CN109408652B - Picture searching method, device and equipment - Google Patents

Abstract

The invention discloses a picture searching method, a picture searching device and picture searching equipment, which are applied to the field of image processing, wherein the method comprises the following steps: obtaining first content carried by a first picture element in a picture to be searched, wherein the first content is formed by replacing original image content of the first picture element in the picture to be searched, and the first content is used for representing picture description information corresponding to the picture to be searched; obtaining target picture description information corresponding to the picture to be searched according to the first content; and searching the picture according to the target picture description information to obtain a picture searching result. The invention improves the accuracy and efficiency of picture searching.

Description

Picture searching method, device and equipment

Technical Field

The present invention relates to the field of image search, and in particular, to a method, an apparatus, and a device for searching an image.

Background

The picture search is a service for providing relevant picture data to users through a search program, and aims to find out pictures needed by the users. Currently, technical means related to picture search include: the picture search is performed based on the characters provided by the user, or the picture search may be performed based on the pictures provided by the user.

If the image search is performed based on the image input by the user, the prior art scheme can only perform similarity matching between the image provided by the user and each image in the image library, so that the image similar to the image provided by the user is searched. However, the similarity calculation process and the image preprocessing have strict requirements, and the images provided by the user need to be subjected to similarity matching with each image in the gallery one by one, so that the calculation amount is large, and the image search efficiency is low.

The image search is performed based on the characters provided by the user, and the prior art scheme is to perform the image search based on the context content of the document where the image is located, or perform the image search based on the file name of the image. Therefore, when the file name of the picture is not related to the picture itself, or the picture does not match the context content of the document in which the picture is located, the picture search result is inaccurate.

Therefore, the search result obtained by the conventional picture search method is not high in accuracy and search efficiency.

Disclosure of Invention

The embodiment of the invention provides a picture searching method, a picture searching device and picture searching equipment, and solves the technical problems of low picture searching efficiency and low picture searching accuracy.

In a first aspect, an embodiment of the present invention provides an image searching method, including:

obtaining first content carried by a first picture element in a picture to be searched, wherein the first content is formed by replacing original image content of the first picture element in the picture to be searched, and the first content is used for representing picture description information corresponding to the picture to be searched;

obtaining target picture description information corresponding to the picture to be searched according to the first content;

and searching the picture according to the target picture description information to obtain a picture searching result.

Optionally, the method further includes:

and determining whether the picture to be searched comprises a first picture element carrying the first content, if so, executing the obtaining of the first content carried by the first picture element in the picture to be searched.

Optionally, the method further includes:

the method comprises the steps of processing a picture in advance, replacing original image content of a first picture element in the picture with the first content, wherein the first picture element is a specific image area or a specific pixel point included in the picture.

Optionally, the replacing the original image content of the first picture element in the picture with the first content includes:

selecting a specific pixel point outside the main image region of the picture as the first picture element, and replacing an original color coding sequence in the first picture element with a color coding sequence corresponding to the first content;

and/or the presence of a gas in the gas,

selecting a specific image area outside the main image area of the picture as the first picture element, and adding a graphic coding sequence corresponding to the first content in the first picture element;

and/or the presence of a gas in the gas,

selecting specific pixel points less than a preset number threshold value in a main image area of the picture as the first picture element, and replacing an original color coding sequence in the first picture element with a color coding sequence corresponding to the first content;

and/or the presence of a gas in the gas,

and selecting a first number of outer boundary pixel points in the picture as the first picture element, and replacing the original color coding sequence of the first picture element with the color coding sequence corresponding to the first content.

Optionally, the method further includes:

setting position indication information for the picture, wherein the position indication information is used for indicating the position of the first picture element in the picture.

Optionally, the obtaining the first content carried by the first picture element in the picture to be searched includes:

obtaining position indication information carried by the picture to be searched, wherein the position indication information is used for indicating the position of the first picture element in the picture to be searched;

determining the first picture element from the picture to be searched according to the position indication information;

and extracting first content carried in the first picture element.

Optionally, the setting of the position indication information for the picture includes:

setting a first delimiter encoding value on a first side of the first picture element in the picture and a second delimiter encoding value on a second side of the first picture element, wherein the first delimiter encoding value and the second delimiter encoding value are used as position indication information corresponding to the picture;

and/or the presence of a gas in the gas,

setting position indication information for the picture; the position indication information includes: presetting a starting point position identifier and a quantity parameter; the starting position identifier is used for identifying a starting pixel point of the first picture element, and the quantity parameter is used for identifying the number of pixel points occupied by the first picture element;

and/or the presence of a gas in the gas,

setting position indication information for the picture; the position indication information includes: and the first jumping pixel points and the second jumping pixel points in the picture outer boundary area.

Optionally, the method further includes: presetting and storing a mapping relation between the first content and the picture description information; comprises the following steps of;

setting and storing a mapping relation between a graphic coding sequence of a specific image area in a picture and picture description information;

and/or the presence of a gas in the gas,

and setting and storing the mapping relation between the color coding sequence of the specific pixel point of the picture and the picture description information.

In a second aspect, an embodiment of the present invention provides an image searching apparatus, including:

the content obtaining unit is used for obtaining first content carried by a first picture element in a picture to be searched, wherein the first content is formed by replacing original image content of the first picture element in the picture to be searched, and the first content is used for representing picture description information corresponding to the picture to be searched;

the description information obtaining unit is used for obtaining the description information of the target picture corresponding to the picture to be searched according to the first content;

and the picture searching unit is used for searching pictures according to the target picture description information to obtain a picture searching result.

Optionally, the apparatus further comprises:

and the element distinguishing unit is used for determining whether the picture to be searched comprises a first picture element carrying the first content, and if so, executing the acquisition of the first content carried by the first picture element in the picture to be searched.

Optionally, the apparatus further comprises:

the image processing unit is used for processing an image in advance, replacing original image content of a first picture element in the image with the first content, wherein the first picture element is a specific image area or a specific pixel point included in the image.

Optionally, the picture processing unit includes:

a first element selection subunit, configured to select a specific pixel point outside the main image region of the picture as the first picture element, and replace an original color coding sequence in the first picture element with a color coding sequence corresponding to the first content;

and/or the presence of a gas in the gas,

a second element selection subunit, configured to select a specific image region outside the main image region of the picture as the first picture element, and add a graphics coding sequence corresponding to the first content to the first picture element;

and/or the presence of a gas in the gas,

a third element selecting unit, configured to select, as the first picture element, a specific pixel point less than a preset number threshold in a main image region of the picture, and replace an original color coding sequence in the first picture element with a color coding sequence corresponding to the first content;

and/or the presence of a gas in the gas,

and the fourth element selection subunit is used for selecting a first number of outer boundary pixel points in the picture as the first picture element and replacing the original color coding sequence of the first picture element with the color coding sequence corresponding to the first content.

Optionally, the apparatus further comprises:

a position indication setting unit, configured to set position indication information for the picture, where the position indication information is used to indicate a position of the first picture element in the picture.

Optionally, the content obtaining unit includes:

the information obtaining subunit is configured to obtain position indication information carried by the picture to be searched, where the position indication information is used to indicate a position of the first picture element in the picture to be searched;

an element determining subunit, configured to determine, according to the position indication information, the first picture element from the picture to be searched;

and the content extraction subunit is used for extracting the first content carried in the first picture element.

Optionally, the position indication setting unit includes:

a delimiter setting subunit, configured to set a first delimiter encoding value on a first side of the first picture element in the picture and a second delimiter encoding value on a second side of the first picture element, and use the first delimiter encoding value and the second delimiter encoding value as position indication information corresponding to the picture;

and/or the presence of a gas in the gas,

the identification setting subunit is used for setting position indication information for the picture; the position indication information includes: presetting a starting point position identifier and a quantity parameter; the starting position identifier is used for identifying a starting pixel point of the first picture element, and the quantity parameter is used for identifying the number of pixel points occupied by the first picture element;

and/or the presence of a gas in the gas,

a jumping point determining subunit, configured to set position indication information for the picture; the position indication information includes: and the first jumping pixel points and the second jumping pixel points in the picture outer boundary area.

Optionally, the apparatus further comprises: the mapping unit is used for presetting and storing the mapping relation between the first content and the picture description information;

the mapping unit includes:

the first setting subunit is used for setting and storing the mapping relation between the graphic coding sequence of the specific image area in the picture and the picture description information;

and/or the presence of a gas in the gas,

and the second setting subunit is used for setting the mapping relationship between the color coding sequence of the specific pixel point of the picture and the picture description information and storing the mapping relationship.

In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps described in any possible implementation manner of the first aspect.

In a fourth aspect, an embodiment of the present invention provides a picture search apparatus, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps described in any possible implementation manner of the first aspect when executing the program.

One or more technical solutions provided by the embodiments of the present invention at least achieve the following technical effects or advantages:

the method and the device can obtain first content contained in a first picture element in the picture to be searched, and obtain target picture description information corresponding to the picture to be searched according to the first content; and then searching the picture according to the target picture description information. Therefore, when the picture is actually searched, the target picture description information is determined according to the first content, the picture is searched according to the target picture description information, image recognition is not needed to be carried out on the picture to be searched, the calculated amount during the picture searching can be reduced, and the picture searching efficiency is improved. Moreover, the picture searching is carried out according to the target picture description information, and the picture similarity calculation required by picture searching is avoided, so that the picture searching accuracy is improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

Fig. 1 is a schematic flowchart of a picture searching method according to an embodiment of the present invention;

FIG. 2 is a schematic diagram illustrating a position relationship between a color code sequence and first and second delimiter code values according to an embodiment of the present invention;

FIG. 3 is a diagram illustrating location indications for location markers in an embodiment of the present invention;

FIG. 4a is a diagram illustrating a searched picture according to an embodiment of the present invention;

FIG. 4b is an enlarged view of the portion of FIG. 4a where the description information is located;

FIG. 5 is a diagram illustrating an image search apparatus according to an embodiment of the present invention;

fig. 6 is a schematic diagram of a picture searching apparatus according to an embodiment of the present invention;

fig. 7 is a schematic structural diagram of a server in an embodiment of the present invention.

Detailed Description

The invention provides a picture searching method, a picture searching device and picture searching equipment, which aim to solve the technical problems of low picture searching efficiency and low picture searching accuracy, and have the following general idea:

obtaining first content contained in a first picture element in a picture to be searched, wherein the first content is formed by replacing original image content in the first picture element and is used for representing picture description information corresponding to the picture to be searched; according to the first content, obtaining target picture description information corresponding to the first content; and searching the picture according to the target picture description information to obtain a picture searching result.

By the technical scheme, when the picture is actually searched, the target picture description information corresponding to the picture to be searched is determined only according to the first content carried by the picture to be searched, and then the picture is searched according to the target picture description information. Therefore, the image identification of the picture to be searched is avoided, the calculated amount during picture searching can be reduced, and the picture searching efficiency is improved. Moreover, the picture searching is carried out according to the picture description information, the picture similarity calculation required by picture searching is avoided, and the picture searching accuracy is improved.

The image searching method provided by the embodiment of the invention can be applied to user equipment, local searching based on the user equipment can be realized, and the user equipment can also be a smart phone, a tablet computer, a computer and the like. The method can also be applied to a search engine server which is established with user equipment and has data interaction, and network search based on a search engine is realized.

Referring to fig. 1, fig. 1 is a schematic flow chart of a picture searching method according to an embodiment of the present invention, where the picture searching method according to the embodiment of the present invention includes the following steps:

step S101: the method comprises the steps of obtaining first content carried by a first picture element in a picture to be searched, wherein the first content is formed by replacing original image content of the first picture element in the picture to be searched, and the first content is used for representing picture description information corresponding to the picture to be searched.

The picture description information is a text describing the picture to be searched, and specifically, may be a description of image content presented in the picture to be searched. For example, if the picture to be searched shows the Qinghai lake, the picture description information is the text "Qinghai lake"; or may be a description of picture attribute information of a picture to be searched. Such as, the photographing time, the photographing author, the source of the picture, etc., and the type of the picture description information may be one of a single character, a single word, a single phrase, and a single sentence.

In this embodiment, the first picture element may be a specific image region or a specific pixel point in the picture to be searched. In the embodiment of the application, a first content is set for a picture in advance, and the first content can represent picture description information of the picture; specifically, original image content in a first picture element included in the picture may be replaced with the first content, that is, original image content of a specific image area or a specific pixel included in the picture is replaced with the first content; therefore, in the process of executing the picture search, the picture description information corresponding to the picture can be determined according to the first content included in the picture, so as to determine whether the picture meets the current search requirement.

Before step S101, the method may further include: determining whether the picture to be searched comprises a first picture element carrying first content, if so, executing the step S101 to obtain the first content carried by the first picture element in the picture to be searched; if not, the searching operation of the picture is realized by adopting a conventional picture searching method.

Further, in this embodiment, the method may further include: the method includes the steps of processing pictures included in a picture library in advance, and setting first content for the pictures, wherein the first content can represent picture description information corresponding to the pictures.

As can be seen from the foregoing, original image content in a first picture element included in the picture may be replaced with the first content. Specifically, the original image content of a specific image region or a specific pixel included in the picture may be replaced with the first content.

Since the first content does not belong to the original image content in the picture, the replaced first content may reduce the picture quality of the picture. In order to reduce the effect of the first content on the picture quality, the following method may be adopted: the first content is located outside or implicit in the main image area of the picture so that the first content does not obscure important image content of the picture.

In an embodiment of the present specification, the following method is provided to implement that the first content is located outside the main image region of the picture:

the first method is as follows: selecting a specific pixel point outside a main image area of a picture as a first picture element, and replacing an original color coding sequence in the first picture element with a color coding sequence corresponding to the first content. Specifically, the specific pixel point is one or more than one pixel point outside the main image area.

The corresponding step S101 is specifically: and extracting a color coding sequence included by a specific pixel point in the picture to be searched, wherein the color coding sequence is the first content used for expressing the picture description information corresponding to the picture.

It should be noted that a pixel contains a set of color-coded values for forming the color of the pixel. The specific pixel point may be one or more pixel points outside the main image area of the picture, or one or more pixel points in the main image area, thereby reducing adverse effects of the first content on the picture quality. If the number of the pixel points of the specific pixel points is less than the preset number, even if the specific pixel points are in the main image area, the specific pixel points are not easy to be found visually, and therefore the effect that the color coding sequence is hidden in the main image area is achieved.

In a specific implementation process, the color coding sequence used for representing the picture description information corresponding to the picture may be an RGB (red green blue, red green blue light mode) coding sequence. The color coding sequence can also be in other color modes, such as Lab coding sequence, CMYK (Cyan Magenta Yellow Key printing color mode) coding sequence, HSB (hue preservation brightness) coding sequence.

The second method comprises the following steps: selecting a specific image area outside a main image area of a picture as a first picture element, and adding a graphic coding sequence corresponding to the first content in the first picture element.

The corresponding step S101 is specifically: and extracting a graphic coding sequence included in a specific image area in the picture to be searched, wherein the graphic coding sequence is first content used for representing picture description information corresponding to the picture.

It should be noted that the graphic coding sequence is a visual symbol which takes a graphic symbol as a main feature and is used for representing the picture description information corresponding to the picture, and specifically, the graphic coding sequence is formed by one or more graphic symbols. The specific image area may be located outside the main image area, thereby reducing an adverse effect of the first content on the picture quality.

In the embodiment of the present specification, the following method is provided to implement that the first content is hidden in the main image area of the picture:

selecting specific pixel points less than a preset number threshold value in a main image area of a picture as first picture elements, and replacing original color coding sequences in the first picture elements with color coding sequences corresponding to the first content.

It should be noted that the main image area in the embodiment of the present invention refers to a central image area of a picture or an image area in which a specific object exists. The specific object may be a person, an animal, a building, a plant, or the like.

In the embodiment, only specific pixel points less than the preset number threshold value in the main image region of the picture are replaced, so that the first content only occupies a few pixel points in the main image region of the picture, and a user cannot feel the change of the color coding value in the few pixel points from the visual angle, and therefore, the replaced first content is hidden in the main image region visually, and the picture quality cannot be damaged.

The corresponding step S101 is specifically: and extracting a color coding sequence included by a specific pixel point in the picture to be searched, wherein the color coding sequence is the first content used for representing the picture description information corresponding to the picture.

In order to further avoid the adverse effect of the first content on the picture quality, a first number of outer boundary pixel points in the picture can be selected as first picture elements, and the original color coding sequence of the first picture elements is replaced by the color coding sequence corresponding to the first content. Specifically, N outer boundary pixel points in the picture may be selected as the first picture element, where N is an integer greater than 1, that is: and replacing the original color coding sequences of the N outer boundary pixel points in the picture by the color coding sequences used for representing the picture description information corresponding to the picture. Wherein, the outer boundary pixel point means that at least one side has no other pixel point and the adjacent pixel point. The outer boundary pixel points of the picture are occupied by the first content obtained by adopting the mode, and for the whole picture, the first content is not easy to be visually perceived, so that the influence on the picture quality of the picture is further reduced.

In order to reduce the influence range of the first content on the picture quality, the embodiment of the present invention further includes the following steps: determining the number of replaceable pixel points in a picture, and judging whether the number of color coding values used for expressing picture description information corresponding to the picture is larger than the number of the replaceable pixel points; and if not, writing the color coding sequence for representing the picture description information corresponding to the picture into the picture.

In a specific implementation process, there may be a plurality of implementation manners for determining the number of replaceable pixels in the picture, which are described below:

the first method is as follows: and acquiring the total number of pixel points in the picture, and determining the product result of the total number of the pixel points and the preset proportion value as the number of replaceable pixel points in the picture.

Specifically, the picture size can be obtained from the picture details of the picture, and the total number of pixel points in the picture is calculated according to the picture size. For example, if the picture size of the picture is 2084 × 1536, the total number of pixels in the picture is 3201024(2084 × 1536). Specifically, the preset proportion value can be matched with the size of an image in the picture, and the larger the image size is, the more the pixel points are, and the larger the corresponding preset proportion value is. The preset proportion value may also be a fixed value independent of the image size of the picture, for example, the preset proportion value may be set to a fixed value in the range of 0.1% to 5%.

The second method comprises the following steps: and determining the total number of the outer boundary pixel points in the picture as the number of the replaceable pixel points in the picture.

And obtaining the picture size of the picture from the picture details of the picture, and calculating the total number of the outer boundary pixel points of the picture according to the picture size. For example, if the picture size of the picture is 2084 × 1536, the total number of outer-boundary pixels 3620 of the picture is (2084+ 1536).

In addition, it should be noted that, in the color code sequence used for representing the picture description information corresponding to the picture, taking the example that the color code value in the color code sequence is an RGB value, the value is taken within the range of [0, 255] according to the difference of the specific content in the picture description information represented by the color code value.

In a specific implementation process, the first content for replacing the original image content in the first picture element may be determined based on a preset mapping relationship between the picture description information corresponding to the picture and the first content.

By the technical scheme, the pictures in the picture library can comprise the first picture element carrying the first content, and in the process of executing the picture search, the picture description information corresponding to the pictures can be determined according to the first content included in the identified pictures, so that whether the pictures meet the current search requirement or not is determined.

Next, the execution process of step S101 is described with reference to different application scenarios:

if the scene is searched based on the network of the search engine, the search engine receives the picture to be searched from the user equipment. Specifically, the picture to be searched can be imported from a local gallery of the user equipment into a search input box provided by a search engine; the picture to be searched can also be one selected from a plurality of pictures presented by the current webpage and imported into a search input box provided by a search engine; the picture to be searched imported into the search input box is reported to a search engine, and the search engine executes step S101, so that the search engine obtains first content contained in a first picture element in the picture to be searched. It should be noted that, the search engine may first determine whether the picture to be searched includes a first picture element carrying first content, and if so, execute step S101 to obtain the first content contained in the first picture element in the picture to be searched; if not, the searching operation of the picture is realized by adopting a conventional picture searching method.

If the local search is based on the user equipment, a local search input box can be arranged on the user equipment, or a search input box is arranged on an application program interface corresponding to the local gallery. The picture to be searched can be obtained by the user equipment from a local gallery, can also be received by the user equipment from opposite-end user equipment, can also be from a storage space different from the local gallery in the user equipment, and can also be a picture currently shot by the user equipment. On this basis, step S101 is performed by the user equipment, so that the user equipment obtains the first content contained in the first picture element in the picture to be searched. It should be noted that the user equipment may first determine whether the picture to be searched includes a first picture element carrying first content, and if so, execute step S101 to obtain the first content included in the first picture element in the picture to be searched; if not, the searching operation of the picture is realized by adopting a conventional picture searching method. In an optional implementation manner, in step S101, in order to accurately identify the first content included in the first picture element, so as to avoid erroneously identifying the content in the other picture elements as the first content, the picture to be searched may carry position indication information, where the position indication information is used to indicate a position of the first picture element in the picture to be searched.

Based on this, step S101 may specifically include the following steps S1011 to S1013:

s1011, obtaining position indication information carried by the picture to be searched, wherein the position indication information is used for indicating the position of the first picture element in the picture to be searched.

S1012, determining the first picture element from the picture to be searched according to the position indication information;

and S1013, extracting the first content carried in the first picture element.

The method according to the embodiment of the present application, when the pictures included in the picture library are processed in advance and the first content is set for the pictures, the method may further include: setting position indication information for a picture in which the first content is set, the position indication information indicating a position of the first picture element in the picture.

Specifically, indication information may be set for the picture in which the first content is set in the picture attribute information of the picture, or position indication information may be set for the picture in which the first content is set in the image area of the picture.

In order to set the picture of the first content, the setting of the position indication information in the image area may include the following various ways:

in a first manner, a first delimiter coding value is set on a first side of a first picture element in the picture, and a second delimiter coding value is set on a second side of the first picture element, so that the first delimiter coding value and the second delimiter coding value are position indication information corresponding to the picture.

Then, in step S1012, determining a first picture element from the picture to be searched according to the position indication information, which may specifically include: analyzing the picture to be searched, and determining the position of the first delimiter code value and the position of the second delimiter code value from the picture to be searched; and determining pixel points included between the position of the first delimiter encoding value and the position of the second delimiter encoding value as the first picture elements.

Specifically, the first delimiter encoding value and the second delimiter encoding value are: and after the original image content in the first picture element is replaced by the first content, correspondingly adding the first content to the first side and the second side of the first picture element, and indicating the position of the first picture element in the picture.

Wherein the first side and the second side are correspondingly located on opposite sides of the first picture element. Such as: the first side is adjacent to a first pixel point of the first picture element in the clockwise direction, and the second side is adjacent to a last pixel point of the first picture element in the clockwise direction. Or the reverse, namely: the first side is adjacent to the last pixel point of the first picture element in the clockwise direction, and the second side is adjacent to the first pixel point of the first picture element in the clockwise direction.

By setting the first delimiter encoding value and the second delimiter encoding value, when step S1012 is implemented, the position of the first picture element can be accurately determined according to the first delimiter encoding value and the second delimiter encoding value, and the first content in the first picture element can be accurately identified.

In a specific implementation process, when the first picture element is N outer-boundary pixel points on the picture, the first delimiter encoding value may be: color coding values in one or more outer boundary pixel points located before the N outer boundary pixel points along the clockwise direction; the second delimiter encoding value may be: and the color coding values in one or more than one outer-boundary pixel points behind the N outer-boundary pixel points along the clockwise direction.

Next, referring to the example shown in fig. 2, the first picture element is N outer-boundary pixels in the picture to be searched, and the first delimiter encoding value is a color encoding value among 5 outer-boundary pixels located before the N outer-boundary pixels in the clockwise direction; the second delimiter encoding value is a color encoding value located in 5 outer boundary pixel points behind the N outer boundary pixel points in the clockwise direction.

It should be noted that, in the embodiment of the present specification, the first delimiter encoding value and the second delimiter encoding value do not establish a mapping relationship with any picture description information, so that the first delimiter encoding value and the second delimiter encoding value are not mistakenly identified as the picture description information.

Specifically, the first delimiter code value and the second delimiter code value may be the same color code value, for example, they may be the same: {0,0,0}, or both {255, 255, 255 }. The first delimiter encoding value and the second delimiter encoding value may also be different color encoding values. For example, the first delimiter code value is {0,0,0} and the second delimiter code value is {255, 255, 255 }. Of course, the first delimiter encoding value and the second delimiter encoding value may also be set to other color encoding values with certain rules according to actual needs.

In a second mode, position indication information is set for the picture, and the position indication information includes: presetting a starting point position identifier and a quantity parameter; the starting point position identification is used for identifying a starting pixel point of the first picture element, and the quantity parameter is used for identifying the number of pixel points occupied by the first picture element.

Then, in step S1012, determining a first picture element from the picture to be searched according to the position indication information may specifically include: analyzing the picture to be searched, and determining the position indicated by the starting point position identification from the picture to be searched; and sequentially determining the number of the pixel points corresponding to the quantity parameter by taking the pixel point corresponding to the position indicated by the starting position identification as a starting pixel point, namely the pixel point is the first picture element.

In a specific implementation process, the starting point location identifier may be: a first special pixel point in the picture; for example, the picture may be an outer boundary pixel point located at the upper left corner/lower left corner/upper right corner/lower right corner of the picture, and the like. Referring to fig. 3, a small square in fig. 3 represents a pixel, and the first special pixel may be: any one of an outer boundary pixel point a located at the upper left corner of the picture, an outer boundary pixel point b located at the lower left corner of the picture, an outer boundary pixel point c located at the upper right corner of the picture and a pixel point d located at the lower right corner of the picture is specifically selected based on actual requirements.

Specifically, when the original image content in the first picture element is replaced by the first content, the first special pixel point in the picture can be used as the starting pixel point, and the position corresponding to the first special pixel point is the position indicated by the starting position identifier; and sequentially selecting n pixel points (including the first special pixel point) as the first picture element by taking the first special pixel point as an initial pixel point, wherein n is the number parameter.

Therefore, when step S1012 is implemented, the first special pixel point can be used as the initial pixel point, and the pixel points with the number indicated by the quantity parameter are sequentially determined as the first picture element, so that the position of the first picture element is accurately determined, and the first content in the first picture element is accurately identified.

In this embodiment, the first picture element may be: the first special pixel point is used as a starting pixel point, and n pixel points which are determined along the clockwise direction and contain the first special pixel point are determined; or, the first special pixel point is taken as an initial pixel point, and n pixel points which are determined along the anticlockwise direction and contain the first special pixel point are determined; wherein n is the quantity parameter. In a specific implementation, the color-coded value indication in another specific pixel point can be predefined or predefined in a clockwise direction or a counterclockwise direction. And the quantity parameter may be represented by a color-coded value in the second special pixel.

Specifically, the second special pixel point may be as shown in fig. 3: any one of an outer boundary pixel point a at the upper left corner in the picture, an outer boundary pixel point b at the lower left corner in the picture, an outer boundary pixel point c at the upper right corner in the picture and a pixel point d at the lower right corner in the picture. It should be noted that, in the embodiment of the present invention: the second special pixel point and the first special pixel point are not the same pixel point, for example, the first special pixel point is an outer boundary pixel point a of an upper left corner, and the second special pixel point is set to be one of an outer boundary pixel point b, an outer boundary pixel point c or a pixel point d of a lower left corner in the picture, but not the outer boundary pixel point a of the upper left corner.

Specifically, the second special pixel point may also be a pixel point adjacent to the first special pixel point but not belonging to the first picture element. Such as: if the first special pixel point is taken as the initial pixel point, n pixel points (including the first special pixel point) are sequentially selected as the first picture element, and one pixel point behind the first special pixel point along the counterclockwise direction is taken as the second special pixel point.

Next, referring to fig. 4a to 4b, taking the outer boundary pixel point b at the lower left corner of the picture as the initial pixel point, n pixel points (including the first special pixel point) are sequentially selected as the first picture element for explanation. The first picture element contains a color coding sequence consisting of the following 3 color coding values: {10,21,234}, {4,156,86}, {141,78,179}, wherein the color coding value in the outer boundary pixel point b is {10,21,234}, and a mapping relation is established between the color coding value and the character "cyan"; the color coding value of the pixel b1 adjacent to the clockwise direction of the outer boundary pixel b is {4,156,86}, a preset mapping relation is established between the color coding value and the character "sea", and the color coding value of the pixel b2 adjacent to the clockwise direction of the pixel b1 is {141,78,179}, a mapping relation is established between the color coding value and the character "lake". Thus, the color code sequence {10,21,234}, {4,156,86}, {141,78,179} represents the target picture description information of the picture to be searched: "Qinghai lake".

Based on this, the process of determining the first picture element in the picture is as follows: the color coding values of the outer boundary pixel point b, the pixel point b1 and the pixel point b2 can be sequentially identified from the outer boundary pixel point b at the lower left corner of the picture, so that the color coding sequence for representing the target picture information "Qinghai lake" in the first picture element is identified as follows: {10,21,234},{4,156,86},{141,78,179}.

The third mode is that position indication information is set for the picture; the position indication information includes: and the first jumping pixel points and the second jumping pixel points in the picture outer boundary area. Specifically, the first skip pixel point and the second skip pixel point in the picture outer boundary area are used as the position indication information corresponding to the picture.

Then, in step S1012, determining a first picture element from the picture to be searched according to the position indication information may specifically include: finding a first jumping pixel point and a second jumping pixel point from the outer boundary area of the picture to be searched; and determining pixel points included between the positions of the first jumping pixel points and the positions of the second jumping pixel points as first picture elements, wherein the first picture elements comprise the first jumping pixel points and the second jumping pixel points.

The first jumping pixel point may specifically be: and in the color coding sequence corresponding to the first content, the pixel point where the first color coding value in the clockwise direction is located. The second jumping pixel point may specifically be: and in the color coding sequence corresponding to the first content, the pixel point where the last color coding value in the clockwise direction is located. It should be noted that the skipping pixel point means: the color coding value of the pixel point and the color coding value of the adjacent pixel point exceed a preset difference value. For example, assume that in the outer boundary region of the picture, the following color-coded values exist clockwise: {0,0,0}, {0,0,0}, {10,21,234}, {4,156,86}, {141,78,179}, {0,0,0}, {0,0,0}, then {10,21,234} is determined to be a first-hop pixel and {141,78,179} is determined to be a second-hop pixel.

Specifically, when the original image content in the first picture element is replaced by the first content, the content in part of the pixel points is changed, so that the first and second jumping pixel points are generated.

In the specific implementation process, if after the first jumping pixel point is found, the outer boundary pixel points behind the first jumping pixel point are sequentially found until the first preset number of non-jumping pixel points are found behind the first jumping pixel point, and then the jumping pixel points adjacent to the first preset number of non-jumping pixel points are determined as second jumping pixel points.

In an optional implementation manner, the implementation manner of determining the first picture element based on the first jumping pixel point and the second jumping pixel point may be applied to: the method comprises the steps that a first delimiter code value and a second delimiter code value are not found in a picture to be searched, and a starting point position identification is not found, so that the position of a first picture element can be determined based on the characteristic of a color coding sequence which represents target picture description information in the first picture element under the condition that information used for accurately determining the position of the first picture element is not preset on the picture to be searched, and the color coding sequence which represents the target picture description information in the first picture element is identified. In the two modes, the information for identifying the position of the first picture element is specially set, so that the position of the first picture element is better identified, and the third mode is used under the condition that the first delimiter code value and the second delimiter code value are not found and the starting point position identification is not found, so that the possibility and the accuracy of obtaining the first picture element are improved.

And S102, obtaining target picture description information corresponding to the first content according to the first content.

Specifically, the target picture description information may include one or more unit description contents. And the unit description content can be one or more of a single character, a single word, a single phrase and a single sentence. A single character may refer to letters, numbers, chinese characters, symbols, and the like. For example, if the target picture description information is "Qinghai lake", the "Qinghai lake" includes 3 characters. It is noted that a phrase is a combination of two or more words. A single sentence includes at least a subject + predicate, and other sentence components may be included on the basis of the subject + predicate.

In a specific implementation process, a mapping relation between the first content and the picture description information can be preset and stored; in step S102, according to the first content obtained in step S101, in combination with a mapping relationship between the first content and picture description information that is pre-stored, target picture description information corresponding to the first content contained in the first picture element in the picture to be searched is obtained.

The mapping relationship between the first content and the picture description information is preset and stored, and various embodiments are possible:

the first implementation mode comprises the following steps: and setting and storing the mapping relation between the graphic coding sequence of the specific image area in the picture and the picture description information.

Specifically, the unit description content set and the graphic symbol set are mapped in advance and stored. The second preset number of graphic symbols form a graphic symbol set, and the second preset number of unit description contents form a unit description content set.

It should be noted that the graphic code sequence of the specific image region constituting the first content may be composed of one or more graphic symbols in the graphic symbol set; and the picture description information may be composed of one or more unit description contents in the unit description content set. And each unit description content in the unit description content set is mapped with each graphic symbol in the graphic symbol set one by one, so that each graphic symbol in the graphic symbol set has uniquely mapped unit description content. And searching and obtaining the mapping relation between the graphic coding sequence of the specific image area forming the first content and the picture description information from the total mapping relation between the unit description content set and the graphic symbol set, thereby determining the target picture description information corresponding to the first content.

The second embodiment: and setting and storing the mapping relation between the color coding sequence of the specific pixel point of the picture and the picture description information.

Specifically, the preset unit describes and stores the total mapping relation between the content set and the color coding value set. The second preset number of color coding values form a color coding value set, and the second preset number of unit description contents form a unit description content set.

It should be noted that the color coding sequence of a specific pixel point constituting the first content may be composed of one or more color coding values in the color coding value set, and the picture description information may be composed of one or more unit description contents in the unit description content set. And each unit description content in the unit description content set is mapped with each color coding value in the color coding value set one by one, so that each color coding value in the color coding value set has uniquely mapped unit description content. Then, the mapping relation between the color coding sequence and the picture description information forming the first content is searched and obtained from the total mapping relation between the unit description content set and the color coding value set, so as to determine the target picture description information corresponding to the first content.

In the specific implementation process, the unit description content set has a plurality of forms, and the total mapping relationship established between the unit description content set and the color coding value set is correspondingly different, which is explained below.

The unit describes the form one of the content set: the character set comprises various characters of different types such as letters, numbers, Chinese characters, symbols and the like, and each character in the character set and each color coding value in the color coding value set satisfy a one-to-one mapping relation.

Taking the color coding value as an RGB value as an example, since 1600 ten thousand characters (256 × 256) can be represented in the RGB color mode, and the number of the kanji characters is less than 10 ten thousand, even though the character set includes characters such as letters, numbers, kanji characters, symbols, characters, etc., the number is much less than 1600 ten thousand. Accordingly, various characters may be stored encoded based on RGB values such that each character in the character set has a unique corresponding RGB value. The multilingual characters can be all added into the overall mapping relation, so that the multilingual picture description information can be represented in the picture to be searched by the color coding sequence.

For example, in the overall mapping: cyan {11,32,43}, sea {51,15,96}, lake {221,223,1}, based on the color coding sequence: {11,32,43}, {51,15,96}, {221,223,1}, and obtaining corresponding target picture description information as: "Qinghai lake". Only the RGB values of 3 pixel points in the picture to be searched need to be identified.

The unit describes the form two of the content set: a set of words. The word set can contain words such as Chinese words and English words, and the mapping relation between each word in the word set and each color coding value in the color coding value set is satisfied.

Specifically, words may be stored uniquely encoded based on RGB values such that each word in the set of words has a unique RGB value. For example, in the mapping: "blue sky" ═ 12,1,43, and "white cloud" ═ 21,12,45, then based on the colorcode sequence: {12,1,43}, {21,12,45} obtains the corresponding target picture description information as: "blue sky white cloud". Therefore, only the RGB values of 2 pixels need to be identified.

The unit describes the form three of the first set of content: and the phrase set is a one-to-one mapping between each phrase in the phrase set and each color coding value in the color coding value set.

In particular, the phrases may be stored uniquely encoded based on RGB values such that each phrase in the set of phrases has a unique RGB value. For example, in the overall mapping: "at home" - {11,9,234 }. Then the corresponding target picture description information obtained based on the color coding sequence {11,9,234} is: "at home". Therefore, only the RGB values in 1 pixel point need to be identified.

The unit describes the form four of the content set: and the sentences in the sentence set and the color coding values in the color coding value set meet one-to-one mapping relationship.

Specifically, the sentences may be uniquely encoded and stored based on RGB values such that each sentence in the set of sentences has a unique RGB value. In the overall mapping relationship: "i is watching tv" - {168, 0, 24 }. Then, based on the color coding sequence {168, 0, 24}, the corresponding target picture description information is obtained as: "I are watching TV". The realization only discerns the RGB value in 1 pixel.

As can be seen from the above description, based on the mapping relationship, the target picture description information corresponding to the first content contained in the first picture element is obtained, so as to avoid image recognition of the entire picture to be searched, and therefore, the amount of calculation is greatly reduced.

It should be noted that the unit description content set may be applied in only one of the above four forms, or may be applied in multiple forms at the same time. If the image contains a plurality of types, the images are sequentially searched in different mapping relations until the mapping relation between the color coding sequence contained in the specific pixel point of the image to be searched and the image description information is obtained.

In a preferred embodiment, the mapping relationship between the first content and the picture description information is stored in a storage area corresponding to the input method program, and when step S102 is executed, the method specifically includes: and calling a mapping relation between the first content and the picture description information from a storage area corresponding to the input method program, and acquiring target picture description information corresponding to the first content.

Specifically, the preset mapping relationship is included in the input method installation package. The input method installation package comprises a mapping relation file, wherein the mapping relation file stores the total mapping relation between a unit description content set and a color coding value set or stores the total mapping relation between the unit description content set and a graphic coding value set. And obtaining a mapping relation file by downloading the input method installation package and storing the mapping relation file in the user equipment. Based on this, step S102 may specifically be: based on the input method program, calling a mapping relation file from the user equipment, obtaining a mapping relation between the first content and the picture description information from the mapping relation file, and obtaining target picture description information corresponding to the first content based on the mapping relation between the first content and the picture description information.

And S103, searching the picture according to the target picture description information to obtain a picture searching result.

Specifically, the implementation process of performing the picture search according to the target picture description information may include the following specific steps S1031 to S1032:

and step S1031, obtaining source picture description information of each searched picture in the target search range. And if the scene is a scene for local search based on the user equipment, the target search range is a local gallery used for storing pictures in the user equipment, and the user equipment searches the pictures in the local gallery. If the scene is a scene for network search based on a search engine, the target search range is a network range in which the search engine can find and capture pictures.

It should be noted that the source picture description information included in the searched picture may be obtained by setting the first content for the picture and based on the mapping relationship between the first content and the picture description information as described in the foregoing embodiment, and details are not repeated here. Of course, in practical applications, the source picture description information included in the searched picture may also be obtained by adding picture description information to the picture, which is known in the art, for example, recognizable text information existing in the picture itself, text information added in the picture name, information added in the picture attribute, and the like.

In the first case, the description information of the source picture is located outside or hidden in the main picture area of the searched picture to avoid the main picture area of the searched picture, thereby ensuring the picture quality of each searched picture in the target search range.

If the case one is, the source picture description information for representing the picture may be set for the searched picture based on the aforementioned embodiment of setting the picture description information for representing the picture for the picture, specifically: original image content in a second picture element included in the searched picture is replaced by second content of source picture description information for representing the picture.

Of course, the source picture description information may also be added to the searched picture in the existing manner, for example, directly displayed outside the main image area of the picture in text form. The source picture description information may also be already carried by the searched picture itself.

If the source picture description information is directly displayed outside the main image area of the picture in a text form, the step S1031 of obtaining the source picture description information of each searched picture in the target search range may specifically include: and performing image recognition on each searched picture in the target search range, and taking the character information on each recognized searched picture as the source picture description information of each searched picture. Therefore, the source picture description information of each searched picture in the target search range can be obtained.

If the original image content in the second picture element included in the searched picture is replaced with the second content of the source picture description information used for representing the picture, the obtaining of the source picture description information of each searched picture in the target search range in step S1031 may specifically include: and obtaining the source picture description information of each searched picture according to the mapping relation between the picture description information and the second content contained in the second picture element in each searched picture in the target searching range.

It should be noted that the implementation principle of obtaining the source picture description information of each searched picture is the same as or similar to the implementation principle of obtaining the target picture description information of the picture to be searched, and for the sake of brevity of the description, detailed description is not provided here.

And in the second case, the source picture description information is located in the context environment where the searched picture is located. The context environment where the searched picture is located is as follows: the text contents belonging to the same webpage as the searched picture or the text contents belonging to the same file page as the searched picture. The obtaining of the source picture description information of each searched picture in the target search range in step S1031 may specifically include: and searching the source picture description information corresponding to each searched picture from the context environment where each searched picture is located in the target search range.

Step S1032 searches in the target search range to obtain a searched picture in which the source picture description information matches the target picture description information.

Specifically, the searching in the target search range in step S1032 to obtain the searched picture with the source picture description information matched with the target picture description information may have multiple embodiments, which are respectively described below:

the first implementation mode comprises the following steps: and directly comparing the target picture description information with the source picture description information of each searched picture to obtain the searched picture in the target search range, wherein the source picture description information comprises the target picture description information. By the embodiment, the searched picture with the information to be matched being completely the same as the target picture description information or the searched picture with the part of the source picture description information being the same as the target picture description information can be obtained.

The second embodiment: extracting M keywords to be searched from the target picture description information, wherein M is an integer greater than 1; and respectively comparing the source picture description information of each searched picture in the target search range with the M keywords to be searched to obtain the searched picture in the target search range, wherein the source picture description information comprises the searched picture of one or more keywords in the M keywords to be searched.

Specifically, the source picture description information is segmented to obtain M keywords to be searched. In the specific implementation process, if the source picture description information is Chinese, performing Chinese word segmentation on the source picture description information to obtain M keywords to be searched; and if the source picture description information is English, performing English word segmentation on the source picture description information to obtain M keywords to be searched.

The foregoing specific implementation of step S1032 is suitable for the local search scenario because there is no need to establish an inverted index service for the source picture description information of each searched picture.

If the scenario is a scenario applied to a network search based on a search engine, before executing step S103, the method further includes: and establishing reverse index service aiming at the source picture description information of each searched picture in the target search range. The establishment of the inverted index service is realized through the following steps 1-2:

step 1: and extracting keywords from the source picture description information of each searched picture in the target search range, and forming a keyword set.

Specifically, carrying out word segmentation on the source picture description information of each searched picture in a target search range to obtain a plurality of basic words; and then, carrying out repeated word removal on all basic words obtained by word segmentation processing to obtain a keyword set without repeated keywords.

Step 1 is illustrated with the following two source picture description information, but is not meant to limit the invention:

one source picture description information is 'West lake under burning sun', Chinese word segmentation is carried out to obtain the following basic words: "under the sun", "in" and "in the west lake". The other source picture description information is 'peasants under burning sun', Chinese word segmentation is carried out to obtain basic words: "under burning sun", "for" and "farmers". And (3) carrying out repeated word removal to obtain a keyword set as follows: "under burning sun", "in", "West lake" and "farmer".

After step 1, step 2 is performed: and establishing an inverted index between each keyword in the keyword set and each searched picture in the target search range.

For a certain keyword, if the keyword exists in one source picture description information, establishing a picture index record of the keyword, and further establishing the picture index record of each keyword.

In a specific implementation process, each keyword in the keyword set is assigned with a unique keyword number (ID), and each picture in the target search range is assigned with a unique picture number (ID). And establishing a picture index record between the key word number of each key word and the picture number of the searched picture with the key word. Specifically, each picture index record may further include location information, frequency of occurrence, and the like where the keyword appears in the information to be matched.

For example, a plurality of searched pictures as shown in table 1 below exist for the target search range:

TABLE 1

Picture numbering	Description information corresponding to color coding sequence
		1	Qinghai lake in spring
2	Qinghai lake in summer
		3	West lake in autumn
4	West lake in winter

The method comprises the steps of dividing the appearing 'spring Qinghai lake', 'summer Qinghai lake', 'autumn Qinghai lake' and 'winter West lake' into words to obtain a plurality of basic words, and repeating the words to obtain a keyword set which is 'spring', 'summer', 'autumn', 'winter', 'Qinghai lake' and 'West lake'.

The service of establishing an inverted index between each keyword in the keyword set and the corresponding searched picture is shown in table 2 below. Wherein each column in table 2 is: one keyword corresponds to one posting list.

TABLE 2

Key word numbering	Key word	Picture numbering
			1	Spring	(1)
2	Summer	(2)
			3	Autumn	(3)
4	In winter	(4)
			5	Is/are as follows	(1)，(2)，(3)，(4)
6	Qinghai lake	(1)，(2)
			7	West lake	(3)，(4)

In the embodiment of the present invention, the inverted index service is a data structure that implements a mapping relationship between each keyword and source picture description information of a searched picture. Through the pre-established inverted index service, all searched pictures containing a certain keyword can be acquired at a time. The inverted index service is composed of two parts: keyword sets and inverted files. Each index in the key set records some information about the key itself and a pointer to a posting list. The inverted file comprises a plurality of inverted lists, one keyword corresponds to one inverted list, each inverted list records all searched pictures with a certain keyword and position information of the keyword appearing in the source picture description information of the searched pictures, each inverted list comprises more than one picture index record, and one picture index record is an inverted item (nesting), namely: mapping relation between a keyword and a searched picture.

Based on the pre-established reverse index service, in step S103, searching is performed within the target search range to obtain a searched picture with matching source picture description information and target picture description information. The method specifically comprises the following steps: searching in the target searching range according to the inverted index service, and obtaining a searched picture with the source picture description information matched with the target picture description information.

More specifically, according to searching in a target search range by an inverted index service, a searched picture with source picture description information matched with target picture description information is obtained, and the specific implementation mode is as follows: searching in the reverse index based on each keyword to be searched in the M keywords to be searched, and acquiring a picture index record corresponding to each keyword to be searched; and determining the searched pictures including the keywords to be searched in the source picture description information from the searched pictures in the target search range according to the picture index record corresponding to each keyword to be searched.

Specifically, the picture search result includes one or more searched pictures. If the picture search result includes a plurality of pictures, after step S103, the method may further include: and sequencing each picture in the picture search results according to the correlation degree between each picture in the picture search results and the target picture description information, and displaying each picture in the picture search results based on the sequenced sequence.

The degree of relevance may be measured based on the number of keywords to be searched included in the source picture description information of each picture in the picture search result. In a specific implementation process, all pictures in the picture search result are sequenced according to the fact that the source picture description information contains at least a plurality of keywords to be searched.

Further, the embodiment of the present invention may further include: and newly adding searched pictures in the target searching range.

The method specifically comprises the following steps of adding a searched picture in a target search range: acquiring an original picture added to a target search range, and acquiring source picture description information comprising one or more unit description contents for the original picture; determining a color coding sequence corresponding to the source picture description information according to the mapping relation between the source picture description information and the picture description information; writing the color coding sequence in the original picture to obtain a new searched picture; and adding the new searched picture to the target searching range.

Specifically, the original picture does not have the source picture description information represented by a color coding sequence, and the original picture can be obtained by one of a photographing application program, a picture browsing application program and a video playing application program.

The source picture description information can be obtained by performing voice input or key input through an input method program or by performing network matching. For example, similarity matching is performed between the original picture and each searched picture in the target search range, one searched picture with the similarity larger than a preset similarity threshold is determined as a candidate picture, and a color coding sequence on the candidate picture is written into the original picture, so that a new searched picture is obtained.

In order to avoid that the picture quality is influenced by writing the color coding sequence into the original picture, the color coding sequence is written into the outer boundary pixel points of the original picture. Because the outer boundary pixel points are generally not easy to be perceived by vision, the color coding value change in a small number of the outer boundary pixel points does not affect the picture quality.

Based on the same inventive concept, the embodiment of the invention provides an image searching method, which comprises the following steps:

step S301: the method comprises the steps of determining information to be searched for searching in a target searching range from a user input object, wherein the target searching range comprises more than one searched picture, a second picture element in the searched picture comprises second content used for representing source picture description information of the searched picture, and the second content is formed by replacing original image content in the second picture element.

Specifically, the user input object is text content input by the user or an operation gesture. The information to be searched determined according to the text content input by the user or the operation gesture is specifically the text content.

The form of the searched picture and the implementation process of obtaining the source picture description information from the searched picture in this embodiment may refer to the corresponding implementation manner in the first aspect, and for brevity of the description, details are not repeated here.

Step S302: and comparing the information to be searched with the source picture description information corresponding to the second content contained in the second picture element in each searched picture.

Step S303: and determining the searched picture meeting the preset similar condition between the source picture description information and the information to be searched as a picture searching result.

Specifically, the preset similar conditions are as follows: the source picture description information includes information to be searched, or the source picture description information includes more than one keyword in M keywords to be searched extracted from the information to be searched. In a specific implementation process, the specific implementation process of steps S302 to S303 may refer to step S103 described in the foregoing embodiment of the picture searching method, and for brevity of the description, details are not repeated here.

Based on the same inventive concept, an embodiment of the present invention provides an image search apparatus, as shown in fig. 5, including: a content obtaining unit 501, a description information obtaining unit 502, and a picture searching unit 503.

A content obtaining unit 501, configured to obtain first content carried by a first picture element in a picture to be searched, where the first content is formed by replacing an original image content of the first picture element in the picture to be searched, and the first content is used to represent picture description information corresponding to the picture to be searched;

a description information obtaining unit 502, configured to obtain, according to the first content, target picture description information corresponding to the picture to be searched;

the picture searching unit 503 is configured to perform picture searching according to the target picture description information, and obtain a picture searching result.

Optionally, the apparatus further comprises: an element discrimination unit.

And the element distinguishing unit is used for determining whether the picture to be searched comprises a first picture element carrying the first content, and if so, executing the acquisition of the first content carried by the first picture element in the picture to be searched.

Optionally, the apparatus further comprises: and a picture processing unit.

The image processing unit is used for processing an image in advance, replacing original image content of a first picture element in the image with the first content, wherein the first picture element is a specific image area or a specific pixel point included in the image.

Optionally, the picture processing unit includes: the first element selection subunit, and/or the second element selection subunit, and/or the third element selection subunit, and/or the fourth element selection subunit.

A first element selection subunit, configured to select a specific pixel point outside the main image region of the picture as the first picture element, and replace an original color coding sequence in the first picture element with a color coding sequence corresponding to the first content;

and/or the presence of a gas in the gas,

a second element selection subunit, configured to select a specific image region outside the main image region of the picture as the first picture element, and add a graphics coding sequence corresponding to the first content to the first picture element;

and/or the presence of a gas in the gas,

a third element selecting unit, configured to select, as the first picture element, a specific pixel point less than a preset number threshold in a main image region of the picture, and replace an original color coding sequence in the first picture element with a color coding sequence corresponding to the first content;

and/or the presence of a gas in the gas,

and the fourth element selection subunit is used for selecting a first number of outer boundary pixel points in the picture as the first picture element and replacing the original color coding sequence of the first picture element with the color coding sequence corresponding to the first content.

Optionally, the apparatus further comprises: a position indication setting unit.

A position indication setting unit, configured to set position indication information for the picture, where the position indication information is used to indicate a position of the first picture element in the picture.

Optionally, the content obtaining unit 501 includes: the system comprises an information obtaining subunit, an element determining subunit and a content extracting subunit.

The information obtaining subunit is configured to obtain position indication information carried by the picture to be searched, where the position indication information is used to indicate a position of the first picture element in the picture to be searched;

an element determining subunit, configured to determine, according to the position indication information, the first picture element from the picture to be searched;

and the content extraction subunit is used for extracting the first content carried in the first picture element.

Optionally, the position indication setting unit includes: a delimiter setting subunit, and/or an identification setting subunit, and/or a jumping point determination subunit.

A delimiter setting subunit, configured to set a first delimiter encoding value on a first side of the first picture element in the picture and a second delimiter encoding value on a second side of the first picture element, and use the first delimiter encoding value and the second delimiter encoding value as position indication information corresponding to the picture;

and/or the presence of a gas in the gas,

the identification setting subunit is used for setting position indication information for the picture; the position indication information includes: presetting a starting point position identifier and a quantity parameter; the starting position identifier is used for identifying a starting pixel point of the first picture element, and the quantity parameter is used for identifying the number of pixel points occupied by the first picture element;

and/or the presence of a gas in the gas,

a jumping point determining subunit, configured to set position indication information for the picture; the position indication information includes: and the first jumping pixel points and the second jumping pixel points in the picture outer boundary area.

Optionally, the apparatus further comprises: the mapping unit is used for presetting and storing the mapping relation between the first content and the picture description information;

the mapping unit includes: a first setting subunit, and/or a second setting subunit.

The first setting subunit is used for setting and storing the mapping relation between the graphic coding sequence of the specific image area in the picture and the picture description information;

and/or the presence of a gas in the gas,

and the second setting subunit is used for setting the mapping relationship between the color coding sequence of the specific pixel point of the picture and the picture description information and storing the mapping relationship.

With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Based on the same inventive concept, an embodiment of the present invention provides a picture search apparatus 800, and fig. 6 is a block diagram illustrating the picture search apparatus 800 according to an exemplary embodiment. For example, the device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and the like.

Referring to fig. 6, device 800 may include one or more of the following components: processing component 802, memory 804, power component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814, and communication component 816.

The processing component 802 generally controls overall operation of the device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing elements 802 may include one or more processors 820 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operation at the device 800. Examples of such data include instructions for any application or method operating on device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

Power component 806 provides power to the various components of device 800. Power components 806 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for device 800.

The multimedia component 808 includes a screen that provides an output interface between the device 800 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front-facing camera and/or the rear-facing camera may receive external multimedia data when the device 800 is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor assembly 814 includes one or more sensors for providing various aspects of state assessment for the device 800. For example, the sensor assembly 814 may detect the open/closed state of the device 800, the relative positioning of components, such as a display and keypad of the device 800, the sensor assembly 814 may also detect a change in the position of the device 800 or a component of the device 800, the presence or absence of user contact with the device 800, orientation or acceleration/deceleration of the device 800, and a change in the temperature of the device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

Communications component 816 is configured to facilitate communications between device 800 and other devices in a wired or wireless manner. The device 800 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast associated information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communications component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the device 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

In an exemplary embodiment, a non-transitory computer-readable storage medium comprising instructions, such as the memory 804 comprising instructions, executable by the processor 820 of the device 800 to perform the above-described method is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

Fig. 7 is a schematic diagram of a server in some embodiments of the invention. The server 1900 may vary widely by configuration or performance and may include one or more Central Processing Units (CPUs) 1922 (e.g., one or more processors) and memory 1932, one or more storage media 1930 (e.g., one or more mass storage devices) storing applications 1942 or data 1944. Memory 1932 and storage medium 1930 can be, among other things, transient or persistent storage. The program stored in the storage medium 1930 may include one or more modules (not shown), each of which may include a series of instructions operating on a server. Still further, a central processor 1922 may be provided in communication with the storage medium 1930 to execute a series of instruction operations in the storage medium 1930 on the server 1900.

The server 1900 may also include one or more power supplies 1926, one or more wired or wireless network interfaces 1950, one or more input-output interfaces 1958, one or more keyboards 1956, and/or one or more operating systems 1941, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

A non-transitory computer-readable storage medium, in which instructions are executed by a processor of an apparatus (server or terminal), so that the apparatus can perform the data processing method described in the foregoing embodiments.

A non-transitory computer readable storage medium in which instructions, when executed by a processor of an apparatus (server or terminal), enable the apparatus to perform a data processing method, the method comprising: obtaining first content carried by a first picture element in a picture to be searched; the first content is formed by replacing original image content of a first picture element in the picture to be searched, and the first content is used for representing picture description information corresponding to the picture to be searched; obtaining target picture description information corresponding to the picture to be searched according to the first content; and searching the picture according to the target picture description information to obtain a picture searching result.

One or more technical solutions provided by the embodiments of the present invention at least achieve the following technical effects or advantages:

the method comprises the steps that first content contained in a first picture element in a picture to be searched is obtained, the first content is formed by replacing original image content in the first picture element, the first content is used for representing picture description information corresponding to the picture to be searched, and target picture description information corresponding to the first content is obtained according to the first content; and then searching the picture according to the target picture description information. Therefore, when the picture is actually searched, the target picture description information is determined according to the first content, the picture is searched according to the target picture description information, image recognition of the picture to be searched is not needed, and therefore the calculation amount during the picture searching can be reduced. Thereby improving picture search efficiency. Moreover, the picture searching is carried out according to the target picture description information, and the picture similarity calculation required by picture searching is avoided, so that the picture searching accuracy is improved.

Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.

It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is defined only by the appended claims, which are not intended to limit the present invention, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims (18)

1. An image searching method, comprising:

obtaining first content carried by a first picture element in a picture to be searched; the first content is formed by replacing original image content of a first picture element in the picture to be searched, the first content is a color coding sequence or a graph coding sequence which has a preset and stored mapping relation with picture description information corresponding to the picture to be searched, and the picture description information is characters for describing the picture to be searched;

obtaining target picture description information corresponding to the first content in the picture to be searched according to the first content and the preset and stored mapping relation;

and searching the picture according to the target picture description information to obtain a picture searching result.

2. The picture searching method of claim 1, wherein the method further comprises:

and determining whether the picture to be searched comprises a first picture element carrying the first content, if so, executing the obtaining of the first content carried by the first picture element in the picture to be searched.

3. The picture searching method of claim 1, wherein the method further comprises:

the method comprises the steps of processing a picture in advance, replacing original image content of a first picture element in the picture with the first content, wherein the first picture element is a specific image area or a specific pixel point included in the picture.

4. The picture searching method of claim 3, wherein the replacing of the original image content of the first picture element in the picture with the first content comprises:

selecting a specific pixel point outside the main image region of the picture as the first picture element, and replacing an original color coding sequence in the first picture element with a color coding sequence corresponding to the first content;

and/or the presence of a gas in the gas,

selecting a specific image area outside the main image area of the picture as the first picture element, and adding a graphic coding sequence corresponding to the first content in the first picture element;

and/or the presence of a gas in the gas,

selecting specific pixel points less than a preset number threshold value in a main image area of the picture as the first picture element, and replacing an original color coding sequence in the first picture element with a color coding sequence corresponding to the first content;

and/or the presence of a gas in the gas,

and selecting a first number of outer boundary pixel points in the picture as the first picture element, and replacing the original color coding sequence of the first picture element with the color coding sequence corresponding to the first content.

5. The picture searching method as claimed in claim 3, wherein the method further comprises:

setting position indication information for the picture, wherein the position indication information is used for indicating the position of the first picture element in the picture.

6. The picture searching method according to claim 5, wherein the obtaining of the first content carried by the first picture element in the picture to be searched comprises:

obtaining position indication information carried by the picture to be searched, wherein the position indication information is used for indicating the position of the first picture element in the picture to be searched;

determining the first picture element from the picture to be searched according to the position indication information;

and extracting first content carried in the first picture element.

7. The picture searching method according to claim 5, wherein the setting of the position indication information for the picture comprises:

setting a first delimiter encoding value on a first side of the first picture element in the picture and a second delimiter encoding value on a second side of the first picture element, wherein the first delimiter encoding value and the second delimiter encoding value are used as position indication information corresponding to the picture;

and/or the presence of a gas in the gas,

setting position indication information for the picture; the position indication information includes: presetting a starting point position identifier and a quantity parameter; the starting position identifier is used for identifying a starting pixel point of the first picture element, and the quantity parameter is used for identifying the number of pixel points occupied by the first picture element;

and/or the presence of a gas in the gas,

setting position indication information for the picture; the position indication information includes: and the first jumping pixel points and the second jumping pixel points in the picture outer boundary area.

8. The picture searching method as claimed in claim 3, wherein the method further comprises: presetting and storing a mapping relation between the first content and the picture description information; comprises the following steps of;

setting and storing a mapping relation between a graphic coding sequence of a specific image area in a picture and picture description information;

and/or the presence of a gas in the gas,

and setting and storing the mapping relation between the color coding sequence of the specific pixel point of the picture and the picture description information.

9. An image search device, comprising:

the content obtaining unit is used for obtaining first content carried by a first picture element in a picture to be searched, wherein the first content is formed by replacing original image content of the first picture element in the picture to be searched, the first content is a color coding sequence or a graph coding sequence which has a preset and stored mapping relation with picture description information corresponding to the picture to be searched, and the picture description information is characters for describing the picture to be searched;

the description information obtaining unit is used for obtaining target picture description information corresponding to the first content in the picture to be searched according to the first content and the preset and stored mapping relation;

and the picture searching unit is used for searching pictures according to the target picture description information to obtain a picture searching result.

10. The picture search apparatus of claim 9, wherein the apparatus further comprises:

and the element distinguishing unit is used for determining whether the picture to be searched comprises a first picture element carrying the first content, and if so, executing the acquisition of the first content carried by the first picture element in the picture to be searched.

11. The picture search apparatus of claim 9, wherein the apparatus further comprises:

the image processing unit is used for processing an image in advance, replacing original image content of a first picture element in the image with the first content, wherein the first picture element is a specific image area or a specific pixel point included in the image.

12. The picture search device as claimed in claim 11, wherein the picture processing unit comprises:

a first element selection subunit, configured to select a specific pixel point outside the main image region of the picture as the first picture element, and replace an original color coding sequence in the first picture element with a color coding sequence corresponding to the first content;

and/or the presence of a gas in the gas,

a second element selection subunit, configured to select a specific image region outside the main image region of the picture as the first picture element, and add a graphics coding sequence corresponding to the first content to the first picture element;

and/or the presence of a gas in the gas,

a third element selecting unit, configured to select, as the first picture element, a specific pixel point less than a preset number threshold in a main image region of the picture, and replace an original color coding sequence in the first picture element with a color coding sequence corresponding to the first content;

and/or the presence of a gas in the gas,

and the fourth element selection subunit is used for selecting a first number of outer boundary pixel points in the picture as the first picture element and replacing the original color coding sequence of the first picture element with the color coding sequence corresponding to the first content.

13. The picture search apparatus of claim 11, wherein the apparatus further comprises:

a position indication setting unit, configured to set position indication information for the picture, where the position indication information is used to indicate a position of the first picture element in the picture.

14. The picture search apparatus according to claim 13, wherein said content obtaining unit includes:

the information obtaining subunit is configured to obtain position indication information carried by the picture to be searched, where the position indication information is used to indicate a position of the first picture element in the picture to be searched;

an element determining subunit, configured to determine, according to the position indication information, the first picture element from the picture to be searched;

and the content extraction subunit is used for extracting the first content carried in the first picture element.

15. The picture search apparatus according to claim 13, wherein said position indication setting unit includes:

a delimiter setting subunit, configured to set a first delimiter encoding value on a first side of the first picture element in the picture and a second delimiter encoding value on a second side of the first picture element, and use the first delimiter encoding value and the second delimiter encoding value as position indication information corresponding to the picture;

and/or the presence of a gas in the gas,

the identification setting subunit is used for setting position indication information for the picture; the position indication information includes: presetting a starting point position identifier and a quantity parameter; the starting position identifier is used for identifying a starting pixel point of the first picture element, and the quantity parameter is used for identifying the number of pixel points occupied by the first picture element;

and/or the presence of a gas in the gas,

a jumping point determining subunit, configured to set position indication information for the picture; the position indication information includes: and the first jumping pixel points and the second jumping pixel points in the picture outer boundary area.

16. The picture search apparatus of claim 11, wherein the apparatus further comprises: the mapping unit is used for presetting and storing the mapping relation between the first content and the picture description information;

the mapping unit includes:

the first setting subunit is used for setting and storing the mapping relation between the graphic coding sequence of the specific image area in the picture and the picture description information;

and/or the presence of a gas in the gas,

and the second setting subunit is used for setting the mapping relationship between the color coding sequence of the specific pixel point of the picture and the picture description information and storing the mapping relationship.

17. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method of any one of claims 1 to 8.

18. A picture search device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any one of claims 1 to 8 when executing the program.

Images