CN111563181B - Digital image file query method, device and readable storage medium - Google Patents
Digital image file query method, device and readable storage medium Download PDFInfo
- Publication number
- CN111563181B CN111563181B CN202010396924.3A CN202010396924A CN111563181B CN 111563181 B CN111563181 B CN 111563181B CN 202010396924 A CN202010396924 A CN 202010396924A CN 111563181 B CN111563181 B CN 111563181B
- Authority
- CN
- China
- Prior art keywords
- digital image
- target digital
- image
- target
- relation
- 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
- G06F16/58—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
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- 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
- G06F16/5854—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 shape and object relationship
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The application discloses a digital image file query method, a digital image file query device and a computer readable storage medium. Adding the acquired target digital image and the digital image set to be searched to a display container constructed in advance, and assigning values to the digital images in the display container according to a preset assignment rule; the target digital image and each digital image to be searched in the digital image set to be searched are not overlapped with each other and are displayed in a display container according to a preset row-column format; extracting image features, numerical features and position relation features of the target digital images as identification features, wherein the numerical features and the position relation features are determined based on assigned values of the digital images and position coordinates of a display container where the digital images are located; the position relation feature is used for determining the required position relation condition; and querying the digital images to be retrieved, which meet the position relation condition and have the same image content as the target digital image, from the digital image set to be retrieved based on the identification characteristics, thereby realizing efficient and rapid digital image query.
Description
Technical Field
The present invention relates to the field of information retrieval technologies, and in particular, to a method and apparatus for querying a digital image file, and a computer readable storage medium.
Background
With the rapid development of data detection technology, the search based on text information does not meet the information search requirement of users, and image search technology is generated. The traditional digital image is matched and inquired by extracting the characteristics of color, texture, shape, gray scale and the like of the image as retrieval characteristics in the retrieval process. There are commonly used color-based search methods, image search methods based on texture features such as statistical methods, spectrum methods, model methods, etc., and shape search methods based on edges and regions. However, these classical methods are based on the characteristics of artificial design, and the quality of the design method directly affects the effect of image retrieval. It can be appreciated that deep learning is a chum in machine learning, which has the advantage of utilizing big data to automatically learn data features to resolve uncertainty caused by human factors. Based on this, in order to solve the technical drawbacks of the conventional digital image, the related art applies deep learning to the field of image data retrieval.
However, the related art directly inputs an original image into a deep learning model such as a convolutional neural network, and does not consider a case where an object or region of interest may appear in different regions of the image, the size of the size, and the field of application of the image may also be different. Meanwhile, the dimension of the depth feature is high, and the direct utilization of the depth feature for large data image retrieval is not feasible in practical application. In particular, in the actual multi-image input process, the inconvenience in terms of similarity measurement between features is generally calculated by adopting the distance between vectors, but for a batch of digital images, the simple distance between vectors is difficult to truly reflect the similarity and the association degree between the digital images. In addition, in the process of searching a plurality of digital picture files, the position relation of picture elements such as pixels, colors and the like and random hashes of the digital picture files are required to be checked, so that the calculation is complex, and the method is not suitable for efficient query of similar array combinations with numerical relation. Particularly, the method is used for the contrast relation query of big data, such as sales data of different types of commodities of enterprises or personal identity characteristic data and the like, which need to flexibly and dynamically give values representing relations in the data analysis process.
In view of this, how to efficiently and rapidly perform digital image query is a technical problem that needs to be solved by those skilled in the art.
Disclosure of Invention
The application provides a digital image file query method, a digital image file query device and a computer readable storage medium, which can realize digital image query efficiently and rapidly.
In order to solve the technical problems, the embodiment of the invention provides the following technical scheme:
in one aspect, an embodiment of the present invention provides a method for querying a digital image file, including:
adding the acquired target digital image and the digital image set to be retrieved to a display container constructed in advance, and assigning values to the digital images in the display container according to a preset assignment rule; the target digital image and each digital image to be searched in the digital image set to be searched are not overlapped with each other and are displayed in the display container according to a preset row-column format;
extracting identification features of the target digital image; the identification features comprise image features, numerical features and position relation features, wherein the numerical features and the position relation features are determined based on the assigned values of the digital images and the position coordinates of the display container; the position relation feature is used for determining position relation conditions required by the target digital image;
Querying the digital image set to be retrieved from the digital image set to be retrieved based on the identification feature, wherein the digital image set to be retrieved meets the position relation condition and has the same image content as the target digital image.
