A ceramic identification method based on the Internet of Things

Abstract

The present invention relates to a ceramic identification method based on the Internet of Things, including: collecting images of the surface of ceramic products; determining the material, shape and size of the ceramics, and preliminarily determining the age and origin of the ceramics; selecting corresponding feature points to collect coordinates to collect the surface texture of the ceramics; retrieving corresponding texture features from the cloud Internet of Things to determine the authenticity of the ceramics; detecting cracks on the surface of the ceramics and determining the etching time of the cracks; and generating an identification report. The present invention connects an identifier to the Internet of Things. After the identifier has detected the material crystal phase of the ceramic product to be identified, the identifier can directly retrieve from the cloud Internet of Things to quickly determine the origin and age of the ceramic product to be identified. By determining the origin and age of the ceramic product to be identified, it can be used as a reference in subsequent identification, thereby improving the identification accuracy of the identifier and improving the identification efficiency of the method.

Description

Technical Field

[0001] The present invention relates to the technical field of ceramic identification, and in particular to a ceramic identification method based on the Internet of Things. Background Art

[0002] The invention and firing of ancient Chinese ceramics laid a solid foundation for human civilization all over the world. Due to the historical culture and non-renewable scarcity of ancient ceramics, they have become important collections sought after by people. Many ancient ceramics have become rare and valuable treasures. In order to pursue profits, the trend of imitating ancient styles began in the Song Dynasty, and has developed into a huge industry in recent decades.

[0003] Cultural relics are valuable remains of human history and culture. Various types of cultural relics reflect the social activities, social relations, ideology, and the use and transformation of nature and the ecological environment of human beings in various historical periods from different perspectives. These are all precious historical and cultural heritage of mankind. Cultural relics are produced in a certain historical environment. In the development and changes of nature and history, they will undergo various changes. Some are even difficult to recognize, which makes it very difficult for people to understand their age and value. Especially in human history, people have made a large number of replicas or counterfeits of cultural relics for various purposes. Among the "cultural relics" we encounter, there are often true and false, and good and bad. There are also some cultural relics whose original appearance has been covered up in the long years of change, and it is difficult for people to correctly understand them. Therefore, before using cultural relics, the most important task is identification. Cultural relic identification is the foundation and technical prerequisite for cultural relic management workers.

[0004] As cultural relics have high historical and cultural heritage value and economic and ornamental value, more and more people buy and collect cultural relics, resulting in a large number of fakes and forgeries flooding the market. Therefore, the identification of cultural relics has received more and more attention from all walks of life. The authenticity of cultural relics can be identified because cultural relics produced under certain historical conditions cannot exist without the form of time and cannot be reproduced.

[0005] The identification of ceramic cultural relics generally includes the type, kiln site and era of the ceramics; the traditional method of identifying ceramic cultural relics is generally based on empirical visual inspection, which relies on the experience accumulated by people in long-term research and identification of ceramic cultural relics since ancient times, and examines the apparent characteristics of ceramics by comparison, classification and other methods. This identification method has high requirements on the experience and experience of the appraiser, and the appraiser needs a long period of self-learning. Despite this, it is sometimes blinded by modern high-tech means. The reliability and accuracy of the identification have been challenged by more and more high-quality imitations.

[0006] At present, counterfeits are flooding the entire market. Whether it is antique cities in various places or the auction industry, there is a phenomenon of rampant counterfeits. The method of identifying the authenticity of ancient ceramics is generally to use manual eye identification, which is mainly based on the master teaching the apprentice and relying on the recognition and memory of ancient ceramic standard parts. When identifying the authenticity of ceramics, the identifier calls out the standard from the memory to compare with the identified product, and this comparison is originally scientific. However, errors sometimes occur in human brain memory and calling out brain memory, and each apprentice's memory, eyesight, and comparison ability are limited. In addition, since eye identification is usually conceptual and not quantified, when identifying the same piece of porcelain, some people identify it as authentic, while others identify it as a counterfeit. Moreover, the same person may identify the same piece of porcelain as authentic at this time and a counterfeit at that time when identifying it at different time periods. Therefore, the identification errors caused by manual authenticity identification make people at a loss. This is a problem existing in the current traditional identification of ancient ceramics.

[0007] There are already devices for identifying ceramic products in the prior art. However, the above devices all use modern detection methods and are unable to accurately detect the kiln site and age of the ceramics. Therefore, although the material composition of the ceramics can be determined, due to the lack of reference to the kiln site and age, the authenticity of the ceramics cannot be accurately determined, and the identification efficiency is low. Summary of the invention

[0008] To this end, the present invention provides a ceramic identification method based on the Internet of Things to overcome the problem of low identification efficiency caused by the inability to detect the origin and age of ceramic products in the prior art.

