CN113139220A - Intelligent package design system based on Internet of things big data - Google Patents
Intelligent package design system based on Internet of things big data Download PDFInfo
- Publication number
- CN113139220A CN113139220A CN202110515946.1A CN202110515946A CN113139220A CN 113139220 A CN113139220 A CN 113139220A CN 202110515946 A CN202110515946 A CN 202110515946A CN 113139220 A CN113139220 A CN 113139220A
- Authority
- CN
- China
- Prior art keywords
- module
- electrically connected
- image
- input end
- output end
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/12—Geometric CAD characterised by design entry means specially adapted for CAD, e.g. graphical user interfaces [GUI] specially adapted for CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/20—Configuration CAD, e.g. designing by assembling or positioning modules selected from libraries of predesigned modules
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Human Computer Interaction (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Architecture (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an intelligent package design system based on Internet of things big data, which belongs to the technical field of commodity package design and production and comprises an intelligent control module, wherein the output end of the intelligent control module is electrically connected with the input end of a big data mining module, the output end of the big data mining module is electrically connected with the input end of a propaganda image information retrieval module, the output end of the intelligent control module is also electrically connected with the input end of a feature vector output module in an image database, the output end of the feature vector output module in the image database is electrically connected with the input end of a feature matching module, and the input end of the feature matching module is electrically connected with the output end of a feature vector forming module. Through the set image feature extraction module, feature content is obtained in an image, features are extracted through position information of color, shape, texture and space by utilizing CBIR, and features which are observed by designers and are relatively close to each other are extracted.
Description
Technical Field
The invention belongs to the technical field of commodity package design and production, and particularly relates to an intelligent package design system based on Internet of things big data.
Background
The internet of things is an organic integration of the internet and various traditional industries, promotes the transformation and upgrading of the traditional industries, creates new products, new service modes and new business modes, provides basic information of commodities for consumers, needs to perform packaging treatment after the commodities are manufactured and produced, and simultaneously generally designs packaging images with different shapes and colors on the surfaces of packaging boxes, packaging bags and the like to achieve a certain propaganda effect, at present, when a designer performs packaging design, the designer designs according to the requirements of customers, the demands of the customers are mostly generated after market research, and finally the packaging boxes and packaging bag manufacturers complete production, because the customer research is mostly to take hot sold commodities of the same type as a target object, the propaganda images with higher similarity are easily generated in the process of sale, and because the design cost of the propaganda images is higher, not only seriously influences the propaganda effect, has still wasted a large amount of funds, consequently, need an intelligent package design system based on thing networking big data to solve above-mentioned problem urgently at present.
Disclosure of Invention
The invention aims to: the intelligent packaging design system based on the Internet of things is provided for solving the problems that when a designer carries out packaging design, the designer carries out design according to the requirements of a client, the requirement of the client is mostly generated after market research, and finally, a packaging box and a packaging bag manufacturer complete production.
In order to achieve the purpose, the invention adopts the following technical scheme:
the utility model provides an intelligence packing design system based on thing networking big data, includes intelligent control module, intelligent control module's output and big data mining module's input electric connection, big data mining module's output and propaganda image information retrieval module's input electric connection, intelligent control module's output still with image database in eigenvector output module's input electric connection, image database in eigenvector output module's output and characteristic matching module's input electric connection, characteristic matching module's input and eigenvector form the output electric connection of module.
As a further description of the above technical solution:
the output end of the characteristic matching module is electrically connected with the input end of the final retrieval output module, and the final retrieval output module comprises a sector statistical chart establishing module.
As a further description of the above technical solution:
the input end of the characteristic vector forming module is electrically connected with the input end of the wavelet transformation module, the input end of the wavelet transformation module is electrically connected with the output end of the image preprocessing module, the input end of the image preprocessing module is electrically connected with the output end of the package design module, and the input end of the package design module is electrically connected with the output end of the designer input module.
As a further description of the above technical solution:
the image preprocessing module is composed of an image feature extraction module, an image dominant hue distinguishing module and an image dominant hue confirming module, wherein the input end of the image feature extraction module is electrically connected with the output end of the package design module, and the output end of the image dominant hue confirming module is electrically connected with the input end of the wavelet transformation module.
