CN116189173A - Seawater pearl texture recognition method based on big data - Google Patents
Seawater pearl texture recognition method based on big data Download PDFInfo
- Publication number
- CN116189173A CN116189173A CN202211706578.XA CN202211706578A CN116189173A CN 116189173 A CN116189173 A CN 116189173A CN 202211706578 A CN202211706578 A CN 202211706578A CN 116189173 A CN116189173 A CN 116189173A
- Authority
- CN
- China
- Prior art keywords
- pearl
- seawater
- information
- big data
- color
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/66—Trinkets, e.g. shirt buttons or jewellery items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- 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
- G06V10/54—Extraction of image or video features relating to texture
-
- 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
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/80—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in fisheries management
- Y02A40/81—Aquaculture, e.g. of fish
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of seawater pearl identification, and discloses a seawater pearl texture identification method based on big data, which comprises the following steps: 1) Fixing the sample, and shooting the appearance, color and surface texture of the pearl by a camera; 2) Initially identifying the identity; 3) Artificial intelligence to identify pearl appearance; 4) Color identification, wherein artificial intelligence analyzes the color of a circular image; 5) Identifying the growth patterns of the pearls, analyzing the patterns in the circular image by artificial intelligence, searching for comparison matching, feeding back no commodity information to the client terminal if no matching data exists, and executing the next operation if matching; 6) And feeding back to the client so information representative of the sample. The visitor only needs to photograph the pearl commodity, measure the outer diameter and the color, upload the pearl commodity to the service platform, extract relevant information through the artificial intelligence AI technology, then compare with the information stored by the service platform, and can realize the true and false identification of the seawater pearl commodity through information comparison.
Description
Technical Field
The invention relates to the technical field of seawater pearl identification, in particular to a seawater pearl texture identification method based on big data.
Background
The culture of south pearl in China has a long history, and south pearl enjoys extremely high position in the international luxury market. The Western beads were not as good as the east beads, which were less good as the south beads. The south pearl is centered on the Hepu seawater pearl and mainly focused on the northern bay coastal zone in Guangxi, guangdong and san Diego. More than 80 ten thousand people are engaged in related work in the pearl industry chain, and the related work relates to raw beads, pearl ornaments, rough processed and deep processed products, sales and the like. The North Guangxi sea is a key area of national sea water pearl production, and is a famous 'countryside of south pearl', and the produced south pearl is fine, smooth, crystal and clear and is named as 'tribute' by the Chinese calendar. The first artificial cultured seawater pearl in 1958 is born in the north sea, and the north sea has become the largest seawater pearl culture base in the northern bay area, the yield of the seawater pearl in the north sea is about 50% of the total yield in the whole country, and the seawater pearl culture base is the largest distribution area for circulating the seawater pearl in the country and accounts for more than 60% of sales in the country. Sea water pearl trade volume and trade amount are listed as forensic cogongrass in China. The pearl industry in North sea has gradually transitioned from the traditional single production type to the current industry management of integrated cultivation and processing. There is a refulgence in the north sea pearl, but in recent years, the south pearl industry in the north sea is increasingly serious. The phenomenon that the freshwater pearls are used as seawater pearls is mainly manifested in the prior art, and the reputation of the south pearls is seriously damaged, so that the cultivation of the south pearls is greatly reduced, and the development space of the south pearls is impacted.
In order to save south pearl industry in North China, the Guangxi non-matter cultural heritage of 'Zhu Huo Pu' is protected, and according to the deployment requirements of the autonomous region party and the autonomous region people government on the south pearl industry in Zhou Xingxing, the opinion (North NodeB 2017 15) is formulated, the opinion indicates that a three-center (a south pearl culture modern agricultural core demonstration area, a south pearl processing research and development center, a south pearl transaction center and a south pearl culture communication center) is to be constructed as a handle, one planning is perfected, five actions are implemented, two developments are realized, the purposes of adjusting the culture area, expanding the scale and standardizing the technology, improving the processing and research and development capability, constructing a standard demonstration base of the south pearl industry in China, comprehensively vibrating the south pearl industry, and making the south pearl industry into the north China with the most resource advantages and cultural connotation in the future as 100 hundred million yen.
