CN111125410A - Intelligent identification and retrieval system for massive graphic images - Google Patents
Intelligent identification and retrieval system for massive graphic images Download PDFInfo
- Publication number
- CN111125410A CN111125410A CN201911320080.8A CN201911320080A CN111125410A CN 111125410 A CN111125410 A CN 111125410A CN 201911320080 A CN201911320080 A CN 201911320080A CN 111125410 A CN111125410 A CN 111125410A
- Authority
- CN
- China
- Prior art keywords
- module
- image
- retrieval
- identification
- electrically connected
- 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
- 238000012545 processing Methods 0.000 claims abstract description 82
- 230000008676 import Effects 0.000 claims abstract description 11
- 230000002457 bidirectional effect Effects 0.000 claims abstract description 8
- 230000010354 integration Effects 0.000 claims description 17
- 239000011159 matrix material Substances 0.000 claims description 17
- 238000006243 chemical reaction Methods 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 15
- 230000005540 biological transmission Effects 0.000 claims description 14
- 230000003993 interaction Effects 0.000 claims description 13
- 230000009467 reduction Effects 0.000 claims description 13
- 238000009877 rendering Methods 0.000 claims description 13
- 238000011156 evaluation Methods 0.000 claims description 12
- 238000012216 screening Methods 0.000 abstract description 4
- 239000003086 colorant Substances 0.000 abstract 1
- 238000000034 method Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010422 painting Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5838—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour
Landscapes
- Engineering & Computer Science (AREA)
- Library & Information Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an intelligent identification and retrieval system for massive graphic images, which comprises a central processing module, an image data import module and a user login module, wherein the output end of the image data import module is electrically connected with the input end of the central processing module, and the central processing module is electrically connected with the user login module in a bidirectional mode. The intelligent identification and retrieval system for the massive graphic images can realize identification and retrieval of color features and continuous dynamic features in the images, well achieve the aims of identifying and retrieving shape features and retrieving colors and dynamic features, reduce the retrieval range of massive image data by combining the three features, well enrich the retrieval function, reduce the retrieval range, avoid spending a great deal of waiting and screening time of retrieval personnel, and greatly save the working time of the retrieval personnel.
Description
Technical Field
The invention relates to the technical field of image identification and retrieval, in particular to an intelligent identification and retrieval system for massive graphic images.
Background
Since the 20 th century 70 s, research on image retrieval has been started, and at this time, text-based image retrieval technology, abbreviated as TBIR, has been mainly used to describe features of images, such as authors, years, genres, sizes, etc., of paintings, in a text description manner, and after 90 s, image retrieval technology has appeared to analyze and retrieve content semantics of images, such as textures and layouts of images, etc., that is, content-based image retrieval, abbreviated as CBIR, which belongs to one of content-based retrieval, abbreviated as CBR, which also includes retrieval technology for multimedia information in other forms, such as video and audio, and in principle, whether text-based image retrieval or content-based image retrieval, mainly includes three aspects: on one hand, the analysis and the conversion of the user requirements form a question which can search the index database; on the other hand, image resources are collected and processed, characteristics are extracted, analysis and indexing are carried out, and an index database of the images is established; on the last hand, according to a similarity algorithm, the similarity between the user question and records in an index database is calculated, records meeting a threshold value are extracted as results and output in a similarity descending mode, and in order to further improve the retrieval accuracy, many systems are combined with a related feedback technology to collect feedback information of the user on the retrieval results, which is more prominent in CBIR because the CBIR realizes an image retrieval process of gradually refining and needs to continuously interact with the user in the same retrieval process.
At present, when a large amount of images are identified and searched, image searching is mostly carried out in a parallel searching mode, however, the searching method is single, only some shape features in the images can be identified and searched, a large amount of waiting and screening time of searching personnel is still needed, identification and searching of color features and continuous dynamic features in the images cannot be realized, the purposes of identifying and searching the shape features and searching the color and dynamic features cannot be achieved, the searching range of mass image data is narrowed by combining the three features, the working time of the searching personnel is greatly wasted, and therefore great inconvenience is brought to image identification and searching work of the searching personnel.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides an intelligent identification and retrieval system for massive graphic images, which solves the problems that the existing retrieval method is single, only can identify and retrieve some shape features in the images, still needs a great deal of waiting and screening time of a retrieval person, cannot identify and retrieve color features and continuous dynamic features in the images, cannot achieve the purposes of identifying and retrieving the shape features and retrieving the color and dynamic features, cannot reduce the retrieval range of massive image data by combining the three features, and greatly wastes the working time of the retrieval person.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme: the utility model provides a magnanimity figure image intelligent identification retrieval system, includes central processing module, image data import module and user login module, the output of image data import module and central processing module's input electric connection, and central processing module and user login module realize two-way electric connection, central processing module realizes two-way electric connection with user interaction unit, image retrieval recognition unit, image processing unit and image distribution formula parallel processing unit respectively, and user interaction unit includes figure type selection module, retrieval image modeling module, retrieval image rendering module and continuous image characteristic integration module, image retrieval recognition unit includes conventional image retrieval recognition module, continuous image retrieval recognition unit and color figure retrieval recognition module.
Preferably, the output end of the graphic type selection module is electrically connected to the input end of the retrieval image modeling module, the output end of the retrieval image modeling module is electrically connected to the input end of the retrieval image rendering module, and the output end of the retrieval image rendering module is electrically connected to the input end of the continuous image feature integration module.
Preferably, the continuous image retrieval and identification unit comprises a continuous image model importing module, a database matching module and an identification and evaluation module.
Preferably, the output end of the continuous image model importing module is electrically connected with the input end of the database matching module, and the output end of the database matching module is electrically connected with the input end of the identification and evaluation module.
Preferably, the image processing unit comprises an image dimension reduction algorithm processing module, an a/D conversion module, an image feature matrix extraction module and a feature identification module, and an output end of the image dimension reduction algorithm processing module is electrically connected with an input end of the a/D conversion module.
Preferably, the output end of the a/D conversion module is electrically connected to the input end of the image feature matrix extraction module, and the output end of the image feature matrix extraction module is electrically connected to the input end of the feature identification module.
Preferably, the image distributed parallel processing unit includes a parallel line selection module, a processing bus data transmission module, and a parallel line data distribution module, wherein an output end of the parallel line selection module is electrically connected to an input end of the processing bus data transmission module, and an output end of the processing bus data transmission module is electrically connected to an input end of the parallel line data distribution module.
Preferably, the central processing module is electrically connected with the retrieval image feature integration module and the system security protection module in a bidirectional manner, and the output end of the retrieval image feature integration module is electrically connected with the input end of the image processing unit.
(III) advantageous effects
The invention provides an intelligent identification and retrieval system for massive graphic images. Compared with the prior art, the method has the following beneficial effects:
(1) the intelligent identification and retrieval system for the massive graphic images realizes bidirectional electrical connection with a user interaction unit, an image retrieval and identification unit, an image processing unit and an image distributed parallel processing unit through a central processing module, the user interaction unit comprises a graphic type selection module, a retrieval image modeling module, a retrieval image rendering module and a continuous image characteristic integration module, the image retrieval and identification unit comprises a conventional image retrieval and identification module, a continuous image retrieval and identification unit and a color image retrieval and identification module, can realize identification and retrieval of color characteristics and continuous dynamic characteristics in images, well achieves the aims of not only carrying out shape characteristic identification and retrieval but also color and dynamic characteristic retrieval, and realizes the reduction of the retrieval range of massive image data by combining the three characteristics, the method has the advantages of enriching retrieval functions, reducing the retrieval range, saving a large amount of waiting and screening time of the retrieval personnel, and greatly saving the working time of the retrieval personnel, thereby greatly facilitating the image identification and retrieval work of the retrieval personnel.
(2) The image processing unit comprises an image dimension reduction algorithm processing module, an A/D conversion module, an image feature matrix extraction module and a feature recognition module, the output end of the image dimension reduction algorithm processing module is electrically connected with the input end of the A/D conversion module, the output end of the A/D conversion module is electrically connected with the input end of the image feature matrix extraction module, the output end of the image feature matrix extraction module is electrically connected with the input end of the feature recognition module, preprocessing of data to be recognized can be achieved, therefore modeling data can be rapidly paired with data to be matched, and data matching time is well saved.
Drawings
FIG. 1 is a schematic block diagram of the architecture of the system of the present invention;
FIG. 2 is a schematic block diagram of the structure of an image processing unit according to the present invention;
FIG. 3 is a schematic block diagram of the architecture of the image distributed parallel processing unit according to the present invention.
In the figure, 1 a central processing module, 2 an image data import module, 3 a user login module, 4 a user interaction unit, 41 an image type selection module, 42A retrieval image modeling module, 43 a retrieval image rendering module, 44 a continuous image feature integration module, 5 an image retrieval identification unit, 51 a conventional image retrieval identification module, 52A continuous image retrieval identification unit, 521 a continuous image model import module, 522A database proportioning module, 523 a recognition evaluation module, 53 a color image retrieval identification module, 6 an image processing unit, 61 an image dimension reduction algorithm processing module, 62A/D conversion module, 63 an image feature matrix extraction module, 64 a feature identification module, 7 an image distributed parallel processing unit, 71 a parallel line selection module, 72A processing bus data transmission module, 73 a parallel line data distribution module, 8 a retrieval image feature integration module, And 9, a system safety protection 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.
Referring to fig. 1-3, an embodiment of the present invention provides a technical solution: an intelligent identification and retrieval system for massive graphic images comprises a central processing module 1, an image data import module 2 and a user login module 3, wherein the output end of the image data import module 2 is electrically connected with the input end of the central processing module 1, the central processing module 1 is electrically connected with the user login module 3 in a bidirectional way, the central processing module 1 is respectively electrically connected with a user interaction unit 4, an image retrieval identification unit 5, an image processing unit 6 and an image distributed parallel processing unit 7 in a bidirectional way, the user interaction unit 4 comprises a graphic type selection module 41, a retrieval image modeling module 42, a retrieval image rendering module 43 and a continuous image characteristic integration module 44, the user interaction with the whole identification and retrieval system is carried out through the user interaction unit 4, and at the moment, the user can select and limit the image types to be identified and retrieved through the image type selection module 41, then, the retrieved image modeling module 42 performs modeling processing according to the characteristics of the image to be retrieved, the retrieved image rendering module 43 renders the color characteristics in the image characteristics and matches the color characteristics to the retrieved characteristics, and the continuous image characteristic integration module 44 integrates two or more image characteristics to be retrieved into dynamic characteristics, wherein the image retrieval and identification unit 5 comprises a conventional image retrieval and identification module 51, a continuous image retrieval and identification unit 52 and a color pattern retrieval and identification module 53, the output end of the graph type selection module 41 is electrically connected with the input end of the retrieved image modeling module 42, the output end of the retrieved image modeling module 42 is electrically connected with the input end of the retrieved image rendering module 43, the output end of the retrieved image rendering module 43 is electrically connected with the input end of the continuous image characteristic integration module 44, and the continuous image retrieval and identification unit 52 comprises a continuous image model importing module 521, The output end of the continuous image model importing module 521 is electrically connected with the input end of the database matching module 522, the output end of the database matching module 522 is electrically connected with the input end of the identification evaluation module 523, when the dynamic characteristic image is identified and retrieved, the created dynamic characteristic model is imported into the system through the continuous image model importing module 521 in the continuous image retrieval and identification unit 52, then the data matching processing is performed through the database matching module 522, then the matching degree evaluation is performed through the identification evaluation module 523, the continuous dynamic image information can be determined after the evaluation value reaches the qualified value, the image processing unit 6 comprises an image dimension reduction algorithm processing module 61, an A/D conversion module 62, an image feature matrix extraction module 63 and a feature identification module 64, the central processing module 1 controls the image dimension reduction algorithm processing module 61 in the image processing unit 6 to reduce the image dimension Dimension processing, converting the data into binary data through an A/D conversion module 62, extracting a feature matrix matched with the required conventional image feature or color image feature through an image feature matrix extraction module 63, then identifying the extracted feature again through a feature identification module 64, determining image information if the identification is successful, electrically connecting the output end of the image dimension reduction algorithm processing module 61 with the input end of the A/D conversion module 62, electrically connecting the output end of the A/D conversion module 62 with the input end of the image feature matrix extraction module 63, electrically connecting the output end of the image feature matrix extraction module 63 with the input end of the feature identification module 64, wherein the image distributed parallel processing unit 7 comprises a parallel line selection module 71, a processing bus data transmission module 72 and a parallel line data distribution module 73, the output end of the parallel line selection module 71 is electrically connected with the input end of the processing bus data transmission module 72, the output end of the processing bus data transmission module 72 is electrically connected with the input end of the parallel line data distribution module 73, the central processing module 1 controls the parallel line selection module 71 in the image distributed parallel processing unit 7 to determine the number of processed lines, then the bus data transmission is carried out through the processing bus data transmission module 72, then the line data distribution processing is carried out through the parallel line data distribution module 73, the central processing module 1 is respectively electrically connected with the retrieval image feature integration module 8 and the system security protection module 9 in a bidirectional mode, and the output end of the retrieval image feature integration module 8 is electrically connected with the input end of the image processing unit 6.
When the system is used, firstly, a user logs in through the user login module 3, interaction with the whole identification and retrieval system can be carried out through the user interaction unit 4 after the login is successful, at the moment, the user can select and limit the image type to be identified and retrieved through the image type selection module 41, then modeling processing is carried out through the retrieval image modeling module 42 according to the characteristics of the image to be retrieved, then color characteristics in the image characteristics are rendered through the retrieval image rendering module 43 and matched into retrieval characteristics, then two or more than two image characteristics required to be retrieved are integrated into dynamic characteristics through the continuous image characteristic integration module 44, external massive image data can be introduced into the system through the image data introduction module 2, then the central processing module 1 controls the parallel line selection module 71 in the image distributed parallel processing unit 7 to determine the number of lines to be processed, then, the bus data transmission is performed by the processing bus data transmission module 72, and then the line data distribution processing is performed by the parallel line data distribution module 73.
When the conventional image or the image with color is identified, the central processing module 1 controls the conventional image retrieval identification module 51 and the color image retrieval identification module 53 in the image retrieval identification unit 5 to retrieve, then the central processing module 1 controls the image dimension reduction algorithm processing module 61 in the image processing unit 6 to perform dimension reduction processing on the image, and converts the image into binary data through the A/D conversion module 62, then the image feature matrix extraction module 63 extracts the feature matrix matched with the required conventional image feature or color image feature, then the feature identification module 64 performs recognition again on the extracted feature, if the recognition is successful, the image information can be determined, when the dynamic feature image is identified and retrieved, the created dynamic feature model is imported into the system through the continuous image model import module 521 in the continuous image retrieval identification unit 52, then, the data matching processing is performed through the database matching module 522, then the matching degree evaluation is performed through the identification evaluation module 523, and after the evaluation value reaches a qualified value, the continuous dynamic image information can be determined, so that the whole working process of the intelligent identification and retrieval system for the massive graphic images is completed.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments 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 utility model provides a magnanimity figure image intelligent recognition retrieval system, includes central processing module (1), image data import module (2) and user login module (3), the output of image data import module (2) and the input electric connection of central processing module (1), and central processing module (1) and user login module (3) realize two-way electric connection, its characterized in that: the image retrieval system is characterized in that the central processing module (1) is respectively electrically connected with the user interaction unit (4), the image retrieval identification unit (5), the image processing unit (6) and the image distributed parallel processing unit (7) in a bidirectional mode, the user interaction unit (4) comprises a graphic type selection module (41), a retrieval image modeling module (42), a retrieval image rendering module (43) and a continuous image feature integration module (44), and the image retrieval identification unit (5) comprises a conventional image retrieval identification module (51), a continuous image retrieval identification unit (52) and a color image retrieval identification module (53).
2. The intelligent identification and retrieval system for massive graphic images according to claim 1, wherein: the output end of the graph type selection module (41) is electrically connected with the input end of the retrieval image modeling module (42), the output end of the retrieval image modeling module (42) is electrically connected with the input end of the retrieval image rendering module (43), and the output end of the retrieval image rendering module (43) is electrically connected with the input end of the continuous image feature integration module (44).
3. The intelligent identification and retrieval system for massive graphic images according to claim 1, wherein: the continuous image retrieval and identification unit (52) comprises a continuous image model importing module (521), a database proportioning module (522) and an identification and evaluation module (523).
4. The intelligent identification and retrieval system for massive graphic images according to claim 3, wherein: the output end of the continuous image model importing module (521) is electrically connected with the input end of the database proportioning module (522), and the output end of the database proportioning module (522) is electrically connected with the input end of the identification evaluation module (523).
5. The intelligent identification and retrieval system for massive graphic images according to claim 1, wherein: the image processing unit (6) comprises an image dimension reduction algorithm processing module (61), an A/D conversion module (62), an image characteristic matrix extraction module (63) and a characteristic identification module (64), and the output end of the image dimension reduction algorithm processing module (61) is electrically connected with the input end of the A/D conversion module (62).
6. The intelligent identification and retrieval system for massive graphic images according to claim 5, wherein: the output end of the A/D conversion module (62) is electrically connected with the input end of the image characteristic matrix extraction module (63), and the output end of the image characteristic matrix extraction module (63) is electrically connected with the input end of the characteristic identification module (64).
7. The intelligent identification and retrieval system for massive graphic images according to claim 1, wherein: the image distributed parallel processing unit (7) comprises a parallel line selection module (71), a processing bus data transmission module (72) and a parallel line data distribution module (73), wherein the output end of the parallel line selection module (71) is electrically connected with the input end of the processing bus data transmission module (72), and the output end of the processing bus data transmission module (72) is electrically connected with the input end of the parallel line data distribution module (73).
8. The intelligent identification and retrieval system for massive graphic images according to claim 1, wherein: the central processing module (1) is respectively electrically connected with the retrieval image feature integration module (8) and the system safety protection module (9) in a bidirectional mode, and the output end of the retrieval image feature integration module (8) is electrically connected with the input end of the image processing unit (6).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911320080.8A CN111125410A (en) | 2019-12-19 | 2019-12-19 | Intelligent identification and retrieval system for massive graphic images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911320080.8A CN111125410A (en) | 2019-12-19 | 2019-12-19 | Intelligent identification and retrieval system for massive graphic images |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111125410A true CN111125410A (en) | 2020-05-08 |
Family
ID=70500356
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911320080.8A Pending CN111125410A (en) | 2019-12-19 | 2019-12-19 | Intelligent identification and retrieval system for massive graphic images |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111125410A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114248490A (en) * | 2021-12-06 | 2022-03-29 | 汇源印刷包装科技（天津）股份有限公司 | Automatic fault self-checking system of box making machine |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102831187A (en) * | 2012-08-02 | 2012-12-19 | 成都众合云盛科技有限公司 | Content-based image retrieval system |
| CN103927387A (en) * | 2014-04-30 | 2014-07-16 | 成都理想境界科技有限公司 | Image retrieval system, method and device |
| CN104021229A (en) * | 2014-06-25 | 2014-09-03 | 厦门大学 | Shape representing and matching method for trademark image retrieval |
| CN104462481A (en) * | 2014-12-18 | 2015-03-25 | 浪潮(北京)电子信息产业有限公司 | Comprehensive image retrieval method based on colors and shapes |
| CN105574035A (en) * | 2014-10-16 | 2016-05-11 | 西安景行数创信息科技有限公司 | Intelligent recognition and retrieval system and method for mass graphic images |
| CN107004025A (en) * | 2015-03-13 | 2017-08-01 | 株式会社日立制作所 | Image retrieving apparatus and the method for retrieving image |
-
2019
- 2019-12-19 CN CN201911320080.8A patent/CN111125410A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102831187A (en) * | 2012-08-02 | 2012-12-19 | 成都众合云盛科技有限公司 | Content-based image retrieval system |
| CN103927387A (en) * | 2014-04-30 | 2014-07-16 | 成都理想境界科技有限公司 | Image retrieval system, method and device |
| CN104021229A (en) * | 2014-06-25 | 2014-09-03 | 厦门大学 | Shape representing and matching method for trademark image retrieval |
| CN105574035A (en) * | 2014-10-16 | 2016-05-11 | 西安景行数创信息科技有限公司 | Intelligent recognition and retrieval system and method for mass graphic images |
| CN104462481A (en) * | 2014-12-18 | 2015-03-25 | 浪潮(北京)电子信息产业有限公司 | Comprehensive image retrieval method based on colors and shapes |
| CN107004025A (en) * | 2015-03-13 | 2017-08-01 | 株式会社日立制作所 | Image retrieving apparatus and the method for retrieving image |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114248490A (en) * | 2021-12-06 | 2022-03-29 | 汇源印刷包装科技（天津）股份有限公司 | Automatic fault self-checking system of box making machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109992645B (en) | Data management system and method based on text data | |
| CN109189991B (en) | Duplicate video identification method, device, terminal and computer readable storage medium | |
| CN107169106B (en) | Video retrieval method, device, storage medium and processor | |
| CN102915299A (en) | Word segmentation method and device | |
| CN114077682B (en) | Intelligent recognition matching processing method and system for image retrieval and storage medium | |
| CN115203421A (en) | Method, device and equipment for generating label of long text and storage medium | |
| CN102722528A (en) | Real-time mass image retrieval method based on mobile devices | |
| CN111666263A (en) | Method for realizing heterogeneous data management in data lake environment | |
| CN113761242A (en) | A big data image recognition system and method based on artificial intelligence | |
| CN101515286A (en) | Image matching method based on image feature multi-level filtration | |
| CN108121806A (en) | One kind is based on the matched image search method of local feature and system | |
| CN111597416A (en) | Matching pushing system based on big data processing | |
| CN118779458B (en) | A sensitive information analysis and identification method, system, device and readable storage medium | |
| CN111125410A (en) | Intelligent identification and retrieval system for massive graphic images | |
| CN103020630B (en) | The disposal route of characteristics of image and device | |
| CN112148938B (en) | Cross-domain heterogeneous data retrieval system and retrieval method | |
| CN108875050A (en) | Digital evidence obtaining analysis method, device and the computer-readable medium of text-oriented | |
| CN112732646A (en) | File searching method and device and electronic equipment | |
| CN118551060A (en) | Method and system for identifying and managing content of intelligent media editing based on data mining | |
| CN116595043A (en) | Big data retrieval method and device | |
| CN113449173B (en) | Information technology extraction system based on feature sampling | |
| CN112967759B (en) | DNA material evidence identification STR typing comparison method based on memory stack technology | |
| CN110895541A (en) | Intelligent platform for Timing cloud data statistics | |
| Yan et al. | Research on application value analysis of real estate registration based on big data mining | |
| Cheng et al. | Content-based video retrieval using the shot cluster tree |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200508 |
|
| RJ01 | Rejection of invention patent application after publication |