Optionally, the target digital image is multiple, and the extracting the identification feature of the target digital image includes:
extracting image characteristics of each target digital image, and obtaining the total number of the target digital images;
if the target digital image is not more than 2, calculating the linear distance between the first target digital image and the second target digital image according to the position coordinates of the first target digital image and the second target digital image, and calculating the magnitude relation and sum relation between natural numerical values assigned to the first target digital image and the second target digital image; taking image features of the linear distance, the size relation, the sum value relation, the first target digital image and the second target digital image as the identification features;
if the target digital image is more than 2 but not more than 3, calculating the linear distance between any two of the first target digital image, the second target digital image and the third target digital image and the angle value formed by the linear distance and the linear distance, the angle value and the angle value formed by the first target digital image, the second target digital image and the third target digital image according to the position coordinates of the first target digital image, the second target digital image and the third target digital image, and calculating the magnitude relation and the sum relation of natural numerical values assigned to the first target digital image, the second target digital image and the third target digital image; taking image features of a plurality of groups of linear distances, the angle values, the size relation, the sum value relation, the first target digital image, the second target digital image and the third target digital image as the identification features;
If the number of the target digital images is more than 3, calculating a linear distance between any two of the target digital images and a plurality of groups of angle values formed by adjacent three according to the position coordinates of each target digital image, and calculating a magnitude relation and a sum relation between natural values assigned to each target digital image; and taking a plurality of groups of linear distances, a plurality of groups of angle values, the size relation, the sum value relation and the image characteristics of each target digital image as the identification characteristics.
Optionally, the target digital image is 1, and the extracting the identification feature of the target digital image includes:
if the assignment rule is that all the digital images in the same column of the display container are assigned the same value;
the assigned value and image feature of the target digital image are taken as identifying features.
Optionally, the assignment rule assigns a natural number to each line of digital images in the display container in a form of sequentially increasing by 1 from the first column to the last column.
Optionally, after the querying, based on the identifying feature, the to-be-retrieved digital image that satisfies the positional relationship condition and has the same image content as the target digital image from the to-be-retrieved digital image set, the method further includes:
And outputting the position information of the digital image to be retrieved, which meets the position relation condition and has the same image content as the target digital image, and displaying the digital image obtained by inquiry to the user.
Optionally, before adding the acquired target digital image and the digital image set to be retrieved to the pre-constructed display container, the method further includes:
and determining the target digital image and the digital image set to be retrieved according to the received touch instruction.
Another aspect of the embodiment of the present invention provides a digital image file querying device, including:
the image acquisition module is used for acquiring a target digital image and a digital image to be retrieved;
the image storage module is used for adding the target digital image and the digital image set to be searched to a display container constructed in advance;
the image assignment module is used for assigning values to the digital images in the display container according to a preset assignment rule; the target digital image and each digital image to be searched in the digital image set to be searched are not overlapped with each other and are displayed in the display container according to a preset row-column format;
the feature extraction module is used for extracting the identification features of the target digital image; the identification features comprise image features, numerical features and position relation features, wherein the numerical features and the position relation features are determined based on the assigned values of the digital images and the position coordinates of the display container; the position relation feature is used for determining position relation conditions required by the target digital image;
And the image retrieval module is used for querying the digital images to be retrieved, which meet the position relation condition and have the same image content as the target digital image, from the digital image set to be retrieved based on the identification characteristics.
Optionally, the feature extraction module includes:
the image feature extraction submodule is used for extracting image features of each target digital image;
the first type identification feature generation sub-module is used for taking the assigned value and the image feature of the target digital image as identification features if the assignment rule is that all the digital images in the same column of the display container are assigned the same value;
the second class identification feature generation sub-module is used for calculating the linear distance between the first target digital image and the second target digital image according to the position coordinates of the first target digital image and the second target digital image if the target digital image is not more than 2, and calculating the magnitude relation and sum relation between natural values assigned to the first target digital image and the second target digital image; taking image features of the linear distance, the size relation, the sum value relation, the first target digital image and the second target digital image as the identification features;
A third type of recognition feature generation sub-module, configured to calculate a linear distance between any two of the first target digital image, the second target digital image and the third target digital image and an angle value formed by the linear distance and the three according to position coordinates of the first target digital image, the second target digital image and the third target digital image, and calculate a magnitude relationship and a sum value relationship between natural values assigned to the first target digital image, the second target digital image and the third target digital image if the target digital image is greater than 2 but not greater than 3; taking image features of a plurality of groups of linear distances, the angle values, the size relation, the sum value relation, the first target digital image, the second target digital image and the third target digital image as the identification features;
a fourth type of recognition feature generation sub-module, configured to calculate a magnitude relation and a sum relation between natural values assigned to each target digital image according to a linear distance between any two of the target digital images and a plurality of groups of angle values formed by adjacent three of the target digital images if the target digital images are greater than 3; and taking a plurality of groups of linear distances, a plurality of groups of angle values, the size relation, the sum value relation and the image characteristics of each target digital image as the identification characteristics.
The embodiment of the invention also provides a digital image file inquiring device, which comprises a processor, wherein the processor is used for realizing the steps of the digital image file inquiring method when executing the computer program stored in the memory.
The embodiment of the invention finally provides a computer readable storage medium, wherein the computer readable storage medium stores a digital image file inquiry program, and the digital image file inquiry program realizes the steps of the digital image file inquiry method according to any one of the previous claims when being executed by a processor.
The technical scheme provided by the application has the advantages that the combination mode of the numerical relation of the picture and the regional relation of the picture is adopted to inquire the images of the similar relation between the digital image set to be searched and the target digital image, the deep learning of image features is not needed, the position relation of picture elements such as pixels and colors between the target digital image and the image to be searched and random hash is not needed, the calculation process is simple, the operation is convenient, the digital image which simultaneously meets the position relation and the image content can be inquired efficiently and rapidly, and the inquiry efficient method for big data analysis can be formed in the mode of image searching.
In addition, the embodiment of the invention also provides a corresponding implementation device and a computer readable storage medium for the digital image file query method, so that the method has more practicability, and the device and the computer readable storage medium have corresponding advantages.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the related art, the drawings that are required to be used in the embodiments or the description of the related art will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort to those of ordinary skill in the art.
Fig. 1 is a flow chart of a digital image file query method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram showing an arrangement of digital images in a container according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a feature extraction process according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a relationship between two target digital images according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of the relationship between three target digital images according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a relationship between four target digital images according to an embodiment of the present invention;
FIG. 7 is a flowchart of another digital image file querying method according to an embodiment of the present invention;
FIG. 8 is a block diagram of a digital image file querying device according to an embodiment of the present invention;
fig. 9 is a block diagram of another embodiment of a digital image file querying device according to an embodiment of the present invention.
Detailed Description
In order to better understand the aspects of the present invention, the present invention will be described in further detail with reference to the accompanying drawings and detailed description. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims of this application and in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements but may include other steps or elements not expressly listed.
Having described the technical solutions of embodiments of the present invention, various non-limiting implementations of the present application are described in detail below.
Referring first to fig. 1, fig. 1 is a flow chart of a digital image file query method according to an embodiment of the present invention, where the embodiment of the present invention may include the following:
s101: a target digital image and a set of digital images to be retrieved are acquired.
In this application, a digital image is an image whose image content is a natural number, that is, an image generated by photographing a natural number without any background. The image content on the digital image is 10 natural numbers of 0-9, and each digital image has only one number. The target digital image is an image of a target type that the user wants to retrieve from the database, for example, the user wants to retrieve all images with the number of 2 from the database, then the target digital image is an image with the number of 2, the digital image set to be retrieved is used as the image retrieval database, that is, the retrieval range, and the digital image set to be retrieved contains a plurality of digital images to be retrieved.
The target digital image and the digital image set to be retrieved can be imported from the outside through a USB interface and the like, and can also be selected from an image database stored in the system, so that the realization of the application is not affected. In the process of selecting images from the database, in order to improve the operation flexibility and convenience, the system can be provided with a touch display screen, a user selects a target digital image and a digital image set to be searched through the touch display screen, and the system determines the target digital image and the digital image set to be searched after receiving a touch instruction of the user.
S102: and adding the target digital image and the digital image set to be retrieved to a pre-constructed display container, and assigning values to the digital images in the display container according to a preset assignment rule.
The display container of the embodiment of the invention is a storage queue and is used for storing target digital images and digital image sets to be retrieved. The target digital image and each of the set of digital images to be retrieved are non-overlapping with each other and are displayed in a predetermined rank format within a display container, such as shown in fig. 2. The target digital image and each digital image to be searched in the digital image set to be searched can be randomly placed in the display container, and after the target digital image and each digital image to be searched are placed in the display container, position information, such as the row and the column, or coordinate information, of the container in which the target digital image is located is determined in the display container.
After the target digital image and the digital image set to be searched are added to the display container, each digital image in the container can be assigned according to a preset assignment rule. The assignment rule may be, for example, to assign a natural number to each line of digital images in the display container in a form of sequentially increasing 1 from the first column to the last column, where each digital image in the same column is assigned the same value, as shown in fig. 2, and of course, to assign a natural number to each line of digital images in the display container in an arithmetic sequence or an arithmetic sequence from left to right, which does not affect the implementation of the present application.
S103: and extracting the identification characteristics of the target digital image.
It will be appreciated that the target digital image may be one or more. For one target digital image, no internal relation exists between the target digital images; for a plurality of target digital images, each target digital image is arranged in a display container, and forms a combination, and each target digital image in the combination has a certain internal association relationship, such as a magnitude relationship, an angle relationship and a position relationship. Accordingly, the search result of the target digital image set formed by the plurality of target digital images is necessarily a plurality of sets, and the digital image content in each set is not only the same as each digital image content in the target digital image set, but also satisfies the corresponding position relation. For example, the target digital image set includes a first target digital image and a second target digital image, the first target digital image is 2 and is located in the third column of the first row, the second target digital image is 5 and is located in the second column of the third row, then the search result is two groups, one group is an image with the number of 2 in the sixth column of the first row and an image with the number of 5 in the fifth column of the third row, the other group is an image with the number of 2 in the third column of the fourth row and an image with the number of 5 in the second column of the sixth row, and the images with the numbers of 2 in the sixth column and 5 in the sixth row do not satisfy the positional relationship although the image contents are the same, so they are not output as a group of search results.
In the present application, the identification features may include image features, numerical features, and positional relationship features, which are determined based on the value to which each digital image is assigned and the positional coordinates of the display container in which it is located; the positional relationship feature is used to determine the positional relationship condition required for the target digital image. The image features are used for identifying the features of the image content, any existing related image feature extraction and identification method can be adopted for carrying out digital content identification, the numerical features are assigned sizes of target digital images, if the digital features are a plurality of target digital images, the numerical features can also be assigned size relations of the plurality of target digital images, the numerical features are assigned sums and the like. Two-dimensional coordinate axes can be established in the display container, each image is abstracted into a point, so that each image has a position coordinate value under the same coordinate system, and the distance between the images and the angle formed by a plurality of images can be calculated based on the position coordinate value.
S104: querying the digital images to be retrieved from the digital image set to be retrieved based on the identification features, wherein the digital images to be retrieved meet the position relation condition and have the same image content as the target digital image.
In the image query process, the method and the device not only need to query the image with the same image content as the target digital image, but also need to meet a certain position relationship. For example, if the target digital image is an image with image content 2 in the third column of the first row, the results of the query in S104 are all digital images with image content 2 in the third column, and the results of the query in other columns are similar query results with image content 2, which are not the target digital image. The target digital image set includes a first target digital image having a digital image content of 2 and located in a third column of a first row and a second target digital image having an image content of 5 and located in a second column of a third row, then the search result may be a result set composed of an image having a number of 2 in the sixth column of the first row and an image having a number of 5 in the fifth column of the third row, and the images having a number of 2 in the sixth column and a number of 5 in the second column of the sixth row do not satisfy the positional relationship although the image contents are the same, and therefore are not output as a set of search results.
It should be noted that, because the present application involves the retrieval of two factors, namely image content and positional relationship, in the image retrieval process, a candidate digital image set identical to the image content of the target digital image can be determined first, and then a digital image satisfying the positional relationship condition is selected from the candidate digital image set; of course, the candidate digital image set meeting the position relation condition can be firstly determined and selected, and then the digital image with the same image content as the target digital image can be selected from the candidate digital image set, or the candidate digital image set and the target digital image can be simultaneously performed, so that the realization of the application is not affected.
In the technical scheme provided by the embodiment of the invention, the combination mode of the numerical relation of the picture and the regional relation of the picture is adopted to inquire the images of the similar relation of the digital image set to be searched and the target digital image, the deep learning of image features is not needed, the position relation of picture elements such as pixels, colors and the like and random hash between the target digital image and the image to be searched is not needed, the calculation process is simple, the operation is convenient, the digital image which simultaneously meets the position relation and the image content can be inquired efficiently and rapidly, and the inquiry efficient method for analyzing big data can be formed in the mode of image searching.
In the above embodiment, how to extract the image recognition feature is not limited, and an implementation manner of S103 is given in this embodiment, please refer to fig. 3, which may include the following:
a: all target digital images are acquired.
B: image features of each target digital image are extracted.
In this step, the image features are features reflecting which digits the image is in the image, and any kind of digital recognition algorithm can be used for image feature extraction and image recognition, which is not limited in this application.
C: calculating the position relation feature and the digital feature of each target digital image, as an alternative embodiment, the C step may include:
c1: judging the total number of the target digital images;
c11: if the target digital image is 1, the position relation characteristic and the digital characteristic are position information and assignment information in the display container where the image is located.
In this step, if the target digital image is 1 sheet, the positional relationship feature is a feature having neither distance nor angle. And if the assignment rule is that all the digital images in the same column of the display container are assigned the same value, the assigned value of the target digital image is used as the identification characteristic.
And C12: if the target digital image is not more than 2, calculating the linear distance between the first target digital image and the second target digital image according to the position coordinates of the first target digital image and the second target digital image, and calculating the magnitude relation and sum relation between natural numerical values assigned to the first target digital image and the second target digital image; and taking the linear distance, the size relation, the value relation, the image characteristics of the first target digital image and the second target digital image as identification characteristics. That is, in this step, the positional relationship feature is a feature in which there is a distance between the respective target digital images, as shown in fig. 4.
C13: if the target digital image is more than 2 but not more than 3, calculating the linear distance between any two of the first target digital image, the second target digital image and the third target digital image and the angle value formed by the linear distance, the linear distance and the angle value formed by the first target digital image, the second target digital image and the third target digital image according to the position coordinates of the first target digital image, the second target digital image and the third target digital image, and calculating the magnitude relation and sum relation between natural numerical values assigned to the first target digital image, the second target digital image and the third target digital image; and taking the image characteristics of the plurality of groups of linear distances, the angle values, the size relations, the sum value relations, the first target digital image, the second target digital image and the third target digital image as identification characteristics. That is, in this step, the positional relationship feature is a feature of having a distance or an angle between the respective target digital images, as shown in fig. 5.
C14: if the number of the target digital images is more than 3, calculating a plurality of groups of angle values formed by the linear distance between any two of the target digital images and the adjacent three of the target digital images according to the position coordinates of the target digital images, and calculating the magnitude relation and sum relation between natural values assigned to the target digital images; and taking the image characteristics of the plurality of groups of linear distances, the plurality of groups of angle values, the magnitude relation, the sum value relation and the target digital images as identification characteristics. That is, in this step, the position relation features are features of multiple sets of distances and multiple sets of angles between the target digital images, and each adjacent three images determine an angle, as shown in fig. 6.
D: and taking the image characteristics of the step B and the position relation characteristics and the digital characteristics of the step C as identification characteristics in the image query process of the step S104. And D, according to the result of the step D, the translation patterns on the left, the right, the top and the bottom in the fixed display container are quickly output and found out the digital image meeting the condition position according to the relation of the target digital image group.
As an alternative embodiment, referring to fig. 7, further includes:
s105: and outputting the position information of the digital image to be searched which meets the position relation condition and has the same image content as the target digital image, and displaying the digital image obtained by inquiry to the user.
In the embodiment of the invention, in order to further ensure the image query accuracy, the position information such as the coordinate value of the digital image to be searched can be output, and if the output result is incorrect, maintenance personnel can perform fault location based on the output coordinate value, so that the image query efficiency is further improved.
It should be noted that, in the present application, the steps may be performed simultaneously or may be performed in a certain preset order as long as the steps conform to the logic order, and fig. 1 and fig. 7 are only schematic, and do not represent only such an execution order.
The embodiment of the invention also provides a corresponding device for the digital image file query method, so that the method has more practicability. Wherein the device may be described separately from the functional module and the hardware. The digital image file querying device provided by the embodiment of the invention is described below, and the digital image file querying device described below and the digital image file querying method described above can be referred to correspondingly.
Based on the angles of the functional modules, referring to fig. 8, fig. 8 is a block diagram of a digital image file querying apparatus according to an embodiment of the present invention, where the apparatus may include:
an image acquisition module 801, configured to acquire a target digital image and a digital image to be retrieved.
An image storage module 802 for adding the target digital image and the set of digital images to be retrieved to a pre-built display container.
An image assignment module 803, configured to assign values to each digital image in the display container according to a preset assignment rule; the target digital image and each digital image to be retrieved in the set of digital images to be retrieved are non-overlapping with each other and are displayed in a display container in a preset rank format.
A feature extraction module 804, configured to extract an identification feature of the target digital image; the identification features comprise image features, numerical features and position relation features, and the numerical features and the position relation features are determined based on the assigned values of the digital images and the position coordinates of the display container; the positional relationship feature is used to determine the positional relationship condition required for the target digital image.
The image retrieval module 805 is configured to query, from the set of digital images to be retrieved, for digital images to be retrieved that satisfy the positional relationship condition and have the same image content as the target digital image based on the identification feature.
Optionally, in some implementations of this embodiment, the feature extraction module 804 may further include:
the image feature extraction submodule is used for extracting image features of each target digital image;
the first type identification feature generation sub-module is used for taking the assigned value and the image feature of the target digital image as identification features if the assignment rule is that all the digital images in the same column of the display container are assigned the same value;
the second type identification feature generation sub-module is used for calculating the linear distance between the first target digital image and the second target digital image according to the position coordinates of the first target digital image and the second target digital image if the target digital image is not more than 2, and calculating the magnitude relation and sum relation between natural numerical values assigned to the first target digital image and the second target digital image; taking the linear distance, the size relation, the sum value relation and the image characteristics of the first target digital image and the second target digital image as identification characteristics;
The third type identification feature generation sub-module is used for calculating the linear distance between any two of the first target digital image, the second target digital image and the third target digital image and the angle value formed by the first target digital image, the second target digital image and the third target digital image according to the position coordinates of the first target digital image, the second target digital image and the third target digital image if the target digital image is more than 2 but not more than 3, and calculating the magnitude relation and the sum relation between natural values assigned to the first target digital image, the second target digital image and the third target digital image; taking the image characteristics of a plurality of groups of linear distances, angle values, magnitude relations, sum value relations, a first target digital image, a second target digital image and a third target digital image as identification characteristics;
a fourth type of recognition feature generation sub-module, configured to calculate a magnitude relation and a sum relation between natural values assigned to each target digital image according to a plurality of groups of angle values formed by a straight line distance between any two and adjacent three of the position coordinates of each target digital image if the target digital image is greater than 3; and taking the image characteristics of the plurality of groups of linear distances, the plurality of groups of angle values, the magnitude relation, the sum value relation and the target digital images as identification characteristics.
In other implementations of this embodiment, the apparatus may further include, for example, a result output module configured to output location information of the digital image to be retrieved that satisfies the location relationship condition and is identical to the image content of the target digital image, while presenting the queried digital image to the user.
As another alternative implementation manner, the image acquisition module 801 may also be a module for determining a target digital image and a digital image set to be retrieved according to a received touch instruction.
The functions of each functional module of the digital image file querying device according to the embodiment of the present invention may be specifically implemented according to the method in the embodiment of the method, and the specific implementation process may refer to the related description of the embodiment of the method, which is not repeated herein.
From the above, the embodiment of the invention can realize the digital image query efficiently and quickly.
The above-mentioned digital image file inquiry device is described from the perspective of functional modules, and further, the application also provides a digital image file inquiry device, which is described from the perspective of hardware. Fig. 9 is a block diagram of another digital image file querying device according to an embodiment of the present application. As shown in fig. 9, the apparatus includes a memory 90 for storing a computer program;
a processor 91 for implementing the steps of the digital image file querying method as mentioned in the above embodiments when executing a computer program.
Processor 91 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 91 may be implemented in at least one hardware form of DSP (Digital Signal Processing ), FPGA (Field-Programmable Gate Array, field programmable gate array), PLA (Programmable Logic Array ). The processor 91 may also include a main processor, which is a processor for processing data in an awake state, also called CPU (Central Processing Unit ); a coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 91 may integrate a GPU (Graphics Processing Unit, image processor) for rendering and drawing of content required to be displayed by the display screen. In some embodiments, the processor 91 may also include an AI (Artificial Intelligence ) processor for processing computing operations related to machine learning.
Memory 90 may include one or more computer-readable storage media, which may be non-transitory. Memory 90 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In this embodiment, the memory 90 is at least used for storing a computer program 901, where the computer program, when loaded and executed by the processor 91, can implement the relevant steps of the digital image file querying method disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 90 may further include an operating system 902, data 903, and the like, where the storage mode may be transient storage or permanent storage. The operating system 902 may include Windows, unix, linux, among others. The data 903 may include, but is not limited to, data corresponding to the digital image file query results, and the like.
In some embodiments, the digital image file querying device may further comprise a display 99, an input/output interface 93, a communication interface 94, a power supply 95, and a communication bus 96.
Those skilled in the art will appreciate that the structure shown in fig. 9 does not constitute a limitation of the digital image file querying device and may include more or fewer components than illustrated, such as sensor 97.
The functions of each functional module of the digital image file querying device according to the embodiment of the present invention may be specifically implemented according to the method in the embodiment of the method, and the specific implementation process may refer to the related description of the embodiment of the method, which is not repeated herein.
From the above, the embodiment of the invention can realize the digital image query efficiently and quickly.
It will be appreciated that the digital image file querying method of the above embodiment, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in part or all of the technical solution contributing to the prior art, or in a software product stored in a storage medium, performing all or part of the steps of the methods of the various embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random-access Memory (Random Access Memory, RAM), an electrically erasable programmable ROM, registers, a hard disk, a removable disk, a CD-ROM, a magnetic disk, or an optical disk, etc. various media capable of storing program codes.
Based on this, an embodiment of the present invention further provides a computer readable storage medium storing a digital image file querying program, where the digital image file querying program is executed by a processor, and the steps of the digital image file querying method according to any one of the embodiments above are described.
The functions of each functional module of the computer readable storage medium according to the embodiments of the present invention may be specifically implemented according to the method in the embodiments of the method, and the specific implementation process may refer to the relevant description of the embodiments of the method, which is not repeated herein.
From the above, the embodiment of the invention can realize the digital image query efficiently and quickly.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, so that the same or similar parts between the embodiments are referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The above describes in detail a method, apparatus and computer readable storage medium for querying digital image files provided in the present application. The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to facilitate an understanding of the method of the present invention and its core ideas. It should be noted that it would be obvious to those skilled in the art that various improvements and modifications can be made to the present application without departing from the principles of the present invention, and such improvements and modifications fall within the scope of the claims of the present application.
Claims (8)
1. A digital image file querying method, comprising:
adding the acquired target digital image and the digital image set to be retrieved to a display container constructed in advance, and assigning values to the digital images in the display container according to a preset assignment rule; the target digital image and each digital image to be searched in the digital image set to be searched are not overlapped with each other and are displayed in the display container according to a preset row-column format;
extracting identification features of the target digital image; the identification features comprise image features, numerical features and position relation features, wherein the numerical features and the position relation features are determined based on the assigned values of the digital images and the position coordinates of the display container; the position relation feature is used for determining position relation conditions required by the target digital image;
Querying the digital image set to be retrieved from the digital image set to be retrieved based on the identification feature, wherein the digital image set to be retrieved meets the position relation condition and has the same image content as the target digital image;
wherein the target digital image is a plurality of pieces, and the extracting the identification feature of the target digital image comprises:
extracting image characteristics of each target digital image, and obtaining the total number of the target digital images;
if the target digital image is not more than 2, calculating the linear distance between the first target digital image and the second target digital image according to the position coordinates of the first target digital image and the second target digital image, and calculating the magnitude relation and sum relation between natural numerical values assigned to the first target digital image and the second target digital image; taking image features of the linear distance, the size relation, the sum value relation, the first target digital image and the second target digital image as the identification features;
if the target digital image is more than 2 but not more than 3, calculating the linear distance between any two of the first target digital image, the second target digital image and the third target digital image and the angle value formed by the linear distance and the linear distance, the angle value and the angle value formed by the first target digital image, the second target digital image and the third target digital image according to the position coordinates of the first target digital image, the second target digital image and the third target digital image, and calculating the magnitude relation and the sum relation of natural numerical values assigned to the first target digital image, the second target digital image and the third target digital image; taking image features of a plurality of groups of linear distances, the angle values, the size relation, the sum value relation, the first target digital image, the second target digital image and the third target digital image as the identification features;
If the number of the target digital images is more than 3, calculating a linear distance between any two of the target digital images and a plurality of groups of angle values formed by adjacent three according to the position coordinates of each target digital image, and calculating a magnitude relation and a sum relation between natural values assigned to each target digital image; and taking a plurality of groups of linear distances, a plurality of groups of angle values, the size relation, the sum value relation and the image characteristics of each target digital image as the identification characteristics.
2. The digital image file querying method according to claim 1, wherein the target digital image is 1, and wherein extracting the identification feature of the target digital image comprises:
if the assignment rule is that all the digital images in the same column of the display container are assigned the same value;
the assigned value and image feature of the target digital image are taken as identifying features.
3. The digital image file querying method according to claim 2, wherein the assignment rule assigns a natural number to each row of digital images in the display container in a form of sequentially increasing by 1 from the first column to the last column.
4. The digital image file querying method according to claim 3, wherein after querying the digital image to be retrieved, which satisfies the positional relationship condition and has the same image content as the target digital image, from the digital image set to be retrieved based on the identification feature, further comprises:
And outputting the position information of the digital image to be retrieved, which meets the position relation condition and has the same image content as the target digital image, and displaying the digital image obtained by inquiry to the user.
5. The method according to any one of claims 1 to 4, wherein before adding the acquired target digital image and the set of digital images to be retrieved to the pre-constructed display container, further comprising:
and determining the target digital image and the digital image set to be retrieved according to the received touch instruction.
6. A digital image file querying device, comprising:
the image acquisition module is used for acquiring a target digital image and a digital image to be retrieved;
the image storage module is used for adding the target digital image and the digital image set to be searched to a display container constructed in advance;
the image assignment module is used for assigning values to the digital images in the display container according to a preset assignment rule; the target digital image and each digital image to be searched in the digital image set to be searched are not overlapped with each other and are displayed in the display container according to a preset row-column format;
The feature extraction module is used for extracting the identification features of the target digital image; the identification features comprise image features, numerical features and position relation features, wherein the numerical features and the position relation features are determined based on the assigned values of the digital images and the position coordinates of the display container; the position relation feature is used for determining position relation conditions required by the target digital image;
the image retrieval module is used for querying the digital images to be retrieved, which meet the position relation condition and have the same image content as the target digital image, from the digital image set to be retrieved based on the identification characteristics;
wherein, the feature extraction module includes:
the image feature extraction submodule is used for extracting image features of each target digital image;
the first type identification feature generation sub-module is used for taking the assigned value and the image feature of the target digital image as identification features if the assignment rule is that all the digital images in the same column of the display container are assigned the same value;
the second class identification feature generation sub-module is used for calculating the linear distance between the first target digital image and the second target digital image according to the position coordinates of the first target digital image and the second target digital image if the target digital image is not more than 2, and calculating the magnitude relation and sum relation between natural values assigned to the first target digital image and the second target digital image; taking image features of the linear distance, the size relation, the sum value relation, the first target digital image and the second target digital image as the identification features;
A third type of recognition feature generation sub-module, configured to calculate a linear distance between any two of the first target digital image, the second target digital image and the third target digital image and an angle value formed by the linear distance and the three according to position coordinates of the first target digital image, the second target digital image and the third target digital image, and calculate a magnitude relationship and a sum value relationship between natural values assigned to the first target digital image, the second target digital image and the third target digital image if the target digital image is greater than 2 but not greater than 3; taking image features of a plurality of groups of linear distances, the angle values, the size relation, the sum value relation, the first target digital image, the second target digital image and the third target digital image as the identification features;
a fourth type of recognition feature generation sub-module, configured to calculate a magnitude relation and a sum relation between natural values assigned to each target digital image according to a linear distance between any two of the target digital images and a plurality of groups of angle values formed by adjacent three of the target digital images if the target digital images are greater than 3; and taking a plurality of groups of linear distances, a plurality of groups of angle values, the size relation, the sum value relation and the image characteristics of each target digital image as the identification characteristics.
7. A digital image file querying device, comprising a processor for implementing the steps of the digital image file querying method according to any one of claims 1 to 5 when executing a computer program stored in a memory.