[0009] To achieve the above object, the present invention provides a ceramic identification method based on the Internet of Things, comprising:

[0010] Step 1: Use a high-definition camera to collect images of the surface of the ceramic product to be identified;

[0011] Step 2: The identifier determines the material, shape and size of the ceramic product to be identified based on the image captured by the high-definition camera. The identifier uses the cloud Internet of Things to search to preliminarily determine the preparation age and origin of the ceramic product to be identified;

[0012] Step 3: The identifier selects corresponding feature points according to the origin of the ceramic product to be identified and collects coordinates. After the selection is completed, the identifier collects texture features of the surface of the ceramic product to be identified from the specified position in the image;

[0013] Step 4: The identification device retrieves the texture features corresponding to the preparation year and origin from the cloud IoT to compare with the texture features actually collected, and determines the authenticity of the ceramic to be identified based on the determination result;

[0014] Step 5: The identifier detects cracks on the surface of the ceramic product to be identified from the image and identifies etching marks on the cracks. The identifier uses the cloud-based Internet of Things to retrieve the etching marks to determine the time when the cracks were generated;

[0015] Step 6: After the determination is completed, the identification device generates an identification report for the ceramic product to be identified;

[0016] The cloud-based Internet of Things pre-stores a preset material crystal phase matrix R0 and a preset origin matrix L0; for the preset material crystal phase matrix R0, R0 (R1, R2, R3...Rn), wherein R1 is the first preset material crystal phase, R2 is the second preset material crystal phase, R3 is the third preset material crystal phase, and Rn is the nth preset material crystal phase; for the preset origin matrix L0, L0 (L1, L2, L3...Ln), wherein L1 is the first preset origin, L2 is the second preset origin, L3 is the third preset origin, and Ln is the nth preset origin; when the high-definition camera captures an image of the ceramic product to be identified, the identifier controls the crystal phase detector to detect the surface of the ceramic product to be identified to determine the crystal phase R of the material of the ceramic product to be identified. After the determination is completed, the identifier determines the origin of the ceramic product to be identified:

[0017] When the crystal phase R of the material of the ceramic product to be identified has the highest similarity to the crystal phase R1 of the first preset material in the R0 matrix, the identification device determines that the origin of the ceramic product to be identified is L1;

[0018] When the crystal phase R of the material of the ceramic product to be identified has the highest similarity to the crystal phase R2 of the second preset material in the R0 matrix, the identification device determines that the origin of the ceramic product to be identified is L2;

[0019] When the crystal phase R of the ceramic product to be identified has the highest similarity to the crystal phase R3 of the third preset material in the R0 matrix, the identification device determines that the origin of the ceramic product to be identified is L3;

[0020] When the crystal phase R of the ceramic product to be identified has the highest crystal phase similarity with the crystal phase Rn of the nth preset material in the R0 matrix, the identification device determines that the origin of the ceramic product to be identified is Ln;

[0021] The cloud-based Internet of Things also stores a preset size coefficient matrix group C0 (C1, C2, C3...Cn), wherein C1 is the first preset origin size coefficient matrix, C2 is the second preset origin size coefficient matrix, C3 is the third preset origin size coefficient matrix, and Cn is the nth preset origin size coefficient matrix; for the nth preset origin size coefficient matrix Cn, Cn (Cn1, Cn2, Cn3...Cni), wherein Cn1 is the first-generation preset size coefficient of the nth preset origin, Cn2 is the second-generation preset size coefficient of the nth preset origin, Cn3 is the third-generation preset size coefficient of the nth preset origin, and Cni is the i-th generation preset size coefficient of the nth preset origin;

[0022] When the identifier determines that the origin of the ceramic product to be identified is L1, the identifier selects the C1 matrix from the C0 matrix group as a basis for determining the preparation age of the ceramic product to be identified;

[0023] When the identifier determines that the origin of the ceramic product to be identified is L2, the identifier selects the C2 matrix from the C0 matrix group as a basis for determining the preparation age of the ceramic product to be identified;

[0024] When the identifier determines that the origin of the ceramic product to be identified is L3, the identifier selects the C3 matrix from the C0 matrix group as a basis for determining the preparation age of the ceramic product to be identified;

[0025] When the identification device determines that the origin of the ceramic product to be identified is Ln, the identification device selects the Cn matrix from the C0 matrix group as a basis for determining the preparation age of the ceramic product to be identified;

[0026] The cloud Internet of Things also stores a preset preparation age matrix group B0 (B1, B2, B3, Bn), wherein B1 is the preset preparation age matrix of the first preset origin, B2 is the preset preparation age matrix of the second preset origin, B3 is the preset preparation age matrix of the third preset origin, and Bn is the preset preparation age matrix of the nth preset origin; for the preset preparation age matrix Bn of the nth preset origin, Bn (Bn1, Bn2, Bn3...Bni), wherein Bn1 is the first preset preparation age of the nth preset origin, Bn2 is the second preset preparation age of the nth preset origin, Bn3 is the third preset preparation age of the nth preset origin, and Bni is the i-th preset preparation age of the nth preset origin;

[0027] When detecting the size of the ceramic product to be identified, the identifier establishes a detection size matrix K (H, S, D), wherein H is the height of the ceramic product to be identified, S is the edge curvature of the ceramic product to be identified, and D is the average thickness of the ceramic product to be identified; after the establishment is completed, the identifier calculates the size coefficient C of the ceramic product to be identified. After the calculation is completed, the identifier selects the corresponding preset size coefficient from the C0 matrix group according to the determined origin of the ceramic product to be identified; when the identifier determines that the origin of the ceramic product to be identified is Ln, the identifier selects the Cn matrix from the C0 matrix group as the determination basis for the preparation age of the ceramic product to be identified to determine the preparation age of the ceramic product to be identified:

[0028] When the deviation between the size coefficient C of the ceramic product to be identified and Cn1 in the Cn matrix is ​​the smallest, the identification device determines that the preparation age of the ceramic product to be identified is Bn1;

[0029] When the deviation between the size coefficient C of the ceramic product to be identified and Cn2 in the Cn matrix is ​​the smallest, the identification device determines that the preparation age of the ceramic product to be identified is Bn2;

[0030] When the deviation between the size coefficient C of the ceramic product to be identified and Cn3 in the Cn matrix is ​​the smallest, the identification device determines that the preparation age of the ceramic product to be identified is Bn3;

[0031] When the deviation between the size coefficient C of the ceramic product to be identified and Cni in the Cn matrix is ​​the smallest, the identification device determines that the preparation age of the ceramic product to be identified is Bni;

[0032] The cloud Internet of Things also stores a preset texture detection point coordinate matrix group X0 (X1, X2, X3...Xn), wherein X1 is the preset texture detection point coordinate matrix of the first origin, X2 is the preset texture detection point coordinate matrix of the second origin, X3 is the preset texture detection point coordinate matrix of the third origin, and Xn is the preset texture detection point coordinate matrix of the nth origin; for the nth preset texture detection point coordinate matrix Xn, Xn (Xn1, Xn2, Xn3...Xni), wherein Xn1 is the preset texture detection point coordinate of the nth origin in the first generation, Xn2 is the preset texture detection point coordinate of the nth origin in the second generation, Xn3 is the preset texture detection point coordinate of the nth origin in the third generation, and Xni is the preset texture detection point coordinate of the nth origin in the ith generation;

[0033] When the identifier determines the origin Ln and the production year Bni of the ceramic product to be identified, the identifier selects Xni coordinates from the Xn matrix as the texture feature collection coordinates for the ceramic product to be identified.

[0034] Further, when the identifier completes the determination of the origin Ln and the preparation age Bni of the ceramic product to be identified, the identifier retrieves the outer wall texture features of the ceramics fired in the corresponding region in the corresponding age from the cloud Internet of Things and establishes a corresponding texture feature determination matrix Wni0 (Wni1, Wni2, Wni3...Wnij), wherein Wni1 is the first texture determination feature of the Ln origin Bni age, Wni2 is the second texture determination feature of the Ln origin Bni age, Wni3 is the third texture determination feature of the Ln origin Bni age, and Wnij is the jth texture determination feature of the Ln origin Bni age;

[0035] When the identifier determines that the ceramic product to be identified is a product produced in the nth production area in the i-th generation and the identifier determines the authenticity of the ceramic product to be identified, the identifier extracts the surface texture feature W of the ceramic product to be identified from the specified coordinates and compares W with each texture determination feature in the texture feature determination matrix Wni0:

[0036] When the similarity of each parameter in the W and Wni0 matrices is less than 85%, the identifier determines that the ceramic product to be identified is a counterfeit;

[0037] When the similarity between at least one parameter in the W and Wni0 matrices is higher than 90%, the identifier determines that the ceramic product to be identified is authentic;

[0038] When the similarity of multiple parameters in the W and Wni0 matrices is higher than 85%, the identifier determines that the ceramic product to be identified is authentic.

[0039] Furthermore, the cloud IoT also stores a preset etching degree K0 and a preset etching time T0; for the preset etching degree K0, K0 (K1, K2, K3, K4), wherein K1 is the first preset etching degree, K2 is the second preset etching degree, K3 is the third preset etching degree, K4 is the fourth preset etching degree, and each etching degree increases gradually in sequence; for the preset etching time T0, T0 (T1, T2, T3, T4), wherein T1 is the first preset etching time, T2 is the second preset etching time, T3 is the third preset etching time, T4 is the fourth preset etching time, and each etching time value increases gradually in sequence;

[0040] When the identifier identifies the etching marks on the surface cracks of the ceramic product to be identified, the identifier detects the etching degree K of the cracks and compares K with the parameters in the K0 matrix:

[0041] When K≤K1, the identifier determines that the etching occurred at a time T1 from now;

[0042] When K1<K≤K2, the identifier determines that the etching occurred at a time T2 from now;

[0043] When K2<K≤K3, the identifier determines that the etching occurred at a time T3 from now;

[0044] When K3<K≤K4, the identifier determines that the etching occurred at time T4 from now.

[0045] Furthermore, after the identification is completed, the identifier generates an identification result matrix A (H, S, D, R, L, B, X, W, Y / N, K, T), wherein H is the height of the ceramic product to be identified, S is the edge curvature of the ceramic product to be identified, D is the average thickness of the ceramic product to be identified, R is the material crystal phase of the ceramic product to be identified, L is the origin of the ceramic product to be identified, B is the preparation age of the ceramic product to be identified, X is the coordinate point when the identifier collects texture features, W is the texture features collected by the identifier, Y / N is the identification result of the identifier on whether the ceramic product to be identified is authentic, K is the etching degree of the surface cracks of the ceramic product to be identified, and T is the etching time of the surface cracks of the ceramic product to be identified; when the identifier determines that the ceramic product to be identified is authentic, Y / N is Y, and when the identifier determines that the ceramic product to be identified is a counterfeit, Y / N is N.

