CN111241313A

CN111241313A - Retrieval method and device supporting image input

Info

Publication number: CN111241313A
Application number: CN202010011390.8A
Authority: CN
Inventors: 郑红
Original assignee: Individual
Current assignee: Individual
Priority date: 2020-01-06
Filing date: 2020-01-06
Publication date: 2020-06-05

Abstract

The application discloses a retrieval method and a retrieval device supporting image input, wherein the method comprises the following steps: acquiring a keyword; searching on the Internet by using search terms, wherein the search terms comprise: keywords and pictures; acquiring an image in the webpage from the retrieved webpage; acquiring a source code of a webpage, and searching for the text description of an image in a label corresponding to the image in the source code; and establishing a character index of the image at least according to the character description, and correspondingly storing the image and the character index in a database. The method and the device solve the problem of low processing efficiency caused by the fact that the pictures for comparison in the picture index library need to be manually preset with the character indexes in the related art, and improve the efficiency of storing the pictures and the character indexes in the picture index library.

Description

Retrieval method and device supporting image input

Technical Field

The application relates to the field of software, in particular to a retrieval method and a retrieval device supporting image input.

Background

Data information of images on the internet is becoming huge, and the requirements of users on searching images on the internet are increasing continuously, so that various image search engines based on Web are produced. The advent of image search engines has made searching for image information on the web very simple for users, and some of the needs of users have been satisfied, although not perfectly.

One of the image search engines is semantic-based search, which needs to establish index information for images, perform image analysis and discrimination, annotate images, and establish an index library for storing extracted index information.

This way of retrieval can be understood as a semantic level of matching. Therefore, the content of the image (such as the object, the background, the composition, the color feature, etc.) needs to be described and classified in advance manually, and a descriptor is given. Thus, a more robust index library can be established. When searching, the user input search word is mainly searched in the descriptors. The query mode is accurate, and generally, better precision rate can be obtained.

However, the use of this method requires a great number of pictures to be described in advance, which takes a lot of labor. Therefore, the number of images that can be processed is limited, thereby restricting the retrieval accuracy of the images.

Disclosure of Invention

The application provides a retrieval method and a retrieval device supporting image input, which aim to solve the problem of low processing efficiency caused by the fact that pictures for comparison in a picture index library in the related art need to be manually preset with character indexes.

According to one aspect of the application, a retrieval method supporting image entry is provided, and comprises the following steps: acquiring a keyword, wherein the keyword is used for indicating the type of a picture to be collected; searching on the Internet by using search terms, wherein the search terms comprise: the keyword and the picture, wherein the 'picture' is used as a search word for searching; acquiring an image in the webpage from the retrieved webpage; acquiring a source code of the webpage, and searching a text description of the image in a label corresponding to the image in the source code; and establishing a text index of the image at least according to the text description, and correspondingly storing the image and the text index in a database.

Further, a pre-configured keyword list is obtained, wherein the list comprises a plurality of keywords;

the steps of the above method are performed in sequence for each keyword in the keyword list.

Further, establishing a text index of the image according to at least the text description comprises: and taking the text description as a text index of the image.

Further, the label is an IMG label, and the textual description is recorded in an ALT attribute in the IMG label.

According to another aspect of the present application, there is also provided a retrieval apparatus supporting image entry, including: the device comprises a first acquisition module, a second acquisition module and a display module, wherein the first acquisition module is used for acquiring a keyword, and the keyword is used for indicating the type of a picture to be collected; the system comprises a retrieval module, a search module and a search module, wherein the retrieval module is used for retrieving on the Internet by using a retrieval word, and the retrieval word comprises: the keyword and the picture, wherein the 'picture' is used as a search word for searching; the second acquisition module is used for acquiring the image in the webpage from the retrieved webpage; a third obtaining module, configured to obtain a source code of the web page, and search for a text description of the image in a tag corresponding to the image in the source code; and the establishing module is used for establishing a character index of the image at least according to the character description and correspondingly storing the image and the character index in a database.

Further, the first obtaining module is configured to obtain a pre-configured keyword list, and sequentially obtain each keyword from the keyword list.

Further, the establishing module is configured to: and taking the text description as a text index of the image.

According to another aspect of the present application, there is also provided a memory for storing software for performing the above method.

According to another aspect of the present application, there is also provided a processor for executing software, wherein the software is configured to perform the above method.