As a further description of the above technical solution:
the feature vector forming module is composed of an image segmentation module, a fuzzification processing module and an image feature library establishing module, wherein the input end of the image segmentation module is electrically connected with the output end of the wavelet transformation module, and the output end of the image feature library establishing module is electrically connected with the input end of the feature matching module.
As a further description of the above technical solution:
the intelligent control module is characterized in that the input end of the intelligent control module is electrically connected with the output end of the keyword input module, and the output end of the intelligent control module is also electrically connected with the input end of the hot spot module.
As a further description of the above technical solution:
the keyword input module consists of a type module for packaging articles, a size module for packaging boxes and a propaganda image module for packaging boxes, the output end of the propaganda image module for packaging boxes is electrically connected with the input end of the intelligent control module, and the type module for packaging articles selects proper packaging box materials according to the types of the articles to be packaged; the packing box size module determines the size of the packing box according to the size of the object to be packed; the packing box propaganda image module determines the characteristics of the input packing box propaganda image according to the material and the size of the packing box.
As a further description of the above technical solution:
the intelligent control module is electrically connected with the information uploading storage module in a bidirectional mode, the input end of the information uploading storage module is electrically connected with the output end of the automatic updating module, the input end of the automatic updating module is electrically connected with the output end of the intelligent server, the input end of the intelligent server is electrically connected with the output end of the information uploading storage module, and the output end of the intelligent server is electrically connected with the input end of the intelligent control module.
As a further description of the above technical solution:
big data mining module is by analysis module, mining module, filter module, impurity information elimination module, refine the module and output module constitutes, analysis module's input and intelligent control module's output electric connection, output module's output and propaganda image information retrieval module's input electric connection.
As a further description of the above technical solution:
the propaganda image information retrieval module is composed of a distributed image information processing module, a parallel image information processing module and a similarity distinguishing module, and the input end of the distributed image information processing module is electrically connected with the output end of the output module.
As a further description of the above technical solution:
the wavelet transformation module grades the image according to the definition of wavelet orthogonal basis under the square integrable function space, and each grade of decomposition is decomposed into a low-frequency part and three high-frequency parts.
In summary, due to the adoption of the technical scheme, the invention has the beneficial effects that:
1. according to the invention, through the arranged keyword input module, the keyword input module consists of a type module for packaging articles, a packaging box size and dimension module and a packaging box propaganda image module, a proper packaging box material is selected through the type module for packaging articles, the size and dimension of the packaging box are determined by the packaging box size and dimension module according to the size and dimension of the articles to be packaged, and the characteristics of the input packaging box propaganda image are determined by the packaging box propaganda image module according to the material and dimension of the packaging box, and the keyword input module mainly comprises three representation modes: numerical values, semantics, and relationships, wherein semantics and relationships include characteristics of materials, sizes, shapes, and color textures.
2. According to the invention, the data information is analyzed through the arranged big data mining module and an efficient technical method, potential filtering of the data information is mined, interference of impurity information is eliminated, key information beneficial to user decision is extracted, and powerful support is provided for data retrieval service.
3. According to the invention, the set propaganda image information retrieval module and the distributed image information processing module are used as a Hadoop cluster architecture, Hdps can process the propaganda images of the packing box more quickly by utilizing a distributed storage and data orientation mode, not only can the orientation of data be realized in a single-input multi-response mode, and the information access effect is improved, but also the data processing is not influenced by a single-level hardware environment, high-performance computer equipment is not required to be input, the cluster cost is effectively reduced, then, the parallel image information processing module adopts one item of parallel calculation, and finally, the similarity between image information is distinguished by the similarity distinguishing module, so that the distance between the high-level semantics and the bottom-level characteristics of the image can be effectively reduced, and the image retrieval is used as the distinguishing condition, and the image retrieval efficiency is improved.
4. In the invention, the image feature extraction module is arranged, the CBIR image extraction technology is adopted, the feature content is obtained in the image, the features are extracted from the position information of color, shape, texture and space by utilizing the CBIR, and the more similar features observed by a designer are extracted.
