CN108399052B - Picture compression method and device, computer equipment and storage medium - Google Patents
Picture compression method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN108399052B CN108399052B CN201810124554.0A CN201810124554A CN108399052B CN 108399052 B CN108399052 B CN 108399052B CN 201810124554 A CN201810124554 A CN 201810124554A CN 108399052 B CN108399052 B CN 108399052B
- Authority
- CN
- China
- Prior art keywords
- picture
- compression
- compressed
- format
- size
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0608—Saving storage space on storage systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0638—Organizing or formatting or addressing of data
- G06F3/0643—Management of files
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
- Compression Of Band Width Or Redundancy In Fax (AREA)
Abstract
The application relates to a picture compression method, which comprises the following steps: acquiring characteristic parameters of a picture to be compressed; classifying the pictures to be compressed according to the picture sizes in the characteristic parameters to obtain picture types corresponding to the pictures to be compressed; obtaining a compression rule corresponding to the picture type, and determining a compression loss rate and a compression format corresponding to the picture to be compressed according to the characteristic parameters and the compression rule; obtaining a compression processing algorithm corresponding to the compression lossy rate and the compression format; and compressing the picture to be compressed according to the compression processing algorithm. The image compression method improves the compression ratio under the condition of ensuring the subjective quality, thereby saving the occupation of the storage space. In addition, a picture compression device, a computer device and a storage medium are also provided.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for compressing pictures, a computer device, and a storage medium.
Background
The size of App (Application) is the key point for mobile developers to optimize, and pictures in App occupy a large part of resources, so how to control the size occupied by the pictures becomes the key point for solving the problem. The current picture compression only can artificially select a picture compression tool to compress the picture according to the picture format to reduce the occupied size of the picture, which is not only inefficient, but also the selected picture compression tool is probably not optimal, thus resulting in low compression rate and waste of storage space.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a picture compression method, an apparatus, a computer device, and a storage medium, which improve the compression rate and save the storage space while ensuring the subjective quality.
A method of picture compression, the method comprising:
acquiring characteristic parameters of a picture to be compressed;
classifying the pictures to be compressed according to the picture sizes in the characteristic parameters to obtain picture types corresponding to the pictures to be compressed;
obtaining a compression rule corresponding to the picture type, and determining a compression loss rate and a compression format corresponding to the picture to be compressed according to the characteristic parameters and the compression rule;
obtaining a compression processing algorithm corresponding to the compression lossy rate and the compression format;
and compressing the picture to be compressed according to the compression processing algorithm.
In one embodiment, the step of classifying the picture to be compressed according to the picture size in the feature parameters to obtain the picture type corresponding to the picture to be compressed includes: when the picture size is smaller than or equal to a first preset size, determining the picture to be compressed as a first type picture; when the picture size is larger than a first preset size and smaller than a second preset size, determining the picture to be compressed as a second type picture; and when the picture size is larger than or equal to a second preset size, determining the picture to be compressed as a third type picture.
In one embodiment, the characteristic parameters further include a picture size, a color number, and a transparency attribute; the step of obtaining the compression rule corresponding to the picture type and determining the compression lossy rate and the compression format corresponding to the picture to be compressed according to the characteristic parameters and the compression rule comprises the following steps: acquiring a compression rule corresponding to the picture type, wherein the compression rule is associated with the picture size, the color number and the transparency attribute; and determining the compression lossy rate and the compression format corresponding to the picture to be compressed according to the picture size, the color number, the transparent attribute and the compression rule.
In one embodiment, the step of classifying the picture to be compressed according to the picture size in the feature parameters to obtain the picture type corresponding to the picture to be compressed includes: and obtaining a picture format contained in the characteristic parameters, and classifying the picture to be compressed according to the picture format and the picture size to obtain a picture type corresponding to the picture to be compressed.
In one embodiment, the step of obtaining the picture format included in the characteristic parameter, and classifying the picture to be compressed according to the picture format and the picture size to obtain the picture type corresponding to the picture to be compressed includes: determining a main picture type corresponding to the picture format according to the picture format contained in the characteristic parameters, wherein the main picture type contains a plurality of sub-picture types; and matching a sub-picture type corresponding to the picture to be compressed from a plurality of sub-picture types contained in the main picture type according to the picture size.
A picture compression device, the device comprising:
the characteristic parameter acquisition module is used for acquiring the characteristic parameters of the picture to be compressed;
the classification module is used for classifying the picture to be compressed according to the picture size in the characteristic parameters to obtain a picture type corresponding to the picture to be compressed;
the determining module is used for acquiring a compression rule corresponding to the picture type and determining a compression loss rate and a compression format corresponding to the picture to be compressed according to the characteristic parameters and the compression rule;
the algorithm obtaining module is used for obtaining a compression processing algorithm corresponding to the compression lossy rate and the compression format;
and the compression module is used for compressing the picture to be compressed according to the compression processing algorithm.
In one embodiment, the classification module is further configured to determine the picture to be compressed as a first type picture when the picture size is smaller than or equal to a first preset size; when the picture size is larger than a first preset size and smaller than a second preset size, determining the picture to be compressed as a second type picture; and when the picture size is larger than or equal to a second preset size, determining the picture to be compressed as a third type picture.
In one embodiment, the characteristic parameters further include a picture size, a color number, and a transparency attribute; the determining module is further configured to obtain a compression rule corresponding to the picture type, where the compression rule is associated with the picture size, the color number, and the transparency attribute; and determining the compression lossy rate and the compression format corresponding to the picture to be compressed according to the picture size, the color number, the transparent attribute and the compression rule.
In one embodiment, the classification module is further configured to acquire a picture format included in the feature parameters, and classify the picture to be compressed according to the picture format and the picture size to obtain a picture type corresponding to the picture to be compressed.
In one embodiment, the classification module is further configured to determine, according to a picture format included in the feature parameters, a main picture type corresponding to the picture format, where the main picture type includes a plurality of sub-picture types; and matching a sub-picture type corresponding to the picture to be compressed from a plurality of sub-picture types contained in the main picture type according to the picture size.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the above picture compression method when executing the computer program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, implements the above-mentioned picture compression method.
