CN112732968A - Case material image retrieval method, device, equipment and storage medium - Google Patents
Case material image retrieval method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112732968A CN112732968A CN202110040758.8A CN202110040758A CN112732968A CN 112732968 A CN112732968 A CN 112732968A CN 202110040758 A CN202110040758 A CN 202110040758A CN 112732968 A CN112732968 A CN 112732968A
- Authority
- CN
- China
- Prior art keywords
- color
- case material
- label
- enterprise
- material image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
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
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F16/54—Browsing; Visualisation therefor
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a case material image retrieval method, a case material image retrieval device, case material image retrieval equipment and a storage medium. A case material image retrieval method, comprising: receiving related information of a target enterprise input by a user; determining a color label corresponding to the target enterprise according to the relevant information of the target enterprise; determining a case material image corresponding to the color label in a pre-stored case material image database according to the color label; and displaying the case material images. According to the method, before the advertising case is designed and in the case material image retrieval process, a designer can input the relevant information of an enterprise and obtain the case material image with the color corresponding to the relevant information through retrieval. The technical scheme of the invention greatly improves the retrieval efficiency of the designer for designing the advertisement case.
Description
Technical Field
The application relates to the technical field of image processing, in particular to a case material image retrieval method, device, equipment and storage medium.
Background
When designers of an advertisement design company design advertisements, business clients who are served often need to be searched to search out related case material images; and then, the case material image is used for reprocessing and redesigning. In the current image retrieval function, simple retrieval from the internet can be performed only by keywords of an enterprise, and images obtained by retrieval are often irrelevant. The effect of helping designers is limited.
Disclosure of Invention
The present application is directed to a case material image retrieval method, apparatus, device and storage medium, so as to solve the above problems.
In order to achieve the above object, according to one aspect of the present application, there is provided a case material image retrieval method including:
receiving related information of a target enterprise input by a user;
determining a color label corresponding to the target enterprise according to the relevant information of the target enterprise;
determining a case material image corresponding to the color label in a pre-stored case material image database according to the color label;
and displaying the case material images.
In one embodiment, the information about the target enterprise includes the nationality to which the enterprise belongs; determining a color label corresponding to the target enterprise according to the nationality;
the related information of the target enterprise comprises an industry to which the enterprise belongs, and the color label corresponding to the target enterprise is determined according to the industry;
the related information of the target enterprise comprises an enterprise name of the enterprise, and the color label corresponding to the target enterprise is determined according to the enterprise name.
In one embodiment, if the nationality of the enterprise is japan, the type of the corresponding color tag is determined to be a light type;
determining a label of a light type and corresponding case materials;
if the nationality of the enterprise is Europe and America, determining that the type of the corresponding color label is a deep color type;
determining a dark label and corresponding case materials;
if the nationality of the enterprise is China, determining the province of the enterprise;
if the Tibetan is the color label, the color label is blue or white;
if the color is Xinjiang, the corresponding color label is yellow;
if the three provinces are northeast, the corresponding color label is white;
if the color is Hainan island, the color label of the drink is green or blue;
if the industry is the new energy wind power generation industry, the color label is green and/or blue;
if the industry is the animal husbandry industry, the color label is green;
if the industry is the drinking water industry, the color label is white;
if the industry is the medical and pharmaceutical industry, the color labels are red and white;
if the industry is the transportation industry, the color label is blue.
In one embodiment, the method further comprises: generating an image color label comprising:
acquiring a case material image to be identified;
identifying the case material image to be identified to determine the dominant color of the case material image to be identified;
and generating the case material dominant color label.
In one embodiment, identifying the case material images to be identified to determine the dominant color of the case material images to be identified includes:
acquiring the RGB value of each pixel point of the case material image to be identified;
converting the RGB values to HSV values;
clustering calculation is carried out on the HSV value of each pixel point on the case material image by using a clustering algorithm, and the proportion distribution value of each color of the case material image is obtained;
and determining the dominant color of the image according to the ratio distribution value of each color.
In one embodiment, before generating the dominant color label tag, the method further comprises: determining the name of the dominant color label specifically comprises:
acquiring RGB values of the dominant color;
calculating the distance between the RGB value of the dominant color and the RGB value of the standard color;
and if the distance is less than a preset threshold value, determining that the name of the standard color is the label name of the dominant color.
In one embodiment, after displaying the case material images, the method further comprises:
receiving a color proportion range input by a user;
and determining the corresponding case material images according to the color proportion range and the color proportion distribution statistical table of each image.
In order to achieve the above object, according to a second aspect of the present application, there is provided a case material image retrieval apparatus; the device includes:
the receiving module is used for receiving the related information of the target enterprise input by the user;
the image determining module is used for determining a color label corresponding to the target enterprise according to the related information of the target enterprise;
determining a case material image corresponding to the color label in a pre-stored case material image database according to the color label;
and the display module is used for displaying the case material images.
In one embodiment, the image determination module is further configured to determine the related information of the target enterprise includes a nationality to which the enterprise belongs; determining a color label corresponding to the target enterprise according to the nationality;
the related information of the target enterprise comprises the industry to which the enterprise belongs, and the color label corresponding to the target enterprise is determined according to the industry.
If the nationality of the enterprise is Japan, determining the type of the corresponding color label to be a light type;
determining a label of a light type and corresponding case materials;
if the nationality of the enterprise is Europe and America, determining that the type of the corresponding color label is a deep color type;
determining a dark label and corresponding case materials;
if the nationality of the enterprise is China, determining the province of the enterprise;
if the Tibetan is the color label, the color label is blue or white;
if the color is Xinjiang, the corresponding color label is yellow;
if the three provinces are northeast, the corresponding color label is white;
if the color is Hainan island, the color label of the drink is green or blue;
if the industry is the new energy wind power generation industry, the color label is green and/or blue;
if the industry is the animal husbandry industry, the color label is green;
if the industry is the drinking water industry, the color label is white;
if the industry is the medical and pharmaceutical industry, the color labels are red and white;
if the industry is the transportation industry, the color label is blue.
In one embodiment, the system further comprises an image color label generation module, which is specifically used for acquiring a case material image to be identified;
identifying the case material image to be identified to determine the dominant color of the case material image to be identified;
and generating the case material dominant color label.
In one embodiment, the image color label generating module is further configured to obtain an RGB value of each pixel point of the case material image to be identified;
converting the RGB values to HSV values;
clustering calculation is carried out on the HSV value of each pixel point on the case material image by using a clustering algorithm, and the proportion distribution value of each color of the case material image is obtained;
and determining the dominant color of the image according to the ratio distribution value of each color.
In an embodiment, the image color tag generating module is further configured to, before generating the dominant color tag, determine the dominant color tag name, and specifically configured to:
acquiring RGB values of the dominant color;
calculating the distance between the RGB value of the dominant color and the RGB value of the standard color;
and if the distance is less than a preset threshold value, determining that the name of the standard color is the label name of the dominant color.
In one embodiment, the receiving module is further configured to receive a color proportion range input by a user after the case material image is displayed;
the image determining module is also used for determining the corresponding case material images according to the color proportion range and the color proportion distribution statistical table of each image.
In order to achieve the above object, according to a third aspect of the present application, there is provided a case material image retrieval apparatus; comprising at least one processor and at least one memory; the memory is to store one or more program instructions; the processor, configured to execute one or more program instructions, is configured to perform the following steps:
receiving related information of a target enterprise input by a user;
determining a color label corresponding to the target enterprise according to the relevant information of the target enterprise;
determining a case material image corresponding to the color label in a pre-stored case material image database according to the color label;
and displaying the case material images.
In one embodiment, the processor is further configured to determine whether the information related to the target enterprise includes a nationality of the enterprise; determining a color label corresponding to the target enterprise according to the nationality;
the related information of the target enterprise comprises the industry to which the enterprise belongs, and the color label corresponding to the target enterprise is determined according to the industry;
the related information of the target enterprise comprises an enterprise name of the enterprise, and the color label corresponding to the target enterprise is determined according to the enterprise name.
In one embodiment, the processor is further configured to, if the nationality of the business is japan, determine the type of the corresponding color tag as a light type;
determining a label of a light type and corresponding case materials;
if the nationality of the enterprise is Europe and America, determining that the type of the corresponding color label is a deep color type;
determining a dark label and corresponding case materials;
if the nationality of the enterprise is China, determining the province of the enterprise;
if the Tibetan is the color label, the color label is blue or white;
if the color is Xinjiang, the corresponding color label is yellow;
if the three provinces are northeast, the corresponding color label is white;
if the color is Hainan island, the color label of the drink is green or blue;
if the industry is the new energy wind power generation industry, the color label is green and/or blue;
if the industry is the animal husbandry industry, the color label is green;
if the industry is the drinking water industry, the color label is white;
if the industry is the medical and pharmaceutical industry, the color labels are red and white;
if the industry is the transportation industry, the color label is blue.
In one embodiment, the processor is further configured to obtain case material images to be identified;
identifying the case material image to be identified to determine the dominant color of the case material image to be identified;
and generating the case material dominant color label.
In one embodiment, the processor is further configured to obtain an RGB value of each pixel point of the case material image to be identified;
converting the RGB values to HSV values;
clustering calculation is carried out on the HSV value of each pixel point on the case material image by using a clustering algorithm, and the proportion distribution value of each color of the case material image is obtained;
and determining the dominant color of the image according to the ratio distribution value of each color.
In one embodiment, the processor is further configured to, prior to generating a dominant color label tag, obtain RGB values for the dominant color;
calculating the distance between the RGB value of the dominant color and the RGB value of the standard color;
and if the distance is less than a preset threshold value, determining that the name of the standard color is the label name of the dominant color.
In one embodiment, the processor is further configured to receive a user-entered color ratio range after displaying the case material images;
and determining the corresponding case material images according to the color proportion range and the color proportion distribution statistical table of each image.
To achieve the above object, according to a fourth aspect of the present application, there is provided a computer-readable storage medium having one or more program instructions embodied therein, the one or more program instructions being for performing the steps of:
receiving related information of a target enterprise input by a user;
determining a color label corresponding to the target enterprise according to the relevant information of the target enterprise;
determining a case material image corresponding to the color label in a pre-stored case material image database according to the color label;
and displaying the case material images.
In one embodiment, the information about the target enterprise includes the nationality to which the enterprise belongs; determining a color label corresponding to the target enterprise according to the nationality;
the related information of the target enterprise comprises the industry to which the enterprise belongs, and the color label corresponding to the target enterprise is determined according to the industry;
the related information of the target enterprise comprises an enterprise name of the enterprise, and the color label corresponding to the target enterprise is determined according to the enterprise name.
In one embodiment, if the nationality of the enterprise is japan, the type of the corresponding color tag is determined to be a light type;
determining a label of a light type and corresponding case materials;
if the nationality of the enterprise is Europe and America, determining that the type of the corresponding color label is a deep color type;
determining a dark label and corresponding case materials;
if the nationality of the enterprise is China, determining the province of the enterprise;
if the Tibetan is the color label, the color label is blue or white;
if the color is Xinjiang, the corresponding color label is yellow;
if the three provinces are northeast, the corresponding color label is white;
if the color is Hainan island, the color label of the drink is green or blue;
if the industry is the new energy wind power generation industry, the color label is green and/or blue;
if the industry is the animal husbandry industry, the color label is green;
if the industry is the drinking water industry, the color label is white;
if the industry is the medical and pharmaceutical industry, the color labels are red and white;
if the industry is the transportation industry, the color label is blue.
In one embodiment, the method further comprises: generating an image color label comprising:
acquiring a case material image to be identified;
identifying the case material image to be identified to determine the dominant color of the case material image to be identified;
and generating the case material dominant color label.
In one embodiment, identifying the case material images to be identified to determine the dominant color of the case material images to be identified includes:
acquiring the RGB value of each pixel point of the case material image to be identified;
converting the RGB values to HSV values;
clustering calculation is carried out on the HSV value of each pixel point on the case material image by using a clustering algorithm, and the proportion distribution value of each color of the case material image is obtained;
and determining the dominant color of the image according to the ratio distribution value of each color.
In one embodiment, before generating the dominant color label, determining the name of the dominant color label specifically includes:
acquiring RGB values of the dominant color;
calculating the distance between the RGB value of the dominant color and the RGB value of the standard color;
and if the distance is less than a preset threshold value, determining that the name of the standard color is the label name of the dominant color.
In one embodiment, after the case material images are displayed, a color proportion range input by a user is received;
and determining the corresponding case material images according to the color proportion range and the color proportion distribution statistical table of each image.
According to the method, before the advertising case is designed, a designer inputs the relevant information of the enterprise to search in the process of searching the case material images, and the case material images with the colors corresponding to the relevant information of the enterprise can be obtained. The technical scheme of the invention greatly improves the retrieval efficiency of the designer for designing the advertisement case.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, serve to provide a further understanding of the application and to enable other features, objects, and advantages of the application to be more apparent. The drawings and their description illustrate the embodiments of the invention and do not limit it. In the drawings:
fig. 1 is a schematic view of a case material image according to an embodiment of the present application;
fig. 2 is a flowchart of a case material image retrieval method according to an embodiment of the present application;
fig. 3 is a schematic diagram of a case material image retrieval interface according to an embodiment of the application;
fig. 4 is a schematic structural diagram of a case material image retrieval apparatus according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a case material image retrieval apparatus according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
The case material images have a reference role in the design of the designer. See fig. 1 for a schematic representation of a case image of an enterprise. Case images are images of paying treasures; the Chinese characters comprise two colors, and the branches of the Chinese characters are white; the background is blue. Before a designer designs a case for a customer, the designer often needs to search materials in advance and collect related materials for design. The efficiency and effectiveness of the case material image retrieval has a significant impact on designers. In the prior art, when a designer searches from the internet, the designer only inputs keywords of some enterprises to search, and the searched pictures are often irrelevant and do not help much in design work.
Based on this, the present application proposes a case material image retrieval method, which is referred to as a flow chart of the case material image retrieval method shown in fig. 2; the method comprises the following steps:
step S202, receiving related information of a target enterprise input by a user;
the related information of the enterprise includes, but is not limited to, information of enterprise name, nationality, region, industry, and the like.
Specifically, the advertisement designer enters the name of the business customer on the client to search.
Illustratively, the ad designer enters the customer's business name in the business name column on the interface: distant view energy wind power generation company.
Step S204, determining a color label corresponding to the target enterprise according to the relevant information of the target enterprise;
step S206, determining case material images corresponding to the color labels in a pre-stored case material image database according to the color labels;
wherein the case material image database is a collection of enterprise case material images. Updating and maintaining the case material image database regularly; updating includes adding new case material images.
Sources of case material images include, but are not limited to, the following forms: a trademark of an enterprise; a brochure of an enterprise; promotional pictures in promotional material on the official website of the enterprise; screenshot of the propaganda video; in the case material image could also be an icon of an application of the enterprise, in the case of an internet company.
Distributing an identifier for each case material image; the identification can be in the form of Arabic numerals, or a combination of letters, and the like.
Each case material image is provided with a color label;
generating a color label statistical table of each case material image;
generating a plurality of case material images corresponding to each color label;
illustratively, in one embodiment, the number of case material images in the database is 200; see table 1 for a table of correspondence between color labels and case material image identifiers.
| Color label | Case material image |
| Green colour | |
| 1、3、6、9、10 | |
| Red colour | 2、11； |
| … | … |
| Blue color | 110、200 |
TABLE 1
The case material image corresponding to the green label is as follows: 1. 3, 7, 9, 10;
the case material images corresponding to the red labels are as follows: 2. 11;
the case material images corresponding to the blue labels are as follows: 110. 200 of a carrier;
in the table, other colors and corresponding case identifications are omitted from display.
And step S208, displaying the case material images.
The method of the invention sets up a special database of enterprise material case images. And maintaining and updating the database. The method comprises the steps that before the advertising case is designed, a designer searches from an enterprise material case image database, and in the case material image searching process, after relevant information of an enterprise is input, case material images of colors corresponding to the relevant information can be obtained through searching. The technical scheme of the invention greatly improves the retrieval efficiency of the designer for designing the advertisement case.
In one embodiment, the related information of the target enterprise comprises an enterprise name of the enterprise, and a color label corresponding to the target enterprise is determined according to the enterprise name;
illustratively, if "starbucks" is entered, since starbucks coffee gives the person a color impression of starbucks green, a greenish black color; determining that the color label is dark green according to the starbucks, and displaying the dark green case material image.
If the user inputs the lattice force, because the color of the font of the lattice force grid given to the lattice force air conditioner is sky blue, the color label is determined to be sky blue according to the lattice force, and the blue case material image is displayed.
In one embodiment, the related information of the enterprise includes the nationality of the enterprise.
If the nationality of the enterprise is Japan, determining the type of the corresponding color label to be a light type;
determining a label of a light type and corresponding case materials;
if the nationality of the enterprise is Europe and America, determining that the type of the corresponding color label is a deep color type;
determining a dark label and corresponding case materials;
illustratively, the dark color, especially the deep red color, is liked by western people; japanese enjoys the light colors including white and pink.
Therefore, after receiving the enterprise name input by the user, judging whether the enterprise is European and American according to the enterprise name; an enterprise information base can be established in advance, and related information such as enterprise names, enterprise nationalities, enterprise industries and the like is stored in the enterprise information base; the corresponding nationality can be determined by inquiring the database through the enterprise name; alternatively, the user may directly enter the nationality of the enterprise.
If so, searching a case image with red as a dominant color; if the case image is a day enterprise, the case image with white as the main color is searched out.
If the nationality of the enterprise is China, determining the province of the enterprise;
determining corresponding colors according to regional climates of provinces; if the product is evergreen in four seasons, the product is green; and if the ice and snow cover all the year round, the color is white.
Illustratively, if Tibet, the color label is blue or white;
if the color is Xinjiang, the corresponding color label is yellow;
if the three provinces are northeast, the corresponding color label is white;
if Hainan island, the color label of the drink is green or blue.
Southern provinces include, but are not limited to, Guangdong, Guangxi, Yunnan, Guizhou, evergreen, so the color label of the enterprise in the region is green.
The provinces in the north, the three provinces in the northeast, especially Tibet, are covered by ice and snow, so the color can be white.
Of course, seasonal factors and industry-related factors can be considered, and in inner Mongolia areas, grassland with green color also exists in summer, and if the grassland is in the livestock husbandry industry, green color can also be used as a label.
In one embodiment, the relevant information for the business includes the industry to which the business belongs;
if the industry is the new energy wind power generation industry, the color label is green and/or blue;
if the industry is the animal husbandry industry, the color label is green;
if the industry is the drinking water industry, the color label is white;
if the industry is the medical and pharmaceutical industry, the color labels are red and white;
if the industry is the transportation industry, the color label is blue.
Illustratively, if the client is an internet company, the product is an application App; considering the red cross sign of the hospital, the icons in the application should be mainly red plus white; red is auxiliary; after searching and inputting the enterprise name, a designer can search the case material image with coexisting red and white; can be used for reference design, thus greatly improving the design efficiency of designers.
Considering that designers often search for a specific color in actual work; so in one embodiment, if the user enters "white cloud," the case material images are displayed in the same color as the white cloud.
If the user inputs "rainbow," case material images in the same plurality of colors are displayed.
It is noted that the color label may also be provided with a combination of different colors, such as red + white; red + blue; white + green, etc. In consideration of the color distribution characteristics of case material images, generally, the case material images with pure colors are fewer, and most of the case material images comprise two or more colors.
For example, the colors of the icons of the WeChat application App include: white + green;
the color of the icon of the pay application App comprises white + blue;
the color of the icon of the application program APP of the express hand comprises: white + yellow;
the colors of the icons of the application App for public opinion include: white + orange;
the colors included in the case material images can also be three colors; for example, the colors of the icons of the application APP of jingle fast drug include: white + red + yellow.
In one implementation mode, the method can be further subdivided, and the proportion of each color is calculated for each case material image through an image processing algorithm; and carrying out statistics to generate a color proportion distribution statistical table.
Receiving a color proportion range input by a user;
determining corresponding case material images according to the color proportion range and the color proportion distribution statistical table of each image;
for example, in the icon of the pay application, the distribution of white is the Chinese character "zhi"; the background color is blue, so the blue ratio occupies a large part; white proportion occupies a very small part; the proportion of each color can be calculated through an algorithm of image processing, statistics is carried out, and a color distribution statistical table is generated.
For example, see a blue-plus-white color ratio and image profile shown in table 2:
TABLE 2
As shown in table 2, a correspondence table of different ratios of blue and white to the identification of the corresponding case material image; and determining the corresponding image according to the corresponding relation table.
In order to facilitate the designer to further refine the search, in one embodiment, a user-entered percentage for each color is received; and determining and displaying the corresponding case material image according to the proportion of each color.
Specifically, the designer can input the proportion range of each color, thereby narrowing the search range and accurately searching.
A user inputs a color; and the proportion of the color; and clicking a search button to display the searched case material images.
Illustratively, referring to fig. 3A, a color name input box, a proportion lower bound input box, and a proportion upper bound input box are provided; and after the user inputs the proportion range of each color, clicking a query button to perform query. The query result is a plurality of related case material images; the images can be displayed in a sorted manner according to the click rate; the highest ranking with a high number of clicks.
Referring to fig. 3B, the user enters white in the color input box and the input in the proportion input box is less than 0.9.
Exemplary, designer input: blue is more than 0.9, white is less than 0.1; after the second retrieval, the picture 1 and the image 2 are displayed to a designer, so that the design efficiency of the designer can be greatly improved.
In one embodiment, displaying the case material images further comprises: sequencing the reference times of each case material image from high to low;
illustratively, if the reference amount of the case material image 1 is 100; the number of times of reference of the case material image 2 is 90; then in the displayed case material image list, the case material image 1 is positioned at the top end; the case material images 2 are located at the lower end of the picture 1.
In one implementation, when an image color label is generated, a case material image to be identified is acquired;
identifying the case material image to be identified to determine the dominant color of the case material image to be identified;
and generating the case material dominant color label.
Specifically, when the case material image to be identified is identified and the dominant color of the case material image to be identified is determined, the RGB value of each pixel point of the case material image to be identified is obtained;
converting the RGB values to HSV values;
and clustering calculation is carried out on the HSV value of each pixel point on the case material image by using a clustering algorithm, so as to obtain the proportion distribution value of each color of the case material image.
Exemplarily, the case material image shown in fig. 1 is obtained through clustering calculation, and the ratio of blue is 0.9; the white color ratio was 0.1.
And determining the dominant color of the image according to the ratio distribution value of each color.
Exemplarily, in fig. 1, the blue ratio is 0.9; the dominant color of the image is blue.
In one embodiment, before generating the dominant color label tag, the method further comprises: determining the name of the dominant color label specifically comprises:
acquiring RGB values of the dominant color;
calculating the distance between the RGB value of the dominant color and the RGB value of the standard color;
and if the distance is less than a preset threshold value, determining that the name of the standard color is the label name of the dominant color.
In one embodiment, the case of three colors and more than three colors in the case material image generally account for the largest ratio, i.e., the dominant color in the image, but the background color of the image is often relatively large, and the definition of the dominant color is more biased to be other than the background: "most prominent color", so if 90% of the colors are a single solid color during the calculation; such as pure white (255, 255, 255) or pure black (0, 0, 0); the color is determined as the background color, the background color can be ignored, and the color which is more than the second color is selected as the dominant color.
In the naming process of the color labels of the case material images of the sample, for the material images of the collected cases, the proportion of each color in the images is calculated, and the specific name of each color is determined according to the specific color value of each color; thereby establishing a corresponding tag name.
In particular, the distance between the two colors can be calculated to determine whether the color is adjacent to a standard color. Extracting neighbor colors, wherein in an RGB color model, R, G, B three components are equivalent to an x axis, a y axis and a z axis of a three-dimensional space; the distance of the two pixels in RGB space (color difference) is calculated. And judging whether the two colors are adjacent or not according to the calculated distance.
All colors in the visible spectrum, red, orange, yellow, green, blue, violet, etc., are the primary colors. The different amounts of mixing between the base colors, and between the base colors and the achromatic colors produce millions of colors belonging to the chromatic system, and among the numerous colors, 15 colors are relatively common as standard colors. See table 3 for standard color values.
TABLE 3
See fig. 4 for a schematic 24 color circle; on a 24 color circle, colors that are adjacent within an angle of 60 degrees on the color circle are collectively referred to as neighbor colors. The positions of 15 standard colors are found on the color circle, for any color a, the color distance from the standard color is calculated, if the color distance is smaller than a threshold value, the color a and the standard color can be considered to be adjacent, and through calculation, the color distance corresponding to an angle of 60 degrees on the color circle is 180, so the threshold value is set to be 180. Calculating the color distance by:
obtaining a GRB value (r1, g1, b1) for the first color;
obtaining GRB values (r2, g2, b2) for the second color;
calculating an average value of the R elements of the first color and the second color; r _ mean ═ (r1+ r 2)/2;
calculating a difference value of the R elements of the first color and the second color; r-r 1-r 2;
calculating a difference value of G elements of the first color and the second color; g-g 1-g 2;
calculating a difference value of B elements of the first color and the second color; b-b 1-b 2.
The distance D is calculated by the following formula:
if D is greater than a predetermined threshold, then the colors are determined not to be adjacent.
If D is less than a predetermined threshold, colors of the first color that are adjacent to the second color are determined.
If the first color is a standard color, the second color is a color of a certain standby name of the case material image.
Determining the name of the color of the standby name as the name of the standard color; the corresponding color label is the name of the standard color.
Illustratively, the second color is red. The first color is one color in the case material image, and the distance between the color and the red is calculated to be smaller than a threshold value; the name of the color label that determines the color is red.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
According to an embodiment of the present invention, there is also provided a case material image retrieval apparatus, as shown in fig. 4, including:
a receiving module 41, configured to receive information related to a target enterprise, which is input by a user;
an image determining module 42, configured to determine a color label corresponding to the target business according to the related information of the target business;
determining a case material image corresponding to the color label in a pre-stored case material image database according to the color label;
and a display module 43, configured to display the case material images.
In one embodiment, the image determination module 42 is further configured to determine the related information of the target enterprise includes a nationality of the enterprise; determining a color label corresponding to the target enterprise according to the nationality;
the related information of the target enterprise comprises the industry to which the enterprise belongs, and the color label corresponding to the target enterprise is determined according to the industry.
The related information of the target enterprise comprises an enterprise name of the enterprise, and the color label corresponding to the target enterprise is determined according to the enterprise name.
If the nationality of the enterprise is Japan, determining the type of the corresponding color label to be a light type;
determining a label of a light type and corresponding case materials;
if the nationality of the enterprise is Europe and America, determining that the type of the corresponding color label is a deep color type;
determining a dark label and corresponding case materials;
if the nationality of the enterprise is China, determining the province of the enterprise;
if the Tibetan is the color label, the color label is blue or white;
if the color is Xinjiang, the corresponding color label is yellow;
if the three provinces are northeast, the corresponding color label is white;
if the color is Hainan island, the color label of the drink is green or blue;
if the industry is the new energy wind power generation industry, the color label is green and/or blue;
if the industry is the animal husbandry industry, the color label is green;
if the industry is the drinking water industry, the color label is white;
if the industry is the medical and pharmaceutical industry, the color labels are red and white;
if the industry is the transportation industry, the color label is blue.
In one embodiment, the system further comprises an image color label generation module, which is specifically used for acquiring a case material image to be identified;
identifying the case material image to be identified to determine the dominant color of the case material image to be identified;
and generating the case material dominant color label.
In one embodiment, the image color label generating module is further configured to obtain an RGB value of each pixel point of the case material image to be identified;
converting the RGB values to HSV values;
clustering calculation is carried out on the HSV value of each pixel point on the case material image by using a clustering algorithm, and the proportion distribution value of each color of the case material image is obtained;
and determining the dominant color of the image according to the ratio distribution value of each color.
In an embodiment, the image color tag generating module is further configured to, before generating the dominant color tag, determine the dominant color tag name, and specifically configured to:
acquiring RGB values of the dominant color;
calculating the distance between the RGB value of the dominant color and the RGB value of the standard color;
and if the distance is less than a preset threshold value, determining that the name of the standard color is the label name of the dominant color.
In one embodiment, the receiving module 41 is further configured to receive a color proportion range input by a user after the case material image is displayed;
the image determining module 42 is further configured to determine corresponding case material images according to the color ratio range and the color ratio distribution statistical table of each image.
According to a third aspect of the present application, there is provided a case material image retrieval apparatus; referring to fig. 5, including at least one processor 51 and at least one memory 52; the memory 52 is used to store one or more program instructions; the processor 51 is configured to execute one or more program instructions to perform the following steps:
receiving related information of a target enterprise input by a user;
determining a color label corresponding to the target enterprise according to the relevant information of the target enterprise;
determining a case material image corresponding to the color label in a pre-stored case material image database according to the color label;
and displaying the case material images.
In one embodiment, the processor 51 is further configured to, the related information of the target enterprise includes a nationality to which the enterprise belongs; determining a color label corresponding to the target enterprise according to the nationality;
the related information of the target enterprise comprises the industry to which the enterprise belongs, and the color label corresponding to the target enterprise is determined according to the industry.
The related information of the target enterprise comprises an enterprise name of the enterprise, and the color label corresponding to the target enterprise is determined according to the enterprise name.
In one embodiment, the processor 51 is further configured to determine that the type of the corresponding color tag is a light type if the nationality of the enterprise is japan;
determining a label of a light type and corresponding case materials;
if the nationality of the enterprise is Europe and America, determining that the type of the corresponding color label is a deep color type;
determining a dark label and corresponding case materials;
if the nationality of the enterprise is China, determining the province of the enterprise;
if the Tibetan is the color label, the color label is blue or white;
if the color is Xinjiang, the corresponding color label is yellow;
if the three provinces are northeast, the corresponding color label is white;
if the color is Hainan island, the color label of the drink is green or blue;
if the industry is the new energy wind power generation industry, the color label is green and/or blue;
if the industry is the animal husbandry industry, the color label is green;
if the industry is the drinking water industry, the color label is white;
if the industry is the medical and pharmaceutical industry, the color labels are red and white;
if the industry is the transportation industry, the color label is blue.
In one embodiment, the processor 51 is further configured to obtain case material images to be identified;
identifying the case material image to be identified to determine the dominant color of the case material image to be identified;
and generating the case material dominant color label.
In one embodiment, the processor 51 is further configured to obtain an RGB value of each pixel point of the case material image to be identified;
converting the RGB values to HSV values;
clustering calculation is carried out on the HSV value of each pixel point on the case material image by using a clustering algorithm, and the proportion distribution value of each color of the case material image is obtained;
and determining the dominant color of the image according to the ratio distribution value of each color.
In one embodiment, the processor 51 is further configured to, before generating a dominant color label tag, obtain RGB values of the dominant color;
calculating the distance between the RGB value of the dominant color and the RGB value of the standard color;
and if the distance is less than a preset threshold value, determining that the name of the standard color is the label name of the dominant color.
In one embodiment, the processor 51 is further configured to receive a user-entered color ratio range after displaying the case material images;
and determining the corresponding case material images according to the color proportion range and the color proportion distribution statistical table of each image.
In an embodiment of the invention, the processor may be an integrated circuit chip having signal processing capability. The Processor may be a general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete Gate or transistor logic device, discrete hardware component.
The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The processor reads the information in the storage medium and completes the steps of the method in combination with the hardware.
The storage medium may be a memory, for example, which may be volatile memory or nonvolatile memory, or which may include both volatile and nonvolatile memory.
The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory.
The volatile Memory may be a Random Access Memory (RAM) which serves as an external cache. By way of example and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), SLDRAM (SLDRAM), and Direct Rambus RAM (DRRAM).
The storage media described in connection with the embodiments of the invention are intended to comprise, without being limited to, these and any other suitable types of memory.
Those skilled in the art will appreciate that the functionality described in the present invention may be implemented in a combination of hardware and software in one or more of the examples described above. When software is applied, the corresponding functionality may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A case material image retrieval method is characterized by comprising the following steps:
receiving related information of a target enterprise input by a user;
determining a color label corresponding to the target enterprise according to the relevant information of the target enterprise;
determining a case material image corresponding to the color label in a pre-stored case material image database according to the color label;
and displaying the case material images.
2. The case material image retrieval method of claim 1,
the related information of the target enterprise comprises nationality of the enterprise; determining a color label corresponding to the target enterprise according to the nationality;
the related information of the target enterprise comprises an industry to which the enterprise belongs, and the color label corresponding to the target enterprise is determined according to the industry;
the related information of the target enterprise comprises an enterprise name of the enterprise, and the color label corresponding to the target enterprise is determined according to the enterprise name.
3. The case material image retrieval method of claim 2,
if the nationality of the enterprise is Japan, determining the type of the corresponding color label to be a light type;
determining a label of a light type and corresponding case materials;
if the nationality of the enterprise is Europe and America, determining that the type of the corresponding color label is a deep color type;
determining a dark label and corresponding case materials;
if the nationality of the enterprise is China, determining the province of the enterprise;
if the Tibetan is the color label, the color label is blue or white;
if the color is Xinjiang, the corresponding color label is yellow;
if the three provinces are northeast, the corresponding color label is white;
if the color is Hainan island, the color label of the drink is green or blue;
if the industry is the new energy wind power generation industry, the color label is green and/or blue;
if the industry is the animal husbandry industry, the color label is green;
if the industry is the drinking water industry, the color label is white;
if the industry is the medical and pharmaceutical industry, the color labels are red and white;
if the industry is the transportation industry, the color label is blue.
4. The case material image retrieval method of claim 1, further comprising: generating an image color label comprising:
acquiring a case material image to be identified;
identifying the case material image to be identified to determine the dominant color of the case material image to be identified;
and generating the case material dominant color label.
5. The method of case material image retrieval of claim 4, wherein identifying the case material images to be identified to determine the dominant color of the case material images to be identified comprises:
acquiring the RGB value of each pixel point of the case material image to be identified;
converting the RGB values to HSV values;
clustering calculation is carried out on the HSV value of each pixel point on the case material image by using a clustering algorithm, and the proportion distribution value of each color of the case material image is obtained;
and determining the dominant color of the image according to the ratio distribution value of each color.
6. The case material image retrieval method of claim 4, wherein, prior to generating the dominant color label, further comprising: determining the name of the dominant color label specifically comprises:
acquiring RGB values of the dominant color;
calculating the distance between the RGB value of the dominant color and the RGB value of the standard color;
and if the distance is less than a preset threshold value, determining that the name of the standard color is the label name of the dominant color.
7. The method of case material image retrieval as set forth in claim 4, after displaying the case material images, the method further comprising:
receiving a color proportion range input by a user;
and determining the corresponding case material images according to the color proportion range and the color proportion distribution statistical table of each image.
8. A case material image retrieval apparatus, comprising:
the receiving module is used for receiving the related information of the target enterprise input by the user;
the image determining module is used for determining a color label corresponding to the target enterprise according to the related information of the target enterprise;
determining a case material image corresponding to the color label in a pre-stored case material image database according to the color label;
and the display module is used for displaying the case material images.
9. A case material image retrieval apparatus, comprising: at least one processor and at least one memory; the memory is to store one or more program instructions; the processor, configured to execute one or more program instructions to perform the method of any of claims 1-7.
