CN110826627A - Image similarity measuring method and device and electronic equipment - Google Patents
Image similarity measuring method and device and electronic equipment Download PDFInfo
- Publication number
- CN110826627A CN110826627A CN201911080156.4A CN201911080156A CN110826627A CN 110826627 A CN110826627 A CN 110826627A CN 201911080156 A CN201911080156 A CN 201911080156A CN 110826627 A CN110826627 A CN 110826627A
- Authority
- CN
- China
- Prior art keywords
- image
- vector
- analytic
- similarity
- initial
- 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/42—Document-oriented image-based pattern recognition based on the type of document
- G06V30/422—Technical drawings; Geographical maps
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Library & Information Science (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Biology (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an image similarity measuring method, an image similarity measuring device and electronic equipment, which relate to the technical field of images and comprise the steps of obtaining an initial image; analyzing the initial image to obtain an analyzed image; extracting feature vectors of the analytic images based on a pre-trained convolutional neural network; similarity measurement is performed based on the feature vectors of the analytic images. The invention effectively improves the accuracy of measurement, can improve the efficiency of image retrieval, and has the value of popularization and application.
Description
Technical Field
The present invention relates to the field of image technologies, and in particular, to a method and an apparatus for measuring image similarity, and an electronic device.
Background
At present, in order to obtain an image to be used or referred from a plurality of images, searching for the image is generally required, such as a designer who is engaged in home decoration design, when designing a plan, a similar house type diagram plan is often searched according to a house type diagram provided by a client so as to obtain design inspiration, and when searching for the image, a technology of measuring similarity is generally required, namely, a search result is determined by calculating the similarity of two images.
A Convolutional Neural Network (CNN) is a Neural Network with better visual representation, but the CNN directly performs image representation through extracted feature vectors, and there is a large limitation, and certain features are not fully utilized when searching is performed, so that when similarity is measured, the measurement result may be inaccurate, and the searching efficiency may be low. In view of the above-mentioned drawbacks of the prior art in image similarity measurement, no effective solution has been proposed.
Disclosure of Invention
The invention aims to provide an image similarity measurement method, an image similarity measurement device and electronic equipment, which are used for solving the technical problems that in the prior art, when similarity is measured, the measurement result is inaccurate and the retrieval efficiency is low.
In a first aspect, an embodiment provides an image similarity measurement method, including: acquiring an initial image; analyzing the initial image to obtain an analyzed image; extracting feature vectors of the analytic images based on a pre-trained convolutional neural network; similarity measurement is performed based on the feature vectors of the analytic images.
In an alternative embodiment, the step of analyzing the initial image to obtain an analysis image includes: acquiring a data file of an initial image; the data file comprises line information; and extracting the line information of the initial image in the data file to obtain an analytic image.
In an alternative embodiment, the convolutional neural network comprises a variational self-encoder; the method for extracting the feature vector of the analytic image based on the pre-trained convolutional neural network comprises the following steps: inputting the analytic image into a pre-trained variational self-coder model to obtain a corresponding digital vector code; feature vectors of the parsed image are extracted based on the digital vector encoding.
In an alternative embodiment, the step of performing similarity measurement based on the feature vector of the analytic image includes: obtaining a first vector of the analytic image based on the feature vector of the analytic image; and calculating the similarity of the analytic image and the sample pictures in the image sample set according to the first vector so as to measure the similarity of the analytic image.
In an alternative embodiment, the step of calculating the similarity between the analysis image and the sample picture in the image sample set according to the first vector includes: acquiring a second vector of a sample picture in the image sample set; the similarity measure is performed by calculating the distance of the first vector from the second vector.
In a second aspect, an embodiment provides an image similarity measuring apparatus, including: the image acquisition module is used for acquiring an initial image; the image analysis module is used for analyzing the initial image to obtain an analysis image; the characteristic extraction module is used for extracting a characteristic vector of an analytic image based on a pre-trained convolutional neural network;
and the similarity measurement module is used for carrying out similarity measurement based on the feature vector of the analytic image. In an alternative embodiment, the image parsing module is configured to: acquiring a data file of an initial image; the data file comprises line information; and extracting the line information of the initial image in the data file to obtain an analytic image.
In an alternative embodiment, the convolutional neural network comprises a variational self-encoder; a feature extraction module to: inputting the analytic image into a pre-trained variational self-coder model to obtain a corresponding digital vector code; feature vectors of the parsed image are extracted based on the digital vector encoding.
In a third aspect, an embodiment provides an electronic device, including a processor and a memory; the memory has stored thereon a computer program which, when executed by the processor, performs the method according to any of the preceding embodiments.
In a fourth aspect, embodiments provide a computer readable storage medium for storing a computer program for use in any one of the methods of the preceding embodiments.
According to the image similarity measurement method, the image similarity measurement device and the electronic equipment, the initial image is obtained and analyzed to obtain the analytic image (including the line information of the initial image), the feature vector of the analytic image is extracted based on the pre-trained convolutional neural network, and the similarity measurement is performed based on the feature vector of the analytic image. By analyzing the image, the analyzed image containing line information can be obtained, so that the influence of other information on similarity measurement is reduced, and the measurement accuracy is improved. The feature extraction is carried out on the analytic image by using the convolutional neural network to obtain the feature vector, and the similarity measurement is carried out based on the feature vector, so that the measurement accuracy is further improved. Therefore, the embodiment of the invention effectively improves the accuracy of measurement, can improve the efficiency of image retrieval, and has the value of popularization and application.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic flow chart of an image similarity measurement method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an initial image and an analytic image according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a variational self-coder model according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an image similarity measurement apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, 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 some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. 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.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
In the description of the present invention, it should be noted that the terms "first", "second", and the like are used only for distinguishing the description, and are not intended to indicate or imply relative importance.
Some embodiments of the invention are described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
In consideration of the fact that the measurement result may be inaccurate and the retrieval efficiency is low in similarity measurement in the prior art, the invention provides the image similarity measurement method, the image similarity measurement device and the electronic equipment, which effectively improve the measurement accuracy, can improve the image retrieval efficiency and have popularization and application values.
For convenience of understanding, first, a detailed description is given of an image similarity measurement method according to an embodiment of the present invention, referring to a schematic flow chart of the image similarity measurement method shown in fig. 1, where the method mainly includes the following steps S102 to S108:
step S102: an initial image is acquired.
In one embodiment, the initial image includes an image to be searched, the information included in the image may be in multiple types, and the mode of acquiring the initial image may be acquired by receiving an upload from a user, or may be imported by a digital camera, drawn by using drawing software, captured by a screen, or the like.
Step S104: and analyzing the initial image to obtain an analysis image.
In one embodiment, the acquired image may include various information, such as color information, line information, article information, and the like in the image, and therefore, when the similarity measurement is performed, the initial image needs to be analyzed, so as to divide or segment the initial image, and obtain an analyzed image (i.e., an analytic image).
Step S106: and extracting the feature vector of the analytic image based on a pre-trained convolutional neural network.
The convolutional neural network is obtained by training and tuning a large number of data sets, and the analytic images are subjected to feature extraction through the pre-trained convolutional neural network, so that features required to be subjected to similarity measurement, such as color information, line information, article information and the like in the images, are extracted and embodied in a feature vector coding mode (also called as feature vectors).
Step S108: and carrying out similarity measurement based on the feature vector of the analytic image.
In one embodiment, the similarity measure may be a measure of the distance of the feature vectors, such as the euclidean distance or the chebyshev distance; it is also possible to measure the positional relationship of the feature vectors of the initial image, such as whether the vectors are collinear or not. The similarity between the images is measured by the calculated relationship between the vectors.
