CN112528066A - Trademark retrieval method and system based on attention mechanism, computer equipment and storage medium - Google Patents
Trademark retrieval method and system based on attention mechanism, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112528066A CN112528066A CN202011511790.1A CN202011511790A CN112528066A CN 112528066 A CN112528066 A CN 112528066A CN 202011511790 A CN202011511790 A CN 202011511790A CN 112528066 A CN112528066 A CN 112528066A
- Authority
- CN
- China
- Prior art keywords
- trademark
- image
- module
- feature
- retrieval
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000000605 extraction Methods 0.000 claims description 18
- 238000007781 pre-processing Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 9
- 238000005259 measurement Methods 0.000 claims description 8
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 230000000007 visual effect Effects 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
- G06F16/55—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention provides an attention mechanism-based trademark retrieval method, an attention mechanism-based trademark retrieval system, computer equipment and a storage medium.
Description
Technical Field
The invention relates to the field of image retrieval, in particular to a trademark retrieval method and system based on an attention mechanism, a computer device and a storage medium.
Background
Trademarks are increasingly regarded by various industries as important marks of commodities and manufacturers. The core technology in trademark retrieval is extraction and measurement of trademark features. Whether the extraction of the trademark features is accurate or not directly influences the subsequent retrieval result. In the past, a trademark management department searches in a form of 'classification number' and judges the similarity between images by manpower, and the method has the problems of large workload and low efficiency. In order to solve the difficult problem of the search work, researchers at home and abroad begin to capture more accurate trademark feature information in a content-based image search mode, and deviation caused by character description is avoided.
In the conventional image trademark retrieval method, people prefer to perform feature extraction through the shallow visual features of the image, such as a shape context method, extraction of SIFT features, a trademark retrieval algorithm based on the zernike moment and edge gradient co-occurrence moment proposed from the perspective of the shape descriptor of the trademark, and the like. The content of the trademark image has no equal importance, and information elements which are more important relative to surrounding features exist, so that the existing method cannot judge the information with different importance, and the capability of extracting key features is insufficient.
Chinese patent CN111797260A published in 10/20/2020 provides a trademark retrieval system based on image recognition, which comprises a database, wherein the database is in signal connection with a classification unit, the classification unit is in signal connection with a plurality of data sets, the data sets are in signal connection with an algorithm module, the algorithm module is in signal connection with a training module, the training module is in signal connection with a storage module, the storage module is in signal connection with a plurality of initial centroid sets, the initial centroid sets are in signal connection with a comparison unit and a search module, the comparison unit is in signal connection with an output module, the search module is in signal connection with a characteristic recognition unit, the characteristic recognition unit is in signal connection with a temporary storage module, and the temporary storage module is in signal connection with an input module. The invention has the characteristics of comparing the characteristics of the trademark independently and being beneficial to the retrieval effect, but the extracted trademark characteristics are inaccurate.
Disclosure of Invention
The invention provides a trademark retrieval method, a system, computer equipment and a storage medium based on an attention mechanism, aiming at overcoming the defect that the key features of trademark images extracted by the prior art are inaccurate.
The technical scheme of the invention is as follows:
the invention provides a trademark retrieval method based on an attention mechanism, which comprises the following steps of:
s1: acquiring a trademark data set;
s2: building a channel attention network module;
s3: the preprocessing module preprocesses the trademark image in the trademark data set to obtain a preprocessed trademark image xiI is 1,2, …, n, n is the number of the preprocessed trademark images and is input into the channel attention network module;
s4: the channel attention network module is used for weighting omega according to the characteristic channel domainiFor the preprocessed trademark image xiTraining and distributing to obtain preprocessed trademark image xiCorresponding initial brand feature viI 1,2, … n, the initial brand feature viForming an initial trademark feature set V, and inputting the initial trademark feature set V into an example distinguishing module;
s5: instance Distinguishing Module for initial Brand feature V in initial Brand feature set ViCalculating loss and optimizing the loss, continuously and iteratively updating the trademark feature set V to obtain trademark feature training data to form a training data set, and training an unsupervised network by using the training data set to obtain a feature extraction network;
s6: inputting all trademark images in the trademark data set into a feature extraction network to obtain a trademark image feature database, and storing the trademark image feature database into a retrieval module;
s7: inputting the trademark image to be retrieved into a feature extraction network to obtain the trademark image feature to be retrieved, and transmitting the trademark image feature to be retrieved to a retrieval module;
s8: and the retrieval module performs similarity measurement on the trademark image features to be retrieved and the trademark features in the trademark image feature database, and outputs a trademark image sequencing result similar to the trademark images to be retrieved.
