AU2021103787A4 - Method for identifying hand-painted thangka and printed thangka - Google Patents
Method for identifying hand-painted thangka and printed thangka Download PDFInfo
- Publication number
- AU2021103787A4 AU2021103787A4 AU2021103787A AU2021103787A AU2021103787A4 AU 2021103787 A4 AU2021103787 A4 AU 2021103787A4 AU 2021103787 A AU2021103787 A AU 2021103787A AU 2021103787 A AU2021103787 A AU 2021103787A AU 2021103787 A4 AU2021103787 A4 AU 2021103787A4
- Authority
- AU
- Australia
- Prior art keywords
- thangka
- painted
- hand
- image
- identifying
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/95—Pattern authentication; Markers therefor; Forgery detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/467—Encoded features or binary features, e.g. local binary patterns [LBP]
Abstract
OF THE DISCLOSURE
According to the present disclosure, method research and model construction are
conducted on the basis of analysis of the features of a thangka in combination with a related
computer vision processing method, a canvas texture is analyzed by means of an LBP
algorithm, a thangka canvas is identified according to a training result, light transmittance of
the thangka is analyzed by means of a restricted Boltzmann machine; a clustering method for
analyzing a gold line of the thangka is combined with various methods, and then a feasible
method for identifying a hand-painted thangka and a machine-painted thangka is provided.
The type of the thangka may be determined by comprehensively considering canvas materials,
gold line features and overall light transmittance analysis.
ABSTRACT DRAWING - Fig 1
17838891_1 (GHMatters) P116645.AU
1/4
100
Analyze a canvas of the thangka to obtain an 0
analysis result of the canvas
200
Analyze a gold line part of the thangka to obtain an
analysis result of a gold line
300
Analyze overall light trarnsmittance of the thangka to30
obtain an analysis result of the light transmittance
Comprehensively scoring the thangka according to the 400
analysis result of the canvas, the analysis result of the
gold line and the analysis result of the light
transmittance to obtain a scoring result
Ir 500
Identify whether the thangka is a hand-painted
thangka according to the scoring result.
FIG 1
FIG 2
Description
1/4
100 Analyze a canvas of the thangka to obtain an 0 analysis result of the canvas
200 Analyze a gold line part of the thangka to obtain an analysis result of a gold line
300 Analyze overall light trarnsmittance of the thangka to30 obtain an analysis result of the light transmittance
Comprehensively scoring the thangka according to the 400 analysis result of the canvas, the analysis result of the gold line and the analysis result of the light transmittance to obtain a scoring result
Ir 500 Identify whether the thangka is a hand-painted thangka according to the scoring result.
FIG 1
FIG 2
[01] The present disclosure relates to the field of thangkas, in particular to a method for identifying a hand-painted thangka and a printed thangka by using a visual processing method.
[02] Qinghai is a multi-national region in a vast extent of mysterious plateau having 720,000 square kilometers, where more than twenty nationalities of Han, Tibetan, Hui, Tu, Sala, Mongolian, etc. have lived and thrived. In long-term production and life, people of all nationalities in Qinghai create their own history, culture, accomplishments and dreams, and develop and maintain the unique and colorful local customs and artistic forms.
[03] As a unique painting artistic form in Tibetan culture, thangka is approved as the first batch of national intangible cultural heritage by the State Council and the Department of Culture in 2006, and becomes increasingly appealing to vast artistic enthusiasts and collectors, and however, numerous printed thangkas also swarm into the market, which are sold as a hand-painted thangka at high price by some merchants. As a result, the original value of the hand-painted thangka is destroyed. How to identify a hand-painted thangka and a machine-painted thangka so as to effectively protect and inherit the old and exquisite handicrafts, and how to explore a suitable development road to popularize these exquisite national handicrafts to the world so as to further develop national culture are urgent problems to be solved.
[04] Provided is a method capable of accurately identifying a hand-painted thangka and a machine-painted thangka.