5. In the invention, through the arranged wavelet transform module, the image is graded according to the definition of the wavelet orthogonal basis under the square integrable function space, each grade of decomposition is decomposed into a low-frequency part and three high-frequency parts, the low-frequency part is continuously decomposed when the lower-grade decomposition is carried out, the low-frequency part can be regarded as the thumbnail of the image content, and the high-frequency part stores the detail information of the texture, the edge and the like of the image.
6. In the invention, the image area characteristics are fuzzified by the arranged fuzzification processing module, and finally the area fuzzy characteristics are obtained.
7. In the invention, the set image feature library establishing module applies a Cauthy function membership function with simple calculation to act on each area to obtain the fuzzy feature of the area: and (3) fuzzy color histograms, fuzzy texture features and fuzzy shape features, extracting the features of the image, and establishing an image feature library.
8. According to the invention, through the set feature matching module, the matching degree measurement is that the similarity calculation is carried out on the information of two images, a distance measurement method is adopted, the measurement technology is applied according to a vector space model, the extracted features of the images are regarded as points in the vector space, then the distance between the two points is spread and calculated, the similarity between new images is judged, a measurement method is selected according to different features in the calculation process, for example, the distance between histograms of the color features of the images, and the similarity measurement can be completed by using the distance between the absolute values of the histograms or the weighted distance.
Drawings
Fig. 1 is a block diagram of an intelligent package design system based on internet of things big data according to the present invention;
FIG. 2 is a sub-module block diagram of a big data mining module in the intelligent package design system based on big data of the Internet of things, which is provided by the invention;
FIG. 3 is a sub-module block diagram of a promotion image information retrieval module in the intelligent package design system based on big data of the Internet of things, which is provided by the invention;
fig. 4 is a sub-module block diagram of a graphics pre-processing module in an intelligent package design system based on internet of things big data according to the present invention;
FIG. 5 is a sub-module block diagram of a feature vector forming module in the intelligent package design system based on big data of the Internet of things, which is provided by the invention;
fig. 6 is a sub-module block diagram of a keyword input module in the intelligent package design system based on internet of things big data provided by the invention.
Illustration of the drawings:
100. an intelligent control module; 110. a keyword input module; 120. a big data mining module; 130. a publicity image information retrieval module; 140. a hot spot module is arranged; 150. the information uploading and storing module; 160. an automatic update module; 170. an intelligent server; 180. a feature vector output module in the image database; 190. a feature matching module; 200. a feature vector forming module; 210. a wavelet transform module; 220. an image preprocessing module; 230. a package design module; 240. a designer input module; 250. and finally searching an output module.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
The utility model provides an intelligence packing design system based on thing networking big data, includes intelligent control module 100, the output of intelligent control module 100 and the input electric connection of big data mining module 120, the output of big data mining module 120 and the input electric connection of propaganda image information retrieval module 130, the output of intelligent control module 100 still with the input electric connection of eigenvector output module 180 in the image database, the output of eigenvector output module 180 and the input electric connection of characteristic matching module 190 in the image database, the input of characteristic matching module 190 and the output electric connection of eigenvector formation module 200.
Specifically, as shown in fig. 1, an output end of the feature matching module 190 is electrically connected to an input end of the final retrieval output module 250, the final retrieval output module 250 includes a sector statistical graph establishing module, and the matching degree measurement is performed on two image information by using the set feature matching module 190, and a distance measurement method is adopted, wherein the measurement technology is applied according to a vector space model, the extracted features of the image are regarded as "points" in a vector space, and then the distance between the two points is spread and calculated to determine the similarity between new images, and a measurement method needs to be selected according to different features in the calculation process, for example, the distance between color feature histograms of the images, and the similarity measurement can be completed by using the distance between the absolute values of the histograms, or the weighted distance.
Specifically, as shown in fig. 1, the input end of the feature vector forming module 200 is electrically connected to the input end of the wavelet transform module 210, the input end of the wavelet transform module 210 is electrically connected to the output end of the image preprocessing module 220, the input end of the image preprocessing module 220 is electrically connected to the output end of the package design module 230, and the input end of the package design module 230 is electrically connected to the output end of the designer input module 240.