Preferably, in S2, the method for constructing the channel attention network module includes: and selecting ResNet50 as a basic network, and inserting a channel attention module between each convolution layer of the basic network to form a channel attention network module.
Preferably, in S3, the specific method for the preprocessing module to preprocess the trademark image in the data set is as follows: and cutting the trademark image, converting the trademark image into a gray-scale image, converting the gray-scale image into a tensor, and normalizing the tensor.
Preferably, in S3, the preprocessed trademark image xiThe input channel attention network module inputs in time-division batches.
Preferably, in S4, the characteristic channel domain weight ωiCalculated by the following formula:
where σ () is the Sigmoid function, k is the convolution kernel size of the channel attention module,is a tilt parameter.
Preferably, in S5, the trademark feature v is calculatediThe loss J of (a) is calculated by the following loss function:
wherein ,image x representing a trademarkiIn the expectation that the position of the target is not changed,representing the expectation of noisy data, PnRepresenting noisy data, viImage x representing a trademarkiCorresponding brand features, V, in the set of brand features VjIndicating a difference from V in the set of characteristics V of the trademarkiM represents that the noise data is m times the trademark image,representing a characteristic channel domain weight ωiτ denotes a temperature parameter, ZiFor normalization constants, exp () represents an exponential function with e as the base.
Preferably, in S8, the specific method for measuring the similarity includes: the searching module calculates the Euclidean distance between the trademark image feature to be searched and the trademark feature in the trademark image feature database, wherein the smaller the Euclidean distance is, the more similar the corresponding trademark image and the trademark image to be searched are.
The invention also provides a trademark retrieval system based on the attention mechanism, which comprises a preprocessing module, a channel attention network module, an instance distinguishing module and a retrieval module;
the preprocessing module is used for preprocessing the trademark image in the trademark data set to obtain a preprocessed trademark image;
the channel attention network module trains and distributes the preprocessed trademark images to obtain an initial trademark feature set;
the example distinguishing module calculates loss of the initial trademark features in the initial trademark feature set and optimizes the loss to obtain trademark feature training data to form a training data set, and the training data set is used for training an unsupervised network to obtain a feature extraction network;
and the retrieval module performs similarity measurement on the trademark image features to be retrieved and the trademark features in the trademark image feature database, and outputs a trademark image sequencing result similar to the trademark images to be retrieved.
The invention also provides computer equipment which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the trademark retrieval method based on the attention mechanism when executing the computer program.
The present invention also proposes a computer-readable storage medium on which a computer program is stored, which, when executed by a processor, implements the steps of the above-mentioned attention-based trademark retrieval method.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that:
according to the invention, more reasonable weight distribution is carried out on the trademark image features through the channel attention network module, the difference of the trademark image features is learned through the instance distinguishing module, the loss of the trademark image features is optimized, the unsupervised network is trained by utilizing the obtained training data set to form the feature extraction network, and the feature extraction network can accurately extract the key features of the trademark image.
Drawings
Fig. 1 is a flowchart of a trademark retrieval method based on an attention mechanism in embodiment 1;
FIG. 2 is a schematic diagram illustrating the effect of the trademark retrieval method based on the attention mechanism in embodiment 1;
fig. 3 is a schematic block diagram of a trademark retrieval system based on an attention mechanism in embodiment 2.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the patent;
for the purpose of better illustrating the embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product;
it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
Example 1
The embodiment provides a trademark retrieval method based on an attention mechanism, as shown in fig. 1, the method comprises the following steps:
s1: acquiring a trademark data set; the trademark dataset is a METU trademark dataset.