[0046] Compared with the prior art, the beneficial effect of the present invention lies in that the present invention connects the identifier to the Internet of Things. After the identifier detects the material crystal phase of the ceramic product to be identified, the identifier can directly retrieve from the cloud-based Internet of Things to quickly determine the origin of the ceramic product to be identified; after the identifier detects the size of the ceramic product to be identified, it will calculate the size coefficient of the ceramic product to be identified based on the detected size and select the corresponding preset size coefficient matrix based on the determined origin, and compare the size coefficient of the ceramic product to be identified with the parameters in the preset size coefficient matrix to determine the age of the ceramic product to be identified. By determining the origin and age of the ceramic product to be identified, it can be used as a reference in subsequent identification, thereby improving the identification accuracy of the identifier and improving the identification efficiency of the method.

[0047] Furthermore, after pre-determining the origin and age of the ceramic product to be identified, the method further determines the surface texture of the ceramic product to be identified, which can effectively improve the identification accuracy of the identifier, thereby further improving the identification efficiency of the method.

[0048] Furthermore, the cloud-based Internet of Things pre-stores a preset material crystal phase matrix R0 (R1, R2, R3...Rn) and a preset origin matrix L0 (L1, L2, L3...Ln). By detecting the material crystal phase R of the ceramic product to be identified and comparing R with the parameters in the R0 matrix to determine the origin of the ceramic product to be identified, the origin of the ceramic product to be identified can be accurately determined, thereby further improving the identification efficiency of the method.

[0049] Furthermore, the cloud-based Internet of Things also stores a preset size coefficient matrix group C0 (C1, C2, C3...Cn). For the nth preset origin size coefficient matrix Cn, Cn (Cn1, Cn2, Cn3...Cni), when the identifier completes the determination of the origin Ln of the ceramic product to be identified, the identifier will select the corresponding preset size coefficient matrix Cn from the C0 matrix to determine the ceramic product to be identified; at the same time, when the identifier completes the height H, edge curvature S and average thickness D of the ceramic product to be identified, it uses the formula The size coefficient C of the ceramic product to be identified is calculated and C is compared with the parameters in the corresponding Cn matrix to determine the age Bni of the ceramic product to be identified. By selecting different judgment criteria according to different origins, the identification accuracy of the identification device for the age of the ceramic product to be identified can be further improved, thereby further improving the identification efficiency of the method.

[0050] Furthermore, the cloud-based Internet of Things also stores a preset texture detection point coordinate matrix group X0 (X1, X2, X3...Xn). For the nth preset texture detection point coordinate matrix Xn, Xn (Xn1, Xn2, Xn3...Xni), the identifier will select the corresponding detection point coordinate matrix Xn and detection matrix coordinate Xni in turn according to the origin Ln and the age Bni. By using the dual retrieval of origin and age to determine the detection coordinates, the identifier can select the most representative detection points for ceramics of different origins and ages, thereby completing the efficient identification of the ceramic products to be identified, and further improving the identification efficiency of the method.

[0051] Furthermore, when the identifier completes the determination of the origin Ln and the preparation year Bni of the ceramic product to be identified, the identifier retrieves the outer wall texture features of the ceramics fired in the corresponding region in the corresponding year from the cloud-based Internet of Things and establishes a corresponding texture feature determination matrix Wni0 (Wni1, Wni2, Wni3...Wnij). By selecting the most representative texture features from the cloud-based Internet of Things as the determination basis, the identification accuracy of the identifier can be further improved, thereby further improving the identification efficiency of the method.

[0052] Furthermore, the cloud-based Internet of Things also stores a preset etching degree K0 (K1, K2, K3, K4) and a preset etching time T0 (T1, T2, T3, T4). By detecting the etching degree of the crack to determine the etching time of the crack, the etching time can be used as a basis for identification, thereby further improving the identification efficiency of the method.

[0053] Furthermore, after the identification is completed, the identifier generates an identification result matrix A (H, S, D, R, L, B, X, W, Y / N, K, T). By outputting the identification results, the specific process of the identification can be observed more intuitively, thereby further improving the identification efficiency of the method. DETAILED DESCRIPTION

[0054] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0055] The present invention provides a ceramic identification method based on the Internet of Things, comprising the following steps:

[0056] Step 1: Use a high-definition camera to collect images of the surface of the ceramic product to be identified;

[0057] Step 2: The identifier determines the material, shape and size of the ceramic product to be identified based on the image captured by the high-definition camera. The identifier uses the cloud Internet of Things to search to preliminarily determine the preparation age and origin of the ceramic product to be identified;

[0058] Step 3: The identifier selects corresponding feature points according to the origin of the ceramic product to be identified and collects coordinates. After the selection is completed, the identifier collects texture features of the surface of the ceramic product to be identified from the specified position in the image;

[0059] Step 4: The identification device retrieves the texture features corresponding to the preparation year and origin from the cloud IoT to compare with the texture features actually collected, and determines the authenticity of the ceramic to be identified based on the determination result;

[0060] Step 5: The identifier detects cracks on the surface of the ceramic product to be identified from the image and identifies etching marks on the cracks. The identifier uses the cloud-based Internet of Things to retrieve the etching marks to determine the time when the cracks were generated;

[0061] Step 6: After the determination is completed, the identification device generates an identification report for the ceramic product to be identified.

[0062] Specifically, the cloud IoT pre-stores a preset material crystal phase matrix R0 and a preset origin matrix L0; for the preset material crystal phase matrix R0, R0 (R1, R2, R3...Rn), wherein R1 is the first preset material crystal phase, R2 is the second preset material crystal phase, R3 is the third preset material crystal phase, and Rn is the nth preset material crystal phase; for the preset origin matrix L0, L0 (L1, L2, L3...Ln), wherein L1 is the first preset origin, L2 is the second preset origin, L3 is the third preset origin, and Ln is the nth preset origin; when the high-definition camera captures an image of the ceramic product to be identified, the identifier controls the crystal phase detector to detect the surface of the ceramic product to be identified to determine the crystal phase R of the material of the ceramic product to be identified. After the determination is completed, the identifier determines the origin of the ceramic product to be identified:

[0063] When the crystal phase R of the material of the ceramic product to be identified has the highest similarity to the crystal phase R1 of the first preset material in the R0 matrix, the identification device determines that the origin of the ceramic product to be identified is L1;

[0064] When the crystal phase R of the material of the ceramic product to be identified has the highest similarity to the crystal phase R2 of the second preset material in the R0 matrix, the identification device determines that the origin of the ceramic product to be identified is L2;

[0065] When the crystal phase R of the ceramic product to be identified has the highest similarity to the crystal phase R3 of the third preset material in the R0 matrix, the identification device determines that the origin of the ceramic product to be identified is L3;

[0066] When the crystal phase R of the material of the ceramic product to be identified has the highest similarity to the crystal phase Rn of the nth preset material in the R0 matrix, the identifier determines that the origin of the ceramic product to be identified is Ln.

[0067] Specifically, the cloud-based Internet of Things also stores a preset size coefficient matrix group C0 (C1, C2, C3...Cn), wherein C1 is the first preset origin size coefficient matrix, C2 is the second preset origin size coefficient matrix, C3 is the third preset origin size coefficient matrix, and Cn is the nth preset origin size coefficient matrix; for the nth preset origin size coefficient matrix Cn, Cn (Cn1, Cn2, Cn3...Cni), wherein Cn1 is the first-generation preset size coefficient of the nth preset origin, Cn2 is the second-generation preset size coefficient of the nth preset origin, Cn3 is the third-generation preset size coefficient of the nth preset origin, and Cni is the i-th generation preset size coefficient of the nth preset origin;

[0068] When the identifier determines that the origin of the ceramic product to be identified is L1, the identifier selects the C1 matrix from the C0 matrix group as a basis for determining the preparation age of the ceramic product to be identified;

[0069] When the identifier determines that the origin of the ceramic product to be identified is L2, the identifier selects the C2 matrix from the C0 matrix group as a basis for determining the preparation age of the ceramic product to be identified;

[0070] When the identifier determines that the origin of the ceramic product to be identified is L3, the identifier selects the C3 matrix from the C0 matrix group as a basis for determining the preparation age of the ceramic product to be identified;

[0071] When the identifier determines that the origin of the ceramic product to be identified is Ln, the identifier selects the Cn matrix from the C0 matrix group as a basis for determining the preparation age of the ceramic product to be identified.

[0072] Specifically, the cloud-based Internet of Things also stores a preset preparation age matrix group B0 (B1, B2, B3, Bn), wherein B1 is the preset preparation age matrix of the first preset origin, B2 is the preset preparation age matrix of the second preset origin, B3 is the preset preparation age matrix of the third preset origin, and Bn is the preset preparation age matrix of the nth preset origin; for the preset preparation age matrix Bn of the nth preset origin, Bn (Bn1, Bn2, Bn3...Bni), wherein Bn1 is the first preset preparation age of the nth preset origin, Bn2 is the second preset preparation age of the nth preset origin, Bn3 is the third preset preparation age of the nth preset origin, and Bni is the i-th preset preparation age of the nth preset origin.

[0073] Specifically, when detecting the size of the ceramic product to be identified, the identifier establishes a detection size matrix K (H, S, D), wherein H is the height of the ceramic product to be identified, S is the edge curvature of the ceramic product to be identified, and D is the average thickness of the ceramic product to be identified; after the establishment is completed, the identifier calculates the size coefficient C of the ceramic product to be identified, After the calculation is completed, the identifier selects the corresponding preset size coefficient from the C0 matrix group according to the determined origin of the ceramic product to be identified; when the identifier determines that the origin of the ceramic product to be identified is Ln, the identifier selects the Cn matrix from the C0 matrix group as the determination basis for the preparation age of the ceramic product to be identified to determine the preparation age of the ceramic product to be identified:

[0074] When the deviation between the size coefficient C of the ceramic product to be identified and Cn1 in the Cn matrix is ​​the smallest, the identification device determines that the preparation age of the ceramic product to be identified is Bn1;

[0075] When the deviation between the size coefficient C of the ceramic product to be identified and Cn2 in the Cn matrix is ​​the smallest, the identification device determines that the preparation age of the ceramic product to be identified is Bn2;

[0076] When the deviation between the size coefficient C of the ceramic product to be identified and Cn3 in the Cn matrix is ​​the smallest, the identification device determines that the preparation age of the ceramic product to be identified is Bn3;

[0077] When the deviation value between the size coefficient C of the ceramic product to be identified and Cni in the Cn matrix is ​​the smallest, the identifier determines that the preparation age of the ceramic product to be identified is Bni.

[0078] Specifically, the cloud-based Internet of Things also stores a preset texture detection point coordinate matrix group X0 (X1, X2, X3...Xn), wherein X1 is the preset texture detection point coordinate matrix of the first origin, X2 is the preset texture detection point coordinate matrix of the second origin, X3 is the preset texture detection point coordinate matrix of the third origin, and Xn is the preset texture detection point coordinate matrix of the nth origin; for the nth preset texture detection point coordinate matrix Xn, Xn (Xn1, Xn2, Xn3...Xni), wherein Xn1 is the preset texture detection point coordinate of the nth origin in the first generation, Xn2 is the preset texture detection point coordinate of the nth origin in the second generation, Xn3 is the preset texture detection point coordinate of the nth origin in the third generation, and Xni is the preset texture detection point coordinate of the nth origin in the ith generation;

[0079] When the identifier determines the origin Ln and the production year Bni of the ceramic product to be identified, the identifier selects Xni coordinates from the Xn matrix as the texture feature collection coordinates for the ceramic product to be identified.

[0080] Specifically, when the identifier completes the determination of the origin Ln and the preparation age Bni of the ceramic product to be identified, the identifier retrieves the outer wall texture features of the ceramics fired in the corresponding region in the corresponding age from the cloud Internet of Things and establishes the corresponding texture feature determination matrix Wni0 (Wni1, Wni2, Wni3...Wnij), wherein Wni1 is the first texture determination feature of the Ln origin Bni age, Wni2 is the second texture determination feature of the Ln origin Bni age, Wni3 is the third texture determination feature of the Ln origin Bni age, and Wnij is the jth texture determination feature of the Ln origin Bni age;

[0081] When the identifier determines that the ceramic product to be identified is a product produced in the nth production area in the i-th generation and the identifier determines the authenticity of the ceramic product to be identified, the identifier extracts the surface texture feature W of the ceramic product to be identified from the specified coordinates and compares W with each texture determination feature in the texture feature determination matrix Wni0:

[0082] When the similarity of each parameter in the W and Wni0 matrices is less than 85%, the identifier determines that the ceramic product to be identified is a counterfeit;

[0083] When the similarity between at least one parameter in the W and Wni0 matrices is higher than 90%, the identifier determines that the ceramic product to be identified is authentic;

[0084] When the similarity of multiple parameters in the W and Wni0 matrices is higher than 85%, the identifier determines that the ceramic product to be identified is authentic.

[0085] Specifically, the cloud IoT also stores a preset etching degree K0 and a preset etching time T0; for the preset etching degree K0, K0 (K1, K2, K3, K4), wherein K1 is the first preset etching degree, K2 is the second preset etching degree, K3 is the third preset etching degree, K4 is the fourth preset etching degree, and each etching degree increases gradually in sequence; for the preset etching time T0, T0 (T1, T2, T3, T4), wherein T1 is the first preset etching time, T2 is the second preset etching time, T3 is the third preset etching time, T4 is the fourth preset etching time, and each etching time value increases gradually in sequence;

[0086] When the identifier identifies the etching marks on the surface cracks of the ceramic product to be identified, the identifier detects the etching degree K of the cracks and compares K with the parameters in the K0 matrix:

[0087] When K≤K1, the identifier determines that the etching occurred at a time T1 from now;

[0088] When K1<K≤K2, the identifier determines that the etching occurred at a time T2 from now;

[0089] When K2<K≤K3, the identifier determines that the etching occurred at a time T3 from now;

[0090] When K3<K≤K4, the identifier determines that the etching occurred at time T4 from now.

[0091] Specifically, after the identification is completed, the identifier generates an identification result matrix A (H, S, D, R, L, B, X, W, Y / N, K, T), wherein H is the height of the ceramic product to be identified, S is the edge curvature of the ceramic product to be identified, D is the average thickness of the ceramic product to be identified, R is the material crystal phase of the ceramic product to be identified, L is the origin of the ceramic product to be identified, B is the preparation age of the ceramic product to be identified, X is the coordinate point when the identifier collects texture features, W is the texture features collected by the identifier, Y / N is the identification result of the identifier on whether the ceramic product to be identified is authentic, K is the etching degree of the surface cracks of the ceramic product to be identified, and T is the etching time of the surface cracks of the ceramic product to be identified; when the identifier determines that the ceramic product to be identified is authentic, Y / N is Y, and when the identifier determines that the ceramic product to be identified is a counterfeit, Y / N is N.