[05] To implement the foregoing objectives, the present disclosure provides the following solutions:
[06] A method for identifying a thangka includes:
17838891_1 (GHMatters) P116645.AU
[07] analyzing a canvas of the thangka to obtain an analysis result of the canvas;
[08] analyzing a gold line of the thangka to obtain an analysis result of the gold line;
[09] analyzing overall light transmittance of the thangka to obtain an analysis result of the light transmittance;
[10] comprehensively comparing the thangka according to the analysis result of the canvas, the analysis result of the gold line and the analysis result of the light transmittance to obtain a comparison result; and
[11] distinguishing whether the thangka is a hand-painted thangka according to the comparison result of the thangka.
[12] Optionally, the analyzing a canvas of the thangka to obtain an analysis result of the canvas specifically includes:
[13] collecting, when a thangka image is magnified to the maximum times by a Huawei honor 8, the thangka image;
[14] dividing a detection window of the thangka image into 16 * 16 small areas;
[15] for one pixel in each small area, comparing gray values of eight adjacent pixels with that of the pixel, under the condition that the values of surrounding pixels are greater than the value of a central pixel, marking a position of a central pixel point as 1, and otherwise, marking the position of the central pixel point as 0; and comparing eight points in 3 * 3 adjacent areas to obtain an 8-bit binary number, and obtaining an LBP value of the central pixel point of the detection window;
[16] calculating a histogram of each small area;
[17] normalizing the histogram;
[18] connecting obtained statistical histograms of all the small areas into a feature vector, and obtaining a feature vector of a local-binary-pattern texture of the thangka image;
[19] predicting, by a classifier, the thangka image according to the feature vector of the local-binary-pattern texture to obtain a prediction image;
17838891_1 (GHMatters) P116645.AU
[20] comparing the prediction image with a hand-painted thangka and a printed thangka separately; and
[21] under the condition that the prediction image is similar to an image of the hand-painted thangka, identifying and authenticating the thangka as a hand-painted thangka for the first time.
[22] Optionally, the analyzing a gold line of the thangka to obtain an analysis result of the gold line specifically includes:
[23] using a camera to collect a thangka image;
[24] extracting feature values of positive and negative samples and color features of the thangka image;
[25] clustering an indefinite number of feature values and color features into a fixed number of classes by using a clustering method;
[26] normalizing the fixed number of classes to obtain a histogram of 10 classes;
[27] training 10 classes in each picture as feature examples and positive and negative samples to obtain features of the thangka picture;
[28] solving a distance between each feature and 10 classes separately, and determining the class of each feature;
[29] normalizing each feature value, and making a histogram of the 10 classes; and
[30] determining whether the thangka is a hand-painted thangka according to a color gamut of the histogram, and under the condition that a result conforms to a color gamut of the hand-painted thangka, identifying the thangka as a hand-painted thangka for the second time.
[31] Optionally, the analyzing overall light transmittance of the thangka to obtain an analysis result of the light transmittance specifically includes:
[32] placing the thangka in a dim place, and performing image acquisition to obtain an image with sunlight;
[33] make the thangka face a bright place, and performing image acquisition to obtain an
17838891_1 (GHMatters) P116645.AU image without sunlight;
[34] performing differential treatment on the image with sunlight and the image without sunlight to obtain a differentiated image sample;
[35] extracting image texture features from the differentiated image sample;
[36] normalizing the image texture features;
[37] training, by a classifier, the image texture features to obtain a training model; and
[38] determining whether the thangka is a hand-painted thangka by using the training model, and under the condition that the training model is consistent with the hand-painted thangka, identifying and authenticating the thangka as a hand-painted thangka for the third time.