The seawater pearl is required to be strictly controlled in cultivation, picking, processing, trade and the like, and is an important ring for guaranteeing the brand of south pearl. Only if the counterfeit is stopped, the south pearl can develop. The current south bead identification mainly comprises the following ways:
1. observing the surface tissue structure by using a microscope and measuring the thickness of the bead layer;
2. labeling and sealing bags for packaging;
3. and (5) roasting by flame.
The technology is quite behind, and the following problems are particularly existed:
1. the pearl body is difficult to trace back due to the fact that the pearl body is not unique;
2. seawater pearl and freshwater pearl can not be completely distinguished from east pearl, west pearl and south pearl;
3. natural and artificial coloration is indistinguishable.
For anti-counterfeiting domestic scholars and scientific workers in the field propose to embed an ID chip in a pearl nucleus, and some proposals adopt non-toxic and harmless special liquid, but no practical application exists until now, even if the special liquid can be tampered with, so a seawater pearl texture recognition method based on big data is provided to solve the problems.
Disclosure of Invention
(one) solving the technical problems
Aiming at the defects of the prior art, the invention provides a seawater pearl texture identification method based on big data, which establishes big data of different seawater pearl growth textures by means of an artificial intelligence algorithm with textures of known pearls, and predicts unknown pearl attributes by using known texture parameters, namely, the purpose of identifying seawater pearls is achieved by the growth textures.
(II) technical scheme
In order to achieve the above purpose, the present invention provides the following technical solutions: a seawater pearl texture recognition method based on big data comprises the following steps:
1) Fixing the identified sample, shooting the appearance, color and surface texture of the pearl by a camera, and uploading pictures;
2) The identity primary identification, according to the outer diameter size of the pearl, searching and comparing the related information in the database, if no corresponding information is found, feeding back the commodity information to the client terminal, and if matching information is found, executing the next operation;
3) The artificial intelligence identifies the appearance of the pearl, captures a circular image, and executes the color identification operation if the circular image is the same;
4) Color identification, namely, analyzing the color of a circular image by artificial intelligence, searching and comparing related information in a blockchain database, if no corresponding information is found, feeding back information of the commodity to a client terminal, and if matching information is found, classifying the color of the commodity, and simultaneously executing pearl growth line identification operation;
5) Identifying the growth patterns of the pearls, analyzing the patterns in the circular images by artificial intelligence, searching for comparison pairs in an original database, feeding back information of the commodity to a client terminal if no matching data exists, and executing the next operation if the matching data does not exist;
6) And feeding back the information representing the sample to the client, and finishing the identification.
Further, in the step 1), when the identified sample is fixed, auxiliary shading illumination is required to be performed by using a shading device and an illumination device, the model of the camera is GYM300, and the optical size of the camera is 1/2' CMOS (complementary metal oxide semiconductor) color.
Further, the illumination device adopts adjustable LED lamp strip illumination, shade adopts hemisphere lens hood, white fiber container and dull polish semitransparent shading paper.
A seawater pearl texture recognition device based on big data comprises an image sensor, a multi-neutralization big data cloud platform which is difficult to tamper with, an artificial intelligent image recognition algorithm and an original database.
Further, the image sensor identifies the identified object, generates a seawater pearl imaging picture, transmits the imaging picture to a platform with multiple neutralization big data which can not be tampered by an administrator through the Internet, decodes the imaging picture on the platform, extracts related data through an artificial intelligent pearl texture algorithm, and matches the related data with information in an original database, and finally achieves the aim of distinguishing seawater pearls.
Further, the ID code consists of geometry, color and texture, and can be traced back to the origin.
Further, the artificial intelligence image recognition algorithm comprises an artificial intelligence texture algorithm which is mainly used for extracting growth patterns on the surface of the seawater pearl so as to distinguish the seawater pearl from the freshwater pearl.
Further, the raw database is used for storing characteristic data of seawater pearls and freshwater pearls.