[0092] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments, but it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0093] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A ceramic identification method based on the Internet of Things, characterized in that: include: Step 1: Use a high-definition camera to collect images of the surface of the ceramic product to be identified; Step 2: The identifier determines the material, shape and size of the ceramic product to be identified based on the image captured by the high-definition camera. The identifier uses the cloud Internet of Things to search to preliminarily determine the preparation age and origin of the ceramic product to be identified; Step 3: The identifier selects corresponding feature points according to the origin of the ceramic product to be identified and collects coordinates. After the selection is completed, the identifier collects texture features of the surface of the ceramic product to be identified from the specified position in the image; Step 4: The identification device retrieves the texture features corresponding to the preparation year and origin from the cloud IoT to compare with the texture features actually collected, and determines the authenticity of the ceramic to be identified based on the determination result; Step 5: The identifier detects cracks on the surface of the ceramic product to be identified from the image and identifies etching marks on the cracks. The identifier uses the cloud-based Internet of Things to retrieve the etching marks to determine the time when the cracks were generated; Step 6: After the determination is completed, the identification device generates an identification report for the ceramic product to be identified; The cloud-based Internet of Things pre-stores a preset material crystal phase matrix R0 and a preset origin matrix L0; for the preset material crystal phase matrix R0, R0 (R1, R2, R3...Rn), wherein R1 is the first preset material crystal phase, R2 is the second preset material crystal phase, R3 is the third preset material crystal phase, and Rn is the nth preset material crystal phase; for the preset origin matrix L0, L0 (L1, L2, L3...Ln), wherein L1 is the first preset origin, L2 is the second preset origin, L3 is the third preset origin, and Ln is the nth preset origin; when the high-definition camera captures an image of the ceramic product to be identified, the identifier controls the crystal phase detector to detect the surface of the ceramic product to be identified to determine the crystal phase R of the material of the ceramic product to be identified. After the determination is completed, the identifier determines the origin of the ceramic product to be identified: When the crystal phase R of the material of the ceramic product to be identified has the highest similarity to the crystal phase R1 of the first preset material in the R0 matrix, the identifier determines that the origin of the ceramic product to be identified is L1; When the crystal phase R of the material of the ceramic product to be identified has the highest similarity with the crystal phase R2 of the second preset material in the R0 matrix, the identification device determines that the origin of the ceramic product to be identified is L2; When the crystal phase R of the material of the ceramic product to be identified has the highest similarity to the crystal phase R3 of the third preset material in the R0 matrix, the identification device determines that the origin of the ceramic product to be identified is L3; When the crystal phase R of the ceramic product to be identified has the highest crystal phase similarity with the crystal phase Rn of the nth preset material in the R0 matrix, the identification device determines that the origin of the ceramic product to be identified is Ln; The cloud-based Internet of Things also stores a preset size coefficient matrix group C0 (C1, C2, C3...Cn), wherein C1 is the first preset origin size coefficient matrix, C2 is the second preset origin size coefficient matrix, C3 is the third preset origin size coefficient matrix, and Cn is the nth preset origin size coefficient matrix; for the nth preset origin size coefficient matrix Cn, Cn (Cn1, Cn2, Cn3...Cni), wherein Cn1 is the first-generation preset size coefficient of the nth preset origin, Cn2 is the second-generation preset size coefficient of the nth preset origin, Cn3 is the third-generation preset size coefficient of the nth preset origin, and Cni is the i-th generation preset size coefficient of the nth preset origin; When the identifier determines that the origin of the ceramic product to be identified is L1, the identifier selects the C1 matrix from the C0 matrix group as a basis for determining the preparation age of the ceramic product to be identified; When the identifier determines that the origin of the ceramic product to be identified is L2, the identifier selects the C2 matrix from the C0 matrix group as a basis for determining the preparation age of the ceramic product to be identified; When the identifier determines that the origin of the ceramic product to be identified is L3, the identifier selects the C3 matrix from the C0 matrix group as a basis for determining the preparation age of the ceramic product to be identified; When the identification device determines that the origin of the ceramic product to be identified is Ln, the identification device selects the Cn matrix from the C0 matrix group as a basis for determining the preparation age of the ceramic product to be identified; The cloud Internet of Things also stores a preset preparation age matrix group B0 (B1, B2, B3, Bn), wherein B1 is the preset preparation age matrix of the first preset origin, B2 is the preset preparation age matrix of the second preset origin, B3 is the preset preparation age matrix of the third preset origin, and Bn is the preset preparation age matrix of the nth preset origin; for the preset preparation age matrix Bn of the nth preset origin, Bn (Bn1, Bn2, Bn3...Bni), wherein Bn1 is the first preset preparation age of the nth preset origin, Bn2 is the second preset preparation age of the nth preset origin, Bn3 is the third preset preparation age of the nth preset origin, and Bni is the i-th preset preparation age of the nth preset origin; When detecting the size of the ceramic product to be identified, the identifier establishes a detection size matrix K (H, S, D), wherein H is the height of the ceramic product to be identified, S is the edge curvature of the ceramic product to be identified, and D is the average thickness of the ceramic product to be identified; after the establishment is completed, the identifier calculates the size coefficient C of the ceramic product to be identified. After the calculation is completed, the identifier selects the corresponding preset size coefficient from the C0 matrix group according to the determined origin of the ceramic product to be identified; when the identifier determines that the origin of the ceramic product to be identified is Ln, the identifier selects the Cn matrix from the C0 matrix group as the determination basis for the preparation age of the ceramic product to be identified to determine the preparation age of the ceramic product to be identified: When the deviation between the size coefficient C of the ceramic product to be identified and Cn1 in the Cn matrix is ​​the smallest, the identification device determines that the preparation age of the ceramic product to be identified is Bn1; When the deviation between the size coefficient C of the ceramic product to be identified and Cn2 in the Cn matrix is ​​the smallest, the identification device determines that the preparation age of the ceramic product to be identified is Bn2; When the deviation between the size coefficient C of the ceramic product to be identified and Cn3 in the Cn matrix is ​​the smallest, the identification device determines that the preparation age of the ceramic product to be identified is Bn3; When the deviation between the size coefficient C of the ceramic product to be identified and Cni in the Cn matrix is ​​the smallest, the identification device determines that the preparation age of the ceramic product to be identified is Bni; The cloud Internet of Things also stores a preset texture detection point coordinate matrix group X0 (X1, X2, X3...Xn), wherein X1 is the preset texture detection point coordinate matrix of the first origin, X2 is the preset texture detection point coordinate matrix of the second origin, X3 is the preset texture detection point coordinate matrix of the third origin, and Xn is the preset texture detection point coordinate matrix of the nth origin; for the nth preset texture detection point coordinate matrix Xn, Xn (Xn1, Xn2, Xn3...Xni), wherein Xn1 is the preset texture detection point coordinate of the nth origin in the first generation, Xn2 is the preset texture detection point coordinate of the nth origin in the second generation, Xn3 is the preset texture detection point coordinate of the nth origin in the third generation, and Xni is the preset texture detection point coordinate of the nth origin in the ith generation; When the identifier determines the origin Ln and the production year Bni of the ceramic product to be identified, the identifier selects Xni coordinates from the Xn matrix as the texture feature collection coordinates for the ceramic product to be identified.