S2: building a channel attention network module;
s3: the preprocessing module preprocesses the trademark image in the trademark data set to obtain a preprocessed trademark image xiI is 1,2, …, n, n is the number of the preprocessed trademark images and is input into the channel attention network module;
s4: the channel attention network module is used for weighting omega according to the characteristic channel domainiFor the preprocessed trademark image xiTraining and distributing to obtain preprocessed trademark image xiCorresponding initial brand feature viI 1,2, … n, the initial brand feature viForming an initial trademark feature set V, and inputting the initial trademark feature set V into an example distinguishing module;
s5: instance Distinguishing Module for initial Brand feature V in initial Brand feature set ViCalculating loss and optimizing the loss, continuously and iteratively updating the trademark feature set V to obtain trademark feature training data to form a training data set, and training an unsupervised network by using the training data set to obtain a feature extraction network; the unsupervised network is an ECA _ ResNet50 network;
s6: inputting all trademark images in the trademark data set into a feature extraction network to obtain a trademark image feature database, and storing the trademark image feature database into a retrieval module;
s7: inputting the trademark image to be retrieved into a feature extraction network to obtain the trademark image feature to be retrieved, and transmitting the trademark image feature to be retrieved to a retrieval module;
s8: the retrieval module measures the similarity between the trademark image features to be retrieved and the trademark features in the trademark image feature database, and outputs a trademark image sequencing result similar to the trademark images to be retrieved as shown in fig. 2.
In S2, the method for building the channel attention network module includes: and selecting ResNet50 as a basic network, and inserting a channel attention module between each convolution layer of the basic network to form a channel attention network module.
In S3, the specific method for the preprocessing module to preprocess the trademark image in the data set is as follows: and cutting the trademark image, converting the trademark image into a gray-scale image, converting the gray-scale image into a tensor, and normalizing the tensor.
In S3, the preprocessed trademark image xiThe input channel attention network module inputs in time-division batches.
In S4, the characteristic channel domain weight ωiCalculated by the following formula:
where σ () is the Sigmoid function, k is the convolution kernel size of the channel attention module,is a tilt parameter.
In the step S5, a trademark feature v is calculatediThe loss J of (a) is calculated by the following loss function:
wherein ,image x representing a trademarkiIn the expectation that the position of the target is not changed,representing the expectation of noisy data, PnRepresenting noisy data, viImage x representing a trademarkiCorresponding brand features, V, in the set of brand features VjIndicating a difference from V in the set of characteristics V of the trademarkiM represents that the noise data is m times the trademark image,representing a characteristic channel domain weight ωiτ denotes a temperature parameter, ZiFor normalization constants, exp () represents an exponential function with e as the base.
In S8, the specific method of similarity measurement is as follows: the searching module calculates the Euclidean distance between the trademark image feature to be searched and the trademark feature in the trademark image feature database, wherein the smaller the Euclidean distance is, the more similar the corresponding trademark image and the trademark image to be searched are.
The embodiment also proposes a computer device, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above-mentioned trademark retrieval method based on attention mechanism when executing the computer program.
The present embodiment also proposes a computer-readable storage medium on which a computer program is stored, the computer program, when executed by a processor, implementing the steps of the above-described attention-based trademark retrieval method.
Example 2
The embodiment provides a trademark retrieval system based on an attention mechanism, and as shown in fig. 3, the system comprises a preprocessing module, a channel attention network module, an instance distinguishing module and a retrieval module;
the preprocessing module is used for preprocessing the trademark image in the trademark data set to obtain a preprocessed trademark image;
the channel attention network module trains and distributes the preprocessed trademark images to obtain an initial trademark feature set;
the example distinguishing module calculates loss of the initial trademark features in the initial trademark feature set and optimizes the loss to obtain trademark feature training data to form a training data set, and the training data set is used for training an unsupervised network to obtain a feature extraction network;
and the retrieval module performs similarity measurement on the trademark image features to be retrieved and the trademark features in the trademark image feature database, and outputs a trademark image sequencing result similar to the trademark images to be retrieved.
It should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (10)
1. An attention-based trademark retrieval method is characterized by comprising the following steps of:
s1: acquiring a trademark data set;
s2: building a channel attention network module;
s3: the preprocessing module preprocesses the trademark image in the trademark data set to obtain a preprocessed trademark image xiI is 1,2, …, n, n is the number of the preprocessed trademark images and is input into the channel attention network module;
s4: the channel attention network module is used for weighting omega according to the characteristic channel domainiFor the preprocessed trademark image xiTraining and distributing to obtain preprocessed trademark image xiCorresponding initial brand feature viI 1,2, … n, the initial brand feature viForming an initial trademark feature set V, and inputting the initial trademark feature set V into an example distinguishing module;
s5: instance Distinguishing Module for initial Brand feature V in initial Brand feature set ViCalculating the loss and applying itOptimizing, namely obtaining trademark feature training data to form a training data set, and training an unsupervised network by using the training data set to obtain a feature extraction network;
s6: inputting all trademark images in the trademark data set into a feature extraction network to obtain a trademark image feature database, and storing the trademark image feature database into a retrieval module;
s7: inputting the trademark image to be retrieved into a feature extraction network to obtain the trademark image feature to be retrieved, and transmitting the trademark image feature to be retrieved to a retrieval module;
s8: and the retrieval module performs similarity measurement on the trademark image features to be retrieved and the trademark features in the trademark image feature database, and outputs a trademark image sequencing result similar to the trademark images to be retrieved.
2. The trademark retrieval method based on attention mechanism as claimed in claim 1, wherein in S2, the method for constructing the channel attention network module is as follows: and selecting ResNet50 as a basic network, and inserting a channel attention module between each convolution layer of the basic network to form a channel attention network module.
3. The trademark retrieval method based on attention mechanism as claimed in claim 2, wherein in S3, the specific method for the pre-processing module to pre-process the trademark image in the data set is as follows: and cutting the trademark image, converting the trademark image into a gray-scale image, converting the gray-scale image into a tensor, and normalizing the tensor.
4. The trademark retrieval method based on attention mechanism as claimed in claim 3, wherein in the step S3, the preprocessed trademark image xiThe input channel attention network module inputs in time-division batches.
5. The trademark retrieval method based on attention mechanism as claimed in claim 4, wherein in the step S4, the characteristic channel domain weight ω isiFrom belowCalculating by the formula:
6. The trademark retrieval method based on attention mechanism as claimed in claim 5, wherein in the step S5, trademark feature v is calculatediThe loss J of (a) is calculated by the following loss function:
wherein ,image x representing a trademarkiIn the expectation that the position of the target is not changed,representing the expectation of noisy data, PnRepresenting noisy data, viImage x representing a trademarkiCorresponding brand features, V, in the set of brand features VjIndicating a difference from V in the set of characteristics V of the trademarkiM represents that the noise data is m times the trademark image,representing a characteristic channel domain weight ωiτ denotes a temperature parameter, ZiFor normalization constants, exp () represents an exponential function with e as the base.
7. The trademark retrieval method based on attention mechanism as claimed in claim 6, wherein in S8, the specific method of similarity measurement is as follows: the searching module calculates the Euclidean distance between the trademark image feature to be searched and the trademark feature in the trademark image feature database, wherein the smaller the Euclidean distance is, the more similar the corresponding trademark image and the trademark image to be searched are.