[39] Optionally, the identifying whether the thangka is a hand-painted thangka according to the scoring result specifically includes:
[40] identifying the thangka as a hand-painted thangka for the first time under the condition that a thangka image feature is consistent with that of a hand-painted thangka by means of the first time of discrimination and comparison;
[41] identifying the thangka as a hand-painted thangka for the second time under the condition that a color gamut histogram of the thangka is consistent with that of a hand-painted thangka by means of the second time of analysis on a gold line of the thangka through a clustering method; and
[42] identifying the thangka as a hand-painted thangka for the third time under the condition that the light transmittance of the thangka is consistent with a training model of a hand-painted thangka by means of the third time of analysis on the light transmittance of the thangka through the training model.
[43] According to the specific embodiment provided in the present disclosure, the present disclosure has the following technical effects that the method for identifying a hand-painted thangka and a printed thangka provided in the present disclosure may improve the accuracy of thangka identification by comprehensively considering the canvas material, gold line features and overall light transmittance analysis.
17838891_1 (GHMatters) P116645.AU
[44] In order to explain the technical solutions in embodiments of the present disclosure or in the prior art more clearly, the accompanying drawings required in the embodiments will be described below briefly. Apparently, the accompanying drawings in the following description show merely some embodiments of the present disclosure, and other drawings can be derived from these accompanying drawings by those of ordinary skill in the art without creative efforts.
[45] FIG. 1 is a flow diagram of a method for identifying a hand-painted thangka and a printed thangka provided in the present disclosure;
[46] FIG. 2 is a texture analysis result image of a hand-painted thangka provided in the present disclosure;
[47] FIG. 3 is a texture analysis result image of a printed thangka provided in the present disclosure;
[48] FIG. 4 is an analysis result diagram of the printed thangka provided in the present disclosure;
[49] FIG. 5 is an analysis result diagram of the hand-painted thangka provided in the present disclosure;
[50] FIG. 6 is a texture image of the printed thangka in sunlight provided in the present disclosure;
[51] FIG. 7 is a texture image of the hand-painted thangka in sunlight provided in the present disclosure.
[52] The technical solutions of embodiments of the present disclosure will be described below clearly and comprehensively in conjunction with accompanying drawings of the embodiments of the present disclosure. Apparently, the embodiments described are merely some embodiments rather than all embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments acquired by those of ordinary skill in the art without making creative efforts fall within the scope of protection of the
17838891_1 (GHMatters) P116645.AU present disclosure.
[53] The objective of the present disclosure is to provide a method capable of identifying a hand-painted thangka and a machine-painted thangka.
[54] To make the foregoing objective, features, and advantages of the present disclosure clearer and more comprehensible, the present disclosure will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.
[55] As shown in FIG. 1, a method for identifying a thangka includes:
[56] Step 100: analyzing a canvas of the thangka to obtain an analysis result of the canvas; the canvas of the hand-painted thangka is made of specially-made cotton cloth which is made by manual grinding, oxhide gelatin, lime, etc. are mixed and brushed on the cloth, and then the cotton cloth is repeatedly ground with qiayang or putty powder, such that the obtained canvas may more uniformly show the color of a painted pigment, and meanwhile the ground canvas is prevented from being bitten by worms.
[57] A simulated printed thangka generally uses a commonly machine-made canvas (special plastic cloth). The simulated printed thangka mostly uses artificially synthesized polymeric pigments, which are bright in color and luster and large in adhesive force and may be painted on various carriers. The artificially synthesized polymeric pigments are extremely universal to various painting techniques, however, they are unfit when painted on the cotton cloth. The artificially synthesized polymeric pigments are quick to dry and water-resistant, but a dried paint film is tough and stiff, has no flexibility and may crack and generate dregs.
[58] Step 200: analyzing a gold line of the thangka to obtain an analysis result of the gold line.
[59] Step 300: analyzing overall light transmittance of the thangka to obtain an analysis result of the light transmittance.
[60] Step 400: comprehensively scoring the thangka according to the analysis result of the canvas, the analysis result of the gold line and the analysis result of the light transmittance to obtain a scoring result.
[61] Step 500: identifying whether the thangka is a hand-painted thangka according to the
17838891_1 (GHMatters) P116645.AU scoring result.
[62] The analyzing a canvas of the thangka to obtain an analysis result of the canvas specifically includes:
[63] collecting, when a thangka image is magnified to the maximum times by using a Huawei honor 8, the thangka image;
[64] dividing a detection window of the thangka image into 16 * 16 small areas;
[65] for one pixel in each small area, comparing gray values of eight adjacent pixels with that of the pixel, under the condition that the values of surrounding pixels are greater than the value of a central pixel, marking a position of a central pixel point as 1, and otherwise, marking the position of the central pixel point as 0; and comparing eight points in 3 * 3 adjacent areas to obtain an 8-bit binary number, and obtaining an LBP value of the central pixel point of the detection window;
[66] calculating a histogram of each small area;
[67] normalizing the histogram;
[68] connecting obtained statistical histograms of all the small areas into a feature vector, and obtaining a feature vector of a local-binary-pattern texture of the thangka image;
[69] predicting, by a classifier, the thangka image according to the feature vector of the local-binary-patterntexture to obtain a prediction image, as shown in FIGs. 2 and 3;
[70] comparing the prediction image with a hand-painted thangka and a printed thangka separately;
[71] where canvas feature analysis specifically further includes:
[72] (1) observing the canvas by using a magnifying lens, or observing the canvas by magnifying a mobile phone camera to the maximum times under the condition without the magnifying lens;
[73] (2) comparing the obtained image with a hand-painted thangka sample image and a machine-painted thangka sample image; and
17838891_1 (GHMatters) P116645.AU
[74] (3) under the condition that the image is similar to the machine-painted thangka sample image, considering the thangka not to be a hand-painted thangka; and
[75] under the condition that the prediction image is similar to an image of the hand-painted thangka, identifying and authenticating the thangka as a hand-painted thangka for the first time.
[76] Optionally, the analyzing a gold line of the thangka to obtain an analysis result of the gold line specifically includes:
[77] using a camera to collect a thangka image;
[78] extracting feature values of positive and negative samples and color features of the thangka image;
[79] clustering an indefinite number of feature values and color features into a fixed number of classes by using a clustering method;
[80] normalizing the fixed number of classes to obtain a histogram of 10 classes;
[81] training 10 classes in each picture as feature examples and positive and negative samples to obtain features of the thangka picture;
[82] solving a distance between each feature and 10 classes separately, and determining the class of each feature;
[83] normalizing each feature value, and making a histogram of the 10 classes as shown in FIGs. 3 and 4;
[84] comparing the prediction image with a hand-painted thangka and a printed thangka separately;
[85] where the application of gold in thangka painting is a unique skill of the thangka, and whether Buddha statues or costumes of people in surrounding story paintings are outlined by means of gold lines; building, trees and stones are also often decorated with gold lines and gold dots; Tibetan painters are good at using gold, and they often use red gold for bottoming and then use gold to paint patterns, so as to increase gradations of gold; the Tibetan painters have strict requirements on gold quality, they select pure gold for making gold powder and
17838891_1 (GHMatters) P116645.AU process and grind the pure gold in person, whereas in the case of a machine-painted thangka, no pure gold raw materials but chemical raw materials are used for saving cost;
[86] therefore, the gold line is one important basis for distinguishing a hand-painted thangka and a printed thangka;
[87] in an environment with sufficient light, due to the specular reflection of metal, a dazzling phenomenon may occur through side observation; and
[88] in a dim environment without light, a spectacular picture may be observed after a light source is applied to the thangka from a side, which is resplendent and magnificent;
[89] where analysis of gold line features specifically further includes:
[90] (1) making a part with the gold line face a direction of sunlight, and observing whether a dazzling phenomenon occurs from the side based on mirror reflection of metal; and
[91] (2) lighting on one side in a dim environment, and magnifying a mobile phone camera to the maximum times on the other side for photographing; due to mirror reflection of metal, the part with the gold line is exposed and becomes whitish during photographing; and
[92] when (1) and (2) are both met, the thangka may be further classified as a hand-painted thangka;and
[93] under the condition that the prediction feature is similar to that of the image of the hand-painted thangka, identifying and authenticating the thangka as a hand-painted thangka for the second time.
[94] The canvas of the hand-painted thangka is made of specially-made cotton cloth which is made by manual grinding, oxhide gelatin, lime, etc. are mixed and brushed on the cloth, and then the cotton cloth is repeatedly ground with qiayang or putty powder. A simulated printed thangka generally uses a commonly machine-made canvas. A method for distinguishing the two canvases includes steps that thangka is made to face strong light, if irregular scratches are found on a back surface of the thangka, the thangka at least has a manual canvas, because the irregular scratches are generally traces left in the grinding process of manual canvases. On the contrary, with a back surface of the thangka observed in strong light, if the thangka is flat and has no watermark-like scratch, it is determined that the thangka
17838891_1 (GHMatters) P116645.AU is printed
[95] Due to manual color painting of the hand-painted thangka, control over the amount of pigment may not be absolutely even, whereas the machine-painted thangka uses a high-precision spray head, and strictly controls the degree of uniformity of the pigment. When a thangka faces strong light, irregular scratches may be observed on the back surface of the thangka.
[96] Therefore, the overall light transmittance is also one important basis for distinguishing a hand-painted thangka and a printed thangka.
[97] The analyzing overall light transmittance of the thangka to obtain an analysis result of the light transmittance specifically includes:
[98] placing the thangka in a dim place, and performing image acquisition to obtain an image with sunlight;
[99] make the thangka face a bright place, and performing image acquisition to obtain an image without sunlight;
[100] performing differential treatment on the image with sunlight and the image without sunlight to obtain a differentiated image sample;
[101] extracting image texture features from the differentiated image sample;
[102] normalizing the image texture features in image texture feature patterns which are shown in FIGs. 4 and 5;
[103] training, by a classifier, the image texture features to obtain a training model;
[104] where the method for analyzing the overall light transmittance further includes:
[105] as shown in FIGs. 6 and 7, placing a thangka in a dim place (without direct strong light) for image acquisition; making the thangka face the strong light for image acquisition; observing whether irregular scratches exist on a back surface of the thangka; and determining, if yes through observation, that the thangka is a hand-painted thangka, and otherwise, determining that the thangka is a machine-painted thangka; and
[106] determining whether the thangka is a hand-painted thangka by using the training 17838891_1 (GHMatters) P116645.AU model and back texture of the thangka, and under the condition that the features are similar to those of the hand-painted thangka, determining the thangka as a hand-painted thangka for the third time.
[107] Optionally, the identifying whether the thangka is a hand-painted thangka according to the scoring result specifically includes:
[108] identifying the thangka as a hand-painted thangka for the first time under the condition that a thangka image feature is consistent with that of a hand-painted thangka by means of the first time of discrimination and comparison;
[109] identifying the thangka as a hand-painted thangka for the second time under the condition that a color gamut histogram of the thangka is consistent with that of a hand-painted thangka by means of the second time of analysis on a gold line of the thangka through a clustering method; and
[110] identifying the thangka as a hand-painted thangka for the third time under the condition that the light transmittance of the thangka is consistent with a training model of a hand-painted thangka by means of the third time of analysis on the light transmittance of the thangka through the training model and the back texture features.
[111] It is to be understood that, if any prior art publication is referred to herein, such reference does not constitute an admission that the publication forms a part of the common general knowledge in the art, in Australia or any other country.
[112] In the claims which follow and in the preceding description of the invention, except where the context requires otherwise due to express language or necessary implication, the word "comprise" or variations such as "comprises" or "comprising" is used in an inclusive sense, i.e. to specify the presence of the stated features but not to preclude the presence or addition of further features in various embodiments of the invention.