2. The method for identifying ceramics based on the Internet of Things according to claim 1, characterized in that: When the identifier completes the determination of the origin Ln and the preparation age Bni of the ceramic product to be identified, the identifier retrieves the outer wall texture features of the ceramics fired in the corresponding region in the corresponding age from the cloud Internet of Things and establishes the corresponding texture feature determination matrix Wni0 (Wni1, Wni2, Wni3...Wnij), wherein Wni1 is the first texture determination feature of the Ln origin Bni age, Wni2 is the second texture determination feature of the Ln origin Bni age, Wni3 is the third texture determination feature of the Ln origin Bni age, and Wnij is the jth texture determination feature of the Ln origin Bni age; When the identifier determines that the ceramic product to be identified is a product produced in the nth production area in the i-th generation and the identifier determines the authenticity of the ceramic product to be identified, the identifier extracts the surface texture feature W of the ceramic product to be identified from the specified coordinates and compares W with each texture determination feature in the texture feature determination matrix Wni0: When the similarity of each parameter in the W and Wni0 matrices is less than 85%, the identifier determines that the ceramic product to be identified is a counterfeit; When the similarity between at least one parameter in the W and Wni0 matrices is higher than 90%, the identifier determines that the ceramic product to be identified is authentic; When the similarity of multiple parameters in the W and Wni0 matrices is higher than 85%, the identifier determines that the ceramic product to be identified is authentic.

3. The method for identifying ceramics based on the Internet of Things according to claim 2, characterized in that: The cloud IoT also stores a preset etching degree K0 and a preset etching time T0; for the preset etching degree K0, K0 (K1, K2, K3, K4), wherein K1 is the first preset etching degree, K2 is the second preset etching degree, K3 is the third preset etching degree, K4 is the fourth preset etching degree, and each etching degree increases gradually in sequence; for the preset etching time T0, T0 (T1, T2, T3, T4), wherein T1 is the first preset etching time, T2 is the second preset etching time, T3 is the third preset etching time, T4 is the fourth preset etching time, and each etching time value increases gradually in sequence; When the identifier identifies the etching marks on the surface cracks of the ceramic product to be identified, the identifier detects the etching degree K of the cracks and compares K with the parameters in the K0 matrix: When K≤K1, the identifier determines that the etching occurred at a time T1 from now; When K1<K≤K2, the identifier determines that the etching occurred at a time T2 from now; When K2<K≤K3, the identifier determines that the etching occurred at a time T3 from now; When K3<K≤K4, the identifier determines that the etching occurred at time T4 from now.

4. The method for identifying ceramics based on the Internet of Things according to claim 3, characterized in that: After the identification is completed, the identifier generates an identification result matrix A (H, S, D, R, L, B, X, W, Y / N, K, T), wherein H is the height of the ceramic product to be identified, S is the edge curvature of the ceramic product to be identified, D is the average thickness of the ceramic product to be identified, R is the material crystal phase of the ceramic product to be identified, L is the origin of the ceramic product to be identified, B is the preparation age of the ceramic product to be identified, X is the coordinate point when the identifier collects texture features, W is the texture features collected by the identifier, Y / N is the identification result of whether the ceramic product to be identified is authentic, K is the etching degree of the surface cracks of the ceramic product to be identified, and T is the etching time of the surface cracks of the ceramic product to be identified; when the identifier determines that the ceramic product to be identified is authentic, Y / N is Y, and when the identifier determines that the ceramic product to be identified is a counterfeit, Y / N is N.