According to the picture compression method, the device, the computer equipment and the storage medium, the characteristic parameters of the picture to be compressed are obtained, then the picture to be compressed is classified according to the picture size in the characteristic parameters, the picture type corresponding to the picture to be compressed is obtained, then the compression rule corresponding to the picture type is obtained, the compression lossy rate and the compression format corresponding to the picture to be compressed are determined according to the characteristic parameters and the compression rule, then the compression processing algorithm corresponding to the compression lossy rate and the compression format is obtained, and the picture is compressed according to the compression processing algorithm. The picture compression method comprises the steps of classifying pictures, setting compression rules of each picture type, and matching the optimal compression loss rate and compression format through characteristic parameters and the compression rules. In the process, the optimal compression lossy rate and compression format are automatically determined according to the characteristic parameters of the picture, so that the compression rate of the picture is improved on the premise of ensuring the subjective quality, and the occupation of storage space is saved.
A method of picture compression, the method comprising:
acquiring a picture to be compressed, and extracting characteristic parameters of the picture to be compressed, wherein the characteristic parameters comprise a picture format, a picture size, a color number and a transparency attribute;
combining the characteristic parameters into a characteristic vector, taking the characteristic vector as the input of a trained picture classification model, and acquiring the compression lossy rate and the compression format corresponding to the output picture to be compressed;
obtaining a compression processing algorithm corresponding to the compression lossy rate and the compression format;
and compressing the picture to be compressed according to the compression processing algorithm.
In one embodiment, the method further comprises: acquiring a training sample picture, and extracting training characteristic parameters of the training sample picture to form a training characteristic vector; acquiring a compression lossy rate and a compression format label corresponding to the training sample picture; and taking the training feature vector as the input of the picture classification model, taking the corresponding compression lossy rate and the marks of the compression format as the expected output of the picture classification model, and training the picture classification model to obtain a target picture classification model.
A picture compression device, the device comprising:
the extraction module is used for acquiring a picture to be compressed and extracting characteristic parameters of the picture to be compressed, wherein the characteristic parameters comprise a picture format, a picture size, a color number and a transparency attribute;
the output module is used for combining the characteristic parameters into a characteristic vector, using the characteristic vector as the input of a trained picture classification model and acquiring the compression lossy rate and the compression format corresponding to the output picture to be compressed;
a compression algorithm obtaining module, configured to obtain a compression processing algorithm corresponding to the compression lossy rate and the compression format;
and the compression processing module is used for compressing the picture to be compressed according to the compression processing algorithm.
In one embodiment, the picture compression apparatus further includes: a model establishing module 701, configured to obtain a training sample picture, extract training feature parameters of the training sample picture, and form a training feature vector; acquiring a compression lossy rate and a compression format label corresponding to the training sample picture; and taking the training feature vector as the input of the picture classification model, taking the corresponding compression lossy rate and the marks of the compression format as the expected output of the picture classification model, and training the picture classification model to obtain a target picture classification model.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the above picture compression method when executing the computer program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, implements the above-mentioned picture compression method.
According to the picture compression method, the picture compression device, the computer equipment and the storage medium, the characteristic parameters of the picture to be compressed are extracted, and the characteristic parameters comprise a picture format, a picture size, a color number and a transparency attribute. And then combining the characteristic parameters into a characteristic vector, using the characteristic vector as the input of a trained image classification model, then obtaining the compression lossy rate and the compression format corresponding to the output image to be compressed, then obtaining a compression processing algorithm corresponding to the compression lossy rate and the compression format, and compressing the image to be compressed according to the compression processing algorithm. In the process, the feature vector consisting of the feature parameters is used as the input of the trained picture classification model, so that the optimal compression lossy rate and compression format can be obtained, the compression rate of the picture is improved on the premise of ensuring the subjective quality, and the occupation of the storage space is saved.
Drawings
FIG. 1 is a diagram of an exemplary embodiment of a method for compressing pictures;
FIG. 2 is a flow diagram of a method for picture compression in one embodiment;
FIG. 3 is a flowchart of a method for determining a compression lossy rate and a compression format corresponding to a picture to be compressed according to an embodiment;
FIG. 4 is a flowchart of a method for compressing pictures in another embodiment;
FIG. 5 is a flow diagram of a method for creating a picture classification model in one embodiment;
FIG. 6 is a block diagram showing the structure of a picture compression apparatus according to an embodiment;
FIG. 7 is a block diagram showing the construction of a picture compression apparatus according to another embodiment;
FIG. 8 is a block diagram showing the construction of a picture compression apparatus according to still another embodiment;
FIG. 9 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The picture compression method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers. Firstly, a terminal 102 acquires a picture to be compressed, the picture to be compressed is uploaded to a server 104, the server 104 acquires a characteristic parameter of the picture to be compressed, the picture to be compressed is classified according to the picture size in the characteristic parameter to obtain a picture type corresponding to the picture to be compressed, a compression rule corresponding to the picture type is acquired, a compression lossy rate and a compression format corresponding to the picture to be compressed are determined according to the characteristic parameter and the compression rule, a compression processing algorithm corresponding to the compression lossy rate and the compression format is acquired, and the picture to be compressed is compressed according to the compression processing algorithm. The compression rule integrates the optimal compression relation between the characteristic parameters and the compression lossy rate and the compression format.
In one embodiment, as shown in fig. 2, a method for compressing a picture is provided, which is exemplified by the method applied to the server 104 in fig. 1, and includes the following steps:
The feature parameter is a parameter indicating a feature of a picture. The characteristic parameters include one or more of picture size, color number, transparency attribute, and the like. The picture size refers to the product of the length and width of a picture, and the length and width of the picture size are expressed in units of pixels, i.e., in picture resolution, for example, 640X480 pictures. The picture size refers to the size of the storage space occupied by the picture, for example, 1 KB. The color number refers to the number of colors contained in all pixel points contained in the picture, each pixel point is represented by a group of numerical values, all the pixel points in the picture are traversed, the group of numerical values are completely the same, the same color is represented, the same color is classified into one color, if the group of numerical values are different, the different colors are represented, and the color value is increased by one, so that the number of the colors contained in the picture is obtained. The transparent attribute refers to whether transparent pixel points exist in the picture or not, if the transparent pixel points exist in the picture, the picture is a semitransparent picture, and if the transparent pixel points do not exist, the picture is completely opaque.