8. A trademark retrieval system based on an attention mechanism is characterized by comprising a preprocessing module, a channel attention network module, an instance distinguishing module and a retrieval module;
the preprocessing module is used for preprocessing the trademark image in the trademark data set to obtain a preprocessed trademark image;
the channel attention network module trains and distributes the preprocessed trademark images to obtain an initial trademark feature set;
the example distinguishing module calculates loss of the initial trademark features in the initial trademark feature set and optimizes the loss to obtain trademark feature training data to form a training data set, and an unsupervised network is trained by using the training data set to obtain a feature extraction network;
and the retrieval module performs similarity measurement on the trademark image features to be retrieved and the trademark features in the trademark image feature database, and outputs a trademark image sequencing result similar to the trademark images to be retrieved.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011511790.1A CN112528066B (en) | 2020-12-18 | 2020-12-18 | Trademark retrieval method, system, computer device and storage medium based on attention mechanism |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011511790.1A CN112528066B (en) | 2020-12-18 | 2020-12-18 | Trademark retrieval method, system, computer device and storage medium based on attention mechanism |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112528066A true CN112528066A (en) | 2021-03-19 |
CN112528066B CN112528066B (en) | 2023-08-04 |
Family
ID=75001771
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011511790.1A Active CN112528066B (en) | 2020-12-18 | 2020-12-18 | Trademark retrieval method, system, computer device and storage medium based on attention mechanism |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112528066B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108681555A (en) * | 2018-04-08 | 2018-10-19 | 天津大学 | A kind of sketch image search method returned based on shape |
CN108920720A (en) * | 2018-07-30 | 2018-11-30 | 电子科技大学 | The large-scale image search method accelerated based on depth Hash and GPU |
CN109086437A (en) * | 2018-08-15 | 2018-12-25 | 重庆大学 | A kind of image search method merging Faster-RCNN and Wasserstein self-encoding encoder |
CN110059206A (en) * | 2019-03-29 | 2019-07-26 | 银江股份有限公司 | A kind of extensive hashing image search method based on depth representative learning |
-
2020
- 2020-12-18 CN CN202011511790.1A patent/CN112528066B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108681555A (en) * | 2018-04-08 | 2018-10-19 | 天津大学 | A kind of sketch image search method returned based on shape |
CN108920720A (en) * | 2018-07-30 | 2018-11-30 | 电子科技大学 | The large-scale image search method accelerated based on depth Hash and GPU |
CN109086437A (en) * | 2018-08-15 | 2018-12-25 | 重庆大学 | A kind of image search method merging Faster-RCNN and Wasserstein self-encoding encoder |
CN110059206A (en) * | 2019-03-29 | 2019-07-26 | 银江股份有限公司 | A kind of extensive hashing image search method based on depth representative learning |
Also Published As
Publication number | Publication date |
---|---|
CN112528066B (en) | 2023-08-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11816888B2 (en) | Accurate tag relevance prediction for image search | |
CN107085585B (en) | Accurate tag relevance prediction for image search | |
EP2565804B1 (en) | Text-based searching of image data | |
EP2808827A1 (en) | System and method for OCR output verification | |
US20090060351A1 (en) | Visual Language Modeling for Image Classification | |
CN108446334B (en) | Image retrieval method based on content for unsupervised countermeasure training | |
CN112949740B (en) | Small sample image classification method based on multilevel measurement | |
CN113920472A (en) | Unsupervised target re-identification method and system based on attention mechanism | |
CN115393666A (en) | Small sample expansion method and system based on prototype completion in image classification | |
CN114579794A (en) | Multi-scale fusion landmark image retrieval method and system based on feature consistency suggestion | |
CN112269892B (en) | Based on multi-mode is unified at many levels Interactive phrase positioning and identifying method | |
CN113486902A (en) | Three-dimensional point cloud classification algorithm automatic selection method based on meta-learning | |
CN112084353A (en) | Bag-of-words model method for rapid landmark-convolution feature matching | |
CN116128846B (en) | Visual transducer hash method for lung X-ray image retrieval | |
CN115797795A (en) | Remote sensing image question-answering type retrieval system and method based on reinforcement learning | |
CN113780284B (en) | Logo detection method based on target detection and metric learning | |
CN116258938A (en) | Image retrieval and identification method based on autonomous evolution loss | |
CN112528066A (en) | Trademark retrieval method and system based on attention mechanism, computer equipment and storage medium | |
CN116310407A (en) | Heterogeneous data semantic extraction method for power distribution and utilization multidimensional service | |
Su et al. | Parallel big image data retrieval by conceptualised clustering and un-conceptualised clustering | |
Sathiyaprasad et al. | Multi spectral image retrieval in remote sensing big data using fast recurrent convolutional neural network | |
Tabia et al. | Deformable shape retrieval using bag-of-feature techniques | |
Kumar et al. | Automatic feature weight determination using indexing and pseudo-relevance feedback for multi-feature content-based image retrieval | |
CN116662588B (en) | Intelligent searching method and system for mass data | |
TW202004519A (en) | Method for automatically classifying images |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |