CN115357736A - Picture matching method, device, storage medium and equipment - Google Patents
Picture matching method, device, storage medium and equipment Download PDFInfo
- Publication number
- CN115357736A CN115357736A CN202211048673.5A CN202211048673A CN115357736A CN 115357736 A CN115357736 A CN 115357736A CN 202211048673 A CN202211048673 A CN 202211048673A CN 115357736 A CN115357736 A CN 115357736A
- Authority
- CN
- China
- Prior art keywords
- picture
- user
- fingerprint
- gray
- image
- 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
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000000605 extraction Methods 0.000 claims abstract description 23
- 230000008569 process Effects 0.000 claims abstract description 9
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000010276 construction Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000007667 floating Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001093 holography Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009967 tasteless 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
- G06F16/53—Querying
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4092—Image resolution transcoding, e.g. by using client-server architectures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Library & Information Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a method, a device, a storage medium and equipment for picture matching, which are applied to the field of mobile interconnection, and are used for acquiring a video image containing a user from a remote video call between a client and a seat end, and converting the video image into a picture frame to obtain a user picture; fingerprint extraction is carried out on the user picture to obtain a picture fingerprint of the user picture; acquiring picture fingerprints of a plurality of popular pictures from a fingerprint database which is constructed in advance, and calculating the Hamming distance between the picture fingerprint of the user picture and the picture fingerprint of the popular picture aiming at each popular picture to obtain the similarity between each popular picture and the user picture; compared with the prior art, the method has the advantages that the hot pictures with the largest similarity are selected from the hot pictures and sent to the client as the effective pictures, so that the client can display the effective pictures to the user through the preset interface, interestingness can be added in the user service handling process through displaying the effective pictures through the preset interface, and the user experience is enriched.
Description
Technical Field
The present application relates to the field of mobile internet technologies, and in particular, to a method, an apparatus, a storage medium, and a device for matching pictures.
Background
With the expansion of network bandwidth and the popularization of the 5G era, remote video banking develops rapidly, and the business mode of the traditional banking outlets is gradually replaced by the remote video banking.
The remote video bank combines the functions of a self-service bank, a customer service center and a telephone bank, and the customer service remotely guides a client to handle business through a communication mode of video chat, but compared with the offline business handling of traditional bank outlets, the remote video bank realizes face-to-face business handling based on videos, but has a gap in the interaction process, the video display range is only in the range of a camera, and the client is boring and tasteless in the business handling process.
Therefore, how to increase the interest of the business handling process and enrich the use experience of the client becomes a problem which needs to be solved urgently in the field.
Disclosure of Invention
The application provides a method, a device, a storage medium and equipment for picture matching, and aims to increase the interest of a business handling process and enrich the use experience of a client.
In order to achieve the above object, the present application provides the following technical solutions:
a method of picture matching, comprising:
the method comprises the steps that a video image containing a user is obtained from a remote video call between a client and a seat end, and the video image is converted into a picture frame to obtain a user picture;
fingerprint extraction is carried out on the user picture to obtain a picture fingerprint of the user picture;
acquiring picture fingerprints of a plurality of popular pictures from a pre-constructed fingerprint database, and calculating the Hamming distance between the picture fingerprint of the user picture and the picture fingerprint of the popular picture aiming at each popular picture to obtain the similarity between each popular picture and the user picture;
selecting the hot picture with the maximum similarity from all the hot pictures as an effective picture;
and sending the effective picture to the client so that the client displays the effective picture to the user through a preset interface.
Optionally, the process of constructing the fingerprint database includes:
collecting each hot picture from the Internet by using a web crawler;
reducing each hot picture according to a preset size to obtain each target picture;
for each target picture, fingerprint extraction is carried out on the target picture to obtain the picture fingerprint of each popular picture;
and constructing the fingerprint database based on the hot pictures and the picture fingerprints of each hot picture.
Optionally, the fingerprint extraction is performed on the user picture to obtain a picture fingerprint of the user picture, and the method includes:
carrying out gray level conversion on the user picture to obtain a gray level image of the user picture; the gray image comprises pixel points and the gray value of each pixel point;
calculating the average value of the gray values of all pixel points in the gray image to obtain the average value of the gray values;
determining characters corresponding to each pixel point in the gray level image according to the gray level average value;
and establishing a character string based on the characters corresponding to each pixel point, and identifying the character string as the picture fingerprint of the user picture.