The method comprises the following steps: acquiring a keyword, wherein the keyword is used for indicating the type of a picture to be collected; searching on the Internet by using search terms, wherein the search terms comprise: the keyword and the picture, wherein the 'picture' is used as a search word for searching; acquiring an image in the webpage from the retrieved webpage; acquiring a source code of the webpage, and searching a text description of the image in a label corresponding to the image in the source code; and establishing a text index of the image at least according to the text description, and correspondingly storing the image and the text index in a database. The method and the device solve the problem of low processing efficiency caused by the fact that the pictures for comparison in the picture index library need to be manually preset with the character indexes in the related art, and improve the efficiency of storing the pictures and the character indexes in the picture index library.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application. In the drawings:

fig. 1 is a flowchart of a retrieval method supporting image entry according to an embodiment of the present application.

Detailed Description

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.

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.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

In the present embodiment, a retrieval method supporting image entry is provided, and fig. 1 is a flowchart of a retrieval method supporting image entry according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:

step S102, obtaining keywords, wherein the keywords are used for indicating the type of the picture to be collected;

step S104, using the search term to search on the Internet, wherein the search term comprises: the method comprises the following steps of (1) keywords and pictures, wherein the 'picture' is used as a search word for searching;

for example, if flowers are used as keywords, then when searching on the internet: flowers and pictures, these two words are used as key words to search.

Step S106, acquiring images in the web pages from the retrieved web pages;

step S108, acquiring a source code of the webpage, and searching for the text description of the image in the label corresponding to the image in the source code;

the following optional embodiments can be added in implementation: in addition to using the content in the label in the image as the text description of the image, additional text descriptions can be added, because: the more textual descriptions the more convenient the use of the created image database. The additional textual description added may be: after finding out the image file, the image file is associated with the file name or directory name of the image, the path name, the link and the text information around the image as character description.

Step S110, at least establishing a character index of the image according to the character description, and correspondingly storing the image and the character index in a database.

The following embodiment can be added when in implementation, and the modification is carried out by human after the modification is stored in the database. The source website of the picture, e.g. from website a, may also be recorded in the database. If the content of manual modification is less, the source address of the image is obtained, and the picture in the source address is preferentially searched in the next picture processing.

Optionally, in implementation, two text descriptions may be recorded in the database, one is automatically generated through the above steps, and the other is manually corrected. At this time, the manually corrected word description and the manually corrected preceding word description may be compared by using a program, the ratio of correction is counted according to the website of the image source, and if the ratio is lower than a threshold, the image is preferentially retrieved from the website next time.

The following embodiments can be added in the implementation: a machine learning model may be trained, the model being trained using a plurality of sets of training data, wherein each set of training data includes: the character description is automatically acquired when the model is input after training, and the character description is output after correction, so that manual correction can be changed into automatic correction, and the efficiency is further improved.

The method and the device solve the problem of low processing efficiency caused by the fact that the pictures for comparison in the picture index library need to be manually preset with the character indexes in the related art, and improve the efficiency of storing the pictures and the character indexes in the picture index library.

Optionally, a pre-configured keyword list is obtained, wherein the list comprises a plurality of keywords; the steps of the above method are performed in sequence for each keyword in the keyword list. For example, if a database needs to collect multiple types of pictures, the following keywords may be added to the keyword list: animal, plant, advertisement, sport. Then, the above steps S102 to S110 are sequentially performed on the keywords.

Optionally, the creating a text index of the image according to at least the text description comprises: the text description itself is used as a text index for the image.

The following optional embodiments can be added in implementation: the word description and/or external information such as a file name or a directory name of the image, a path name, a link, text information around the image and the like can be segmented, each segmented word is used as a word description label, and thus one picture corresponds to a plurality of word description labels.

The segmentation may be a statistical-based segmentation, as explained below.

The word segmentation method based on statistics is to use a statistical machine learning segmentation model to learn the rules of word segmentation (called training) on the premise of giving a large amount of already segmented texts, thereby realizing the segmentation of unknown texts. Such as a maximum probability word segmentation method, a maximum entropy word segmentation method, and the like. With the establishment of large-scale corpora and the research and development of statistical machine learning methods, the statistical-based Chinese word segmentation method becomes more and more accurate.

The main statistical models are: n-gram (N-gram), Hidden Markov Model (HMM), maximum entropy Model (ME), Conditional Random field model (CRF), etc. In practical application, the word segmentation system based on statistics needs to use a word segmentation dictionary to perform character string matching word segmentation, and meanwhile, a statistical method is used for identifying some new words, namely, the frequency statistics of character strings and the character string matching are combined, so that the characteristics of high matching word segmentation speed and high efficiency are exerted, and the advantages of dictionary-free word segmentation combined with context recognition of new words and automatic ambiguity elimination are utilized.

Optionally, the tag is an IMG tag, and the textual description is recorded in an ALT attribute in the IMG tag.

For example, the presence of displayable image files can be detected by two HTML tags, IMG SRC and HREF, IMG SRC denoting "display underlying image files" and HREF denoting "underlying a link", both tags often leading to an image file. The search engine determines whether the link is an image file by checking the file extension. If the file extension is GIF or JPG, it is a displayable image.

One general IMG tag attribute is as follows:

< img src ═ i/eg _ tulip. jpg "alt ═ Shanghai hong-Tulip"/>, a seafood hong Kong-Tulip >

In this IMG tag, ALT indicates that if the browser cannot display the image, the caption is displayed in the original display position: "Shanghai Huagang-Tulip".

In this embodiment, an apparatus is further provided, where modules in the apparatus correspond to the steps of the method described above, which have already been described in the above embodiments and are not described herein again.

In this embodiment, there is also provided a retrieval apparatus supporting image entry, including: the device comprises a first acquisition module, a second acquisition module and a display module, wherein the first acquisition module is used for acquiring a keyword, and the keyword is used for indicating the type of a picture to be collected; the retrieval module is used for retrieving on the Internet by using retrieval words, wherein the retrieval words comprise: the method comprises the following steps of (1) keywords and pictures, wherein the 'picture' is used as a search word for searching; the second acquisition module is used for acquiring the image in the webpage from the retrieved webpage; the third acquisition module is used for acquiring a source code of the webpage and searching the text description of the image in the label corresponding to the image in the source code; and the establishing module is used for establishing a character index of the image at least according to the character description and correspondingly storing the image and the character index in a database.

Optionally, the first obtaining module is configured to obtain a pre-configured keyword list, and sequentially obtain each keyword from the keyword list.

Optionally, the establishing module is configured to: the text description itself is used as a text index for the image.

In this embodiment, a memory is provided for storing software for performing the above-described method.

In this embodiment, a processor is provided for executing software for performing the above-described method.

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.

An embodiment of the present invention provides a storage medium on which a program or software is stored, the program implementing the above method when executed by a processor. The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.

The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A retrieval method supporting image entry, comprising:

acquiring a keyword, wherein the keyword is used for indicating the type of a picture to be collected;

searching on the Internet by using search terms, wherein the search terms comprise: the keyword and the picture, wherein the picture is used as a retrieval word for retrieval;

acquiring an image in the webpage from the retrieved webpage;

acquiring a source code of the webpage, and searching a text description of the image in a label corresponding to the image in the source code;

and establishing a text index of the image at least according to the text description, and correspondingly storing the image and the text index in a database.

2. The method of claim 1,

acquiring a pre-configured keyword list, wherein the list comprises a plurality of keywords;

the steps in the method of claim 1 are performed in turn for each keyword in the keyword list.

3. The method of claim 1, wherein building a textual index of the image based at least on the textual description comprises:

and taking the text description as a text index of the image.

4. The method according to any one of claims 1 to 3,

the label is an IMG label, and the text description is recorded in an ALT attribute in the IMG label.

5. A retrieval apparatus supporting image entry, comprising:

the device comprises a first acquisition module, a second acquisition module and a display module, wherein the first acquisition module is used for acquiring a keyword, and the keyword is used for indicating the type of a picture to be collected;

the system comprises a retrieval module, a search module and a search module, wherein the retrieval module is used for retrieving on the Internet by using a retrieval word, and the retrieval word comprises: the keyword and the picture, wherein the picture is used as a retrieval word for retrieval;

the second acquisition module is used for acquiring the image in the webpage from the retrieved webpage;

a third obtaining module, configured to obtain a source code of the web page, and search for a text description of the image in a tag corresponding to the image in the source code;

and the establishing module is used for establishing a character index of the image at least according to the character description and correspondingly storing the image and the character index in a database.

6. The apparatus of claim 5, wherein the first obtaining module is configured to obtain a pre-configured keyword list, and obtain each keyword from the keyword list in turn.

7. The apparatus of claim 5, wherein the establishing module is configured to:

and taking the text description as a text index of the image.

8. The apparatus according to any one of claims 5 to 7,

9. A memory for storing software, wherein the software is configured to perform the method of any one of claims 1 to 4.

10. A processor configured to execute software, wherein the software is configured to perform the method of any one of claims 1 to 4.