Specifically, as shown in fig. 1, the image preprocessing module 220 is composed of an image feature extraction module, an image dominant hue distinguishing module, and an image dominant hue confirmation module, an input end of the image feature extraction module is electrically connected to an output end of the package design module 230, an output end of the image dominant hue confirmation module is electrically connected to an input end of the wavelet transformation module 210, and feature content is obtained in an image by using a CBIR image extraction technique through the set image feature extraction module, the features are position information of color, shape, texture, and space, feature extraction is performed by using CBIR, and relatively similar features observed by a designer are extracted.
Specifically, as shown in fig. 1, the feature vector forming module 200 is composed of an image segmentation module, a blurring processing module, and an image feature library establishing module, and performs blurring on the image region features through the arranged blurring processing module to finally obtain the region fuzzy features, an input end of the image segmentation module is electrically connected with an output end of the wavelet transform module 210, an output end of the image feature library establishing module is electrically connected with an input end of the feature matching module 190, and the feature vector forming module applies a simply calculated Cauthy function action membership function to each region through the arranged image feature library establishing module to obtain the fuzzy features of the region: and (3) fuzzy color histograms, fuzzy texture features and fuzzy shape features, extracting the features of the image, and establishing an image feature library.
Specifically, as shown in fig. 1, the input end of the intelligent control module 100 is electrically connected to the output end of the keyword input module 110, the output end of the intelligent control module 100 is also electrically connected to the input end of the hot spot module 140, the keyword input module 110 is set to be composed of a type module for packing an article, a size module for packing a box, and a propaganda image module for packing a box, the output end of the propaganda image module for packing a box is electrically connected to the input end of the intelligent control module 100, the type module for packing an article selects a proper packing box material according to the type of the article to be packed, and the size module for packing a box determines the size of the packing box according to the size of the article to be packed, and the propaganda image module for packing a box determines the characteristics of the propaganda image input into the packing box according to the material and size of the packing box, the method mainly comprises three expression modes: numerical values, semantics, and relationships, wherein semantics and relationships include characteristics of materials, sizes, shapes, and color textures.
Example two
The utility model provides an intelligence packing design system based on thing networking big data, includes intelligent control module 100, the output of intelligent control module 100 and the input electric connection of big data mining module 120, the output of big data mining module 120 and the input electric connection of propaganda image information retrieval module 130, the output of intelligent control module 100 still with the input electric connection of eigenvector output module 180 in the image database, the output of eigenvector output module 180 and the input electric connection of characteristic matching module 190 in the image database, the input of characteristic matching module 190 and the output electric connection of eigenvector formation module 200.
Specifically, as shown in fig. 1, the intelligent control module 100 is electrically connected to the information uploading storage module 150 in a bidirectional manner, the input end of the information uploading storage module 150 is electrically connected to the output end of the automatic updating module 160, the input end of the automatic updating module 160 is electrically connected to the output end of the intelligent server 170, the input end of the intelligent server 170 is electrically connected to the output end of the information uploading storage module 150, and the output end of the intelligent server 170 is electrically connected to the input end of the intelligent control module 100.
Specifically, as shown in fig. 1, the big data mining module 120 is composed of an analysis module, a mining module, a filtering module, an impurity information eliminating module, an extracting module and an output module, an input end of the analysis module is electrically connected with an output end of the intelligent control module 100, an output end of the output module is electrically connected with an input end of the propaganda image information retrieval module 130, and by the big data mining module 120, data information is analyzed through an efficient technical method, potential filtering is performed, interference of impurity information is eliminated, key information beneficial to decision making of a user is extracted, and a powerful support is provided for data retrieval service.