Optionally, the determining, according to the average grayscale value, a character corresponding to each pixel point in the grayscale image includes:
for each pixel point in the gray image, judging whether the gray value of the pixel point is not less than the average gray value;
and if the gray value of the pixel point is not less than the average gray value, identifying a first preset value as a character corresponding to the pixel point.
Optionally, the method further includes:
and if the gray value of the pixel point is smaller than the average gray value, identifying a second preset value as a character corresponding to the pixel point.
An apparatus for picture matching, comprising:
the system comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is used for acquiring a video image containing a user from a remote video call between a client and a seat end, and converting the video image into a picture frame to obtain a user picture;
the extraction unit is used for carrying out fingerprint extraction on the user picture to obtain the picture fingerprint of the user picture;
the calculation unit is used for acquiring the picture fingerprints of a plurality of popular pictures from a fingerprint database which is constructed in advance, and calculating the Hamming distance between the picture fingerprint of the user picture and the picture fingerprint of the popular picture aiming at each popular picture to obtain the similarity between each popular picture and the user picture;
the selecting unit is used for selecting the hot picture with the maximum similarity from all the hot pictures as an effective picture;
and the sending unit is used for sending the effective pictures to the client so that the client can display the effective pictures to the user through a preset interface.
Optionally, the computing unit is specifically configured to:
collecting each hot picture from the Internet by using a web crawler;
carrying out reduction processing on each hot picture according to a preset size to obtain each target picture;
for each target picture, fingerprint extraction is carried out on the target picture to obtain the picture fingerprint of each popular picture;
and constructing the fingerprint database based on each hot picture and the picture fingerprint of each hot picture.
Optionally, the extracting unit is specifically configured to:
carrying out gray level conversion on the user picture to obtain a gray level image of the user picture; the gray image comprises pixel points and the gray value of each pixel point;
calculating the average value of the gray values of all pixel points in the gray image to obtain the average value of the gray values;
determining characters corresponding to each pixel point in the gray level image according to the gray level average value;
and establishing a character string based on the characters corresponding to the pixel points, and identifying the character string as the picture fingerprint of the user picture.
A computer-readable storage medium comprising a stored program, wherein the program performs the method of picture matching.
A picture matching device, comprising: a processor, a memory, and a bus; the processor and the memory are connected through the bus;
the memory is used for storing a program, and the processor is used for executing the program, wherein the program executes the method for matching the pictures.
According to the technical scheme, a video image containing a user is obtained from a remote video call between a client and a seat end, and the video image is converted into a picture frame to obtain a user picture; fingerprint extraction is carried out on the user picture to obtain a picture fingerprint of the user picture; acquiring picture fingerprints of a plurality of popular pictures from a fingerprint database which is constructed in advance, and calculating the Hamming distance between the picture fingerprint of the user picture and the picture fingerprint of the popular picture aiming at each popular picture to obtain the similarity between each popular picture and the user picture; the hot picture with the largest similarity is selected from the hot pictures and sent to the client as the effective picture, so that the client displays the effective picture to the user through the preset interface.
Drawings
In order to more clearly illustrate the embodiments of the present application 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, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a method for matching pictures according to an embodiment of the present disclosure;
fig. 2 is a schematic diagram of a picture display provided in an embodiment of the present application;
fig. 3 is a flowchart of another method for matching pictures according to an embodiment of the present disclosure;
fig. 4 is a schematic diagram illustrating an architecture of an apparatus for picture matching according to an embodiment of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, 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 application.
As shown in fig. 1, a flowchart of a method for matching pictures provided in the embodiment of the present application includes:
s101: and collecting each hot picture from the Internet by using the web crawler.
Wherein, each hit picture includes but is not limited to: star pictures, cartoon character pictures.
Optionally, in order to relieve network pressure, the respective popular pictures may be stored in a storage server.
It should be noted that the specific implementation manner of collecting each popular image by using the web crawler is common knowledge of those skilled in the art, and is not described herein again.
S102: and carrying out reduction processing on each hot picture according to a preset size to obtain each target picture.
Wherein the predetermined dimensions include, but are not limited to: 8 x 8, each of the thermal gate images can be scaled down according to the size of 8 x 8.
It should be noted that each hit picture is processed according to a preset size, so as to remove details of the hit picture, and only retain basic information of structure and brightness, thereby avoiding picture differences caused by different sizes and different proportions.
S103: and for each target picture, carrying out gray level conversion on the target picture to obtain a gray level image of the target picture.
The gray image comprises pixel points and the gray value of each pixel point, and the target picture is subjected to gray conversion, namely the target picture is converted into a gray image with 64 gray levels (namely all the pixel points have 64 colors).
Optionally, the color of a certain pixel in the target picture is RGB (R = red, G = green, B = blue), and the Gray value (Gray) of the pixel may be obtained by a floating point algorithm, an integer method, a shift method, an average value method, only taking green, and the like.
Floating point arithmetic: gray = R × 0.3+ G × 0.59+ B × 0.11
Integer method: gray = (R × 30G × 59+ B × 11)/100
The shifting method comprises the following steps: gray = (R × 76+G × 151+B × 28) > 8
Average value method: gray = (R + G + B)/3
Taking green only: gray = G
Further, R, G, B in the original RGB (RG, B) in the target picture are collectively replaced with Gray to form a new color RGB (Gray ), and the replacement of the original RGB (R, G, B) with it is a Gray image. Generally, the specific implementation principle of the gray scale conversion is common knowledge familiar to those skilled in the art, and the above mentioned specific implementation contents are only used for illustration.
S104: and calculating the average value of the gray values of all the pixel points in the gray image to obtain the average value of the gray values.
Specifically, assuming that 64 pixel points exist in the gray image, the average value of the gray values of the 64 pixel points is calculated to obtain the average value of the gray values.
S105: and judging whether the gray value of each pixel point in the gray image is not less than the average gray value.
If the gray value of the pixel point is not less than the average gray value, executing S106, otherwise executing S107.
Specifically, it is assumed that gray values of three pixel points in the gray image are: 50. 60 and 70, the gray average value is: and 40, judging whether the gray values of the pixel points are not less than the average gray value or not for the three pixel points in the gray image, obviously, the gray values of the three pixel points are not less than the average gray value, and for this reason, continuing to execute the step S106.
Specifically, assuming that the gray values of four pixel points in the gray image are 40, 45, 55, and 60, respectively, and the average gray value is 50, for the four pixel points in the gray image, it is determined whether the gray value of the pixel point is not less than the average gray value, obviously, if 40 and 45 are less than the average gray value 50, S107, 55, and 60 are performed, and S106 is performed.
S106: the first preset value is identified as a character corresponding to the pixel point.
After execution of S106, execution continues with S108.
Alternatively, the first preset value may be set to "1".
It should be noted that, when the gray value of the pixel point is not less than the average gray value, the first preset value is identified as the character corresponding to the pixel point (i.e., "1" is identified as the character corresponding to the pixel point).
S107: and identifying the second preset value as a character corresponding to the pixel point.
After execution of S107, execution continues with S108.
Alternatively, the second preset value may be set to "0".
It should be noted that, if the gray value of the pixel point is smaller than the average gray value, the second preset value is identified as the character corresponding to the pixel point (i.e., "0" is identified as the character corresponding to the pixel point).
S108: and constructing a fingerprint database based on the characters corresponding to the pixel points, identifying the character strings as the picture fingerprints of the hot pictures to which the target picture belongs, and constructing the fingerprint database based on the hot pictures and the picture fingerprints of each hot picture.
Optionally, a character string is created based on the character corresponding to each pixel point, and the character string is identified as the picture fingerprint of the picture (i.e., a 64-bit integer is formed).
It should be noted that the 64-bit integers are combined, and the order of combination is not important, so that each image is ensured to be combined into the 64-bit integers in the same order.
S109: and after receiving a video call request sent by a user at the client, establishing a remote video call between the client and the seat terminal.
S110: and acquiring a video image containing the user from the remote video call.
S111: and converting the video image containing the user into a picture frame to obtain the user picture.
The specific implementation manner of converting the image video containing the user into the picture frame is common knowledge of those skilled in the art, and is not described herein again.
S112: and fingerprint extraction is carried out on the user picture by utilizing a fingerprint acquisition algorithm to obtain the picture fingerprint of the user picture.
The specific implementation process of extracting the fingerprint of the user picture by using the fingerprint acquisition algorithm to obtain the fingerprint of the user picture comprises the following steps: carrying out gray level conversion on the user picture to obtain a gray level image of the user picture; calculating the average value of the gray values of all pixel points in the gray image to obtain the average value of the gray values; judging whether the gray value of each pixel point in the gray image is not less than the average gray value or not; if the gray value of the pixel point is not smaller than the average gray value, identifying the first preset value as a character corresponding to the pixel point; if the gray value of the pixel point is smaller than the average gray value, identifying a second preset value as a character corresponding to the pixel point; and establishing a character string based on the characters corresponding to each pixel point, and identifying the character string as the picture fingerprint of the user picture.
Optionally, multiple fingerprint acquisition algorithms can be selected in actual production, and a service department and a technician can select the algorithms according to the comparison success rate of different scenes.
S113: and acquiring the picture fingerprints of the hot pictures from the fingerprint database, and calculating the Hamming distance between the picture fingerprint of the user picture and the picture fingerprint of the hot picture aiming at each hot picture to obtain the similarity between each hot picture and the user picture.
Wherein the Hamming distance is: the number of different characters at the corresponding positions of the two (same length) strings (e.g., the hamming distance between 1011101 and 1001001 is 2).
It should be noted that the smaller the number of different data bits, the more similar the two pictures are, and the larger the number of different data bits, the more dissimilar the two pictures are. In other words, the smaller the hamming distance between two pictures, the higher the similarity between the two pictures.
S114: and selecting the hot picture with the maximum similarity from the hot pictures as an effective picture.
It should be noted that the effective picture is displayed and reminded at the seat end (i.e. the service staff), and after the seat end confirms, the client end can display the effective picture through a preset interface.
S115: and sending the effective picture to the client so that the client displays the effective picture to the user through a preset interface.
The effective picture is sent to the client, so that the client displays the effective picture through a preset interface, and the mode of displaying the effective picture through the preset interface is shown in fig. 2.
In summary, the picture fingerprints of each hot picture are acquired from the fingerprint database, the hamming distance between the picture fingerprint of the user picture and the picture fingerprint of the hot picture is calculated for each hot picture, the similarity between each hot picture and the user picture is obtained, the hot picture with the largest similarity is selected from each hot picture and is used as an effective picture, and the effective picture is sent to the client side, so that the client side displays the effective picture to the user through the preset interface.
As shown in fig. 3, a flowchart of another method for matching pictures provided in the embodiment of the present application includes:
s301: and acquiring a video image containing the user from a remote video call between the client and the seat end, and converting the video image into a picture frame to obtain a user picture.
S302: and fingerprint extraction is carried out on the user picture to obtain the picture fingerprint of the user picture.
S303: the method comprises the steps of obtaining picture fingerprints of a plurality of popular pictures from a fingerprint database which is constructed in advance, calculating the Hamming distance between the picture fingerprint of a user picture and the picture fingerprint of the popular picture aiming at each popular picture, and obtaining the similarity between each popular picture and the user picture.
S304: and selecting the hot picture with the maximum similarity from the hot pictures as an effective picture.
S305: and sending the effective pictures to the client so that the client can display the effective pictures to a user through a preset interface.
In summary, the picture fingerprints of each hot picture are acquired from the fingerprint database, the hamming distance between the picture fingerprint of the user picture and the picture fingerprint of the hot picture is calculated for each hot picture, the similarity between each hot picture and the user picture is obtained, the hot picture with the largest similarity is selected from each hot picture and is used as an effective picture, and the effective picture is sent to the client side, so that the client side displays the effective picture to the user through the preset interface.
It should be noted that the picture matching method provided by the present invention can be used in the fields of artificial intelligence, block chaining, distributed, cloud computing, big data, internet of things, mobile internet, network security, chip, virtual reality, augmented reality, holography, quantum computing, quantum communication, quantum measurement, digital twinning, and finance. The above is merely an example, and does not limit the application field of the method for matching pictures provided by the present invention.
The method for matching the pictures can be used in the financial field or other fields, for example, can be used in transaction application scenes in the financial field. The other fields are arbitrary fields other than the financial field, for example, the field of mobile internet. The above description is only an example, and does not limit the application field of the method for matching pictures provided by the present invention.
As shown in fig. 4, a schematic diagram of an architecture of an apparatus for picture matching according to an embodiment of the present application includes:
the acquiring unit 100 is configured to acquire a video image including a user from a remote video call between a client and a seat, and convert the video image into a picture frame to obtain a user picture.
An extracting unit 200, configured to perform fingerprint extraction on the user picture to obtain a picture fingerprint of the user picture.
The extraction unit 200 is specifically configured to: carrying out gray level conversion on the user picture to obtain a gray level image of the user picture; the gray image comprises each pixel point and the gray value of each pixel point; calculating the average value of the gray values of all pixel points in the gray image to obtain the average value of the gray values; determining characters corresponding to each pixel point in the gray level image according to the gray level average value; and establishing a character string based on the characters corresponding to each pixel point, and identifying the character string as the picture fingerprint of the user picture.
The extraction unit 200 is specifically configured to: judging whether the gray value of each pixel point in the gray image is not less than the average gray value or not; and if the gray value of the pixel point is not less than the average gray value, identifying the first preset value as a character corresponding to the pixel point.
The extracting unit 200 is further configured to identify the second preset value as a character corresponding to the pixel point if the gray value of the pixel point is smaller than the average gray value.
The calculating unit 300 is configured to obtain picture fingerprints of a plurality of popular pictures from a fingerprint database that is constructed in advance, and calculate a hamming distance between the picture fingerprint of the user picture and the picture fingerprint of the popular picture for each popular picture, so as to obtain a similarity between each popular picture and the user picture.
The computing unit 300 is specifically configured to: collecting each hot picture from the Internet by using a web crawler; reducing each hot picture according to a preset size to obtain each target picture; for each target picture, fingerprint extraction is carried out on the target picture to obtain the picture fingerprint of each popular picture; and constructing a fingerprint database based on each hot picture and the picture fingerprint of each hot picture.
A selecting unit 400, configured to select the top-ranked picture with the largest similarity from the top-ranked pictures as the valid pictures.
The sending unit 500 is configured to send the valid picture to the client, so that the client displays the valid picture to a user through a preset interface.
In summary, the picture fingerprints of the hot pictures are obtained from the fingerprint database, the hamming distance between the picture fingerprint of the user picture and the picture fingerprint of the hot picture is calculated for each hot picture, the similarity between each hot picture and the user picture is obtained, the hot picture with the largest similarity is selected from the hot pictures and is used as an effective picture, and the effective picture is sent to the client side, so that the client side displays the effective picture to the user through the preset interface.
The present application also provides a computer-readable storage medium including a stored program, wherein the program performs the method of picture matching provided by the present application.
The present application further provides an apparatus for matching pictures, including: a processor, a memory, and a bus. The processor is connected with the memory through a bus, the memory is used for storing programs, and the processor is used for running the programs, wherein when the programs are run, the method for matching the pictures provided by the application is executed, and the method comprises the following steps:
the method comprises the steps that a video image containing a user is obtained from a remote video call between a client and a seat end, and the video image is converted into a picture frame to obtain a user picture;
fingerprint extraction is carried out on the user picture to obtain a picture fingerprint of the user picture;
acquiring picture fingerprints of a plurality of popular pictures from a pre-constructed fingerprint database, and calculating the Hamming distance between the picture fingerprint of the user picture and the picture fingerprint of the popular picture aiming at each popular picture to obtain the similarity between each popular picture and the user picture;
selecting the hot picture with the maximum similarity from all the hot pictures as an effective picture;
and sending the effective picture to the client so that the client displays the effective picture to the user through a preset interface.
Optionally, the process of constructing the fingerprint database includes:
collecting each hot picture from the Internet by using a web crawler;
reducing each hot picture according to a preset size to obtain each target picture;
for each target picture, fingerprint extraction is carried out on the target picture to obtain a picture fingerprint of each popular picture;
and constructing the fingerprint database based on each hot picture and the picture fingerprint of each hot picture.
Optionally, the fingerprint extraction is performed on the user picture to obtain a picture fingerprint of the user picture, and the method includes:
carrying out gray level conversion on the user picture to obtain a gray level image of the user picture; the gray image comprises pixel points and the gray value of each pixel point;
calculating the average value of the gray values of all pixel points in the gray image to obtain the average value of the gray values;
determining characters corresponding to each pixel point in the gray level image according to the gray level average value;
and establishing a character string based on the characters corresponding to the pixel points, and identifying the character string as the picture fingerprint of the user picture.
Optionally, the determining, according to the average grayscale value, a character corresponding to each pixel point in the grayscale image includes:
for each pixel point in the gray image, judging whether the gray value of the pixel point is not less than the average gray value;
and if the gray value of the pixel point is not less than the average gray value, identifying a first preset value as a character corresponding to the pixel point.
Optionally, the method further includes:
and if the gray value of the pixel point is smaller than the average gray value, identifying a second preset value as a character corresponding to the pixel point.
The functions described in the method of the embodiment of the present application, if implemented in the form of software functional units and sold or used as independent products, may be stored in a storage medium readable by a computing device. Based on such understanding, part of the technical solutions or portions of the embodiments contributing to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computing device (which may be a personal computer, a server, a mobile computing device, a network device, or the like) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: u disk, removable hard disk, read only memory, random access memory, magnetic or optical disk, etc. for storing program codes.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for picture matching, comprising:
the method comprises the steps that a video image containing a user is obtained from a remote video call between a client and a seat end, and the video image is converted into a picture frame to obtain a user picture;
fingerprint extraction is carried out on the user picture to obtain a picture fingerprint of the user picture;
acquiring picture fingerprints of a plurality of popular pictures from a pre-constructed fingerprint database, and calculating the Hamming distance between the picture fingerprint of the user picture and the picture fingerprint of the popular picture aiming at each popular picture to obtain the similarity between each popular picture and the user picture;
selecting the hot picture with the maximum similarity from all the hot pictures as an effective picture;
and sending the effective picture to the client so that the client displays the effective picture to the user through a preset interface.
2. The method according to claim 1, wherein the construction process of the fingerprint database comprises:
collecting each hot picture from the Internet by using a web crawler;
carrying out reduction processing on each hot picture according to a preset size to obtain each target picture;
for each target picture, fingerprint extraction is carried out on the target picture to obtain a picture fingerprint of each popular picture;
and constructing the fingerprint database based on each hot picture and the picture fingerprint of each hot picture.
3. The method of claim 1, wherein the fingerprint extracting the user picture to obtain the picture fingerprint of the user picture comprises:
carrying out gray level conversion on the user picture to obtain a gray level image of the user picture; the gray image comprises pixel points and the gray value of each pixel point;
calculating the average value of the gray values of all pixel points in the gray image to obtain the average value of the gray values;
determining characters corresponding to each pixel point in the gray level image according to the gray level average value;
and establishing a character string based on the characters corresponding to the pixel points, and identifying the character string as the picture fingerprint of the user picture.
4. The method of claim 3, wherein said determining the character corresponding to each pixel point in the grayscale image according to the grayscale mean comprises:
for each pixel point in the gray image, judging whether the gray value of the pixel point is not less than the average gray value;
and if the gray value of the pixel point is not less than the average gray value, identifying a first preset value as a character corresponding to the pixel point.
5. The method of claim 4, further comprising:
and if the gray value of the pixel point is smaller than the average gray value, identifying a second preset value as a character corresponding to the pixel point.
6. An apparatus for picture matching, comprising:
the system comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is used for acquiring a video image containing a user from a remote video call between a client and a seat end, and converting the video image into a picture frame to obtain a user picture;
the extraction unit is used for carrying out fingerprint extraction on the user picture to obtain the picture fingerprint of the user picture;
the calculation unit is used for acquiring the image fingerprints of a plurality of popular images from a fingerprint database which is constructed in advance, and calculating the Hamming distance between the image fingerprint of the user image and the image fingerprint of the popular image aiming at each popular image to obtain the similarity between each popular image and the user image;
the selecting unit is used for selecting the hot picture with the maximum similarity from all the hot pictures as an effective picture;
and the sending unit is used for sending the effective pictures to the client so that the client can display the effective pictures to the user through a preset interface.
