CN113656622B - Background picture screening method and device - Google Patents
Background picture screening method and device Download PDFInfo
- Publication number
- CN113656622B CN113656622B CN202110936508.2A CN202110936508A CN113656622B CN 113656622 B CN113656622 B CN 113656622B CN 202110936508 A CN202110936508 A CN 202110936508A CN 113656622 B CN113656622 B CN 113656622B
- Authority
- CN
- China
- Prior art keywords
- picture
- color
- pictures
- screening
- attribute
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
- G06F16/532—Query formulation, e.g. graphical querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5838—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Image Analysis (AREA)
Abstract
The application relates to a method and a device for screening background pictures. The method comprises the following steps: obtaining screening conditions; screening pictures according to the screening conditions to obtain a picture set meeting the screening conditions; ordering the pictures in the picture set according to a preset ordering rule; and evaluating the picture according to a preset evaluation rule, and obtaining the background picture according to an evaluation result. According to the method and the device, the picture retrieval results are intelligently sequenced and evaluated, and the background picture is obtained according to the evaluation result, so that the user can more quickly obtain the background picture which meets the screening condition and is suitable for being used as the background, the labor cost and time are greatly saved, the requirement on the professional ability of the user is lower, and the universality is higher.
Description
Technical Field
The present application relates generally to the field of computer technology. More specifically, the present application relates to a method and an apparatus for screening background pictures.
Background
The picture processing technology is widely applied to various scenes, such as various posters, commodity publicity pages, PPT background pictures and the like. In some scenarios, the background picture needs to be designed or modified according to application scenarios, themes, styles, preferences, and the like.
In the prior art, designers usually design or modify corresponding background pictures according to different requirements, so that the requirements on the capabilities of the designers are high, and common users do not have picture processing capability and often obtain required background pictures through network retrieval. For example, with the Baidu picture search function, background picture search is performed by inputting keywords, the obtained picture data volume is large, manual image-by-image and page-by-page screening is required, the efficiency is low, and a user cannot obtain a high-quality background picture because the user does not have professional knowledge.
Based on the technical problems, the application is particularly provided.
Disclosure of Invention
In order to at least partially solve the technical problems mentioned in the background art, the present disclosure provides a method and an apparatus for screening background pictures.
According to a first aspect of the present application, there is provided a method for screening background pictures, wherein the method includes: obtaining screening conditions; screening pictures according to the screening conditions to obtain a picture set meeting the screening conditions; ordering the pictures in the picture set according to a preset ordering rule; and evaluating the picture according to a preset evaluation rule, and obtaining the background picture according to an evaluation result.
Optionally, the screening condition includes one or more of file information, an attribute tag, and a color tag. Wherein, the file information can be freely input by an operator according to actual needs; the attribute labels and the color labels can be freely selected by an operator according to actual needs.
Optionally, in a case that the screening condition includes the document information, the screening the pictures according to the screening condition to obtain the picture set meeting the screening condition includes: extracting attribute keywords and/or color keywords in the file information; under the condition that the attribute keywords are extracted, comparing the attribute keywords with attribute identifications of all pictures in the gallery; screening pictures with attribute identifications identical or similar to the attribute keywords to obtain a picture set conforming to the attribute keywords; under the condition that the color key words are extracted, comparing the color key words with color marks of all pictures in the gallery; and screening pictures with color identifications identical or similar to the color keywords to obtain a picture set conforming to the color keywords.
Optionally, in the case of extracting the color keyword, the sorting the pictures in the picture set according to a preset sorting rule includes: acquiring the color with the largest pixel area in each picture in the picture set; and comparing the color with the largest pixel area in each acquired picture with the color key words, and sequencing the colors from near to far according to the distance between the color key words and the color key words in the color space.
Optionally, in a case that the screening condition includes an attribute tag, the screening pictures according to the screening condition to obtain a picture set that satisfies the screening condition includes: comparing the attribute label with the attribute identifications of all pictures in the gallery; and screening the pictures with the attribute identifications being the same as or similar to the attribute labels, namely obtaining the picture set conforming to the attribute labels.
Optionally, in a case that the screening condition includes a color tag, the screening pictures according to the screening condition, and obtaining a picture set that satisfies the screening condition includes: comparing the color label with the color marks of all pictures in the picture library; and screening pictures with color identifications identical or similar to the color labels to obtain a picture set conforming to the color labels.
Optionally, when the screening condition includes a color tag, the sorting the pictures in the picture set according to a preset sorting rule includes: acquiring the color with the largest pixel area in each picture in the picture set; and comparing the color with the largest pixel area in each acquired picture with the color label, and sequencing the colors from near to far according to the distance between the colors and the label in the color space.
Optionally, the evaluating the picture according to a preset evaluation rule, and obtaining the background picture according to an evaluation result includes: and evaluating the area ratio and/or the color distribution of the maximum available area of the picture, and obtaining the background picture according to the evaluation result.
Optionally, the method for obtaining the maximum available area includes: identifying a main body in the picture and marking an area where the main body is located according to a preset rule; and obtaining a connected domain with the largest area by a connected domain analysis method, namely obtaining the largest available area.
According to a second aspect of the present application, there is provided a device for screening background pictures, wherein the device includes: the acquisition module is used for acquiring screening conditions; the screening module is used for screening pictures according to the screening conditions to obtain a picture set meeting the screening conditions; the sorting module is used for sorting the pictures in the picture set according to a preset sorting rule; and the evaluation module is used for evaluating the picture according to a preset evaluation rule and obtaining the background picture according to an evaluation result.
Optionally, the obtaining module is configured to obtain the following screening conditions: one or more of file information, attribute labels, color labels.
Optionally, when the screening condition includes the document information, the screening module is configured to screen the pictures in the following manner to obtain a picture set that satisfies the screening condition: extracting attribute keywords and/or color keywords in the file information; under the condition that the attribute keywords are extracted, comparing the attribute keywords with attribute identifications of all pictures in a gallery; screening pictures with attribute identifications identical or similar to the attribute keywords to obtain a picture set conforming to the attribute keywords; under the condition that the color key words are extracted, comparing the color key words with color marks of all pictures in the gallery; and screening pictures with color identifications identical or similar to the color keywords to obtain a picture set conforming to the color keywords.
Optionally, in the case of extracting the color keyword, the ranking module is configured to rank the pictures in the picture set in the following manner: acquiring the color with the largest pixel area in each picture in the picture set; and comparing the color with the largest pixel area in each acquired picture with the color key words, and sequencing the colors from near to far according to the distance between the color key words and the color key words in the color space.
Optionally, when the screening condition includes an attribute tag, the screening module is configured to screen an image in the following manner to obtain an image set that meets the screening condition: comparing the attribute label with the attribute identifications of all pictures in the gallery; and screening the pictures with the attribute identifications being the same as or similar to the attribute labels to obtain a picture set conforming to the attribute labels.
Optionally, in a case that the screening condition includes a color tag, the screening module is configured to screen the pictures in the following manner to obtain a picture set that meets the screening condition: comparing the color label with the color marks of all pictures in the picture library; and screening the pictures with the color identifications identical or similar to the color labels to obtain a picture set conforming to the color labels.
Optionally, in a case that the filtering condition includes a color label, the sorting module is configured to sort the pictures in the picture set in the following manner: acquiring the color with the largest pixel area in each picture in the picture set; and comparing the color with the largest pixel area in each acquired picture with the color label, and sequencing the colors from near to far according to the distance between the colors and the label in the color space.
Optionally, the evaluation module is configured to evaluate the picture in the following manner, and obtain the background picture according to an evaluation result: and evaluating the area ratio and/or the color distribution of the maximum available area of the picture, and obtaining the background picture according to the evaluation result.
Optionally, the evaluation module obtains the maximum available area by: identifying a main body of the picture and marking an area where the main body is located according to a preset rule; and obtaining the connected domain with the largest area through connected domain analysis, namely obtaining the largest available area.
According to a third aspect of the present application, an electronic apparatus is provided, where the apparatus includes a memory and a processor, where the memory stores a computer program, and the processor executes the computer program to implement the method for filtering background pictures described above.
According to a sixth aspect of the present application, there is provided a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed, the method for filtering background pictures is implemented.
According to the background picture screening method and device, the picture retrieval results are intelligently sequenced and evaluated, and the background picture is obtained according to the evaluation result, so that a user can more quickly obtain the background picture which meets the screening conditions and is suitable for being used as the background, the labor cost and time are greatly saved, the requirement on the professional ability of the user is low, and the universality is higher.
Drawings
The above and other objects, features and advantages of exemplary embodiments of the present application will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. In the drawings, which illustrate several embodiments of the present application by way of example and not by way of limitation, and in which like reference numerals designate like or corresponding parts throughout the several views:
fig. 1 is a flowchart illustrating a background picture screening method according to an embodiment of the present application;
fig. 2 is a schematic block diagram illustrating a background picture screening apparatus according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Specific embodiments of the present application are described in detail below with reference to the accompanying drawings.
In one embodiment of the present application, a method for screening background pictures is provided, as shown in fig. 1, the method includes the following steps S101 to S104. Step S101: obtaining screening conditions; step S102: screening pictures according to the screening conditions to obtain a picture set meeting the screening conditions; step S103: ordering the pictures in the picture set according to a preset ordering rule; step S104: and evaluating the picture according to a preset evaluation rule, and obtaining the background picture according to an evaluation result.
According to the method and the device, the picture retrieval results are intelligently sequenced and evaluated, and the background picture is obtained according to the evaluation result, so that the user can more quickly obtain the background picture which meets the screening condition and is suitable for being used as the background, the labor cost and time are greatly saved, the requirement on the professional ability of the user is lower, and the universality is higher.
In step S101, a screening condition is acquired.
According to the embodiment of the application, in order to perform the screening of the background picture, firstly, the screening condition should be obtained. The screening condition preferably includes one or more of the document information, the attribute tag and the color tag, wherein the document information can be input by an operator according to the scene suitable for the background picture, the theme and/or style of the background picture, the personal preference of the operator and the like, the document information can be composed of a plurality of sentences or a plurality of words and phrases, and can include words or phrases representing the attribute or the color of the background picture; the attribute labels and the color labels can be set as a plurality of options for an operator to select, and the operator can select the appropriate attribute labels and/or color labels according to actual needs to retrieve and obtain the required background pictures.
In step S102, pictures are screened according to the screening condition, and a picture set satisfying the screening condition is obtained.
As a preferred embodiment, in the case that the screening condition includes document information, the screening pictures according to the screening condition, and obtaining a picture set that satisfies the screening condition includes: extracting attribute keywords and/or color keywords in the file information; under the condition that the attribute keywords are extracted, comparing the attribute keywords with attribute identifications of all pictures in the gallery; screening pictures with attribute identifications identical or similar to the attribute keywords to obtain a picture set conforming to the attribute keywords; under the condition that the color key words are extracted, comparing the color key words with color marks of all pictures in the gallery; and screening pictures with color identifications identical or similar to the color keywords to obtain a picture set conforming to the color keywords. The attribute keywords and/or color keywords extracted from the document information may be extracted by any keyword extraction method in the prior art, which is not limited herein. In this preferred embodiment, an attribute identifier and a color identifier are preset in each picture in the gallery, where the attribute identifier includes a theme, a style, a main body, and the like of the picture, and may include, for example: beach, sunlight, snow, beauty, fresh, nature, characters, plants, animals, etc.; the color identification comprises 3-5 main colors contained in the picture.
Under the condition that the screening condition comprises the attribute tag, screening the pictures according to the screening condition, and obtaining the picture set meeting the screening condition comprises the following steps: comparing the attribute label with the attribute identifications of all pictures in the gallery; and screening the pictures with the attribute identifications being the same as or similar to the attribute labels, namely obtaining the picture set conforming to the attribute labels.
Under the condition that the screening condition comprises a color label, screening pictures according to the screening condition, and obtaining a picture set meeting the screening condition comprises the following steps: comparing the color label with the color marks of all pictures in the picture library; and screening pictures with color identifications identical or similar to the color labels to obtain a picture set conforming to the color keywords.
As will be understood by those skilled in the art, in the present application, the filtering condition may include one or more of the document information, the attribute tag, and the color tag, and the logical relationship between the filtering conditions may be selected or set according to actual needs, for example, the logical relationship may be set as an "and" relationship between the keywords extracted from the document information, and an "or" relationship between the document information and the attribute tag and/or the color tag, and may also be selected or input by an operator.
In step S103, the pictures in the picture set are sorted according to a preset sorting rule. The preset sorting rule can be set according to actual needs and can be selected by an operator.
As a preferred embodiment, in the case of extracting a color keyword from the document information, the sorting the pictures in the picture set according to a preset sorting rule includes: acquiring the color with the largest pixel area in each picture in the picture set; and comparing the color with the largest pixel area in each acquired picture with the color key words, and sequencing the colors from near to far according to the distance between the color key words and the color key words in the color space.
The sorting method of this preferred embodiment is also applicable to the case that the filtering condition includes a color tag, that is, in the case that the filtering condition includes a color tag, the sorting the pictures in the picture set according to the preset sorting rule includes: acquiring the color with the largest pixel area in each picture in the picture set; and comparing the color with the largest pixel area in each acquired picture with the color label, and sequencing the colors from near to far according to the distance between the color label and the color label in the color space.
For the case that the attribute keywords are extracted from the document information and/or the screening conditions include the attribute tags, the method for sorting the pictures in the picture set may adopt any method for sorting the search results obtained by searching through the keywords in the prior art, for example: and sorting according to the correlation between the attribute identification of the picture and the attribute keyword and/or the attribute tag, or sorting according to the update time of the picture, or sorting according to the downloading times of the picture, and the like.
In step S104, the picture is evaluated according to a preset evaluation rule, and the background picture is obtained according to an evaluation result. The evaluation rule can be set according to actual needs, and the pictures which are not suitable for being used as the background are removed and then are sequenced and moved backwards according to the evaluation result, so that the user can more quickly obtain the needed background pictures.
As a preferred embodiment, the evaluating the picture according to a preset evaluation rule and obtaining the background picture according to an evaluation result includes: and evaluating the area ratio and/or the color distribution of the maximum available area of the picture, and obtaining the background picture according to the evaluation result. The method for obtaining the maximum available area comprises the following steps: identifying a main body of the picture and marking an area where the main body is located according to a preset rule; and obtaining a connected domain with the largest area through a connected domain analysis method, namely obtaining the largest available region.
Specifically, the method for recognizing the main body in the picture by adopting a preset algorithm comprises the following steps: humans, animals, goods, buildings, logos, titles, etc., and marking the subject outline; expanding 10% -30% outwards from the outline of the main body according to the maximum edge feathering radius, and marking the area where the main body is located in a frame selection mode by taking the outermost edge after expansion as a reference; analyzing the maximum coherent area in the residual available space outside the area where the main body is located by a connected domain analysis method, namely obtaining a maximum available area; calculating the area proportion of the maximum available area in the picture, and if the area proportion is less than 40%, considering that the blank leaving rate of the picture is too low and the picture is used as a background picture and has fewer editable areas; evaluating the color distribution of the maximum available area by adopting a preset algorithm, and if the colors are more and the distribution is not uniform, considering that the maximum available area is too flower and has poor visual effect as a background picture; and removing the pictures with too low white leaving rate and/or too flower pictures or sorting the pictures backwards according to the evaluation result to obtain the required background pictures.
It should be noted that the subject resolution algorithm, the connected domain analysis method, the color distribution algorithm, and the like can be implemented by using the prior art, and are not described herein again. In addition, one of the two conditions of "area ratio of the maximum usable region" and "color distribution of the maximum usable region" may be selected for evaluation, or both of the two conditions may be evaluated; in the case where both conditions are evaluated, the evaluation order of both conditions may be interchanged, and is not particularly limited.
In another embodiment of the present application, a device for screening background pictures is provided. The apparatus is configured to perform the steps in the embodiment of the background picture screening method described above with reference to fig. 1.
As shown in fig. 2, the apparatus 100 includes an obtaining module 101, a screening module 102, a sorting module 103, and an evaluating module 104, where the obtaining module 101 is configured to obtain a screening condition; the screening module 102 is configured to screen pictures according to the screening conditions to obtain a picture set meeting the screening conditions; the sorting module 103 is configured to sort the pictures in the picture set according to a preset sorting rule; the evaluation module 104 is configured to evaluate the picture according to a preset evaluation rule, and obtain the background picture according to an evaluation result.
As a preferred embodiment, the obtaining module 101 is configured to obtain the following screening conditions: one or more of file information, attribute labels, color labels.
Under the condition that the screening condition includes the document information, the screening module 102 is configured to screen the pictures in the following manner to obtain a picture set that satisfies the screening condition: extracting attribute keywords and/or color keywords in the file information; under the condition that the attribute keywords are extracted, comparing the attribute keywords with attribute identifications of all pictures in the gallery; screening pictures with attribute identifications identical or similar to the attribute keywords to obtain a picture set conforming to the attribute keywords; under the condition that the color key words are extracted, comparing the color key words with color marks of all pictures in the gallery; screening pictures with color identifications identical or similar to the color keywords to obtain a picture set conforming to the color keywords; under the condition that the screening condition includes the attribute tag, the screening module 102 is configured to screen the pictures in the following manner to obtain a picture set that satisfies the screening condition: comparing the attribute label with the attribute identifications of all pictures in the gallery; screening pictures with attribute identifications identical or similar to the attribute labels to obtain a picture set conforming to the attribute labels; in a case that the filtering condition includes a color tag, the filtering module 102 is configured to filter pictures in the following manner to obtain a picture set that satisfies the filtering condition: comparing the color label with the color marks of all pictures in the picture library; and screening pictures with color identifications identical or similar to the color labels to obtain a picture set conforming to the color keywords.
In the case of extracting color keywords from the document information, the ranking module 103 is configured to rank the pictures in the picture set as follows: acquiring the color with the largest pixel area in each picture in the picture set; comparing the color with the largest pixel area in each acquired picture with the color key words, and sequencing the colors from near to far according to the distance between the colors and the color key words in a color space; in a case that the filtering condition includes a color label, the sorting module 103 is configured to sort the pictures in the picture set as follows: acquiring the color with the largest pixel area in each picture in the picture set; and comparing the color with the largest pixel area in each acquired picture with the color label, and sequencing the colors from near to far according to the distance between the color label and the color label in the color space.
The evaluation module 104 is configured to evaluate the picture in the following manner, and obtain the background picture according to an evaluation result: and evaluating the area ratio and/or the color distribution of the maximum available area of the picture, and obtaining the background picture according to an evaluation result.
It is to be understood that, regarding the background picture screening apparatus in the embodiment described above with reference to fig. 2, the specific manner in which each module performs the operation has been described in detail in the embodiment of the background picture screening method described in conjunction with fig. 1, and will not be elaborated herein.
In another embodiment of the present application, an electronic apparatus is further provided, where the apparatus includes a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the following steps: obtaining screening conditions; screening pictures according to the screening conditions to obtain a picture set meeting the screening conditions; ordering the pictures in the picture set according to a preset ordering rule; and evaluating the picture according to a preset evaluation rule, and obtaining the background picture according to an evaluation result.
It is understood that the steps implemented when the processor executes the computer program are substantially the same as the implementation of the steps in the above method, and the specific manner has been described in detail in the embodiments of the method for filtering background pictures, and will not be described in detail here.
In another embodiment of the present application, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and when the computer program is executed, the computer program implements the following steps: obtaining screening conditions; screening pictures according to the screening conditions to obtain a picture set meeting the screening conditions; ordering the pictures in the picture set according to a preset ordering rule; and evaluating the picture according to a preset evaluation rule, and obtaining the background picture according to an evaluation result.
It is understood that the steps implemented when the processor executes the computer program are substantially the same as the implementation of the steps in the above method, and the specific manner has been described in detail in the embodiments of the method for filtering background pictures, and will not be described in detail here.
The foregoing detailed description of the embodiments of the present application has been presented to illustrate the principles and implementations of the present application, and the above description of the embodiments is only provided to help understand the method and the core concept of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
It should be understood that the terms "first" and "second," etc. in the claims, description, and drawings of the present application are used for distinguishing between different objects and not for describing a particular order. The terms "comprises" and "comprising," when used in the specification and claims of this application, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only, and is not intended to be limiting of the application. As used in the specification and claims of this application, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should be further understood that the term "and/or" as used in the specification and claims of this application refers to any and all possible combinations of one or more of the associated listed items and includes such combinations.
Claims (12)
1. A screening method of background pictures, wherein the method comprises the following steps:
obtaining screening conditions;
screening pictures according to the screening conditions to obtain a picture set meeting the screening conditions;
ordering the pictures in the picture set according to a preset ordering rule;
evaluating the picture according to a preset evaluation rule, and obtaining the background picture according to an evaluation result;
evaluating the picture according to a preset evaluation rule, and obtaining the background picture according to an evaluation result comprises the following steps:
identifying a main body in the picture by adopting a main body distinguishing algorithm, and marking the outline of the main body; marking the area where the main body is located in a frame selection mode; analyzing the maximum coherent area in the residual available space outside the area where the main body is located by a connected domain analysis method, namely obtaining a maximum available area; obtaining the white residue rate; evaluating the color distribution of the maximum available area by adopting a color distribution algorithm, and if the colors are more and the distribution is not uniform, considering that the maximum available area is too flower and has poor visual effect as a background picture; removing the pictures with too low white leaving rate and/or too flower pictures or sorting the pictures and moving the pictures backwards according to the evaluation result to obtain the required background pictures;
under the condition that the screening condition comprises the file information, screening pictures according to the screening condition, and obtaining a picture set meeting the screening condition comprises the following steps:
extracting attribute keywords and/or color keywords in the file information;
under the condition that the attribute keywords are extracted, comparing the attribute keywords with attribute identifications of all pictures in the gallery; screening pictures with attribute identifications identical or similar to the attribute keywords to obtain a picture set conforming to the attribute keywords;
under the condition that the color key words are extracted, comparing the color key words with color marks of all pictures in the gallery; screening pictures with color identifications identical or similar to the color keywords to obtain a picture set conforming to the color keywords;
presetting an attribute identifier and a color identifier for each picture in the gallery, wherein the attribute identifier comprises the theme, style and main body of the picture, and the color identifier comprises the main color contained in the picture;
wherein, extracting the attribute key words from the file information to sequence the pictures in the picture set comprises the following steps: and sequencing according to the correlation between the attribute identification of the picture and the attribute keyword and/or the attribute tag, or sequencing according to the updating time of the picture, or sequencing according to the downloading times of the picture.
2. The method for screening background pictures according to claim 1, wherein the screening condition comprises one or more of file information, attribute tags and color tags.
3. The method for screening background pictures according to claim 1, wherein, in the case of extracting color keywords, said sorting the pictures in the picture set according to a preset sorting rule comprises:
acquiring the color with the largest pixel area in each picture in the picture set;
and comparing the color with the largest pixel area in each acquired picture with the color key words, and sequencing the colors from near to far according to the distance between the color and the key words in the color space.
4. The method for screening background pictures according to claim 2, wherein in the case that the screening condition includes a color tag, the sorting the pictures in the picture set according to a preset sorting rule includes:
acquiring the color with the largest pixel area in each picture in the picture set;
and comparing the color with the largest pixel area in each acquired picture with the color label, and sequencing the colors from near to far according to the distance between the colors and the label in the color space.
5. The method for screening the background picture according to any one of claims 1 to 4, wherein the evaluating the picture according to a preset evaluation rule and obtaining the background picture according to an evaluation result comprises:
and evaluating the area ratio and/or the color distribution of the maximum available area of the picture, and obtaining the background picture according to an evaluation result.
6. A background picture screening apparatus, wherein the apparatus comprises:
the acquisition module is used for acquiring screening conditions;
the screening module is used for screening pictures according to the screening conditions to obtain a picture set meeting the screening conditions;
the ordering module is used for ordering the pictures in the picture set according to a preset ordering rule;
the evaluation module is used for evaluating the picture according to a preset evaluation rule and obtaining the background picture according to an evaluation result;
evaluating the picture according to a preset evaluation rule, and obtaining the background picture according to an evaluation result comprises the following steps:
adopting a main body distinguishing algorithm to identify a main body in the picture and marking the outline of the main body; marking the area where the main body is located in a frame selection mode; analyzing the maximum coherent area in the residual available space outside the area where the main body is located by a connected domain analysis method, namely obtaining a maximum available area; obtaining the white residue rate; evaluating the color distribution of the maximum available area by adopting a color distribution algorithm, and if the colors are more and the distribution is not uniform, considering that the maximum available area is too flower and has poor visual effect as a background picture; removing the pictures with too low white leaving rate and/or too flower pictures or sorting the pictures and moving the pictures backwards according to the evaluation result to obtain the required background pictures;
and under the condition that the screening conditions comprise the file information, the screening module is used for screening pictures in the following way to obtain a picture set meeting the screening conditions:
extracting attribute keywords and/or color keywords in the file information;
under the condition that the attribute keywords are extracted, comparing the attribute keywords with attribute identifications of all pictures in the gallery; screening pictures with attribute identifications identical or similar to the attribute keywords to obtain a picture set conforming to the attribute keywords;
under the condition that the color key words are extracted, comparing the color key words with color marks of all pictures in the gallery; screening pictures with color identifications identical or similar to the color keywords to obtain a picture set conforming to the color keywords;
presetting an attribute identifier and a color identifier for each picture in the gallery, wherein the attribute identifier comprises the theme, style and main body of the picture, and the color identifier comprises the main color contained in the picture;
extracting attribute keywords from the document information to sort the pictures in the picture set comprises the following steps: and sorting according to the correlation between the attribute identification of the picture and the attribute keyword and/or the attribute tag, or sorting according to the updating time of the picture, or sorting according to the downloading times of the picture.
7. The background picture screening apparatus according to claim 6, wherein the obtaining module is configured to obtain the following screening conditions: one or more of file information, attribute labels, color labels.
8. The device for screening background pictures according to claim 6, wherein in the case of extracting color keywords, the ranking module is configured to rank the pictures in the picture set as follows:
acquiring the color with the largest pixel area in each picture in the picture set;
and comparing the color with the largest pixel area in each acquired picture with the color key words, and sequencing the colors from near to far according to the distance between the color key words and the color key words in the color space.
9. The background picture screening apparatus of claim 7, wherein, in a case that the screening condition includes a color tag, the sorting module is configured to sort the pictures in the picture set in the following manner:
acquiring the color with the largest pixel area in each picture in the picture set;
and comparing the color with the largest pixel area in each acquired picture with the color label, and sequencing the colors from near to far according to the distance between the color label and the color label in the color space.
10. The device for screening background pictures according to any one of claims 6 to 9, wherein the evaluation module is configured to evaluate the picture and obtain the background picture according to the evaluation result as follows:
and evaluating the area ratio and/or the color distribution of the maximum available area of the picture, and obtaining the background picture according to the evaluation result.