(III) beneficial effects
Compared with the prior art, the invention provides a seawater pearl texture recognition method based on big data, which has the following beneficial effects:
1. according to the seawater pearl texture identification method based on big data, visitors only need to photograph and measure the outer diameter and the color of pearl commodity, upload the pearl commodity to a service platform, extract relevant information through an artificial intelligence AI technology, then compare the information with the information stored by the service platform, and can realize the true and false identification of the seawater pearl commodity through information comparison, so that the sharing of service consumers, farmers, processing enterprises, sales companies, electronic commerce platforms, government departments such as market supervision and business and other third party detection institutions with certain detection qualification is facilitated.
2. According to the seawater pearl texture recognition method based on big data, the light source device and the shading device with simple structures are adopted, so that the pearl reflection area can be effectively eliminated, an ideal pearl image is obtained, the complete pearl image is reserved, the follow-up artificial intelligent image recognition algorithm can recognize the pearl color and the pearl growth texture more accurately, and the accuracy is higher.
Drawings
FIG. 1 is a schematic diagram of a seawater pearl texture recognition method based on big data;
FIG. 2 is a schematic diagram of a seawater pearl texture recognition method based on big data;
fig. 3 is a schematic diagram of a shading device and a lighting device according to the seawater pearl texture recognition method based on big data.
In the figure: 1 camera, 2 hemisphere light shield, 3 white fiber container, 4 dull polish translucent light shield paper, 5LED lamp strip.
Detailed Description
The technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-3, a seawater pearl texture recognition method based on big data comprises the following steps:
1) Fixing the identified sample, shooting the appearance, color and surface texture of the pearl by the camera 1, and uploading the picture;
when the identified sample is fixed, auxiliary shading illumination is needed by a shading device and an illumination device, the model of the camera 1 is GYM300, and the optical size is 1/2' CMOS (complementary metal oxide semiconductor) color.
Meanwhile, the illuminating device adopts the adjustable LED lamp strip 5 for illumination, the shading device adopts the hemispherical shading cover 2, the white paper cylinder 3 and the frosted semitransparent shading paper 4, the hemispherical shading cover 2 is made of white PLA (polylactic acid) materials, the interference of other non-test device light sources such as fluorescent lamps and sunlight and the like can be effectively shielded, the light spots generated by the pearl due to the influence of strong light are reduced, and the white paper cylinder 3 and the frosted semitransparent shading paper 4 can enable the light sources generated by the LED lamp strip 5 to be softer and more uniform.
2) The identity primary identification, according to the outer diameter size of the pearl, searching and comparing the related information in the database, if no corresponding information is found, feeding back the commodity information to the client terminal, and if matching information is found, executing the next operation;
3) The artificial intelligence identifies the appearance of the pearl, captures a circular image, and executes the color identification operation if the circular image is the same;
4) Color identification, namely, analyzing the color of a circular image by artificial intelligence, searching and comparing related information in a blockchain database, if no corresponding information is found, feeding back information of the commodity to a client terminal, and if matching information is found, classifying the color of the commodity, and simultaneously executing pearl growth line identification operation;
specifically, when the color of a sample is identified, firstly, a circular image is preprocessed, the image preprocessing comprises mean filtering denoising and global threshold segmentation, color space conversion is carried out on the segmented image, color characteristic values are extracted, when a classifier is established, a sample pearl image is classified, a classification label is established, a sample chart library is divided into a training set and a testing set, the training set is used for learning of the classifier, the testing set is used for testing the accuracy of a classification model, after a model with ideal classification accuracy is obtained, an identification module is established, pearl image identification is carried out, and a matching image and a category of the image to be detected are output.
5) And (3) identifying the growth patterns of the pearls, analyzing the patterns in the circular image by artificial intelligence, searching for comparison pairs in an original database, feeding back the information of the commodity to a client terminal if no matching data exists, and executing the next operation if the matching data does not exist.
Specifically, after the growth patterns of the sample are identified, the sample pearl image is classified to construct a classification label, and the pearl image is identified through the identification module and the matching image and the belonging category of the image to be detected are output.
6) And feeding back the information representing the sample to the client, and finishing the identification.
A seawater pearl texture recognition device based on big data comprises an image sensor, a multi-neutralization big data cloud platform which is difficult to tamper with, an artificial intelligent image recognition algorithm and an original database.
