crease loss feature values; Based on the acquired images, determine the stain wear characteristic value and texture degradation characteristic value; The newness assessment index of the target paper sheet is determined based on the crease damage characteristic value, the stain damage characteristic value, and the texture degradation characteristic value.
2. The method for distinguishing between new and old paper sheet items according to claim 1, characterized in that, The acquired image includes a vertically polarized image. Multi-scale linear feature detection is performed on the acquired image to obtain crease loss feature values, including: Multi-scale linear feature detection is performed on the vertically polarized image to obtain the multi-scale gradient response corresponding to each pixel. The multi-scale gradient responses are fused to obtain the crease response corresponding to each pixel. The region whose crease response is greater than a preset crease response threshold is designated as a crease candidate region. Obtain the crease loss characteristics corresponding to the crease candidate region.
3. The method for distinguishing between new and old paper sheet items according to claim 1, characterized in that, The acquired images include parallel polarization images and vertical polarization images. Determining stain wear characteristics based on the acquired images includes: Based on the parallel polarization image and the vertical polarization image, determine the reflectance map; The reflectance difference is determined based on the reflectance diagram and the preset reflectance diagram; The area where the reflectance difference is greater than the preset reflectance difference is defined as the stain damage area; Extract the texture features of the stained areas and obtain the texture feature difference values of each stained area; The stain wear characteristics of the stain wear region are determined based on the reflectance difference and the texture feature difference.
4. The method for distinguishing between new and old paper sheet items according to claim 1, characterized in that, The acquired images include parallel polarization images and vertical polarization images. Determining texture degradation features based on the acquired images includes: The diffuse reflection component of the target paper sheet is determined based on the parallel polarization image and the vertical polarization image. The diffuse reflection component is decomposed into four layers of wavelet coefficients to obtain the wavelet coefficient matrix corresponding to each layer of decomposition. The texture degradation features of the target paper sheet are determined based on the wavelet coefficient matrix and the corresponding preset wavelet coefficient matrix.
5. The method for distinguishing between new and old paper sheet items according to claim 1, characterized in that, Also includes: The three-dimensional information data of the surface of the target paper sheet is obtained based on a laser scanning system; Based on the three-dimensional information data, determine the surface height deviation of the target paper sheet; The newness / oldness assessment index of the target paper sheet is determined based on the surface height deviation.
6. The method for distinguishing between new and old paper sheet items according to claim 1, characterized in that, Also includes: Obtain the coating refractive index and polarization correction change of the target paper sheet; The initial polarization angle is determined based on the refractive index of the coating and the refractive index of air; The initial polarization angle is corrected using the polarization correction change to obtain the preset polarization angle.
7. A device for distinguishing between new and old paper sheet-like articles, characterized in that, include: The image acquisition module is used to acquire images of the target paper sheet based on the camera system; The first loss feature acquisition module is used to perform multi-scale linear feature detection on the acquired image to obtain crease loss feature values; The second loss feature acquisition module is used to determine the stain loss feature value and texture degradation feature value based on the acquired image; The evaluation module is used to determine the newness evaluation index of the target paper sheet based on the crease damage characteristic value, the stain damage characteristic value and the texture degradation characteristic value.
8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method for distinguishing between new and old paper sheet items as described in any one of claims 1-6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the method for distinguishing between new and old paper sheet items as described in any one of claims 1-6.
10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the method for distinguishing between new and old paper sheet articles as described in any one of claims 1-6.