17838891_1 (GHMatters) P116645.AU
Claims (5)
1. A method for identifying a hand-painted thangka and a printed thangka through a computer vision processing method, comprising: analyzing the thangka by a same apparatus to obtain an analysis result of a thangka canvas; analyzing a gold line of the thangka to obtain an analysis result of the gold line; analyzing overall light transmittance of the thangka to obtain an analysis result of the light transmittance; comprehensively evaluating the thangka according to the analysis result of the canvas, the analysis result of the gold line and the analysis result of the light transmittance; and identifying whether the thangka is a hand-painted thangka according to an evaluation result.
2. The method for identifying a hand-painted thangka and a printed thangka through a computer vision processing method according to claim 1, wherein the analyzing a canvas of the thangka to obtain an analysis result of the canvas specifically comprises: collecting, when a thangka image is magnified to the maximum times by a Huawei honor 8, the thangka image; dividing a detection window of the thangka image into 16 * 16 small areas; for one pixel in each small area, comparing gray values of eight adjacent pixels with that of the pixel, under the condition that the values of surrounding pixels are greater than the value of a central pixel, marking a position of a central pixel point as 1, and otherwise, marking the position of the central pixel point as 0; and comparing eight points in 3 * 3 adjacent areas to obtain an 8-bit binary number, and obtaining an LBP value of the central pixel point of the detection window; calculating a histogram of each small area; normalizing the histogram; connecting obtained statistical histograms of all the small areas into a feature vector, and obtaining a feature vector of a local-binary-pattern texture of the thangka image; predicting, by a classifier, the thangka image according to the feature vector of the local-binary-pattern texture to obtain a prediction image; comparing the prediction image with a hand-painted thangka and a printed thangka separately; and 17838891_1 (GHMatters) P116645.AU under the condition that the prediction image is similar to an image of the hand-painted thangka, identifying and authenticating the thangka as a hand-painted thangka for the first time.
3. The method for identifying a hand-painted thangka and a printed thangka through a computer vision processing method according to claim 1, wherein the analyzing a gold line of the thangka to obtain an analysis result of the gold line specifically comprises: using a camera to collect a thangka image; extracting feature values of positive and negative samples and color features of the thangka image; clustering an indefinite number of feature values and color features into a fixed number of classes by using a clustering method; normalizing the fixed number of classes to obtain a histogram of 10 classes; training 10 classes in each picture as feature examples and positive and negative samples to obtain features of the thangka picture; solving a distance between each feature and 10 classes separately, and determining the class of each feature; normalizing each feature value, and making a histogram of the 10 classes; and determining whether the thangka is a hand-painted thangka according to a color gamut of the histogram, and under the condition that a result conforms to a color gamut of the hand-painted thangka, identifying the thangka as a hand-painted thangka for the second time.
4. The method for identifying a hand-painted thangka and a printed thangka through a computer vision processing method according to claim 1, wherein the analyzing overall light transmittance of the thangka to obtain an analysis result of the light transmittance specifically comprises: placing the thangka in a dim place, and performing image acquisition to obtain an image without sunlight; make the thangka face a bright place, and performing image acquisition to obtain an image with sunlight; performing differential treatment on the image with sunlight and the image without sunlight to obtain a differentiated image sample; extracting image texture features from the differentiated image sample; normalizing the image texture features; 17838891_1 (GHMatters) P116645.AU training, by a classifier, the image texture features to obtain a training model; and determining whether the thangka is a hand-painted thangka by using the training model, and under the condition that the training model is consistent with the hand-painted thangka, identifying and authenticating the thangka as a hand-painted thangka for the third time.
5. The method for identifying a hand-painted thangka and a printed thangka through a computer vision processing method according to claim 1, wherein the identifying the thangka according to a feature result specifically comprises: identifying the thangka as a hand-painted thangka for the first time under the condition that a thangka image feature is consistent with that of a hand-painted thangka by means of the first time of discrimination and comparison; identifying the thangka as a hand-painted thangka for the second time under the condition that a color gamut histogram of the thangka is consistent with that of a hand-painted thangka by means of the second time of analysis on a gold line of the thangka through a clustering method; and identifying the thangka as a hand-painted thangka for the third time under the condition that the light transmittance of the thangka is consistent with a training model of a hand-painted thangka by means of the third time of analysis on the light transmittance of the thangka through the training model.
17838891_1 (GHMatters) P116645.AU
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2021103787A AU2021103787A4 (en) | 2021-07-01 | 2021-07-01 | Method for identifying hand-painted thangka and printed thangka |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2021103787A AU2021103787A4 (en) | 2021-07-01 | 2021-07-01 | Method for identifying hand-painted thangka and printed thangka |
Publications (1)
Publication Number | Publication Date |
---|---|
AU2021103787A4 true AU2021103787A4 (en) | 2021-08-19 |
Family
ID=77274359
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
AU2021103787A Active AU2021103787A4 (en) | 2021-07-01 | 2021-07-01 | Method for identifying hand-painted thangka and printed thangka |
Country Status (1)
Country | Link |
---|---|
AU (1) | AU2021103787A4 (en) |
-
2021
- 2021-07-01 AU AU2021103787A patent/AU2021103787A4/en active Active
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Jameson et al. | Essay concerning color constancy | |
CN100498788C (en) | Effective pigment identification method, identification system, identification program, and recording medium therefor | |
WO2018049084A1 (en) | Methods and systems for human imperceptible computerized color transfer | |
CN110415181A (en) | Flue-cured tobacco RGB image intelligent recognition and grade determination method under a kind of open environment | |
CN103149214B (en) | Method for detecting flaw on surface of fruit | |
CN106052877B (en) | Mural painting painting material multispectral image color standard colour atla and preparation method thereof | |
CN108416774A (en) | A kind of fabric types recognition methods based on fine granularity neural network | |
CN109509171A (en) | A kind of Fabric Defects Inspection detection method based on GMM and image pyramid | |
CN109598681B (en) | No-reference quality evaluation method for image after repairing of symmetrical Thangka | |
JP2023503564A (en) | Method and apparatus for identifying effect pigments in target coatings | |
AU2021103787A4 (en) | Method for identifying hand-painted thangka and printed thangka | |
CN108960413A (en) | A kind of depth convolutional neural networks method applied to screw surface defects detection | |
CN105373798B (en) | One kind scratching figure and the morphologic writing brush word extracting method of mathematics based on k nearest neighbor | |
Barrantes-Madrigal et al. | Revealing time’s secrets at the National Theatre of Costa Rica via innovative software for cultural heritage research | |
Fu et al. | Line-drawing enhanced interactive mural restoration for Dunhuang Mogao Grottoes | |
CN115546536A (en) | Ivory product identification method and system | |
CN108694412B (en) | Identification method for hand-painted Thangka and printed Thangka | |
JP2003344163A (en) | Stone classifying method and method of manufacturing structure using the same | |
CN109975307A (en) | Bearing surface defect detection system and detection method based on statistics projection training | |
CN106770372B (en) | White glass detection method of surface flaw based on micro-vision | |
CN105259120A (en) | Method for identifying blue and white porcelain | |
AU2020104270A4 (en) | Thangka image inpainting method combining with domain knowledge | |
CN109724921B (en) | Painting and calligraphy identification map feature representation method based on spectral imaging technology | |
Kumar et al. | A multi-level colour thresholding based segmentation approach for improved identification of the defective region in leather surfaces | |
CN110660042A (en) | Traditional Chinese medicine bag number identification algorithm |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
FGI | Letters patent sealed or granted (innovation patent) |