The image sensor identifies the identified object, generates a seawater pearl imaging picture, transmits the imaging picture to a platform with multiple neutralization big data which can not be tampered by an administrator through the Internet, decodes the imaging picture on the platform, extracts related data through an artificial intelligent pearl texture algorithm, and matches the related data with information in an original database, and finally achieves the aim of distinguishing seawater pearls.
The image sensor is mainly used for completing the acquisition of information such as appearance, surface texture, color and the like of the pearl and imaging, and then the Internet uploads an imaging picture to a cloud platform with multiple neutrality and difficulty in tampering; different from the traditional big data platform, the manager of the platform does not have the opportunity of tampering with the module data, so that the real public trust of the data is ensured not to be polluted, and evidence with legal efficacy can be provided when the quality dispute problem occurs.
The artificial intelligent image recognition algorithm is mainly used for image processing, and is used for completing recognition processing of pictures uploaded to a multi-neutralization-difficult-to-tamper original database cloud platform by a client, timely comparing processing results with original data stored in the multi-neutralization-difficult-to-tamper cloud platform, and then feeding back true or false conclusions to the client.
The identity ID code consists of geometric dimensions, colors and textures, the original place can be traced through the identity ID code, the artificial intelligent image recognition algorithm comprises an artificial intelligent texture algorithm, the artificial intelligent texture algorithm is mainly used for extracting growth patterns on the surface of the seawater pearl so as to distinguish the seawater pearl from the freshwater pearl, and the original database is used for storing characteristic data of the seawater pearl and the freshwater pearl.
In addition, the pearl is rotated for a circle to extract the growth texture of the body surface by adopting a ccd sensor, then a data module is formed in a combination mode of connecting according to a time sequence, meanwhile, a special secret algorithm is added to ensure that the data cannot be tampered and the content of a non-counterfeitable distributed file is transmitted to a cloud platform, a visitor only needs to photograph and measure the outer diameter and the color of the pearl commodity and upload the pearl commodity to a service platform, related information is extracted by an artificial intelligence AI technology and then is compared with the information stored by the service platform, the identification of the authenticity of the seawater pearl commodity is realized by comparing the information, and the pearl commodity is beneficial to the implementation and sharing of service consumers, farmers, processing enterprises, sales companies, electronic commerce platforms, government departments, business departments and other third party detection mechanisms with certain detection qualification.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. The seawater pearl texture recognition method based on big data is characterized by comprising the following steps of:
1) Fixing the identified sample, shooting the appearance, color and surface texture of the pearl by a camera (1), and uploading pictures;
2) The identity primary identification, according to the outer diameter size of the pearl, searching and comparing the related information in the database, if no corresponding information is found, feeding back the commodity information to the client terminal, and if matching information is found, executing the next operation;
3) The artificial intelligence identifies the appearance of the pearl, captures a circular image, and executes the color identification operation if the circular image is the same;
4) Color identification, namely, analyzing the color of a circular image by artificial intelligence, searching and comparing related information in a blockchain database, if no corresponding information is found, feeding back information of the commodity to a client terminal, and if matching information is found, classifying the color of the commodity, and simultaneously executing pearl growth line identification operation;
5) Identifying the growth patterns of the pearls, analyzing the patterns in the circular images by artificial intelligence, searching for comparison pairs in an original database, feeding back information of the commodity to a client terminal if no matching data exists, and executing the next operation if the matching data does not exist;
6) And feeding back the information representing the sample to the client, and finishing the identification.
2. The seawater pearl texture recognition method based on big data according to claim 1, wherein in the step 1), when the recognized sample is fixed, auxiliary shading illumination is required by a shading device and an illumination device, the model of the camera (1) is GYM300, and the optical size is 1/2' CMOS (complementary metal oxide semiconductor) color.
3. The seawater pearl texture recognition method based on big data according to claim 2, wherein the illumination device adopts an adjustable LED light bar (5) for illumination, and the shading device adopts a hemispherical shading cover (2), a white paper cylinder (3) and frosted semitransparent shading paper (4).
4. A seawater pearl texture recognition device based on big data for implementing the method of any one of claims 1-3, comprising an image sensor, a multi-neutralization-resistant big data cloud platform, an artificial intelligence image recognition algorithm, and a raw database.