7. The apparatus according to claim 6, wherein the computing unit is specifically configured to:
collecting each hot picture from the Internet by using a web crawler;
carrying out reduction processing on each hot picture according to a preset size to obtain each target picture;
for each target picture, fingerprint extraction is carried out on the target picture to obtain a picture fingerprint of each popular picture;
and constructing the fingerprint database based on the hot pictures and the picture fingerprints of each hot picture.
8. The apparatus according to claim 6, wherein the extraction unit is specifically configured to:
carrying out gray level conversion on the user picture to obtain a gray level image of the user picture; the gray image comprises pixel points and the gray value of each pixel point;
calculating the average value of the gray values of all pixel points in the gray image to obtain the average value of the gray values;
determining characters corresponding to each pixel point in the gray level image according to the gray level average value;
and establishing a character string based on the characters corresponding to each pixel point, and identifying the character string as the picture fingerprint of the user picture.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a stored program, wherein the program performs the method of picture matching according to any one of claims 1 to 5.
10. An apparatus for picture matching, comprising: a processor, memory, and a bus; the processor and the memory are connected through the bus;
the memory is used for storing a program, and the processor is used for executing the program, wherein the program executes the method for matching pictures according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211048673.5A CN115357736A (en) | 2022-08-29 | 2022-08-29 | Picture matching method, device, storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211048673.5A CN115357736A (en) | 2022-08-29 | 2022-08-29 | Picture matching method, device, storage medium and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115357736A true CN115357736A (en) | 2022-11-18 |
Family
ID=84005183
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211048673.5A Pending CN115357736A (en) | 2022-08-29 | 2022-08-29 | Picture matching method, device, storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115357736A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116627445A (en) * | 2023-07-19 | 2023-08-22 | 苏州浪潮智能科技有限公司 | Method, device and product for identifying progress of server out-of-band installation of operating system |
-
2022
- 2022-08-29 CN CN202211048673.5A patent/CN115357736A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116627445A (en) * | 2023-07-19 | 2023-08-22 | 苏州浪潮智能科技有限公司 | Method, device and product for identifying progress of server out-of-band installation of operating system |
| CN116627445B (en) * | 2023-07-19 | 2023-09-29 | 苏州浪潮智能科技有限公司 | Method, device and product for identifying progress of server out-of-band installation of operating system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2018133825A1 (en) | Method for processing video images in video call, terminal device, server, and storage medium | |
| WO2016082277A1 (en) | Video authentication method and apparatus | |
| CN111985281B (en) | Image generation model generation method and device and image generation method and device | |
| WO2021227704A1 (en) | Image recognition method, video playback method, related device, and medium | |
| CN111681177B (en) | Video processing method and device, computer readable storage medium and electronic equipment | |
| CN113763296A (en) | Image processing method, apparatus and medium | |
| CN115345968B (en) | Virtual object driving method, deep learning network training method and device | |
| CN115357736A (en) | Picture matching method, device, storage medium and equipment | |
| CN115022679B (en) | Video processing method, device, electronic equipment and medium | |
| CN114626967A (en) | Digital watermark embedding and extracting method, device, equipment and storage medium | |
| CN111708939A (en) | Push method and device based on emotion recognition, computer equipment and storage medium | |
| CN113839998B (en) | Image data transmission method, apparatus, device, storage medium, and program product | |
| CN111314395B (en) | Image transmission method, terminal and storage medium | |
| CN111429371A (en) | Image processing method and device and terminal equipment | |
| US9036921B2 (en) | Face and expression aligned movies | |
| CN113011254A (en) | Video data processing method, computer equipment and readable storage medium | |
| CN112565887A (en) | Video processing method, device, terminal and storage medium | |
| CN108668169B (en) | Image information processing method and device, and storage medium | |
| CN112215237B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| CN110213457B (en) | Image transmission method and device | |
| CN117218398A (en) | Data processing method and related device | |
| CN115134656A (en) | Video data processing method, device, equipment and medium | |
| CN110414471B (en) | Video identification method and system based on double models | |
| CN114092359A (en) | Screen-splash processing method and device and electronic equipment | |
| CN113313642A (en) | Image denoising method and device, storage medium and electronic equipment |
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 |