The image similarity measurement method obtains an analytic image (including line information of the initial image) by obtaining the initial image and analyzing the initial image, extracts a feature vector of the analytic image based on a pre-trained convolutional neural network, and measures the similarity based on the feature vector of the analytic image. By analyzing the image, the analyzed image containing line information can be obtained, so that the influence of other information on similarity measurement is reduced, and the measurement accuracy is improved. The feature extraction is carried out on the analytic image by using the convolutional neural network to obtain the feature vector, and the similarity measurement is carried out based on the feature vector, so that the measurement accuracy is further improved. Therefore, the embodiment of the invention effectively improves the accuracy of measurement, can improve the efficiency of image retrieval, and has the value of popularization and application.
In an implementation manner, in order to facilitate understanding of step S104, an embodiment of the present invention provides a specific implementation manner of analyzing an initial image to obtain an analyzed image, where the initial image may include color information and line information, and the line information may include calibration image contour information and internal line information, and specifically, the line information may represent an overall structure of the initial image. The specific implementation manner of the step S104 can be seen in the following steps a and B:
step A, acquiring a data file of an initial image; the data file includes line information.
In one embodiment, the initial image has a corresponding data file, such as, for example, referring to a schematic diagram of an initial image and an analytic image shown in fig. 2, the initial image is a house type diagram, fig. 2 (a) is a house type diagram, the image includes spatial position patterns, furniture, and the like, one house type diagram has a corresponding xml image, and all spatial structure information of the house type, including specific sizes, positions, directions, and the like of walls, doors and windows, is recorded in the xml image, and line information is also wall information in the house type diagram.
And step B, extracting the line information of the initial image in the data file to obtain an analytic image.
After the data file corresponding to the initial image is obtained, the data file is analyzed, and the required information, such as the wall information of the house type image, is extracted, so that a top view (i.e., an analysis image) only containing the wall information can be obtained, referring to an analyzed house type image shown in (b) in fig. 2.
In an embodiment, the convolutional neural network includes a variational self-encoder, the variational self-encoder model is a self-supervised machine learning method, and the self-supervised machine learning method can train and learn by itself without manually labeling a label, and has strong mobility, and the step S106 is to encode the parsed image by using a pre-trained variational self-encoder to obtain a digital vector code, and may specifically include the following steps (1) and (2):
and (1) inputting the analysis image into a pre-trained variational self-encoder model to obtain a corresponding digital vector code. Variation self-encoder referring to the schematic structural diagram of a variation self-encoder model shown in fig. 3, after the analytic image is input into the variation self-encoder, a digital vector code is obtained, such as the digital vector code of the analytic image (top view) of the user-type diagram, which actually characterizes the spatial structural feature of the top view, and this step (1) is actually to complete the mapping from the spatial structural information of the top view to the digital vector code that can be identified and processed by the computer.
And (2) extracting a feature vector of the analysis image based on the digital vector coding.
In one embodiment, the digital vector is obtained and then converted into a digital vector, such as the top view input variational self-encoder, and then the corresponding encoded information is output and converted into a vector, thereby facilitating the measurement of image similarity based on the vector.
To facilitate understanding of the step S108, an embodiment of the present invention provides a specific implementation manner for performing similarity measurement based on a feature vector of an analytic image, and the specific implementation manner mainly includes the following steps 1 and 2:
step 1, obtaining a first vector of an analytic image based on the characteristic vector of the analytic image.
In one embodiment, the first vector (i.e., the vector of the analytic image) is used to calibrate the features of the analytic image, such as the first vector of the analytic image of the user-type figure, which is encoded by the trained variational self-encoder of the top view to obtain a digital vector code of a fixed dimension, and the digital vector code represents the picture features of the top view (e.g., the spatial layout information of the kitchen, the bedroom, etc.).
And 2, calculating the similarity between the analytic image and the sample picture in the image sample set according to the first vector so as to measure the similarity of the analytic image.
The step 2 may specifically include step 2.1 and step 2.2:
and 2.1, acquiring a second vector of the sample picture in the image sample set. In order to satisfy the comparability of the similarity measurement, the sample picture is also analyzed and feature extracted to obtain the digital vector code (i.e. the second vector) of the sample picture.
And 2.2, measuring the similarity by calculating the distance between the first vector and the second vector.
After the first vector and the second vector are obtained, the similarity is measured by calculating the distance between the vectors, for example, the distance between the two vectors is calculated by calculating the euclidean distance, and the smaller the distance is, the greater the image similarity between the initial image and the sample picture in the image sample set is, and the smaller the image similarity is otherwise. If the two vectors are [1, 3 ] respectively]And [2, 4 ]]Then their euclidean distance is:
i.e. the similarity result is represented by the result of the euclidean distance.
For the image similarity measuring method, an embodiment of the present invention further provides an image similarity measuring apparatus, referring to a schematic structural diagram of the image similarity measuring apparatus shown in fig. 4, where the apparatus includes:
an image acquisition module 402 for acquiring an initial image;
an image analysis module 404, configured to analyze the initial image to obtain an analysis image;
a feature extraction module 406, configured to extract a feature vector of an analytic image based on a pre-trained convolutional neural network;
and a similarity measurement module 408 for performing similarity measurement based on the feature vector of the analytic image.
The image similarity measuring device provided by the invention obtains an analytic image (including line information of the initial image) by obtaining the initial image and analyzing the initial image, extracts a feature vector of the analytic image based on a pre-trained convolutional neural network, and measures the similarity based on the feature vector of the analytic image. By analyzing the image, the analyzed image containing line information can be obtained, so that the influence of other information on similarity measurement is reduced, and the measurement accuracy is improved. The feature extraction is carried out on the analytic image by using the convolutional neural network to obtain the feature vector, and the similarity measurement is carried out based on the feature vector, so that the measurement accuracy is further improved. Therefore, the embodiment of the invention effectively improves the accuracy of measurement, can improve the efficiency of image retrieval, and has the value of popularization and application.
In an embodiment, the image analysis module 404 is further configured to obtain a data file of an initial image; the data file comprises line information; and extracting the line information of the initial image in the data file to obtain an analytic image.
In one embodiment, a convolutional neural network includes a variational self-encoder; the feature extraction module 406 is further configured to input the analysis image into a pre-trained variational self-encoder model to obtain a corresponding digital vector code; feature vectors of the parsed image are extracted based on the digital vector encoding.
In an embodiment, the similarity measurement module 408 is further configured to obtain a first vector of the analysis image based on the feature vector of the analysis image; and calculating the similarity of the analytic image and the sample pictures in the image sample set according to the first vector so as to measure the similarity of the analytic image.
In one embodiment, the above apparatus further comprises: the similarity calculation module is used for acquiring a second vector of the sample picture in the image sample set; the similarity measure is performed by calculating the distance of the first vector from the second vector.
The invention also provides electronic equipment, which specifically comprises a processor and a storage device; the storage means has stored thereon a computer program which, when executed by the processor, performs the method of any of the above described embodiments.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, where the electronic device 100 includes: the device comprises a processor 50, a memory 51, a bus 52 and a communication interface 53, wherein the processor 50, the communication interface 53 and the memory 51 are connected through the bus 52; the processor 50 is arranged to execute executable modules, such as computer programs, stored in the memory 51.
The memory 51 may include a high-speed Random Access Memory (RAM) and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory. The communication connection between the network element of the system and at least one other network element is realized through at least one communication interface 53 (which may be wired or wireless), and the internet, a wide area network, a local network, a metropolitan area network, and the like can be used.
The bus 52 may be an ISA bus, PCI bus, EISA bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 5, but this does not indicate only one bus or one type of bus.
The memory 51 is used for storing a program, the processor 50 executes the program after receiving an execution instruction, and the method executed by the apparatus defined by the flow process disclosed in any of the foregoing embodiments of the present invention may be applied to the processor 50, or implemented by the processor 50.
The processor 50 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 50. The Processor 50 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the memory 51, and the processor 50 reads the information in the memory 51 and completes the steps of the method in combination with the hardware thereof.
The evaluation text generation method, the evaluation text generation device, and the computer program product of the electronic device provided in the embodiments of the present invention include a computer-readable storage medium storing a nonvolatile program code executable by a processor, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, the method described in the foregoing method embodiments is executed.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the system described above may refer to the corresponding process in the foregoing embodiments, and is not described herein again.
The computer program product of the readable storage medium provided in the embodiment of the present invention includes a computer readable storage medium storing a program code, where instructions included in the program code may be used to execute the method described in the foregoing method embodiment, and specific implementation may refer to the method embodiment, which is not described herein again.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. An image similarity measurement method, characterized by comprising:
acquiring an initial image;
analyzing the initial image to obtain an analyzed image;
extracting a feature vector of the analytic image based on a pre-trained convolutional neural network;
and carrying out similarity measurement based on the feature vector of the analytic image.
2. The method of claim 1, wherein the step of parsing the initial image to obtain a parsed image comprises:
acquiring a data file of the initial image; the data file comprises line information;
and extracting the line information of the initial image in the data file to obtain the analysis image.
3. The method of claim 1, wherein the convolutional neural network comprises a variational self-encoder; the step of extracting the feature vector of the analytic image based on the pre-trained convolutional neural network comprises the following steps:
inputting the analysis image into a pre-trained variational self-coder model to obtain a corresponding digital vector code;
extracting a feature vector of the analytic image based on the digital vector encoding.
4. The method of claim 1, wherein the step of performing similarity measurements based on the feature vectors of the analytical images comprises:
obtaining a first vector of the analytic image based on the feature vector of the analytic image;
and calculating the similarity of the analytic image and the sample pictures in the image sample set according to the first vector so as to measure the similarity of the analytic image.
5. The method of claim 4, wherein the step of calculating the similarity between the analytic image and the sample pictures in the image sample set according to the first vector comprises:
acquiring a second vector of a sample picture in the image sample set;
and measuring the similarity by calculating the distance between the first vector and the second vector.
6. An image similarity measuring apparatus, comprising:
the image acquisition module is used for acquiring an initial image;
the image analysis module is used for analyzing the initial image to obtain an analysis image;
the feature extraction module is used for extracting feature vectors of the analytic images based on a pre-trained convolutional neural network;
and the similarity measurement module is used for carrying out similarity measurement based on the feature vector of the analytic image.
7. The apparatus of claim 6, wherein the image parsing module is configured to:
acquiring a data file of the initial image; the data file comprises line information;
and extracting the line information of the initial image in the data file to obtain the analysis image.
8. The apparatus of claim 6, wherein the convolutional neural network comprises a variational self-encoder; the feature extraction module is configured to:
inputting the analysis image into a pre-trained variational self-coder model to obtain a corresponding digital vector code;
extracting a feature vector of the analytic image based on the digital vector encoding.
9. An electronic device comprising a processor and a memory;
the memory has stored thereon a computer program which, when executed by the processor, performs the method of any of claims 1 to 5.
10. A computer-readable storage medium for storing a computer program for use in the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911080156.4A CN110826627A (en) | 2019-11-06 | 2019-11-06 | Image similarity measuring method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911080156.4A CN110826627A (en) | 2019-11-06 | 2019-11-06 | Image similarity measuring method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110826627A true CN110826627A (en) | 2020-02-21 |
Family
ID=69553037
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911080156.4A Pending CN110826627A (en) | 2019-11-06 | 2019-11-06 | Image similarity measuring method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110826627A (en) |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101038668A (en) * | 2006-03-18 | 2007-09-19 | 辽宁师范大学 | Image searching method based on important bit-plane |
| CN102117337A (en) * | 2011-03-31 | 2011-07-06 | 西北工业大学 | Space information fused Bag of Words method for retrieving image |
| CN102252611A (en) * | 2011-05-09 | 2011-11-23 | 深圳市澎湃图像技术有限公司 | Geometric positioning method |
| CN102331752A (en) * | 2011-05-19 | 2012-01-25 | 刘利华 | Intelligent home control system and method combined with floor plan |
| CN103150330A (en) * | 2013-01-16 | 2013-06-12 | 中南大学 | Local object and block matching-based scanning certificate image search method |
| CN103440262A (en) * | 2013-07-31 | 2013-12-11 | 东莞中山大学研究院 | Image searching system and image searching method basing on relevance feedback and Bag-of-Features |
| CN103971098A (en) * | 2014-05-19 | 2014-08-06 | 北京明兰网络科技有限公司 | Method for recognizing wall in house type image and method for automatically correcting length ratio of house type image |
| CN105320703A (en) * | 2014-08-05 | 2016-02-10 | 北京大学 | Query expansion method and device in retrieval of similar vehicle |
| CN106844614A (en) * | 2017-01-18 | 2017-06-13 | 天津中科智能识别产业技术研究院有限公司 | A kind of floor plan functional area system for rapidly identifying |
| CN108009520A (en) * | 2017-12-21 | 2018-05-08 | 东南大学 | A kind of finger vein identification method and system based on convolution variation self-encoding encoder neutral net |
| CN108227564A (en) * | 2017-12-12 | 2018-06-29 | 深圳和而泰数据资源与云技术有限公司 | A kind of information processing method, terminal and computer-readable medium |
| CN109325549A (en) * | 2018-10-25 | 2019-02-12 | 电子科技大学 | A kind of facial image fusion method |
| CN109522435A (en) * | 2018-11-15 | 2019-03-26 | ***股份有限公司 | A kind of image search method and device |
| CN109543735A (en) * | 2018-11-14 | 2019-03-29 | 北京工商大学 | Video copying detection method and its system |
| CN109740506A (en) * | 2018-12-29 | 2019-05-10 | 广东三维家信息科技有限公司 | A kind of house type image-recognizing method and device |
| CN109783655A (en) * | 2018-12-07 | 2019-05-21 | 西安电子科技大学 | A kind of cross-module state search method, device, computer equipment and storage medium |
| CN109858625A (en) * | 2019-02-01 | 2019-06-07 | 北京奇艺世纪科技有限公司 | Model training method and equipment, prediction technique and equipment, data processing equipment, medium |
| CN110096949A (en) * | 2019-03-16 | 2019-08-06 | 平安城市建设科技(深圳)有限公司 | Floor plan intelligent identification Method, device, equipment and computer readable storage medium |
| CN110188836A (en) * | 2019-06-21 | 2019-08-30 | 西安交通大学 | A kind of brain function network class method based on variation self-encoding encoder |
| CN110263207A (en) * | 2019-06-20 | 2019-09-20 | 杭州时趣信息技术有限公司 | Image search method, device, equipment and computer readable storage medium |
-
2019
- 2019-11-06 CN CN201911080156.4A patent/CN110826627A/en active Pending
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101038668A (en) * | 2006-03-18 | 2007-09-19 | 辽宁师范大学 | Image searching method based on important bit-plane |
| CN102117337A (en) * | 2011-03-31 | 2011-07-06 | 西北工业大学 | Space information fused Bag of Words method for retrieving image |
| CN102252611A (en) * | 2011-05-09 | 2011-11-23 | 深圳市澎湃图像技术有限公司 | Geometric positioning method |
| CN102331752A (en) * | 2011-05-19 | 2012-01-25 | 刘利华 | Intelligent home control system and method combined with floor plan |
| CN103150330A (en) * | 2013-01-16 | 2013-06-12 | 中南大学 | Local object and block matching-based scanning certificate image search method |
| CN103440262A (en) * | 2013-07-31 | 2013-12-11 | 东莞中山大学研究院 | Image searching system and image searching method basing on relevance feedback and Bag-of-Features |
| CN103971098A (en) * | 2014-05-19 | 2014-08-06 | 北京明兰网络科技有限公司 | Method for recognizing wall in house type image and method for automatically correcting length ratio of house type image |
| CN105320703A (en) * | 2014-08-05 | 2016-02-10 | 北京大学 | Query expansion method and device in retrieval of similar vehicle |
| CN106844614A (en) * | 2017-01-18 | 2017-06-13 | 天津中科智能识别产业技术研究院有限公司 | A kind of floor plan functional area system for rapidly identifying |
| CN108227564A (en) * | 2017-12-12 | 2018-06-29 | 深圳和而泰数据资源与云技术有限公司 | A kind of information processing method, terminal and computer-readable medium |
| CN108009520A (en) * | 2017-12-21 | 2018-05-08 | 东南大学 | A kind of finger vein identification method and system based on convolution variation self-encoding encoder neutral net |
| CN109325549A (en) * | 2018-10-25 | 2019-02-12 | 电子科技大学 | A kind of facial image fusion method |
| CN109543735A (en) * | 2018-11-14 | 2019-03-29 | 北京工商大学 | Video copying detection method and its system |
| CN109522435A (en) * | 2018-11-15 | 2019-03-26 | ***股份有限公司 | A kind of image search method and device |
| CN109783655A (en) * | 2018-12-07 | 2019-05-21 | 西安电子科技大学 | A kind of cross-module state search method, device, computer equipment and storage medium |
| CN109740506A (en) * | 2018-12-29 | 2019-05-10 | 广东三维家信息科技有限公司 | A kind of house type image-recognizing method and device |
| CN109858625A (en) * | 2019-02-01 | 2019-06-07 | 北京奇艺世纪科技有限公司 | Model training method and equipment, prediction technique and equipment, data processing equipment, medium |
| CN110096949A (en) * | 2019-03-16 | 2019-08-06 | 平安城市建设科技(深圳)有限公司 | Floor plan intelligent identification Method, device, equipment and computer readable storage medium |
| CN110263207A (en) * | 2019-06-20 | 2019-09-20 | 杭州时趣信息技术有限公司 | Image search method, device, equipment and computer readable storage medium |
| CN110188836A (en) * | 2019-06-21 | 2019-08-30 | 西安交通大学 | A kind of brain function network class method based on variation self-encoding encoder |
Non-Patent Citations (1)
| Title |
|---|
| 那彦等著: "《基于多分辨分析理论的图像融合方法》", 31 May 2007, 西安电子科技大学出版社 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108108426B (en) | Understanding method and device for natural language question and electronic equipment | |
| CN110766096A (en) | Video classification method and device and electronic equipment | |
| US20200175062A1 (en) | Image retrieval method and apparatus, and electronic device | |
| CN108197592B (en) | Information acquisition method and device | |
| CN111144493B (en) | Method for automatically identifying algorithm index test, storage medium and electronic terminal | |
| CN111310037B (en) | Household material recommendation method and device and electronic equipment | |
| CN111582282B (en) | Text recognition method, device, equipment and storage medium | |
| CN111651674B (en) | Bidirectional searching method and device and electronic equipment | |
| US8868571B1 (en) | Systems and methods for selecting interest point descriptors for object recognition | |
| CN111368143A (en) | Video similarity retrieval method and device, electronic equipment and storage medium | |
| WO2017156864A1 (en) | Method, apparatus, and device for image recognition, and nonvolatile computer storage medium | |
| CN115082659A (en) | Image annotation method and device, electronic equipment and storage medium | |
| CN113076961B (en) | Image feature library updating method, image detection method and device | |
| CN113505720A (en) | Image processing method and device, storage medium and electronic device | |
| CN110765291A (en) | Retrieval method and device and electronic equipment | |
| CN111967383A (en) | Age estimation method, and training method and device of age estimation model | |
| CN110826627A (en) | Image similarity measuring method and device and electronic equipment | |
| CN115905524B (en) | Emotion analysis method, device and equipment integrating syntax and semantic information | |
| CN114996360B (en) | Data analysis method, system, readable storage medium and computer equipment | |
| CN111062448A (en) | Equipment type recognition model training method, equipment type recognition method and device | |
| CN111626313A (en) | Feature extraction model training method, image processing method and device | |
| CN113269153B (en) | Form identification method and device | |
| CN112801006B (en) | Training method of expression representation model, and facial expression representation method and device | |
| CN114186576A (en) | Bar code positioning and decoding device, method, electronic equipment and storage medium | |
| JP2012226429A (en) | Image retrieval and recognition system |
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: 20200221 |
|
| RJ01 | Rejection of invention patent application after publication |