Specifically, as shown in fig. 1, the promotion image information retrieval module 130 is composed of a distributed image information processing module, a parallel image information processing module and a similarity distinguishing module, an input end of the distributed image information processing module is electrically connected with an output end of the output module, the promotion image information retrieval module 130 and the distributed image information processing module are arranged to serve as a Hadoop cluster architecture, Hdps can process promotion images of the packing box more quickly by using a distributed storage and data orientation mode, not only can realize orientation of data by a single-input multi-response mode, improve the access effect of information, but also prevent the processing of the data from being affected by a single-stage hardware environment, without investing high-performance computer equipment, effectively reduce the cost of the cluster, and then, the parallel image information processing module adopts a parallel computation, finally, the similarity between the image information is distinguished by the similarity distinguishing module, the distance between the high-level semantics and the bottom-level features of the image can be effectively reduced, and the image information retrieval is used as the distinguishing condition, so that the retrieval efficiency of the image is improved.
Specifically, as shown in fig. 1, the wavelet transform module 210 classifies an image according to a wavelet orthogonal basis definition in a square integrable function space, each classification is decomposed into a low frequency part and three high frequency parts, and the image is classified according to the wavelet orthogonal basis definition in the square integrable function space by the arranged wavelet transform module 210, each classification is decomposed into a low frequency part and three high frequency parts, when a next decomposition is performed, the low frequency part is decomposed continuously, the low frequency part can be regarded as a thumbnail of image content, and the high frequency part stores detailed information such as texture and edge of the image.
The working principle is as follows: when in use, the keyword input module 110 is adopted, the proper packing box material is selected through the type module of the packed article, the size and the dimension of the packing box are determined by the packing box size and dimension module according to the size and the dimension of the article to be packed, the packing box propaganda image module determines the characteristics of the input packing box propaganda image according to the material and the dimension of the packing box, the characteristics mainly comprise three expression modes, numerical values, semantics and relations, wherein the semantics and the relations comprise the characteristics of the material, the size, the shape and the color texture, the big data mining module 120 is adopted, the data information is analyzed through an efficient technical method, the potential filtration of the data information is mined, the interference of impurity information is eliminated, the key information beneficial to the decision of a user is extracted, the powerful support is provided for the data retrieval service, the propaganda image information retrieval module 130 and the distributed image information processing module are adopted, as a Hadoop cluster architecture, Hdps can process packing box publicity images more quickly by using a distributed storage and data orientation mode, not only can realize the orientation of data by a single-input multi-response mode and improve the access effect of information, but also can ensure that the data processing is not influenced by a single-stage hardware environment, does not need to invest high-performance computer equipment, effectively reduces the cluster cost, then adopts parallel computation by using a parallel image information processing module, finally, distinguishes the similarity between image information by using a similarity distinguishing module, can effectively reduce the distance between the high-level semantics and the bottom-level characteristics of the images, and improves the retrieval efficiency of the images by using image information retrieval as a distinguishing condition, the automatic updating module 160 can also automatically update the retrieved image information by using an image characteristic extracting module and adopting a CBIR image extracting technology, acquiring characteristic content in the image, wherein the characteristics are color, shape, texture and spatial position information, extracting the characteristics by using CBIR, extracting the characteristics which are observed by designers and are relatively similar, adopting a wavelet transform module 210, defining according to a wavelet orthogonal basis under a square integrable function space, the image is graded, each level of decomposition is decomposed into a low-frequency part and three high-frequency parts, when the lower level of decomposition is carried out, the low frequency part is decomposed continuously, the low frequency part can be regarded as the abbreviation of the image content, the high frequency part stores the detail information of the texture, the edge and the like of the image, a fuzzification processing module is adopted, blurring the image area characteristics to obtain area fuzzy characteristics, adopting an image characteristic library establishing module, applying a Cauthy function membership function with simple calculation to act on each area to obtain the fuzzy characteristics of the area: the method comprises the steps of blurring a color histogram, blurring texture features and blurring shape features, extracting features of an image, establishing an image feature library, adopting a feature matching module 190, measuring matching degree, namely performing similarity calculation on information of two images, adopting a distance measurement method, taking the extracted features of the image as 'points' in a vector space according to a vector space model by using a measurement technology, then performing spread calculation on the distance between the two points, judging the similarity between new images, selecting the measurement method according to different features in the calculation process, such as the distance of image color feature histograms, and completing the similarity measurement by using the distance of absolute values of histograms or weighted distances.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (10)
1. An intelligent package design system based on Internet of things big data comprises an intelligent control module (100), and is characterized in that the output end of the intelligent control module (100) is electrically connected with the input end of a big data mining module (120), the output end of the big data mining module (120) is electrically connected with the input end of a propaganda image information retrieval module (130), the output end of the intelligent control module (100) is also electrically connected with the input end of a feature vector output module (180) in an image database, the output end of the feature vector output module (180) in the image database is electrically connected with the input end of a feature matching module (190), the input end of the feature matching module (190) is electrically connected with the output end of a feature vector forming module (200), and the output end of the feature matching module (190) is electrically connected with the input end of a final retrieval output module (250), the final retrieval output module (250) includes a sector statistical map creation module.