And 204, classifying the picture to be compressed according to the picture size in the characteristic parameters to obtain the picture type corresponding to the picture to be compressed.
The pictures are classified in advance according to the picture sizes, for example, the pictures can be divided into small pictures, medium pictures and large pictures according to the picture sizes. The small graph is a graph represented by an icon. The middle image is a diagram represented by a screenshot, and the large image is a diagram represented by a high-definition picture. In one embodiment, the corresponding relation between the picture size and the picture type is stored in advance, the picture size of the picture to be compressed is obtained, and the picture type corresponding to the picture to be compressed is determined according to the picture size.
And step 206, acquiring a compression rule corresponding to the picture type, and determining a compression loss rate and a compression format corresponding to the picture to be compressed according to the characteristic parameters and the compression rule.
Here, the compression loss rate is used to indicate a mass loss before and after compression. The compression loss ratio is the ratio of the mass after compression loss to the mass before compression. For example, 80% of the lossy compression is selected, representing a loss of 20% of the mass. The compression loss rate is inversely proportional to the compression ratio, i.e. the smaller the compression loss rate, the greater the mass loss, and the higher the corresponding compression ratio. If the compression is lossless, the corresponding compression has a loss rate of 100%, i.e. no loss. The compression format refers to a format type adopted by compression, such as an SVG format, a JPEG format and the like. Different picture types correspond to different compression rules. The compression rule refers to a preset rule related to the characteristic parameter. And calculating to obtain the compression loss rate and the compression format corresponding to the characteristic parameters by taking the characteristic parameters as variables in the compression rule.
And step 208, acquiring a compression processing algorithm corresponding to the compression lossy rate and the compression format.
Wherein, different compression lossy rates and compression formats correspond to different compression processing algorithms. And pre-establishing a corresponding relation between the compression lossy rate and the compression format and the compression processing algorithm. The compression processing algorithm refers to a preset compression logic rule, and can directly adopt the existing compression processing algorithm aiming at different compression loss rates and compression formats. Namely, intelligently selecting which compression algorithm pair is used to compress the picture to be compressed.
And step 210, compressing the picture to be compressed according to the compression processing algorithm.
The compression processing algorithm is an algorithm for compressing the picture according to a set compression lossy rate and a set compression format. The optimal compression lossy rate and the optimal compression format are intelligently selected for the picture according to the characteristic parameters of the picture, so that the compression rate of the picture is improved on the premise of ensuring the subjective quality, and the occupied space of the picture is reduced.
According to the picture compression method, the characteristic parameters of the picture to be compressed are obtained, then the picture to be compressed is classified according to the picture size in the characteristic parameters, the picture type corresponding to the picture to be compressed is obtained, then the compression rule corresponding to the picture type is obtained, the compression lossy rate and the compression format corresponding to the picture to be compressed are determined according to the characteristic parameters and the compression rule, then the compression processing algorithm corresponding to the compression lossy rate and the compression format is obtained, and the picture is compressed according to the compression processing algorithm. The picture compression method comprises the steps of classifying pictures, setting compression rules corresponding to each picture type, and matching the optimal compression lossy rate and compression format through characteristic parameters and the compression rules. In the process, the optimal compression lossy rate and compression format are automatically determined according to the characteristic parameters of the picture, so that the compression rate of the picture is improved on the premise of ensuring the subjective quality, and the storage space of the picture is saved.
In one embodiment, the step of classifying the picture to be compressed according to the picture size in the characteristic parameters to obtain the picture type corresponding to the picture to be compressed includes: when the picture size is smaller than or equal to a first preset size, determining the picture to be compressed as a first type picture; when the picture size is larger than a first preset size and smaller than a second preset size, determining the picture to be compressed as a second type picture; and when the picture size is larger than or equal to a second preset size, determining the picture to be compressed as a third type picture.
The pictures are divided into three types according to the picture size in advance, wherein the three types are respectively a first type picture, a second type picture and a third type picture. And setting picture size ranges corresponding to each type of pictures, wherein the picture size range corresponding to the first type of pictures is (0, a 1), the picture size range corresponding to the second type of pictures is (a1, a2), and the picture size range corresponding to the third type of pictures is [ a2, + ∞ ]. Wherein a2> a 1. a1 denotes the first preset size, and a2 denotes the second preset size. Specifically, after the picture size of the picture to be compressed is obtained, the picture size range to which the picture belongs is determined according to the size of the picture size, and then the picture type corresponding to the picture is determined.
As shown in fig. 3, in one embodiment, the characteristic parameters further include a picture size, a color number, and a transparency attribute;
the step 206 of obtaining the compression rule corresponding to the picture type and determining the compression lossy rate and the compression format corresponding to the picture to be compressed according to the characteristic parameters and the compression rule includes:
in step 206A, a compression rule corresponding to the picture type is obtained, and the compression rule is associated with the picture size, the color number, and the transparency attribute.
Wherein, the compression rule is related to the picture size, the color number and the transparency attribute. I.e. picture size, number of colors and transparency properties are variables in the compression rules. The compression rules corresponding to different picture types are different, but the picture size, color number and transparency attribute are different, and the obtained compression loss rate and compression format are also different. For example, if two pictures belong to the second type of picture according to the size, and the picture size and the color number of the two pictures belong to the same level, the only difference is that one picture includes transparent pixels, and the other picture does not include transparent pixels, the compression lossy rate and the compression format corresponding to the two pictures are also different, for example, for a picture including transparent pixels, the compression lossy rate corresponding to the picture is 70%, and the corresponding compression format is the JPEG format. For the picture without transparent pixels, the corresponding compression loss rate is 70%, and the corresponding compression format is the WEBP format.
