CN113139589A - Picture similarity detection method and device, processor and electronic device - Google Patents
Picture similarity detection method and device, processor and electronic device Download PDFInfo
- Publication number
- CN113139589A CN113139589A CN202110390919.6A CN202110390919A CN113139589A CN 113139589 A CN113139589 A CN 113139589A CN 202110390919 A CN202110390919 A CN 202110390919A CN 113139589 A CN113139589 A CN 113139589A
- Authority
- CN
- China
- Prior art keywords
- picture
- groups
- pictures
- detected
- similarity detection
- 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
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
- G06F16/55—Clustering; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a picture similarity detection method, a picture similarity detection device, a processor and an electronic device. The method comprises the following steps: performing multiple grouping processing on the picture set to be processed according to preset grouping conditions to obtain a plurality of target picture groups, wherein the preset grouping conditions comprise: picture size, picture content; determining a plurality of picture groups to be detected from a plurality of target picture groups based on picture sizes; and carrying out picture similarity detection on the plurality of picture groups to be detected. The invention solves the technical problems of relatively large calculated amount and low image similarity detection efficiency of image similarity detection in a feature extraction mode in the related technology.
Description
Technical Field
The invention relates to the field of computers, in particular to a picture similarity detection method, a picture similarity detection device, a picture similarity detection processor and an electronic device.
Background
At present, a large amount of art resources exist in the manufacturing process of game applications, and pictures in the art resources occupy a main part. In order to reduce the capacity occupied by the art resources in the installation package, it is generally necessary to detect duplicate resources or similar resources, so as to compress the package body of the installation package as much as possible and reduce the storage space occupied by the game application on the mobile device.
For the image similarity detection mode provided in the related art, the characteristic character strings of the images are extracted through a hash algorithm, and then the similarity degree between different images is judged by comparing the difference between the characteristic character strings of different images.
However, the obvious defects of the picture similarity detection method are as follows: the calculated amount is relatively large, and the efficiency is low. More information is lost in the feature extraction process, and an erroneous conclusion can be drawn in some cases. In addition, in the actual production process of the game application, due to the applicability and display requirements of the code, pictures with different sizes or pictures with different bit depths are often irreplaceable, so similar pictures obtained by performing similarity comparison by using the characteristic character strings are often irreplaceable.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
At least some embodiments of the present invention provide a method, an apparatus, a processor, and an electronic apparatus for detecting picture similarity, so as to at least solve the technical problems of relatively large calculation amount and low picture similarity detection efficiency in detecting picture similarity through a feature extraction method in the related art.
According to an embodiment of the present invention, a method for detecting picture similarity is provided, including:
performing multiple grouping processing on the picture set to be processed according to preset grouping conditions to obtain a plurality of target picture groups, wherein the preset grouping conditions comprise: picture size, picture content; determining a plurality of picture groups to be detected from a plurality of target picture groups based on picture sizes; and carrying out picture similarity detection on the plurality of picture groups to be detected.
Optionally, performing multiple grouping processes on the to-be-processed picture set according to a preset grouping condition, and obtaining multiple target picture groups includes: performing first grouping processing on a picture set to be processed according to the picture size to obtain a plurality of initial picture groups, wherein the picture sizes of a plurality of pictures contained in each initial picture group in the initial picture groups are the same; and performing second grouping processing on the plurality of initial picture groups according to the picture content to obtain a plurality of target picture groups, wherein the picture sizes of a plurality of pictures contained in each target picture group in the plurality of target picture groups are the same as the picture content.
Optionally, the determining of the picture content by the MD5 value, and performing second grouping processing on the multiple initial picture groups according to the picture content to obtain multiple target picture groups includes: and performing second grouping processing according to the MD5 value of each picture contained in each initial picture group in the plurality of initial picture groups to obtain a plurality of target picture groups.
Optionally, determining a plurality of groups of pictures to be detected from the plurality of target groups of pictures based on the picture size includes: and determining a plurality of picture groups to be detected with the same picture size from the plurality of target picture groups.
Optionally, the detecting the picture similarity of the plurality of groups of pictures to be detected includes: selecting a first picture group to be detected and a second picture group to be detected from a plurality of picture groups to be detected; selecting a first picture from the first group of pictures to be detected and selecting a second picture from the second group of pictures to be detected; carrying out picture similarity detection on the first picture and the second picture based on a preset threshold, wherein the picture similarity detection comprises the following steps: local picture region similarity detection and overall picture region similarity detection.
Optionally, the detecting the local picture region similarity of the plurality of groups of pictures to be detected includes: determining a first length and a first width of a picture area to be intercepted in a first picture and a second picture according to a preset threshold value; intercepting a first picture area from a first picture and a second picture area from a second picture by using a first length and a first width; acquiring first image information of a first picture area and second image information of a second picture area, wherein the first image information comprises: a color value and a transparency corresponding to each pixel point in the first picture region, the second image information including: the color value and the transparency corresponding to each pixel point in the second picture area; converting the first image information into a first matrix and converting the second image information into a second matrix; and performing local picture region similarity detection on the plurality of picture groups to be detected based on a second length, a second width and a difference value operation result of the first matrix and the second matrix to obtain a first difference between the first picture region and the second picture region, wherein the second length is the length of the first picture or the second picture, and the second width is the width of the first picture or the second picture.
Optionally, the detecting the overall picture region similarity of the plurality of groups of pictures to be detected includes: when the first difference degree is smaller than or equal to a preset threshold value, acquiring third image information of the first picture and fourth image information of the second picture, wherein the third image information comprises: the color value and the transparency corresponding to each pixel point in the first picture, and the fourth image information includes: the color value and the transparency corresponding to each pixel point in the second picture; converting the third image information into a third matrix and converting the fourth image information into a fourth matrix; carrying out overall picture region similarity detection on the multiple picture groups to be detected based on the second length, the second width and the difference value operation result of the third matrix and the fourth matrix to obtain a second difference between the first picture and the second picture; and when the second difference degree is smaller than or equal to a preset threshold value, determining that the first picture and the second picture are similar pictures.
Optionally, the method for detecting picture similarity further includes: performing picture segmentation processing on the first picture and the second picture to obtain the same part of picture and different part of picture in the first picture and the second picture; and after the same part of picture is subjected to picture duplicate removal processing, drawing and storing the same part of picture and different part of picture.
According to an embodiment of the present invention, there is also provided an apparatus for detecting picture similarity, including:
the grouping module is used for performing multiple grouping processing on the picture sets to be processed according to preset grouping conditions to obtain a plurality of target picture groups, wherein the preset grouping conditions comprise: picture size, picture content; the determining module is used for determining a plurality of picture groups to be detected from a plurality of target picture groups based on the picture size; and the detection module is used for detecting the picture similarity of the plurality of picture groups to be detected.
Optionally, the grouping module is configured to perform first grouping processing on the to-be-processed picture set according to the picture size to obtain a plurality of initial picture groups, where the picture sizes of a plurality of pictures included in each of the plurality of initial picture groups are the same; and performing second grouping processing on the plurality of initial picture groups according to the picture content to obtain a plurality of target picture groups, wherein the picture sizes of a plurality of pictures contained in each target picture group in the plurality of target picture groups are the same as the picture content.
Optionally, the picture content is determined by an MD5 value, and the grouping module is configured to perform second grouping processing according to the MD5 value of each picture included in each of the multiple initial groups of pictures, to obtain multiple target groups of pictures.
Optionally, the determining module is configured to determine, from the plurality of target picture groups, a plurality of picture groups to be detected with the same picture size.
Optionally, the detection module is configured to select a first group of pictures to be detected and a second group of pictures to be detected from the plurality of groups of pictures to be detected; selecting a first picture from the first group of pictures to be detected and selecting a second picture from the second group of pictures to be detected; carrying out picture similarity detection on the first picture and the second picture based on a preset threshold, wherein the picture similarity detection comprises the following steps: local picture region similarity detection and overall picture region similarity detection.
Optionally, the detection module is configured to determine a first length and a first width of a to-be-intercepted picture region in the first picture and the second picture according to a preset threshold; intercepting a first picture area from a first picture and a second picture area from a second picture by using a first length and a first width; acquiring first image information of a first picture area and second image information of a second picture area, wherein the first image information comprises: a color value and a transparency corresponding to each pixel point in the first picture region, the second image information including: the color value and the transparency corresponding to each pixel point in the second picture area; converting the first image information into a first matrix and converting the second image information into a second matrix; and performing local picture region similarity detection on the plurality of picture groups to be detected based on a second length, a second width and a difference value operation result of the first matrix and the second matrix to obtain a first difference between the first picture region and the second picture region, wherein the second length is the length of the first picture or the second picture, and the second width is the width of the first picture or the second picture.
Optionally, the detecting module is configured to acquire third image information of the first picture and fourth image information of the second picture when the first difference is smaller than or equal to a preset threshold, where the third image information includes: the color value and the transparency corresponding to each pixel point in the first picture, and the fourth image information includes: the color value and the transparency corresponding to each pixel point in the second picture; converting the third image information into a third matrix and converting the fourth image information into a fourth matrix; carrying out overall picture region similarity detection on the multiple picture groups to be detected based on the second length, the second width and the difference value operation result of the third matrix and the fourth matrix to obtain a second difference between the first picture and the second picture; and when the second difference degree is smaller than or equal to a preset threshold value, determining that the first picture and the second picture are similar pictures.
Optionally, the image similarity detection apparatus further includes: the processing module is used for carrying out picture segmentation processing on the first picture and the second picture to obtain the same part picture and different part pictures in the first picture and the second picture; and after the same part of picture is subjected to picture duplicate removal processing, drawing and storing the same part of picture and different part of picture.
According to an embodiment of the present invention, there is further provided a non-volatile storage medium, in which a computer program is stored, where the computer program is configured to execute the picture similarity detection method in any one of the above methods when the computer program runs.
According to an embodiment of the present invention, there is further provided a processor, configured to execute a program, where the program is configured to execute the picture similarity detection method in any one of the above methods when running.
According to an embodiment of the present invention, there is further provided an electronic apparatus including a memory and a processor, where the memory stores a computer program, and the processor is configured to execute the computer program to perform the picture similarity detection method in any one of the above.
In at least some embodiments of the present invention, a preset grouping condition is adopted to perform multiple grouping processing on a to-be-processed picture set to obtain multiple target picture groups, where the preset grouping condition includes a picture size and a picture content, and multiple picture groups to be detected are determined from the multiple target picture groups according to the picture size and picture similarity detection is performed on the multiple picture groups to be detected, so as to achieve the purpose of performing multiple grouping processing on the to-be-processed picture set to simplify a picture similarity detection process, thereby achieving the technical effects of effectively reducing the computational complexity of the picture similarity detection process and improving the picture similarity detection efficiency, and further solving the technical problems of relatively large computational complexity and relatively low picture similarity detection efficiency in picture similarity detection performed in a feature extraction manner in the related art.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a flowchart illustrating a method for detecting picture similarity according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for detecting picture similarity according to an alternative embodiment of the present invention;
FIG. 3 is a diagram illustrating subsequent processing of a picture based on a similarity detection result according to an alternative embodiment of the present invention;
FIG. 4 is a block diagram of a picture similarity detecting apparatus according to an embodiment of the present invention;
fig. 5 is a block diagram of a picture similarity detecting apparatus according to an alternative embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In accordance with one embodiment of the present invention, there is provided an embodiment of a picture similarity detection method, it should be noted that the steps shown in the flowchart of the drawings may be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown.
Method embodiment one provided method embodiment may be performed in a mobile terminal, a computer terminal, or a similar computing device. Taking the example of the Mobile terminal running on the Mobile terminal, the Mobile terminal may be a terminal device such as a smart phone (e.g., an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, a Mobile Internet Device (MID), a PAD, a game console, etc. The mobile terminal may include one or more processors (which may include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a Digital Signal Processing (DSP) chip, a Microprocessor (MCU), a programmable logic device (FPGA), a neural Network Processor (NPU), a Tensor Processor (TPU), an Artificial Intelligence (AI) type processor, etc.) and a memory for storing data. Optionally, the mobile terminal may further include a transmission device, an input/output device, and a display device for a communication function. It will be understood by those skilled in the art that the foregoing structural description is only illustrative and not restrictive of the structure of the mobile terminal. For example, the mobile terminal may also include more or fewer components than shown in the above structural description, or may have a different configuration than described in the above structural description.
The memory may be configured to store a computer program, for example, a software program and a module of an application software, such as a computer program corresponding to the picture similarity detection method in the embodiment of the present invention, and the processor executes various functional applications and data processing by running the computer program stored in the memory, that is, implements the picture similarity detection method described above. The memory may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include memory located remotely from the processor, and these remote memories may be connected to the mobile terminal through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device is used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmission device may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
The inputs in the input-output devices may come from a plurality of Human Interface devices (HID for short). For example: keyboard and mouse, game pad, other special game controller (such as steering wheel, fishing rod, dance mat, remote controller, etc.). Some human interface devices may provide output functions in addition to input functions, such as: force feedback and vibration of the gamepad, audio output of the controller, etc.
The display device may be, for example, a head-up display (HUD), a touch screen type Liquid Crystal Display (LCD), and a touch display (also referred to as a "touch screen" or "touch display screen"). The liquid crystal display may enable a user to interact with a user interface of the mobile terminal. In some embodiments, the mobile terminal has a Graphical User Interface (GUI) with which a user can interact by touching finger contacts and/or gestures on a touch-sensitive surface, where the human-machine interaction function optionally includes the following interactions: executable instructions for creating web pages, drawing, word processing, making electronic documents, games, video conferencing, instant messaging, emailing, call interfacing, playing digital video, playing digital music, and/or web browsing, etc., for performing the above-described human-computer interaction functions, are configured/stored in one or more processor-executable computer program products or readable storage media.
In this embodiment, a method for detecting picture similarity running in the mobile terminal is provided, and fig. 1 is a flowchart of the method for detecting picture similarity according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:
step S10, performing multiple grouping processing on the to-be-processed picture sets according to preset grouping conditions to obtain multiple target picture sets, where the preset grouping conditions include: picture size, picture content;
the to-be-processed picture set may be a plurality of picture sets in a specified directory or in a specified storage location. The preset grouping condition may include, but is not limited to: whether the picture sizes of different pictures are the same and whether the picture contents of different pictures are the same. Specifically, the picture sets to be processed may be primarily grouped according to whether the picture sizes of different pictures are the same, so that the picture sizes of the pictures in each primary group are the same; and then performing secondary grouping according to whether the picture contents among different pictures in each group of pictures after primary grouping are the same or not so as to enable the picture contents of all the pictures in each secondary grouping to be the same.
Step S12, determining a plurality of picture groups to be detected from a plurality of target picture groups based on picture size;
because the pictures with the same picture size are divided into the same group in the primary grouping process, and the pictures with different sizes can be directly determined as the overall dissimilar pictures, only a plurality of picture groups to be detected are selected from the secondary groups with different picture contents from the groups with the same size to carry out picture similarity detection, so that the picture similarity detection efficiency is improved.
And step S14, carrying out picture similarity detection on a plurality of picture groups to be detected.
Through the steps, the preset grouping condition can be adopted to carry out grouping processing on the picture set to be processed for multiple times to obtain a plurality of target picture groups, the preset grouping condition comprises a picture size and picture content mode, the picture groups to be detected are determined from the target picture groups through the picture size, and picture similarity detection is carried out on the picture groups to be detected, so that the aim of carrying out grouping processing on the picture set to be processed for multiple times to simplify the picture similarity detection process is fulfilled, the technical effects of effectively reducing the calculation complexity of the picture similarity detection process and improving the picture similarity detection efficiency are achieved, and the technical problems that in the related technology, the calculation amount of picture similarity detection through a feature extraction mode is relatively large, and the picture similarity detection efficiency is relatively low are solved.
Optionally, in step S10, performing grouping processing on the to-be-processed picture set multiple times according to the preset grouping condition, and obtaining multiple target picture groups may include the following steps:
step S100, performing first grouping processing on a picture set to be processed according to picture sizes to obtain a plurality of initial picture groups, wherein the picture sizes of a plurality of pictures contained in each initial picture group in the plurality of initial picture groups are the same;
step S101, performing second grouping processing on the multiple initial picture groups according to the picture content to obtain multiple target picture groups, where picture sizes of multiple pictures included in each target picture group in the multiple target picture groups are the same as the picture content.
In the implementation process, pictures with different sizes are usually irreplaceable, and the detection of similar pictures usually aims at reducing the size of the bag body subsequently. For example: if the game application needs to load a 50 x 50 picture, a display exception occurs within the game application when the game application loads a 100 x 100 picture. Therefore, the first grouping processing may be performed on the to-be-processed picture set according to the picture size to obtain a plurality of initial picture groups, where the picture sizes of the plurality of pictures included in each of the plurality of initial picture groups are the same, for example: initial group of pictures a, initial group of pictures a' … ….
For each initial group of pictures A, A' … …, a second grouping process may be further performed on multiple initial groups of pictures according to picture contents to obtain multiple target groups of pictures, where picture sizes and picture contents of multiple pictures included in each target group of pictures in the multiple target groups of pictures are the same, for example: the initial group of pictures A is further divided into a target group of pictures A1Target picture group A2Target picture group A3… …, the initial group of pictures A 'is further divided into a target group of pictures A'1Target Picture group A'2Target Picture group A'3… …, and the like.
Optionally, the picture content is determined by an MD5 value, and in step S101, performing a second grouping process on the multiple initial picture groups according to the picture content to obtain multiple target picture groups may include the following steps:
step S1010, performing second grouping processing according to the MD5 value of each picture included in each of the plurality of initial picture groups, to obtain a plurality of target picture groups.
The above-mentioned picture content may be determined using a Message Digest Algorithm (MD 5 for short) Algorithm. MD5 is a widely used cryptographic hash function that can be computed to obtain a 128-bit hash value to ensure information consistency. The grouping based on picture size and MD5 values is based on: the MD5 values of pictures with different sizes are definitely different, and the pictures with different sizes are usually not replaceable in practical application, so that the pictures with different sizes are defined as pictures with differences.
When the MD5 values between two different pictures are the same, it can be determined that the two pictures are completely identical. That is, the degree of similarity is 100% and the degree of difference is 0% for different pictures with the same MD5 value. It should be noted that the MD5 value is only one of the image comparison methods with high determination efficiency selected in the embodiment of the present invention, and is not to be construed as a limitation of the present invention, and other equivalent determination methods are also within the scope of the present invention. For example: and comparing two different pictures one by one to judge that the two pictures are completely consistent.
For each first grouping A, A' … …, a second grouping process may be further performed according to the MD5 value of each picture included in each initial group of pictures in the plurality of initial groups of pictures, to obtain a plurality of target groups of pictures, for example: the initial group of pictures A is further divided into a target group of pictures A1Target picture group A2Target picture group A3… …, the initial group of pictures A 'is further divided into a target group of pictures A'1Target Picture group A'2Target Picture group A'3… …, and the like.
If the number of target picture groups contained in the initial picture group is greater than 1, similarity can be calculated for different pictures between different target picture groups in the same initial picture group. For a plurality of pictures with the same MD5 value in the same target group, one of the pictures can be arbitrarily selected to perform similarity comparison with the pictures in another target group. For example: when the picture a and the picture B are completely similar, if the similarity between the picture B and the picture C is 99%, the similarity between the picture a and the picture C is also 99%.
In an optional embodiment, after grouping according to picture sizes, because there is a difference between pictures of different sizes, a multithread processing manner may be adopted to complete secondary grouping processing based on the MD5 value and picture similarity comparison processing after secondary grouping, thereby further improving picture similarity detection efficiency.
Alternatively, in step S12, determining a plurality of groups of pictures to be detected from the plurality of target groups of pictures based on the picture size may include performing the steps of:
step S120, determining a plurality of to-be-detected picture groups with the same picture size from the plurality of target picture groups.
After the second grouping processing is performed according to the MD5 value of each picture contained in each of the plurality of initial groups of pictures to obtain a plurality of target groups of pictures, a dictionary is formed. Then, a plurality of picture groups to be detected with the same picture size can be determined from a plurality of target picture groups of the dictionary.
For example: assuming that a plurality of to-be-detected picture groups with the same picture size determined from a plurality of target picture groups of the dictionary are { md51: [ pic1, pic2, pic3], md52: [ pic4] }, the number of pictures of the md52 corresponding to the target picture group is 1, namely pic4, so that the grouping length of the md52 corresponding to the target picture group is 1. And the number of pictures of md51 corresponding to the target group of pictures is 3, which are pic1, pic2 and pic3, respectively, and pic1, pic2 and pic3 are identical pictures, so that the group length of md51 corresponding to the target group of pictures is 3. In this way, when calculating the similarity between different pictures, only the similarity (labeled as D) between any one of pic1, pic2 and pic3 (for example: pic1) and pic4 is calculated. Then the similarity between the other two pictures pic2, pic3 and pic4 can be directly deduced as D.
Optionally, in step S14, the performing picture similarity detection on multiple picture groups to be detected may include the following steps:
step S140, selecting a first group of pictures to be detected and a second group of pictures to be detected from a plurality of groups of pictures to be detected;
step S141, selecting a first picture from the first group of pictures to be detected and selecting a second picture from the second group of pictures to be detected;
step S142, carrying out image similarity detection on the first image and the second image based on a preset threshold, wherein the image similarity detection comprises the following steps: local picture region similarity detection and overall picture region similarity detection.
The preset threshold is a difference threshold, and the difference threshold is determined by a similarity threshold.
Assume that the similarity threshold between different pictures is STWhen the similarity between the picture A and the picture B is greater than or equal to STIf so, the picture A and the picture B are similar pictures; when the similarity between the picture A and the picture B is less than STWhen the picture a and the picture B are dissimilar pictures. In addition, S isTIs an empirical value set according to the actual needs and goals of the game item.
Assume a degree of difference threshold of DTThen D isT＝(1-ST) 100%. For example: sT99% of DTIs 1%. When the difference degree between the picture A and the picture B is less than DTIf so, the picture A and the picture B are similar pictures; when the difference degree between the picture A and the picture B is greater than or equal to DTWhen the picture a and the picture B are dissimilar pictures.
In an optional embodiment, a first group of pictures to be detected and a second group of pictures to be detected may be selected from the plurality of groups of pictures to be detected, a first picture may be selected from the first group of pictures to be detected, a second picture may be selected from the second group of pictures to be detected, and then picture similarity detection may be performed on the first picture and the second picture based on a preset threshold. In the process of detecting the image similarity, the local image region similarity can be detected first, and then the overall image region similarity can be detected.
Optionally, in step S142, the local picture region similarity detection on multiple picture groups to be detected may include the following steps:
step S1420, determining a first length and a first width of a picture area to be intercepted in the first picture and the second picture according to a preset threshold value;
step S1421, using the first length and the first width to cut out a first picture region from the first picture and a second picture region from the second picture;
step S1422, acquire first image information of the first picture region and second image information of the second picture region, where the first image information includes: a color value and a transparency corresponding to each pixel point in the first picture region, the second image information including: the color value and the transparency corresponding to each pixel point in the second picture area;
step S1423, converting the first image information into a first matrix and converting the second image information into a second matrix;
step S1424, performing local picture region similarity detection on the multiple picture groups to be detected based on a second length, a second width, and a difference operation result between the first matrix and the second matrix, to obtain a first difference between the first picture region and the second picture region, where the second length is the length of the first picture or the second picture, and the second width is the width of the first picture or the second picture.
When L is the length of the whole picture and W is the width of the whole picture, the length L of the picture area to be cut is
Width w of
Where δ is a coefficient. The selection of the coefficient delta directly influences the hit rate of the calculation result of the image intercepting area, and further influences the efficiency of the whole algorithm. In an alternative example, δ may be chosen to be an empirical value (e.g., 5). For picture sets with different characteristics, the ideal operation efficiency can be achieved by adjusting the value of delta.
The method comprises the steps of intercepting a first picture region from a first picture and intercepting a second picture region from a second picture by using the length l and the width w, then respectively obtaining first image information (namely a value of RGB color corresponding to each pixel point in the first picture region and corresponding transparency A) of the first picture region and second image information (namely a value of RGB color corresponding to each pixel point in the second picture region and corresponding transparency A) of the second picture region, converting the first image information and the second image information into a two-dimensional matrix to represent, wherein each pixel point is an element of the matrix:
each element of the matrix is represented by a vector:
mwl＝[Rwl，Gwl，Bwl，Awl]
wherein R iswl，Gwl，BwlRespectively, the values of RGB corresponding to the pixel points, AwlThe Alpha transparency corresponding to this pixel point. For pictures 24 bits deep or without Alpha clear channel, AwlIs 0.
In an optional embodiment, the image information may be buffered to improve the picture similarity detection efficiency.
After the first image information is converted into the first matrix and the second image information is converted into the second matrix, the difference operation may be performed on the first matrix obtained by converting the first image information and the second matrix obtained by converting the second image information, so as to obtain the number non-zero _ num of the non-zero elements in the matrix elements.
Therefore, local picture region similarity detection is performed on a plurality of picture groups to be detected based on the length L, the width W and the non-zero _ num, and a first difference D between the first picture region and the second picture region is obtained as follows:
when D is less than or equal to DTAnd then, the overall picture region similarity detection can be continuously carried out on the plurality of picture groups to be detected. When D > DTAnd when the two different pictures are not similar in whole, determining that the two different pictures are not similar.
Optionally, in step S142, performing overall picture region similarity detection on multiple picture groups to be detected may include the following steps:
step S1420, when the first difference is smaller than or equal to the preset threshold, acquiring third image information of the first picture and fourth image information of the second picture, where the third image information includes: the color value and the transparency corresponding to each pixel point in the first picture, and the fourth image information includes: the color value and the transparency corresponding to each pixel point in the second picture;
step S1421, converting the third image information into a third matrix and converting the fourth image information into a fourth matrix;
step S1422, performing overall picture region similarity detection on the plurality of picture groups to be detected based on the second length, the second width and the difference operation result of the third matrix and the fourth matrix to obtain a second difference between the first picture and the second picture;
in step S1423, when the second difference is smaller than or equal to the preset threshold, it is determined that the first picture and the second picture are similar pictures.
When the first difference is smaller than or equal to the preset threshold, the third image information of the first picture (i.e., the RGB color value corresponding to each pixel point in the first picture and the corresponding transparency a) and the fourth image information of the second picture (i.e., the RGB color value corresponding to each pixel point in the second picture and the corresponding transparency a) may be obtained, and the third image information and the fourth image information are converted into a two-dimensional matrix for representation. Then, overall picture region similarity detection is carried out on the multiple picture groups to be detected based on the second length, the second width and the difference value operation result of the third matrix and the fourth matrix to obtain a second difference D between the first picture and the second picturetotalComprises the following steps:
wherein, nonzeronumtotalThe number of non-zero elements in the matrix elements corresponding to the whole picture.
When D is presenttotal≤DTAnd then determining that the two different pictures are integrally similar. When D is presenttotal＞DTAnd when the two different pictures are not similar in whole, determining that the two different pictures are not similar.
Fig. 2 is a flowchart of a picture similarity detection method according to an alternative embodiment of the present invention, as shown in fig. 2, the method includes the following steps:
in step S202, for two different pictures in different second groups, the size and bit depth between the two different pictures are obtained.
Step S204, comparing whether the size and the bit depth between the two different pictures are the same, if so, continuing to execute the step S206; if the size or bit depth is different between the two different pictures, go to step S218. Note that this step S204 is an optional step.
In step S206, since the two different pictures have the same size, the region at the same position can be intercepted to obtain the image intercepting region (i.e. the set of pixel points).
And S208, locally comparing the image intercepting areas, and calculating the difference between the image intercepting areas so as to determine overall dissimilar images as soon as possible, thereby improving the image similarity detection efficiency.
Step S210, judging whether D is less than or equal to a preset threshold value DTWhen D is less than or equal to DTIf so, continuing to execute step S212; when D > DTThen, the process goes to step S218.
In step S212, the difference degree of the whole picture is calculated.
Step S214, determine DtotalWhether or not it is less than or equal to a preset threshold DTWhen D is presenttotal≤DTIf so, continue to step S216; when D is presenttotal＞DTThen, the process goes to step S218.
Step S216, determining that the two different pictures are integrally similar.
Step S218, it is determined that the two different pictures are not similar as a whole.
Optionally, the image similarity detection method may further include the following steps:
step S15, carrying out picture segmentation processing on the first picture and the second picture to obtain the same part picture and different part pictures in the first picture and the second picture;
in step S16, after the same partial picture is subjected to the picture deduplication processing, the same partial picture and a different partial picture are drawn and stored.
When the size of the bag body of art resources needs to be reduced in an actual game project, the similar pictures can be divided to obtain the same part of pictures and different parts of pictures. For the same part of the picture, the picture duplicate removal processing can be performed on the same part of the picture, and then one same part of the picture is drawn and stored, and different parts of the picture are drawn and stored respectively. Finally, when the picture is loaded in the game, the same part of pictures and different parts of pictures can be dynamically synthesized, so that the overall size of the bag body is reduced.
Therefore, if the two pictures are compared for multiple times and only a small number of pixels are different (namely, the representation in the game is basically not different and is difficult to distinguish by naked eyes), in the practical engineering application, one picture can be used for replacing the other picture so as to realize the cleaning of the art resources and the reduction of redundancy. In addition, in the picture making process, two similar pictures can be divided into the same part and the different part, only one part of the same part is reserved, and the different part is made respectively, so that the use amount of art resources is reduced.
Fig. 3 is a schematic diagram of performing subsequent processing of pictures based on the similarity detection result according to an alternative embodiment of the present invention, where as shown in fig. 3, the picture size of picture a is the same as the picture size of picture B, and the MD5 value of picture a is different from the MD5 value of picture B. Since the two different pictures are the same size, the clipping operation can be performed on the same location areas in picture a and picture B, resulting in a different area 1 in picture a and a different area 2 in picture B. Then, the picture a and the picture B are subjected to picture segmentation processing to obtain a picture C (namely, the same region), a picture D (namely, different region 1) and a picture E (different region 2). Finally, when the bag is loaded in a game, the picture C and the picture D can be dynamically synthesized to obtain the picture A, and the picture C and the picture E can be dynamically synthesized to obtain the picture B, so that the overall size of the bag body is reduced.
By the technical scheme, the size of a game resource bag body can be effectively reduced, and the conversion rate and the equipment coverage rate of a newly added user can be improved. The game downloading willingness of the game player is inversely proportional to the size of the bag body (namely, the larger the bag body, the smaller the downloading willingness) on the premise of not considering the game type and the content influence. In addition, the larger the packet body is, the higher the possibility of abnormality (such as network interruption) in the downloading process is. Therefore, if the size of the game resource bag body can be effectively reduced, the conversion rate and the equipment coverage rate of the newly added user can be further improved.
Moreover, the size of the patch for daily maintenance can be reduced through the technical scheme. Considering that a game player needs to update the patch before entering the game, the resource update amount of the patch is continuously reduced, and the download duration and the waiting duration are reduced under the same network condition, hardware condition and the like, so that the user experience is further improved.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
In this embodiment, a picture similarity detection apparatus is further provided, and the apparatus is used to implement the foregoing embodiments and preferred embodiments, and the description already made is omitted for brevity. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 4 is a block diagram of a picture similarity detecting apparatus according to an embodiment of the present invention, as shown in fig. 4, the apparatus includes: the grouping module 10 is configured to perform multiple grouping processing on the to-be-processed picture set according to preset grouping conditions to obtain multiple target picture groups, where the preset grouping conditions include: picture size, picture content; a determining module 20, configured to determine a plurality of target picture groups from the plurality of target picture groups based on the picture size; the detecting module 30 is configured to perform picture similarity detection on a plurality of groups of pictures to be detected.
Optionally, the grouping module 10 is configured to perform first grouping processing on the to-be-processed picture set according to the picture size to obtain a plurality of initial picture groups, where the picture sizes of a plurality of pictures included in each of the plurality of initial picture groups are the same; and performing second grouping processing on the plurality of initial picture groups according to the picture content to obtain a plurality of target picture groups, wherein the picture sizes of a plurality of pictures contained in each target picture group in the plurality of target picture groups are the same as the picture content.
Optionally, the picture content is determined by an MD5 value, and the grouping module 10 is configured to perform a second grouping process according to the MD5 value of each picture included in each of the multiple initial groups of pictures, to obtain multiple target groups of pictures.
Optionally, the determining module 20 is configured to determine a plurality of groups of pictures to be detected with the same picture size from the plurality of target groups of pictures.
Optionally, the detecting module 30 is configured to select a first to-be-detected picture group and a second to-be-detected picture group from the multiple to-be-detected picture groups; selecting a first picture from the first group of pictures to be detected and selecting a second picture from the second group of pictures to be detected; carrying out picture similarity detection on the first picture and the second picture based on a preset threshold, wherein the picture similarity detection comprises the following steps: local picture region similarity detection and overall picture region similarity detection.
Optionally, the detecting module 30 is configured to determine a first length and a first width of a to-be-intercepted picture region in the first picture and the second picture according to a preset threshold; intercepting a first picture area from a first picture and a second picture area from a second picture by using a first length and a first width; acquiring first image information of a first picture area and second image information of a second picture area, wherein the first image information comprises: a color value and a transparency corresponding to each pixel point in the first picture region, the second image information including: the color value and the transparency corresponding to each pixel point in the second picture area; converting the first image information into a first matrix and converting the second image information into a second matrix; and performing local picture region similarity detection on the plurality of picture groups to be detected based on a second length, a second width and a difference value operation result of the first matrix and the second matrix to obtain a first difference between the first picture region and the second picture region, wherein the second length is the length of the first picture or the second picture, and the second width is the width of the first picture or the second picture.
Optionally, the detecting module 30 is configured to, when the first difference is smaller than or equal to a preset threshold, acquire third image information of the first picture and fourth image information of the second picture, where the third image information includes: the color value and the transparency corresponding to each pixel point in the first picture, and the fourth image information includes: the color value and the transparency corresponding to each pixel point in the second picture; converting the third image information into a third matrix and converting the fourth image information into a fourth matrix; carrying out overall picture region similarity detection on the multiple picture groups to be detected based on the second length, the second width and the difference value operation result of the third matrix and the fourth matrix to obtain a second difference between the first picture and the second picture; and when the second difference degree is smaller than or equal to a preset threshold value, determining that the first picture and the second picture are similar pictures.
Optionally, fig. 5 is a block diagram of a structure of an image similarity detection apparatus according to an alternative embodiment of the present invention, and as shown in fig. 5, the apparatus includes, in addition to all modules shown in fig. 4, the image similarity detection apparatus further includes: the processing module 40 is configured to perform picture segmentation processing on the first picture and the second picture to obtain a same part picture and a different part picture in the first picture and the second picture; and after the same part of picture is subjected to picture duplicate removal processing, drawing and storing the same part of picture and different part of picture.
It should be noted that, the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are respectively located in different processors in any combination.
Embodiments of the present invention also provide a non-volatile storage medium having a computer program stored therein, wherein the computer program is configured to perform the steps of any of the above method embodiments when executed.
Alternatively, in the present embodiment, the above-mentioned nonvolatile storage medium may be configured to store a computer program for executing the steps of:
s1, grouping the picture sets to be processed for multiple times according to preset grouping conditions to obtain a plurality of target picture sets, wherein the preset grouping conditions comprise: picture size, picture content;
s2, determining a plurality of picture groups to be detected from a plurality of target picture groups based on the picture size;
and S3, detecting the picture similarity of the plurality of picture groups to be detected.
Optionally, in this embodiment, the nonvolatile storage medium may include, but is not limited to: various media capable of storing computer programs, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.
Embodiments of the present invention also provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.
Optionally, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:
s1, grouping the picture sets to be processed for multiple times according to preset grouping conditions to obtain a plurality of target picture sets, wherein the preset grouping conditions comprise: picture size, picture content;
s2, determining a plurality of picture groups to be detected from a plurality of target picture groups based on the picture size;
and S3, detecting the picture similarity of the plurality of picture groups to be detected.
Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and this embodiment is not described herein again.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit 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 Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (12)
1. A picture similarity detection method is characterized by comprising the following steps:
performing multiple times of grouping processing on a picture set to be processed according to preset grouping conditions to obtain a plurality of target picture groups, wherein the preset grouping conditions comprise: picture size, picture content;
determining a plurality of picture groups to be detected from the plurality of target picture groups based on the picture size;
and detecting the picture similarity of the plurality of picture groups to be detected.
2. The method of claim 1, wherein grouping the to-be-processed picture set for multiple times according to the preset grouping condition to obtain the multiple target picture groups comprises:
performing first grouping processing on the to-be-processed picture set according to the picture size to obtain a plurality of initial picture groups, wherein the picture sizes of a plurality of pictures contained in each initial picture group in the plurality of initial picture groups are the same;
and performing second grouping processing on the plurality of initial picture groups according to the picture content to obtain a plurality of target picture groups, wherein the picture sizes of a plurality of pictures contained in each target picture group in the plurality of target picture groups are the same as the picture content.
3. The picture similarity detection method according to claim 2, wherein the picture content is determined by a message digest algorithm MD5 value, and performing the second grouping process on the plurality of initial picture groups according to the picture content to obtain the plurality of target picture groups comprises:
and performing second grouping processing according to the MD5 value of each picture contained in each initial picture group in the plurality of initial picture groups to obtain the plurality of target picture groups.
4. The method according to claim 1, wherein determining the plurality of target groups of pictures to be detected from the plurality of target groups of pictures based on the picture size comprises:
and determining the plurality of picture groups to be detected with the same picture size from the plurality of target picture groups.
5. The picture similarity detection method according to claim 1, wherein the picture similarity detection for the plurality of groups of pictures to be detected comprises:
selecting a first picture group to be detected and a second picture group to be detected from the plurality of picture groups to be detected;
selecting a first picture from the first group of pictures to be detected and selecting a second picture from the second group of pictures to be detected;
performing picture similarity detection on the first picture and the second picture based on a preset threshold, wherein the picture similarity detection comprises: local picture region similarity detection and overall picture region similarity detection.
6. The picture similarity detection method according to claim 5, wherein the local picture region similarity detection for the plurality of groups of pictures to be detected comprises:
determining a first length and a first width of a picture region to be intercepted in the first picture and the second picture according to the preset threshold value;
utilizing the first length and the first width to cut out a first picture area from the first picture and cut out a second picture area from the second picture;
acquiring first image information of the first picture area and second image information of the second picture area, wherein the first image information comprises: a color value and a transparency corresponding to each pixel point in the first picture region, wherein the second image information includes: the color value and the transparency corresponding to each pixel point in the second picture area;
converting the first image information into a first matrix and converting the second image information into a second matrix;
and performing local picture region similarity detection on the plurality of picture groups to be detected based on a second length, a second width and a difference value operation result of the first matrix and the second matrix to obtain a first difference between the first picture region and the second picture region, wherein the second length is the length of the first picture or the second picture, and the second width is the width of the first picture or the second picture.
7. The picture similarity detection method according to claim 6, wherein the overall picture region similarity detection for the plurality of groups of pictures to be detected comprises:
when the first difference is smaller than or equal to the preset threshold, acquiring third image information of the first picture and fourth image information of the second picture, wherein the third image information comprises: a color value and a transparency corresponding to each pixel point in the first picture, and the fourth image information includes: the color value and the transparency corresponding to each pixel point in the second picture;
converting the third image information into a third matrix and converting the fourth image information into a fourth matrix;
performing overall picture region similarity detection on the plurality of picture groups to be detected based on the second length, the second width and a difference value operation result of the third matrix and the fourth matrix to obtain a second difference between the first picture and the second picture;
when the second difference degree is smaller than or equal to the preset threshold value, determining that the first picture and the second picture are similar pictures.
8. The method according to claim 7, wherein the method further comprises:
performing picture segmentation processing on the first picture and the second picture to obtain the same part picture and different part pictures in the first picture and the second picture;
and after the same part of picture is subjected to picture duplicate removal processing, drawing and storing the same part of picture and the different part of picture.
9. An apparatus for detecting picture similarity, comprising:
the grouping module is used for performing multiple grouping processing on the picture set to be processed according to preset grouping conditions to obtain a plurality of target picture groups, wherein the preset grouping conditions comprise: picture size, picture content;
a determining module, configured to determine a plurality of target picture groups from the plurality of target picture groups based on the picture size;
and the detection module is used for detecting the picture similarity of the plurality of picture groups to be detected.
10. A non-volatile storage medium, wherein a computer program is stored in the storage medium, and wherein the computer program is configured to execute the picture similarity detection method according to any one of claims 1 to 8 when the computer program runs.
11. A processor, characterized in that the processor is configured to run a program, wherein the program is configured to execute the picture similarity detection method according to any one of claims 1 to 8 when running.
12. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to perform the picture similarity detection method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110390919.6A CN113139589B (en) | 2021-04-12 | 2021-04-12 | Picture similarity detection method and device, processor and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110390919.6A CN113139589B (en) | 2021-04-12 | 2021-04-12 | Picture similarity detection method and device, processor and electronic device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113139589A true CN113139589A (en) | 2021-07-20 |
| CN113139589B CN113139589B (en) | 2023-02-28 |
Family
ID=76811161
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110390919.6A Active CN113139589B (en) | 2021-04-12 | 2021-04-12 | Picture similarity detection method and device, processor and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113139589B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102034113A (en) * | 2009-09-25 | 2011-04-27 | 索尼公司 | A method to measure local image similarity based on the l1 distance measure |
| CN103295217A (en) * | 2012-03-01 | 2013-09-11 | 阿里巴巴集团控股有限公司 | Method and device for processing picture information |
| CN105426914A (en) * | 2015-11-19 | 2016-03-23 | 中国人民解放军信息工程大学 | Image similarity detection method for position recognition |
| CN106844381A (en) * | 2015-12-04 | 2017-06-13 | 富士通株式会社 | Image processing apparatus and method |
| CN109447154A (en) * | 2018-10-29 | 2019-03-08 | 网易（杭州）网络有限公司 | Picture similarity detection method, device, medium and electronic equipment |
| CN110502651A (en) * | 2019-08-15 | 2019-11-26 | 深圳市商汤科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN110717891A (en) * | 2019-09-17 | 2020-01-21 | 平安科技（深圳）有限公司 | Picture detection method and device based on grouping batch and storage medium |
| US20200218890A1 (en) * | 2019-01-04 | 2020-07-09 | Citrix Systems, Inc. | Methods and systems for updating a database based on object recognition |
| CN111444366A (en) * | 2020-04-10 | 2020-07-24 | Oppo广东移动通信有限公司 | Image classification method and device, storage medium and electronic equipment |
| CN112052186A (en) * | 2020-10-10 | 2020-12-08 | 腾讯科技（深圳）有限公司 | Target detection method, device, equipment and storage medium |
| CN112308162A (en) * | 2020-11-06 | 2021-02-02 | 上海软中信息技术有限公司 | Image big data similarity comparison method and system |
| WO2021036906A1 (en) * | 2019-08-27 | 2021-03-04 | 华为技术有限公司 | Picture processing method and apparatus |
| US20210073593A1 (en) * | 2019-09-06 | 2021-03-11 | The Yes Platform | Cluster and Image-Based Feedback System |
-
2021
- 2021-04-12 CN CN202110390919.6A patent/CN113139589B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102034113A (en) * | 2009-09-25 | 2011-04-27 | 索尼公司 | A method to measure local image similarity based on the l1 distance measure |
| CN103295217A (en) * | 2012-03-01 | 2013-09-11 | 阿里巴巴集团控股有限公司 | Method and device for processing picture information |
| CN105426914A (en) * | 2015-11-19 | 2016-03-23 | 中国人民解放军信息工程大学 | Image similarity detection method for position recognition |
| CN106844381A (en) * | 2015-12-04 | 2017-06-13 | 富士通株式会社 | Image processing apparatus and method |
| CN109447154A (en) * | 2018-10-29 | 2019-03-08 | 网易（杭州）网络有限公司 | Picture similarity detection method, device, medium and electronic equipment |
| US20200218890A1 (en) * | 2019-01-04 | 2020-07-09 | Citrix Systems, Inc. | Methods and systems for updating a database based on object recognition |
| CN110502651A (en) * | 2019-08-15 | 2019-11-26 | 深圳市商汤科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| WO2021036906A1 (en) * | 2019-08-27 | 2021-03-04 | 华为技术有限公司 | Picture processing method and apparatus |
| US20210073593A1 (en) * | 2019-09-06 | 2021-03-11 | The Yes Platform | Cluster and Image-Based Feedback System |
| CN110717891A (en) * | 2019-09-17 | 2020-01-21 | 平安科技（深圳）有限公司 | Picture detection method and device based on grouping batch and storage medium |
| CN111444366A (en) * | 2020-04-10 | 2020-07-24 | Oppo广东移动通信有限公司 | Image classification method and device, storage medium and electronic equipment |
| CN112052186A (en) * | 2020-10-10 | 2020-12-08 | 腾讯科技（深圳）有限公司 | Target detection method, device, equipment and storage medium |
| CN112308162A (en) * | 2020-11-06 | 2021-02-02 | 上海软中信息技术有限公司 | Image big data similarity comparison method and system |
Non-Patent Citations (2)
| Title |
|---|
| 史豫坤等: "基于整体特征差异度参数的人脸相似度检测", 《电脑知识与技术》 * |
| 张建春等: "基于属性权值多级分类的测试样本数据预处理", 《电视技术》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113139589B (en) | 2023-02-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105204781B (en) | Compression method, device and equipment | |
| CN110764906B (en) | Memory recovery processing method and device, electronic equipment and storage medium | |
| CN111352597B (en) | Multi-screen display control method and device, electronic equipment and readable storage medium | |
| CN110457235B (en) | Memory compression method, device, terminal and storage medium | |
| CN107959965B (en) | Frame dropping method and device of application program, mobile terminal and readable storage medium | |
| CN111182332B (en) | Video processing method, device, server and storage medium | |
| CN111124173A (en) | Working state switching method and device of touch screen, mobile terminal and storage medium | |
| CN111401524A (en) | Convolutional neural network processing method, device, equipment, storage medium and model | |
| CN114610650A (en) | Memory compression method and device, storage medium and electronic equipment | |
| CN111260220A (en) | Group control equipment identification method and device, electronic equipment and storage medium | |
| CN113139589B (en) | Picture similarity detection method and device, processor and electronic device | |
| CN111784612A (en) | Method and device for eliminating scene object model in game | |
| US10212291B2 (en) | System, method, and non-transitory computer readable storage medium for image recognition based on convolutional neural networks | |
| US9842410B2 (en) | Image compression and decompression with noise separation | |
| WO2020103059A1 (en) | Data processing method and apparatus, electronic device and storage medium | |
| CN114841340B (en) | Identification method and device for depth counterfeiting algorithm, electronic equipment and storage medium | |
| CN114756714A (en) | Graph data processing method and device and storage medium | |
| CN112791387A (en) | Data processing method, device and medium based on mouse and keyboard | |
| CN111163123A (en) | Service request processing method and device | |
| CN112631781A (en) | Operator execution method and device, electronic equipment and storage medium | |
| CN112632054A (en) | Data set duplication removing method based on attribute encryption, storage medium and system | |
| CN112054805A (en) | Model data compression method, system and related equipment | |
| CN105468603A (en) | Data selection method and apparatus | |
| CN116994002B (en) | Image feature extraction method, device, equipment and storage medium | |
| CN112891926B (en) | Game terminal, cloud server, cloud game control method, and storage medium |
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 |