2. The intelligent package design system based on the big data of the internet of things as claimed in claim 1, wherein the input end of the feature vector forming module (200) is electrically connected with the input end of the wavelet transform module (210), the input end of the wavelet transform module (210) is electrically connected with the output end of the image preprocessing module (220), the input end of the image preprocessing module (220) is electrically connected with the output end of the package design module (230), and the input end of the package design module (230) is electrically connected with the output end of the designer input module (240).
3. The intelligent package design system based on the big data of the internet of things as claimed in claim 2, wherein the image preprocessing module (220) is composed of an image feature extraction module, an image dominant hue distinguishing module and an image dominant hue confirmation module, an input end of the image feature extraction module is electrically connected with an output end of the package design module (230), and an output end of the image dominant hue confirmation module is electrically connected with an input end of the wavelet transform module (210).
4. The intelligent package design system based on the big data of the internet of things as claimed in claim 3, wherein the feature vector forming module (200) is composed of an image segmentation module, a blurring processing module and an image feature library establishing module, wherein an input end of the image segmentation module is electrically connected with an output end of the wavelet transformation module (210), and an output end of the image feature library establishing module is electrically connected with an input end of the feature matching module (190).
5. The intelligent package design system based on the big data of the internet of things as claimed in claim 4, wherein an input end of the intelligent control module (100) is electrically connected with an output end of the keyword input module (110), and an output end of the intelligent control module (100) is further electrically connected with an input end of the hot spot module (140).
6. The intelligent packaging design system based on the big data of the Internet of things as claimed in claim 5, wherein the keyword input module (110) is composed of a type module of packaged articles, a size module of a packaging box and a propaganda image module of the packaging box, an output end of the propaganda image module of the packaging box is electrically connected with an input end of the intelligent control module (100), and the type module of the packaged articles selects proper packaging box materials according to the type of the articles to be packaged; the packing box size module determines the size of the packing box according to the size of the object to be packed; the packing box propaganda image module determines the characteristics of the input packing box propaganda image according to the material and the size of the packing box.
7. The intelligent package design system based on the internet of things big data as claimed in claim 1, wherein the intelligent control module (100) is electrically connected with the information uploading storage module (150) in a bidirectional manner, an input end of the information uploading storage module (150) is electrically connected with an output end of the automatic updating module (160), an input end of the automatic updating module (160) is electrically connected with an output end of the intelligent server (170), an input end of the intelligent server (170) is electrically connected with an output end of the information uploading storage module (150), and an output end of the intelligent server (170) is further electrically connected with an input end of the intelligent control module (100).
8. The intelligent packaging design system based on the big data of the Internet of things as claimed in claim 7, wherein the big data mining module (120) is composed of an analysis module, a mining module, a filtering module, an impurity information eliminating module, a refining module and an output module, wherein the input end of the analysis module is electrically connected with the output end of the intelligent control module (100), and the output end of the output module is electrically connected with the input end of the propaganda image information retrieval module (130).
9. The intelligent package design system based on the big data of the internet of things as claimed in claim 8, wherein the promotion image information retrieval module (130) is composed of a distributed image information processing module, a parallel image information processing module and a similarity distinguishing module, and an input end of the distributed image information processing module is electrically connected with an output end of the output module.
10. The intelligent package design system based on big data of the internet of things as claimed in claim 9, wherein the wavelet transform module (210) ranks the images according to the definition of wavelet orthogonal basis under the square integrable function space, and each level of decomposition is decomposed into a low frequency part and three high frequency parts.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110515946.1A CN113139220A (en) | 2021-05-12 | 2021-05-12 | Intelligent package design system based on Internet of things big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110515946.1A CN113139220A (en) | 2021-05-12 | 2021-05-12 | Intelligent package design system based on Internet of things big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113139220A true CN113139220A (en) | 2021-07-20 |
Family
ID=76816970
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110515946.1A Pending CN113139220A (en) | 2021-05-12 | 2021-05-12 | Intelligent package design system based on Internet of things big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113139220A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113988666A (en) * | 2021-11-01 | 2022-01-28 | 常州天晟紫金自动化设备有限公司 | Intelligent quantitative packaging method and system for organic silicon rubber compound |
| CN116611131A (en) * | 2023-07-05 | 2023-08-18 | 大家智合(北京)网络科技股份有限公司 | Automatic generation method, device, medium and equipment for packaging graphics |
-
2021
- 2021-05-12 CN CN202110515946.1A patent/CN113139220A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113988666A (en) * | 2021-11-01 | 2022-01-28 | 常州天晟紫金自动化设备有限公司 | Intelligent quantitative packaging method and system for organic silicon rubber compound |
| CN113988666B (en) * | 2021-11-01 | 2022-08-09 | 常州天晟紫金自动化设备有限公司 | Intelligent quantitative packaging method and system for organic silicon rubber compound |
| CN116611131A (en) * | 2023-07-05 | 2023-08-18 | 大家智合(北京)网络科技股份有限公司 | Automatic generation method, device, medium and equipment for packaging graphics |
| CN116611131B (en) * | 2023-07-05 | 2023-12-26 | 大家智合(北京)网络科技股份有限公司 | Automatic generation method, device, medium and equipment for packaging graphics |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fauqueur et al. | Region-based image retrieval: Fast coarse segmentation and fine color description | |
| Cinque et al. | Color-based image retrieval using spatial-chromatic histograms | |
| Tadi Bani et al. | Content-based image retrieval based on combination of texture and colour information extracted in spatial and frequency domains | |
| US20210312206A1 (en) | System and method for classifier training and retrieval from classifier database for large scale product identification | |
| CN113139220A (en) | Intelligent package design system based on Internet of things big data | |
| CN108985285B (en) | Commodity patent acquisition method and system based on machine identification | |
| Scherer et al. | Histograms of oriented gradients for 3d object retrieval | |
| Rejito et al. | Image indexing using color histogram and k-means clustering for optimization CBIR in image database | |
| Nemade et al. | Co-occurrence patterns based fruit quality detection for hierarchical fruit image annotation | |
| Ji et al. | Research on fabric image retrieval method based on multi-feature layered fusionon | |
| Asadi Amiri et al. | A novel content-based image retrieval system using fusing color and texture features | |
| CN104268535A (en) | Method for extracting features of two-dimensional image | |
| Winter et al. | Differential feature distribution maps for image segmentation and region queries in image databases | |
| Selvarajah et al. | Combined feature descriptor for content based image retrieval | |
| Zhu et al. | A diffusion wavelet approach for 3-D model matching | |
| CN113536018A (en) | E-commerce customer service platform image retrieval method based on convolutional neural network | |
| Pirozmand et al. | Improving the similarity search between images of agricultural products: An approach based on fuzzy rough theory | |
| Liu et al. | Rapid Extraction of Clothing Sample Profile Based on the Improved Canny Algorithm | |
| Bao et al. | Influence of boundary extraction operators on boundary shape classification algorithms based on complex networks | |
| CN112365324A (en) | Commodity picture detection method suitable for E-commerce platform | |
| Jia | Intelligent Clothing Matching Based on Feature Analysis | |
| Li et al. | Application of deep convolutional neural network under region proposal network in patent graphic recognition and retrieval | |
| Tong et al. | Efficient retrieval algorithm for multimedia image information | |
| CN116630725B (en) | Multi-dimensional screening-based garbage classification processing method, device, equipment and medium | |
| An et al. | Image retrieval based on color tone variance difference feature |
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 |