And step 206B, determining the compression loss rate and the compression format corresponding to the picture to be compressed according to the picture size, the color number, the transparent attribute and the compression rule.
The compression rules are predetermined and are associated with the picture characteristic parameters and used for matching compression lossy rate and compression format rules. For each type of picture, a specific compression lossy rate and compression format are obtained by matching the picture size, the number of colors, and the transparency attribute as variables. The compression lossy rate and the compression format are the optimal compression lossy rate and compression format corresponding to the characteristic parameters of the picture, and are rules summarized empirically. When the picture is compressed according to the compression rules, the optimal compression lossy rate and the optimal compression format can be automatically matched according to the extracted picture characteristic parameters, so that the picture compression efficiency is improved, the compression rate can be improved on the premise of ensuring the subjective quality, and the space occupation of the picture is reduced. In this embodiment, as shown in table 1, the picture size, the number of colors, and the compression rules between the transparency attribute and the compression lossy rate and the compression format.
TABLE 1
In one embodiment, the step of classifying the picture to be compressed according to the picture size in the characteristic parameters to obtain the picture type corresponding to the picture to be compressed includes: and acquiring the picture format contained in the characteristic parameters, and classifying the pictures to be compressed according to the picture format and the picture size to obtain the picture type corresponding to the pictures to be compressed.
The characteristic parameters also include a picture format, the picture format refers to a format for storing pictures by a computer, and common storage formats include a JPEG format, a JPG format, a PNG format and the like. Since different picture formats may have different compression rules, in order to more accurately compress pictures, not only the picture size but also the original format of the pictures need to be considered when classifying the pictures, for example, a picture in the original format PNG and a picture in the original format JPG have the same picture size, but the compression rules of the two pictures are different. Therefore, when the pictures are classified, the picture format and the picture size need to be acquired at the same time, and then the pictures to be compressed are classified according to the preset classification standard, wherein the classification is more precise, and the more the picture types are obtained through classification. In one embodiment, there are 36 types obtained by the division.
In one embodiment, the step of obtaining the picture format included in the characteristic parameter, classifying the picture to be compressed according to the picture format and the picture size, and obtaining the picture type corresponding to the picture to be compressed includes: determining a main picture type corresponding to the picture format according to the picture format contained in the characteristic parameters, wherein the main picture type contains a plurality of sub-picture types; and matching the sub-picture type corresponding to the picture to be compressed from a plurality of sub-picture types contained in the main picture type according to the picture size.
In order to more accurately match the picture to be compressed to the optimal compression lossy rate and compression format, the picture is first divided more finely. First, pictures are divided into a plurality of main picture types according to picture formats, i.e., into several major categories. And then sub-divided into a plurality of sub-picture types (i.e., sub-classes) according to the size of the picture size under each main picture type. The optimal compression rule matched for each picture is facilitated to be more accurately set by setting the compression rule corresponding to each sub-picture type, and then the optimal compression loss rate and the optimal compression format are matched.
As shown in fig. 4, in one embodiment, a picture compression method is proposed, which includes:
The characteristic parameters are parameters for representing characteristic attributes of the picture, and include picture format, picture size, number of colors and transparency attributes. The picture size refers to the product of the length and width of a picture, and the length and width of the picture size are expressed in units of pixels, i.e., in picture resolution, for example, 640X480 pictures. The picture size refers to the size of the storage space occupied by the picture, for example, 1 KB. The color number refers to the number of colors contained in all pixel points contained in the picture, each pixel point is represented by a group of numerical values, all the pixel points in the picture are traversed, the group of numerical values are completely the same, the same color is represented, the same color is classified into one color, if the group of numerical values are different, the different colors are represented, and the color value is increased by one, so that the number of the colors contained in the picture is obtained. The transparent attribute refers to whether transparent pixel points exist in the picture or not, if the transparent pixel points exist in the picture, the picture is a semitransparent picture, and if the transparent pixel points do not exist, the picture is completely opaque.
And step 404, combining the feature parameters into a feature vector, using the feature vector as the input of the trained image classification model, and acquiring the compression lossy rate and the compression format corresponding to the output image to be compressed.
Here, the compression loss rate is used to indicate a mass loss before and after compression. The compression loss ratio is the ratio of the mass after compression loss to the mass before compression. For example, 80% of the lossy compression is selected, representing a loss of 20% of the mass. The compression loss rate is inversely proportional to the compression ratio, i.e. the smaller the compression loss rate, the greater the mass loss, and the higher the corresponding compression ratio. If the compression is lossless, the corresponding compression has a loss rate of 100%, i.e. no loss. The compression format refers to a format type adopted by compression, such as an SVG format, a JPEG format and the like. Specifically, the features included in the feature parameters and the corresponding feature values are combined to form a feature vector. For example, feature vectors representing the features of the picture to be compressed are formed by combining the features in the order of (picture format, picture size, number of colors, whether transparent or not). And then, taking the feature vector as the input of the trained image classification model, and then outputting the compression lossy rate and the compression format corresponding to the image to be compressed. The characteristic parameters are used as the learning object of the picture classification model, the relation between the characteristic parameters of the picture and the compression lossy rate and the compression format is obtained through supervised training, and then the learned relation is used for predicting the optimal compression lossy rate and the compression format corresponding to the new picture to be compressed, so that the compression rate is improved on the premise of ensuring the subjective quality, and the storage space is saved.
And 406, acquiring a compression processing algorithm corresponding to the compression lossy rate and the compression format.
Wherein, different compression lossy rates and compression formats correspond to different compression processing algorithms. And pre-establishing a corresponding relation between the compression lossy rate and the compression format and the compression processing algorithm. The compression processing algorithm refers to a preset compression logic rule, and can directly adopt the existing compression processing algorithm aiming at different compression loss rates and compression formats. Namely, intelligently selecting which compression algorithm pair is used to compress the picture to be compressed.
And step 408, compressing the picture to be compressed according to the compression processing algorithm.
The compression processing algorithm is an algorithm for compressing the picture according to a set compression lossy rate and a set compression format. The optimal compression lossy rate and the optimal compression format are intelligently selected for the picture according to the characteristic parameters of the picture, so that the compression lossy rate of the picture is improved on the premise of ensuring the subjective quality, and the occupied space of the picture is reduced.
According to the picture compression method, the characteristic parameters of the picture to be compressed are extracted, and the characteristic parameters comprise a picture format, a picture size, a color number and a transparency attribute. And then combining the characteristic parameters into a characteristic vector, using the characteristic vector as the input of the trained image classification model, then obtaining the compression lossy rate and the compression format corresponding to the output image to be compressed, then obtaining a compression processing algorithm corresponding to the compression lossy rate and the compression format, and compressing the image to be compressed according to the compression processing algorithm. In the process, the feature vector consisting of the feature parameters is used as the input of the trained picture classification model, so that the optimal compression lossy rate and compression format can be obtained, the compression rate of the picture is improved on the premise of ensuring the subjective quality, and the occupation of the storage space is saved.
As shown in fig. 5, in an embodiment, the above-mentioned picture compression method further includes: establishing a picture classification model, wherein the establishing of the picture classification model comprises the following steps:
The method comprises the steps of firstly extracting training characteristic parameters of a training sample picture as in the process of prediction, wherein the training characteristic parameters comprise picture formats, picture sizes, color numbers and transparency attributes. And forming a training feature vector according to the training feature parameters.
The compression lossy rate and the compression format corresponding to the training sample picture are obtained, namely the optimal compression lossy rate and the optimal compression format corresponding to the training sample picture are used as known labels. And the subsequent supervised learning is convenient.
The method comprises the steps of using a training feature vector representing the picture features of a training sample as the input of a picture classification model, using the known optimal compression lossy rate and compression format corresponding to the training sample picture as the expected output, and determining each weight parameter contained in the picture classification model through supervised training so as to obtain a target picture classification model. The training of the image classification model may adopt a linear regression model, may also adopt a decision tree model instead, and may also adopt other machine learning methods for training, for example, a deep neural network model, a cyclic neural network model, and the like.
It should be understood that although the steps in the flowcharts of fig. 2 to 5 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-5 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.
As shown in fig. 6, in one embodiment, a picture compression apparatus is proposed, the apparatus comprising:
a characteristic parameter obtaining module 602, configured to obtain a characteristic parameter of a picture to be compressed.
The classification module 604 is configured to classify the picture to be compressed according to the picture size in the feature parameter, so as to obtain a picture type corresponding to the picture to be compressed.
A determining module 606, configured to obtain a compression rule corresponding to the picture type, and determine a compression lossy rate and a compression format corresponding to the picture to be compressed according to the feature parameter and the compression rule.
An algorithm obtaining module 608, configured to obtain a compression processing algorithm corresponding to the compression lossy rate and the compression format.
And the compression module 610 is configured to perform compression processing on the picture to be compressed according to the compression processing algorithm.
In one embodiment, the classification module 604 is further configured to determine the picture to be compressed as a first type picture when the picture size is smaller than or equal to a first preset size; when the picture size is larger than a first preset size and smaller than a second preset size, determining the picture to be compressed as a second type picture; and when the picture size is larger than or equal to a second preset size, determining the picture to be compressed as a third type picture.
In one embodiment, the characteristic parameters further include a picture size, a color number, and a transparency attribute; the determining module 606 is further configured to obtain a compression rule corresponding to the picture type, where the compression rule is associated with the picture size, the color number, and the transparency attribute; and determining the compression lossy rate and the compression format corresponding to the picture to be compressed according to the picture size, the color number, the transparent attribute and the compression rule.
In an embodiment, the classifying module 604 is further configured to obtain a picture format included in the feature parameter, and classify the picture to be compressed according to the picture format and the picture size to obtain a picture type corresponding to the picture to be compressed.
In one embodiment, the classification module 604 is further configured to determine a main picture type corresponding to a picture format included in the feature parameters, where the main picture type includes a plurality of sub-picture types; and matching a sub-picture type corresponding to the picture to be compressed from a plurality of sub-picture types contained in the main picture type according to the picture size.
As shown in fig. 7, in one embodiment, a picture compression apparatus is proposed, the apparatus comprising:
the extracting module 702 is configured to obtain a picture to be compressed, and extract feature parameters of the picture to be compressed, where the feature parameters include a picture format, a picture size, a color number, and a transparency attribute.
An output module 704, configured to combine the feature parameters into a feature vector, use the feature vector as an input of a trained image classification model, and obtain a compression lossy rate and a compression format corresponding to the output image to be compressed.
A compression algorithm obtaining module 706, configured to obtain a compression processing algorithm corresponding to the compression lossy rate and the compression format.
And a compression processing module 708, configured to perform compression processing on the picture to be compressed according to the compression processing algorithm.
As shown in fig. 8, in an embodiment, the above-mentioned picture compression apparatus further includes:
a model establishing module 701, configured to obtain a training sample picture, extract training feature parameters of the training sample picture, and form a training feature vector; acquiring a compression lossy rate and a compression format label corresponding to the training sample picture; and taking the training feature vector as the input of the picture classification model, taking the corresponding compression lossy rate and the marks of the compression format as the expected output of the picture classification model, and training the picture classification model to obtain a target picture classification model.
For the specific limitation of the picture compression apparatus, reference may be made to the above limitation on the picture compression method, which is not described herein again. The modules in the picture compression apparatus can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal or a server, and its internal structure diagram may be as shown in fig. 9. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a picture compression method.
Those skilled in the art will appreciate that the architecture shown in fig. 9 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program: acquiring characteristic parameters of a picture to be compressed; classifying the pictures to be compressed according to the picture sizes in the characteristic parameters to obtain picture types corresponding to the pictures to be compressed; obtaining a compression rule corresponding to the picture type, and determining a compression loss rate and a compression format corresponding to the picture to be compressed according to the characteristic parameters and the compression rule; obtaining a compression processing algorithm corresponding to the compression lossy rate and the compression format; and compressing the picture to be compressed according to the compression processing algorithm.
In an embodiment, the step of classifying the picture to be compressed according to the picture size in the feature parameters to obtain the picture type corresponding to the picture to be compressed includes: when the picture size is smaller than or equal to a first preset size, determining the picture to be compressed as a first type picture; when the picture size is larger than a first preset size and smaller than a second preset size, determining the picture to be compressed as a second type picture; and when the picture size is larger than or equal to a second preset size, determining the picture to be compressed as a third type picture.
In one embodiment, the characteristic parameters further include a picture size, a color number, and a transparency attribute; the step of obtaining the compression rule corresponding to the picture type and determining the compression lossy rate and the compression format corresponding to the picture to be compressed according to the characteristic parameters and the compression rule comprises the following steps: acquiring a compression rule corresponding to the picture type, wherein the compression rule is associated with the picture size, the color number and the transparency attribute; and determining the compression lossy rate and the compression format corresponding to the picture to be compressed according to the picture size, the color number, the transparent attribute and the compression rule.
In an embodiment, the step of classifying the picture to be compressed according to the picture size in the feature parameters to obtain the picture type corresponding to the picture to be compressed includes: and obtaining a picture format contained in the characteristic parameters, and classifying the picture to be compressed according to the picture format and the picture size to obtain a picture type corresponding to the picture to be compressed.
In one embodiment, the step of obtaining the picture format included in the characteristic parameter, and classifying the picture to be compressed according to the picture format and the picture size to obtain the picture type corresponding to the picture to be compressed includes: determining a main picture type corresponding to the picture format according to the picture format contained in the characteristic parameters, wherein the main picture type contains a plurality of sub-picture types; and matching a sub-picture type corresponding to the picture to be compressed from a plurality of sub-picture types contained in the main picture type according to the picture size.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program: acquiring a picture to be compressed, and extracting characteristic parameters of the picture to be compressed, wherein the characteristic parameters comprise a picture format, a picture size, a color number and a transparency attribute; combining the characteristic parameters into a characteristic vector, taking the characteristic vector as the input of a trained picture classification model, and acquiring the compression lossy rate and the compression format corresponding to the output picture to be compressed; obtaining a compression processing algorithm corresponding to the compression lossy rate and the compression format; and compressing the picture to be compressed according to the compression processing algorithm.
In one embodiment, the processor is further configured to perform the steps of: acquiring a training sample picture, and extracting training characteristic parameters of the training sample picture to form a training characteristic vector; acquiring a compression lossy rate and a compression format label corresponding to the training sample picture; and taking the training feature vector as the input of the picture classification model, taking the corresponding compression lossy rate and the marks of the compression format as the expected output of the picture classification model, and training the picture classification model to obtain a target picture classification model.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: acquiring characteristic parameters of a picture to be compressed; classifying the pictures to be compressed according to the picture sizes in the characteristic parameters to obtain picture types corresponding to the pictures to be compressed; obtaining a compression rule corresponding to the picture type, and determining a compression loss rate and a compression format corresponding to the picture to be compressed according to the characteristic parameters and the compression rule; obtaining a compression processing algorithm corresponding to the compression lossy rate and the compression format; and compressing the picture to be compressed according to the compression processing algorithm.
In an embodiment, the step of classifying the picture to be compressed according to the picture size in the feature parameters to obtain the picture type corresponding to the picture to be compressed includes: when the picture size is smaller than or equal to a first preset size, determining the picture to be compressed as a first type picture; when the picture size is larger than a first preset size and smaller than a second preset size, determining the picture to be compressed as a second type picture; and when the picture size is larger than or equal to a second preset size, determining the picture to be compressed as a third type picture.
In one embodiment, the characteristic parameters further include a picture size, a color number, and a transparency attribute; the step of obtaining the compression rule corresponding to the picture type and determining the compression lossy rate and the compression format corresponding to the picture to be compressed according to the characteristic parameters and the compression rule comprises the following steps: acquiring a compression rule corresponding to the picture type, wherein the compression rule is associated with the picture size, the color number and the transparency attribute; and determining the compression lossy rate and the compression format corresponding to the picture to be compressed according to the picture size, the color number, the transparent attribute and the compression rule.
In an embodiment, the step of classifying the picture to be compressed according to the picture size in the feature parameters to obtain the picture type corresponding to the picture to be compressed includes: and obtaining a picture format contained in the characteristic parameters, and classifying the picture to be compressed according to the picture format and the picture size to obtain a picture type corresponding to the picture to be compressed.
In one embodiment, the step of obtaining the picture format included in the characteristic parameter, and classifying the picture to be compressed according to the picture format and the picture size to obtain the picture type corresponding to the picture to be compressed includes: determining a main picture type corresponding to the picture format according to the picture format contained in the characteristic parameters, wherein the main picture type contains a plurality of sub-picture types; and matching a sub-picture type corresponding to the picture to be compressed from a plurality of sub-picture types contained in the main picture type according to the picture size.
In one embodiment, there is provided a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of: acquiring a picture to be compressed, and extracting characteristic parameters of the picture to be compressed, wherein the characteristic parameters comprise a picture format, a picture size, a color number and a transparency attribute; combining the characteristic parameters into a characteristic vector, taking the characteristic vector as the input of a trained picture classification model, and acquiring the compression lossy rate and the compression format corresponding to the output picture to be compressed; obtaining a compression processing algorithm corresponding to the compression lossy rate and the compression format; and compressing the picture to be compressed according to the compression processing algorithm.
In one embodiment, the processor is further configured to perform the steps of: acquiring a training sample picture, and extracting training characteristic parameters of the training sample picture to form a training characteristic vector; acquiring a compression lossy rate and a compression format label corresponding to the training sample picture; and taking the training feature vector as the input of the picture classification model, taking the corresponding compression lossy rate and the marks of the compression format as the expected output of the picture classification model, and training the picture classification model to obtain a target picture classification model.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of picture compression, the method comprising:
acquiring characteristic parameters of a picture to be compressed;
obtaining a picture format contained in the characteristic parameters, and classifying the picture to be compressed according to the picture format and the picture size to obtain a picture type corresponding to the picture to be compressed;
acquiring a compression rule corresponding to the picture type, wherein the compression rule is associated with the picture size, the color number and the transparent attribute;
determining a compression lossy rate and a compression format corresponding to the picture to be compressed according to the characteristic parameters and the compression rules;
obtaining a compression processing algorithm corresponding to the compression lossy rate and the compression format;
compressing the picture to be compressed according to the compression processing algorithm;
the step of obtaining the picture format contained in the characteristic parameters, classifying the picture to be compressed according to the picture format and the picture size, and obtaining the picture type corresponding to the picture to be compressed comprises the following steps:
determining a main picture type corresponding to the picture format according to the picture format contained in the characteristic parameters, wherein the main picture type contains a plurality of sub-picture types;
and matching a sub-picture type corresponding to the picture to be compressed from a plurality of sub-picture types contained in the main picture type according to the picture size.
2. The method according to claim 1, wherein the step of obtaining the picture format included in the feature parameters, classifying the picture to be compressed according to the picture format and the picture size, and obtaining the picture type corresponding to the picture to be compressed comprises:
when the picture size is smaller than or equal to a first preset size, determining the picture to be compressed as a first type picture;
when the picture size is larger than a first preset size and smaller than a second preset size, determining the picture to be compressed as a second type picture;
and when the picture size is larger than or equal to a second preset size, determining the picture to be compressed as a third type picture.
3. The method of claim 1,
the step of obtaining the compression rule corresponding to the picture type and determining the compression lossy rate and the compression format corresponding to the picture to be compressed according to the characteristic parameters and the compression rule comprises the following steps:
acquiring a compression rule corresponding to the picture type;
and determining the compression lossy rate and the compression format corresponding to the picture to be compressed according to the picture size, the color number, the transparent attribute and the compression rule.
4. A method of picture compression, the method comprising:
acquiring a picture to be compressed, and extracting characteristic parameters of the picture to be compressed, wherein the characteristic parameters comprise a picture format, a picture size, a color number and a transparency attribute;
combining the characteristic parameters into a characteristic vector, taking the characteristic vector as the input of a trained picture classification model, and acquiring the compression lossy rate and the compression format corresponding to the output picture to be compressed;
obtaining a compression processing algorithm corresponding to the compression lossy rate and the compression format;
compressing the picture to be compressed according to the compression processing algorithm; further comprising:
acquiring a training sample picture, and extracting training characteristic parameters of the training sample picture to form a training characteristic vector;
acquiring a compression lossy rate and a compression format label corresponding to the training sample picture;
and taking the training feature vector as the input of the picture classification model, taking the corresponding compression lossy rate and the marks of the compression format as the expected output of the picture classification model, and training the picture classification model to obtain a target picture classification model.
5. A picture compression device, the device comprising:
the characteristic parameter acquisition module is used for acquiring the characteristic parameters of the picture to be compressed;
the classification module is used for acquiring a picture format contained in the characteristic parameters, classifying the picture to be compressed according to the picture format and the picture size, and obtaining a picture type corresponding to the picture to be compressed;
the determining module is used for acquiring a compression rule corresponding to the picture type, and the compression rule is associated with the picture size, the color number and the transparent attribute; determining a compression lossy rate and a compression format corresponding to the picture to be compressed according to the characteristic parameters and the compression rules;
the algorithm obtaining module is used for obtaining a compression processing algorithm corresponding to the compression lossy rate and the compression format;
the compression module is used for compressing the picture to be compressed according to the compression processing algorithm;
the classification module is further configured to determine a main picture type corresponding to the picture format according to the picture format included in the feature parameters, where the main picture type includes a plurality of sub-picture types; and matching a sub-picture type corresponding to the picture to be compressed from a plurality of sub-picture types contained in the main picture type according to the picture size.
6. The apparatus of claim 5,
the classification module is further configured to determine the picture to be compressed as a first type picture when the picture size is smaller than or equal to a first preset size; when the picture size is larger than a first preset size and smaller than a second preset size, determining the picture to be compressed as a second type picture; and when the picture size is larger than or equal to a second preset size, determining the picture to be compressed as a third type picture.
7. The apparatus of claim 5, wherein the characteristic parameters further comprise a picture size, a color number, and a transparency property;
the determining module is further configured to obtain a compression rule corresponding to the picture type; and determining the compression lossy rate and the compression format corresponding to the picture to be compressed according to the picture size, the color number, the transparent attribute and the compression rule.
8. A picture compression device, the device comprising:
the extraction module is used for acquiring a picture to be compressed and extracting characteristic parameters of the picture to be compressed, wherein the characteristic parameters comprise a picture format, a picture size, a color number and a transparency attribute;
the output module is used for combining the characteristic parameters into a characteristic vector, using the characteristic vector as the input of a trained picture classification model and acquiring the compression lossy rate and the compression format corresponding to the output picture to be compressed;
a compression algorithm obtaining module, configured to obtain a compression processing algorithm corresponding to the compression lossy rate and the compression format;
the compression processing module is used for compressing the picture to be compressed according to the compression processing algorithm;
the model establishing module is used for acquiring a training sample picture, extracting training characteristic parameters of the training sample picture and forming a training characteristic vector; acquiring a compression lossy rate and a compression format label corresponding to the training sample picture; and taking the training feature vector as the input of the picture classification model, taking the corresponding compression lossy rate and the marks of the compression format as the expected output of the picture classification model, and training the picture classification model to obtain a target picture classification model.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 4 are implemented when the computer program is executed by the processor.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810124554.0A CN108399052B (en) | 2018-02-07 | 2018-02-07 | Picture compression method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810124554.0A CN108399052B (en) | 2018-02-07 | 2018-02-07 | Picture compression method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108399052A CN108399052A (en) | 2018-08-14 |
| CN108399052B true CN108399052B (en) | 2021-05-14 |
Family
ID=63096090
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810124554.0A Active CN108399052B (en) | 2018-02-07 | 2018-02-07 | Picture compression method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108399052B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109685861B (en) * | 2018-08-31 | 2022-03-15 | 深圳壹账通智能科技有限公司 | Picture compression method, device and equipment and computer readable storage medium |
| CN109685714B (en) * | 2018-08-31 | 2023-06-06 | 深圳壹账通智能科技有限公司 | Picture compression method, device, equipment and computer readable storage medium |
| CN109167919B (en) * | 2018-10-11 | 2020-05-15 | 北京文香信息技术有限公司 | Picture compression method and device |
| CN111260739B (en) * | 2018-11-30 | 2023-07-21 | 中移（杭州）信息技术有限公司 | Picture processing method and device |
| CN109918427A (en) * | 2019-01-16 | 2019-06-21 | 平安普惠企业管理有限公司 | Picture uploads control method, device, computer equipment and storage medium |
| CN110555120B (en) * | 2019-08-14 | 2023-09-08 | 项宇 | Picture compression control method, device, computer equipment and storage medium |
| CN110555816B (en) * | 2019-09-09 | 2021-10-29 | 珠海金山网络游戏科技有限公司 | Picture processing method and device, computing equipment and storage medium |
| CN111009017B (en) * | 2019-10-18 | 2021-08-17 | 珠海格力电器股份有限公司 | Picture compression method and device, storage medium and computer equipment |
| CN111047657A (en) * | 2019-11-26 | 2020-04-21 | 深圳壹账通智能科技有限公司 | Picture compression method, device, medium and electronic equipment |
| CN111558222B (en) * | 2020-04-08 | 2023-11-24 | 完美世界(北京)软件科技发展有限公司 | Method, device and equipment for compressing illumination graph |
| CN113486939A (en) * | 2021-06-30 | 2021-10-08 | 平安证券股份有限公司 | Method, device, terminal and storage medium for processing pictures |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010023397A1 (en) * | 2008-08-28 | 2010-03-04 | Centre National D'etudes Spatiales (Cnes) | Compression of earth observation satellite images |
| CN102957906A (en) * | 2011-08-29 | 2013-03-06 | 广州九游信息技术有限公司 | Method and system for image classifying compression |
| CN103886623A (en) * | 2012-12-19 | 2014-06-25 | 华为技术有限公司 | Image compression method and equipment, and system |
| CN105844588A (en) * | 2016-03-17 | 2016-08-10 | 广州筷子信息科技有限公司 | Method and system for intelligent scalable compression of creative images |
| CN106717006A (en) * | 2014-07-24 | 2017-05-24 | 简·克劳德·科林 | Method for choosing a compression algorithm depending on the image type |
-
2018
- 2018-02-07 CN CN201810124554.0A patent/CN108399052B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010023397A1 (en) * | 2008-08-28 | 2010-03-04 | Centre National D'etudes Spatiales (Cnes) | Compression of earth observation satellite images |
| CN102957906A (en) * | 2011-08-29 | 2013-03-06 | 广州九游信息技术有限公司 | Method and system for image classifying compression |
| CN103886623A (en) * | 2012-12-19 | 2014-06-25 | 华为技术有限公司 | Image compression method and equipment, and system |
| CN106717006A (en) * | 2014-07-24 | 2017-05-24 | 简·克劳德·科林 | Method for choosing a compression algorithm depending on the image type |
| CN105844588A (en) * | 2016-03-17 | 2016-08-10 | 广州筷子信息科技有限公司 | Method and system for intelligent scalable compression of creative images |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108399052A (en) | 2018-08-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108399052B (en) | Picture compression method and device, computer equipment and storage medium | |
| CN109886282B (en) | Object detection method, device, computer-readable storage medium and computer equipment | |
| CN109543627B (en) | Method and device for judging driving behavior category and computer equipment | |
| US20230196837A1 (en) | Action recognition method and apparatus, and device and storage medium | |
| CN110889428A (en) | Image recognition method and device, computer equipment and storage medium | |
| CN111192292A (en) | Target tracking method based on attention mechanism and twin network and related equipment | |
| WO2021135500A1 (en) | Vehicle loss detection model training method and apparatus, vehicle loss detection method and apparatus, and device and medium | |
| WO2022022154A1 (en) | Facial image processing method and apparatus, and device and storage medium | |
| CN110046577B (en) | Pedestrian attribute prediction method, device, computer equipment and storage medium | |
| CN110378230B (en) | Missing face recognition method, device, computer equipment and storage medium | |
| CN110287836B (en) | Image classification method and device, computer equipment and storage medium | |
| CN109325118B (en) | Unbalanced sample data preprocessing method and device and computer equipment | |
| CN110866491A (en) | Target retrieval method, device, computer readable storage medium and computer equipment | |
| CN111145106A (en) | Image enhancement method, device, medium and equipment | |
| WO2022194079A1 (en) | Sky region segmentation method and apparatus, computer device, and storage medium | |
| CN111401524A (en) | Convolutional neural network processing method, device, equipment, storage medium and model | |
| CN110222752B (en) | Image processing method, system, computer device, storage medium and chip | |
| CN112115860A (en) | Face key point positioning method and device, computer equipment and storage medium | |
| CN115687674A (en) | Big data demand analysis method and system serving smart cloud service platform | |
| CN110163151B (en) | Training method and device of face model, computer equipment and storage medium | |
| CN109784379B (en) | Updating method and device of textile picture feature library | |
| CN111445487A (en) | Image segmentation method and device, computer equipment and storage medium | |
| CN112818960A (en) | Waiting time processing method, device, equipment and medium based on face recognition | |
| CN111160240B (en) | Image object recognition processing method and device, intelligent device and storage medium | |
| CN111612732A (en) | Image quality evaluation method, image quality evaluation device, computer equipment 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 |