11. An electronic device, wherein the device comprises a memory having a computer program stored therein and a processor that, when executing the computer program, implements the method of any of claims 1-5.
12. A computer-readable storage medium, wherein the storage medium stores a computer program which, when executed, implements the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110936508.2A CN113656622B (en) | 2021-08-16 | 2021-08-16 | Background picture screening method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110936508.2A CN113656622B (en) | 2021-08-16 | 2021-08-16 | Background picture screening method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113656622A CN113656622A (en) | 2021-11-16 |
| CN113656622B true CN113656622B (en) | 2022-10-14 |
Family
ID=78479222
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110936508.2A Active CN113656622B (en) | 2021-08-16 | 2021-08-16 | Background picture screening method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113656622B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110866875A (en) * | 2019-10-21 | 2020-03-06 | 稿定（厦门）科技有限公司 | Image texture correction method and device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105850146A (en) * | 2013-12-31 | 2016-08-10 | 宇龙计算机通信科技(深圳)有限公司 | Display method and terminal |
| CN104063522A (en) * | 2014-07-18 | 2014-09-24 | 国家电网公司 | Image retrieval method based on reinforced microstructure and context similarity |
| CN107908630A (en) * | 2017-06-28 | 2018-04-13 | 重庆完美空间科技有限公司 | Material picture color classification retrieving method |
| CN111966850A (en) * | 2020-07-21 | 2020-11-20 | 珠海格力电器股份有限公司 | Picture screening method and device, electronic equipment and storage medium |
| CN112069341A (en) * | 2020-09-04 | 2020-12-11 | 北京字节跳动网络技术有限公司 | Background picture generation and search result display method, device, equipment and medium |
-
2021
- 2021-08-16 CN CN202110936508.2A patent/CN113656622B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110866875A (en) * | 2019-10-21 | 2020-03-06 | 稿定（厦门）科技有限公司 | Image texture correction method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113656622A (en) | 2021-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20240070214A1 (en) | Image searching method and apparatus | |
| US6556710B2 (en) | Image searching techniques | |
| KR101289085B1 (en) | Images searching system based on object and method thereof | |
| US6522782B2 (en) | Image and text searching techniques | |
| US9069795B2 (en) | System and process for building a catalog using visual objects | |
| US8144995B2 (en) | System and method for searching digital images | |
| US20140250110A1 (en) | Image attractiveness based indexing and searching | |
| CN111539440A (en) | Efficient image matching for large image sets | |
| US8379990B2 (en) | Object recognition apparatus, computer readable medium storing object recognition program, and image retrieval service providing method | |
| JP2009251850A (en) | Commodity recommendation system using similar image search | |
| CN105518678A (en) | Searching method, searching apparatus, user device and computer program product | |
| JP2001160057A (en) | Method for hierarchically classifying image and device for classifying and retrieving picture and recording medium with program for executing the method recorded thereon | |
| CN110110147A (en) | A kind of method and device of video frequency searching | |
| CN105793867A (en) | Image searching method and apparatus | |
| KR100876214B1 (en) | Apparatus and method for context aware advertising and computer readable medium processing the method | |
| JP5480008B2 (en) | Summary manga image generation apparatus, program and method for generating manga content summary | |
| JP6838167B2 (en) | Web page main image recognition method and device | |
| CN113656622B (en) | Background picture screening method and device | |
| CN111079777A (en) | Page positioning-based point reading method and electronic equipment | |
| US11010978B2 (en) | Method and system for generating augmented reality interactive content | |
| KR20170039524A (en) | Image search system and method using visual part vocabulary | |
| JP2006313497A (en) | Apparatus and method for retrieving image | |
| CN113569077A (en) | Method, device and equipment for recommending clothes | |
| CN111858994A (en) | Character retrieval method and device | |
| KR100754157B1 (en) | Database building method for multimedia contents |
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 |