10. A computer-readable storage medium having one or more program instructions embodied therein for performing the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110040758.8A CN112732968B (en) | 2021-01-12 | 2021-01-12 | Case material image retrieval method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110040758.8A CN112732968B (en) | 2021-01-12 | 2021-01-12 | Case material image retrieval method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112732968A true CN112732968A (en) | 2021-04-30 |
| CN112732968B CN112732968B (en) | 2021-08-31 |
Family
ID=75592804
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110040758.8A Active CN112732968B (en) | 2021-01-12 | 2021-01-12 | Case material image retrieval method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112732968B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030012428A1 (en) * | 1999-11-16 | 2003-01-16 | Syeda-Mahmood Tanveer Fathima | Method and apparatus for indexing and retrieving images from an image database based on a color query |
| CN101763367A (en) * | 2008-12-08 | 2010-06-30 | 新奥特硅谷视频技术有限责任公司 | Method and device for setting file labels |
| CN103226575A (en) * | 2013-04-01 | 2013-07-31 | 北京小米科技有限责任公司 | Image processing method and device |
| CN105488111A (en) * | 2015-11-20 | 2016-04-13 | 小米科技有限责任公司 | Image search method and device |
| US20170140536A1 (en) * | 2013-08-01 | 2017-05-18 | Panasonic Corporation | Similar case retrieval apparatus, similar case retrieval method, non-transitory computer-readable storage medium, similar case retrieval system, and case database |
| CN108206917A (en) * | 2017-12-29 | 2018-06-26 | 中兴通讯股份有限公司 | The method and device of image procossing, storage medium, electronic device |
| CN110232131A (en) * | 2019-04-26 | 2019-09-13 | 特赞（上海）信息科技有限公司 | Intention material searching method and device based on intention label |
| CN110472090A (en) * | 2019-08-20 | 2019-11-19 | 腾讯科技（深圳）有限公司 | Image search method and relevant apparatus, storage medium based on semantic label |
| CN111291210A (en) * | 2020-01-14 | 2020-06-16 | 广州视源电子科技股份有限公司 | Image material library generation method, image material recommendation method and related device |
| CN111340782A (en) * | 2020-02-26 | 2020-06-26 | 苏宁云计算有限公司 | Image marking method, device and system |
-
2021
- 2021-01-12 CN CN202110040758.8A patent/CN112732968B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030012428A1 (en) * | 1999-11-16 | 2003-01-16 | Syeda-Mahmood Tanveer Fathima | Method and apparatus for indexing and retrieving images from an image database based on a color query |
| CN101763367A (en) * | 2008-12-08 | 2010-06-30 | 新奥特硅谷视频技术有限责任公司 | Method and device for setting file labels |
| CN103226575A (en) * | 2013-04-01 | 2013-07-31 | 北京小米科技有限责任公司 | Image processing method and device |
| US20170140536A1 (en) * | 2013-08-01 | 2017-05-18 | Panasonic Corporation | Similar case retrieval apparatus, similar case retrieval method, non-transitory computer-readable storage medium, similar case retrieval system, and case database |
| CN105488111A (en) * | 2015-11-20 | 2016-04-13 | 小米科技有限责任公司 | Image search method and device |
| CN108206917A (en) * | 2017-12-29 | 2018-06-26 | 中兴通讯股份有限公司 | The method and device of image procossing, storage medium, electronic device |
| CN110232131A (en) * | 2019-04-26 | 2019-09-13 | 特赞（上海）信息科技有限公司 | Intention material searching method and device based on intention label |
| CN110472090A (en) * | 2019-08-20 | 2019-11-19 | 腾讯科技（深圳）有限公司 | Image search method and relevant apparatus, storage medium based on semantic label |
| CN111291210A (en) * | 2020-01-14 | 2020-06-16 | 广州视源电子科技股份有限公司 | Image material library generation method, image material recommendation method and related device |
| CN111340782A (en) * | 2020-02-26 | 2020-06-26 | 苏宁云计算有限公司 | Image marking method, device and system |
Non-Patent Citations (1)
| Title |
|---|
| 陈乾明: "基于内容的图像检索系统的设计与实现", 《中国优秀硕士学位论文全文数据库》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112732968B (en) | 2021-08-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10943256B2 (en) | Methods and systems for automatically generating advertisements | |
| CN102833625B (en) | The device and method of dynamic product placement in video | |
| CN105469262B (en) | Commodity information acquisition of information and integration method and device | |
| CN103578098B (en) | Method and device for extracting commodity body in commodity picture | |
| CN103577993B (en) | Color choosing method and device | |
| CN104978565A (en) | Universal on-image text extraction method | |
| CN112232907A (en) | Commodity screening system for live broadcast sales and working method thereof | |
| CN105302560B (en) | A kind of multidimensional labels implement methods towards digital signage | |
| Mostafa et al. | Corresponding regions for shadow restoration in satellite high-resolution images | |
| CN112732968B (en) | Case material image retrieval method, device, equipment and storage medium | |
| Zahrádka et al. | What is the price of outdoor advertising: A case study of the Czech republic? | |
| CN104408189A (en) | Keyword ranking display method and device | |
| Yang et al. | East Asia and solar energy trade network patterns | |
| Schief et al. | Performance of business models: empirical insights from the software industry | |
| CN103593458A (en) | Mass image searching system based on color features and inverted indexes | |
| CN111158647B (en) | Creative material self-adaptive generation method and device based on structural theory | |
| CN110264244B (en) | Advertisement user trajectory tracking management system and method | |
| Berndgen-Kaiser et al. | Post-war single-family houses in europe under pressure? A demographic and economic framework for the future market of elder single-family housing neighbourhoods | |
| CN105786964B (en) | Remote Sensing Products retrieval based on Web Mining limits item semantic extension method | |
| CN101963991A (en) | Accurate searching method of picture | |
| CN102314435A (en) | Method for searching webpage content and system | |
| Kim | Analysis of shop sign colors in Joong-Gu, Seoul—Nadulgage and convenience stores | |
| Ryu et al. | New RGB primary for various multimedia systems | |
| Jenes | The Nature of Country Image-An Extended Literature Review | |
| Cabrera et al. | Price structure of extra virgin olive oil: a hedonic approach |
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 |