8. A computer readable storage medium, wherein a digital image file querying program is stored on the computer readable storage medium, which when executed by a processor, implements the steps of the digital image file querying method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010396924.3A CN111563181B (en) | 2020-05-12 | 2020-05-12 | Digital image file query method, device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010396924.3A CN111563181B (en) | 2020-05-12 | 2020-05-12 | Digital image file query method, device and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111563181A CN111563181A (en) | 2020-08-21 |
| CN111563181B true CN111563181B (en) | 2023-05-05 |
Family
ID=72071962
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010396924.3A Active CN111563181B (en) | 2020-05-12 | 2020-05-12 | Digital image file query method, device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111563181B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117290560B (en) * | 2023-11-23 | 2024-02-23 | 支付宝(杭州)信息技术有限公司 | Method and device for acquiring graph data in graph calculation task |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6584223B1 (en) * | 1998-04-02 | 2003-06-24 | Canon Kabushiki Kaisha | Image search apparatus and method |
| CN101236561A (en) * | 2007-01-31 | 2008-08-06 | 株式会社理光 | Coding device, data searching and image processing device, data searching and image processing system, and data searching and image processing method |
| JP2011113197A (en) * | 2009-11-25 | 2011-06-09 | Kddi Corp | Method and system for image search |
| CN103744903A (en) * | 2013-12-25 | 2014-04-23 | 中国科学技术大学 | Sketch based scene image retrieval method |
| US8983941B1 (en) * | 2011-03-28 | 2015-03-17 | Google Inc. | Visual content retrieval |
| CN106202189A (en) * | 2016-06-27 | 2016-12-07 | 乐视控股（北京）有限公司 | A kind of image search method and device |
| CN109063197A (en) * | 2018-09-06 | 2018-12-21 | 徐庆 | Image search method, device, computer equipment and storage medium |
| CN110413740A (en) * | 2019-08-06 | 2019-11-05 | 百度在线网络技术（北京）有限公司 | Querying method, device, electronic equipment and the storage medium of chemical expression |
| CN110503124A (en) * | 2018-05-18 | 2019-11-26 | 奥多比公司 | Vision like numeral image is identified based on the perceptual property that user selects using based on deep neural network model |
-
2020
- 2020-05-12 CN CN202010396924.3A patent/CN111563181B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6584223B1 (en) * | 1998-04-02 | 2003-06-24 | Canon Kabushiki Kaisha | Image search apparatus and method |
| CN101236561A (en) * | 2007-01-31 | 2008-08-06 | 株式会社理光 | Coding device, data searching and image processing device, data searching and image processing system, and data searching and image processing method |
| JP2011113197A (en) * | 2009-11-25 | 2011-06-09 | Kddi Corp | Method and system for image search |
| US8983941B1 (en) * | 2011-03-28 | 2015-03-17 | Google Inc. | Visual content retrieval |
| CN103744903A (en) * | 2013-12-25 | 2014-04-23 | 中国科学技术大学 | Sketch based scene image retrieval method |
| CN106202189A (en) * | 2016-06-27 | 2016-12-07 | 乐视控股（北京）有限公司 | A kind of image search method and device |
| CN110503124A (en) * | 2018-05-18 | 2019-11-26 | 奥多比公司 | Vision like numeral image is identified based on the perceptual property that user selects using based on deep neural network model |
| CN109063197A (en) * | 2018-09-06 | 2018-12-21 | 徐庆 | Image search method, device, computer equipment and storage medium |
| CN110413740A (en) * | 2019-08-06 | 2019-11-05 | 百度在线网络技术（北京）有限公司 | Querying method, device, electronic equipment and the storage medium of chemical expression |
Non-Patent Citations (2)
| Title |
|---|
| Prototype-Based Image Search Reranking;Linjun Yang等;《IEEE Transactions on Multimedia》;20120213;全文 * |
| 基于草图的图像检索技术研究;郑凯夫;《中国优秀硕士学位论文全文数据库》;20190415;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111563181A (en) | 2020-08-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112434721B (en) | Image classification method, system, storage medium and terminal based on small sample learning | |
| KR102106462B1 (en) | Method for filtering similar problem based on weight | |
| CN109508681B (en) | Method and device for generating human body key point detection model | |
| US20230177821A1 (en) | Document image understanding | |
| CN101419612B (en) | Image processing device and image processing method | |
| AU2018202767B2 (en) | Data structure and algorithm for tag less search and svg retrieval | |
| JP5665125B2 (en) | Image processing method and image processing system | |
| CN111950056B (en) | BIM display method and related equipment for building informatization model | |
| JP2000311246A (en) | Similar image display method and recording medium storing similar image display processing program | |
| JP6880974B2 (en) | Information output program, information output method and information processing device | |
| CN111563181B (en) | Digital image file query method, device and readable storage medium | |
| RU2746152C2 (en) | Detection of a biological object | |
| CN111967478A (en) | Feature map reconstruction method and system based on weight inversion, storage medium and terminal | |
| Climer et al. | Local lines: A linear time line detector | |
| CN113297411B (en) | Method, device and equipment for measuring similarity of wheel-shaped atlas and storage medium | |
| CN114387608B (en) | Table structure identification method combining convolution and graph neural network | |
| CN114332599A (en) | Image recognition method, image recognition device, computer equipment, storage medium and product | |
| CN110309335B (en) | Picture matching method, device and equipment and storage medium | |
| CN103530406B (en) | Rotation image search method based on texture content | |
| Gao et al. | Detecting geometric conflicts for generalisation of polygonal maps | |
| GB2586226A (en) | Processing and storage of location data | |
| US11127158B2 (en) | Image indexing and retrieval using local image patches for object three-dimensional pose estimation | |
| CN114821568B (en) | Menu element extraction method and device, computer equipment and storage medium | |
| Pinho et al. | Voromap: A voronoi-based tool for visual exploration of multi-dimensional data | |
| Wang et al. | Sampling strategies for 3D partial shape matching and retrieval using bag-of-words model |
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 |