5. The seawater pearl texture recognition device based on big data according to claim 4, wherein the image sensor recognizes the recognized object, generates a seawater pearl imaging picture, transmits the imaging picture to a platform with multiple neutral big data which can not be tampered by an administrator through the internet, decodes the imaging picture on the platform, extracts related data through an artificial intelligent pearl texture algorithm, and matches the related data with information in an original database, and finally achieves the purpose of distinguishing seawater pearls.
6. The seawater pearl texture recognition device based on big data of claim 4, wherein the ID code is composed of geometry, color, texture, and can be traced back to the origin by the ID code.
7. The seawater pearl texture recognition device based on big data of claim 4, wherein the artificial intelligence image recognition algorithm comprises an artificial intelligence texture algorithm, which is mainly used for extracting the growth patterns on the surface of the seawater pearl so as to distinguish the seawater pearl from the freshwater pearl.
8. The big data based seawater pearl texture recognition device of claim 4, wherein the raw database is used to store seawater pearl and freshwater pearl characteristic data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211706578.XA CN116189173A (en) | 2022-12-29 | 2022-12-29 | Seawater pearl texture recognition method based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211706578.XA CN116189173A (en) | 2022-12-29 | 2022-12-29 | Seawater pearl texture recognition method based on big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116189173A true CN116189173A (en) | 2023-05-30 |
Family
ID=86439533
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211706578.XA Pending CN116189173A (en) | 2022-12-29 | 2022-12-29 | Seawater pearl texture recognition method based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116189173A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116994248A (en) * | 2023-09-25 | 2023-11-03 | 支付宝(杭州)信息技术有限公司 | Texture detection processing method and device |
-
2022
- 2022-12-29 CN CN202211706578.XA patent/CN116189173A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116994248A (en) * | 2023-09-25 | 2023-11-03 | 支付宝(杭州)信息技术有限公司 | Texture detection processing method and device |
CN116994248B (en) * | 2023-09-25 | 2024-03-15 | 支付宝(杭州)信息技术有限公司 | Texture detection processing method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
He et al. | A fully convolutional neural network for wood defect location and identification | |
Di et al. | Surface defect classification of steels with a new semi-supervised learning method | |
CN109829914B (en) | Method and device for detecting product defects | |
CN110310259A (en) | It is a kind of that flaw detection method is tied based on the wood for improving YOLOv3 algorithm | |
CN110349126A (en) | A kind of Surface Defects in Steel Plate detection method based on convolutional neural networks tape label | |
CN110033040B (en) | Flame identification method, system, medium and equipment | |
CN107437293A (en) | A kind of bill anti-counterfeit discrimination method based on bill global characteristics | |
CN109376591A (en) | The ship object detection method of deep learning feature and visual signature joint training | |
CN116189173A (en) | Seawater pearl texture recognition method based on big data | |
CN109726660A (en) | A kind of remote sensing images ship identification method | |
Sun et al. | Image recognition technology in texture identification of marine sediment sonar image | |
CN114998783A (en) | Front-end equipment for video analysis of smoke, fire and personnel behaviors | |
CN115731198A (en) | Intelligent detection system for leather surface defects | |
CN109815957A (en) | A kind of character recognition method based on color image under complex background | |
CN109492445A (en) | A kind of anti-fake method for preventing goods from altering based on sequential information code image recognition | |
CN108073873A (en) | Human face detection and tracing system based on high-definition intelligent video camera | |
CN109493084A (en) | A kind of anti-fake method for preventing goods from altering based on the identification of sequential image information code | |
Surinwarangkoon et al. | Traffic sign recognition system for roadside images in poor condition | |
CN104573743A (en) | Filtering method for facial image detection | |
Walder et al. | Neural network based methods for cloud classification on AVHRR images | |
Tsai et al. | Saw-Mark Defect Detection in Heterogeneous Solar Wafer Images using GAN-based Training Samples Generation and CNN Classification. | |
CN110443306A (en) | The classification method of grape wine stopper | |
CN110288570A (en) | A kind of weak iridescent image detection method of the rotor winding of view-based access control model attention mechanism | |
Lu et al. | Detecting defects on citrus surface based on circularity threshold segmentation | |
Han et al. | Automatic used mobile phone color determination: Enhancing the used mobile phone recycling in China |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |