WO2016173278A1

WO2016173278A1 - Image management method and device

Info

Publication number: WO2016173278A1
Application number: PCT/CN2015/098118
Authority: WO
Inventors: 尚国强
Original assignee: 中兴通讯股份有限公司
Priority date: 2015-04-28
Filing date: 2015-12-21
Publication date: 2016-11-03
Also published as: CN106156247A; CN106156247B

Abstract

Provided are an image management method and device. The method comprises: acquiring pixel feature information of an image to be grouped, wherein the pixel feature information characterizes a pixel property corresponding to specified image content in the image to be grouped; and dividing the images to be grouped having the same pixel feature information into groups of the same type. The above technical solution provided by the present invention addresses the problem in the related art in which no effective technical solution effectively manages a large number of images photographed by the user, thus providing a convenient and quick image management mode, and greatly improving user experience.

Description

Image management method and device

Technical field

The present invention relates to the field of communications, and in particular to an image management method and apparatus.

Background technique

With the rapid development of digital imaging technology and the rapid marketization of smartphones with camera functions, it has greatly satisfied the needs of people to take pictures quickly. With the appearance of a large number of high-quality digital photos, how to manage these photos effectively and reasonably It is an important issue that people often face.

In view of the related art, how to effectively manage a large number of photos taken by users, and no effective solution has been proposed.

Summary of the invention

In order to solve the above technical problem, an embodiment of the present invention provides an image management method and apparatus.

According to an embodiment of the present invention, there is provided an image management method, comprising: acquiring pixel feature information of an image to be grouped, wherein the pixel feature information is used to represent pixels corresponding to a specified image content in the image to be grouped Characteristic; dividing the image to be grouped with the same pixel feature information into the same category group.

In the embodiment of the present invention, acquiring pixel feature information of the image to be grouped includes: acquiring image background information of the image to be grouped; and/or acquiring image foreground information of the image to be grouped.

In the embodiment of the present invention, after the image to be grouped with the same pixel feature information is divided into the same category group, the method further includes: generating an index picture according to the pixel feature information, wherein different identifiers of the index picture are used for Link to different images in the category group.

In the embodiment of the present invention, generating an index picture according to the pixel feature information includes: extracting part or all of the image content corresponding to the other image content, wherein the other image content is in the image to be grouped Image content outside the specified image content corresponding to the pixel feature information; generating the index picture according to a specified arrangement rule by the part or all of the image content.

In the embodiment of the present invention, after the image to be grouped with the same pixel feature information is divided into the same category group, the method further includes: saving the attribute information corresponding to the category group, wherein the attribute information includes: The number of images included in the category group.

According to another embodiment of the present invention, there is further provided an image management apparatus, comprising: an acquisition module configured to acquire pixel feature information of an image to be grouped, wherein the pixel feature information is used to represent the image to be grouped Specifying pixel characteristics corresponding to image content; dividing module, configured to divide the image to be grouped with the same pixel feature information into In the same category group.

In the embodiment of the present invention, the acquiring module is configured to acquire image background information of the image to be grouped; and/or acquire image foreground information of the image to be grouped.

In the embodiment of the present invention, the device further includes: a generating module, configured to generate an index picture according to the pixel feature information, where different identifiers of the index picture are used to link to different images in the category group .

In the embodiment of the present invention, the generating module includes: an extracting unit configured to extract part or all of the image content corresponding to the other image content, wherein the other image content is in the image to be grouped An image content outside the specified image content corresponding to the pixel feature information; and a generating unit configured to generate the index image according to a specified arrangement rule.

In the embodiment of the present invention, the device further includes: a saving module, configured to save the attribute information corresponding to the category group, wherein the attribute information includes: the number of images included in the category group.

According to the embodiment of the present invention, an image including the same pixel feature information can be divided into one group, and the related art has no effective technical solution to effectively manage a large number of photos taken by the user. A convenient and fast image management mode that greatly enhances the user experience.

DRAWINGS

The drawings described herein are intended to provide a further understanding of the invention, and are intended to be a part of the invention. In the drawing:

1 is a flow chart of an image management method according to an embodiment of the present invention;

2 is a block diagram showing the structure of an image management apparatus according to an embodiment of the present invention;

3 is a block diagram showing another structure of an image management apparatus according to an embodiment of the present invention;

4 is a schematic view showing a splicing according to a preferred embodiment of the present invention;

Figure 5 is a schematic illustration of a stitching in accordance with a preferred embodiment 2 of the present invention.

detailed description

The invention will be described in detail below with reference to the drawings in conjunction with the embodiments. It should be noted that the embodiments in the present application and the features in the embodiments may be combined with each other without conflict.

Other features and advantages of the invention will be set forth in the description which follows, The objectives and other advantages of the invention may be realized and obtained by means of the structure particularly pointed in the appended claims.

In order to make those skilled in the art better understand the solution of the present invention, the following will be combined with the drawings in the embodiments of the present invention. The technical solutions in the embodiments of the present invention are clearly and completely described. It is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of the present invention.

In the embodiment of the present invention, an image management method is further provided. FIG. 1 is a flowchart of an image management method according to an embodiment of the present invention. As shown in FIG. 1, the method includes the following steps:

Step S102, acquiring pixel feature information of the image to be grouped, wherein the pixel feature information is used to represent a pixel characteristic corresponding to the specified image content in the image to be grouped;

Step S104, the image to be grouped with the same pixel feature information is divided into the same category group.

Through the above various steps, the image including the same pixel feature information can be divided into one group, and the related art has no effective technical solution to realize effective management of a large number of photos taken by the user, and provides a A convenient and fast image management mode greatly enhances the user experience.

In the actual application process, the specified image content may include multiple aspects. For example, the pixel features of the object to be grouped may include a certain object or a pixel of the character, and may be selected and divided into one group. In an implementation manner, the foregoing step S102 may be: acquiring image background information of the image to be grouped; and/or acquiring image foreground information of the image to be grouped, that is, the same pixel feature information may indicate two situations: The background of the image contains the same pixel feature information, and the other is that the foreground of the image (information other than the background in the image) contains the same pixel feature information.

Optionally, after performing the foregoing S104, the following process may further be performed, generating an index picture according to the foregoing pixel feature information, where different identifiers of the index picture are used to link to different images in the category group, that is, the foregoing The index picture includes multiple indexes, and each index can be linked to a corresponding image. In the embodiment of the present invention, the index picture is preferentially placed on the cover in the category group, and the user can quickly find different identifiers through the index picture of the cover page. The corresponding image, of course, the identifier may be a graph, and any identifier that enables the user to quickly find the corresponding image, which is not limited by the embodiment of the present invention. The link here can be a relative position link between the newly generated picture and the original picture (also can be understood as a relative path), for example, a relative position link like .\doc\pic\111.jpeg, usually in a computer Such settings are commonly used in applications; of course, absolute positions can also be used, such as d:\doc\pic\111.jpeg.

In the embodiment of the present invention, the generating the index picture according to the pixel feature information may be implemented by: extracting part or all of the image content corresponding to the other image content, wherein the other image content is the pixel in the image to be grouped. The image content other than the specified image content corresponding to the feature information; the part or all of the image content is generated according to the specified arrangement rule, and the above-mentioned scheme can be understood as that the specified image content corresponding to the same pixel feature information is used as the index image. The background, the other image content as the identifier of the index picture.

It should be noted that the foregoing technical solution of the specified arrangement rule can be understood as follows. Of course, the embodiment of the present invention is not limited thereto. When the foreground and the same background are different, when the new pixel feature information is placed, the foreground and the background feature value cannot be covered. The obvious part can be divided into a grid array according to the whole image. These background features are placed in several squares without overlapping each other. When the background is the same and the foreground is different, the foreground part is similar to the above. Features are placed separately Into several squares, do not overlap each other.

In order to better understand the above technical solution, the following description will be made with reference to an example. For example, if a set of images contains an identical photographic background Egyptian pyramid, then the user can correspond to the Egyptian pyramid containing the same pixel characteristic information. The pixels are extracted from the image, and each image has a remaining image corresponding to the pixel after the pyramid pixel is extracted. It should be noted that the remaining image can be understood as the other content image, and the remaining image corresponding to each image can be According to the above-mentioned specified arrangement rule (which may be a clockwise order, which may be a counterclockwise order, or other graphic order specified by the user, which is not limited by the embodiment of the present invention), is arranged on the image of the pyramid as a background, and Setting the remaining image corresponding to each image as a link index, clicking the link index can index the complete image corresponding to the remaining image, and the link index relationship between the remaining image and the complete image can be set and saved in the terminal, and clicked Query the above link index when indexing the remaining images in the image System, and further corresponding link to the full image.

Of course, if the user needs to know the number of images and the shooting time of the specified image in a certain period of time, the embodiment of the present invention further provides the following solution, which stores the attribute information corresponding to the category group, wherein the attribute information includes: The number of images included in the above category group.

The above technical solution can be understood by the following embodiments: for a group of photos (this group of photos can be in one directory, also in different directories, or on the network), through the intelligent pattern recognition method, A photo of roughly the same background is processed to generate a new index photo that can have a link function; or a photo with substantially the same foreground but different background is processed to generate a new index photo with a link function. An index photo that makes it easy to view any other photo in the set of photos, and because the indexed photo has a very intuitive representation (such as having the same background, it means that multiple people are taking photos here); If there are different prospects, it can represent a person taking pictures in different places). This processed indexed photo is a very effective means of quickly viewing photos.

In order to better understand the above image management method, the following description is made in conjunction with an embodiment, but is not intended to limit the embodiments of the present invention:

Usually, a photo is mostly spatially pixel-redundant, that is, deleting this part of the content affects the understanding of the photo. Only a small amount of space represents the main expression of the photo. Based on this consideration, it can be divided into two. Consider the types: one is the same background and the foreground is different; the other is the background is different and the foreground is the same. Describe separately:

The first case: the same background, different prospects

For a selected set of photos, the set of photos is analyzed using artificial intelligence's pattern recognition technology. In the embodiment of the present invention, the image can be analyzed by: if most of the spatial pixels of the set of photos are consistent, only There are a small number of different data, such as mainly people or scenes, you can consider this choice, select one of the photos as the main photo P, and then read the foreground part of the other photo different from the photo as the object Ox Come out, and finally placed in the spatially redundant part of the main photo P, without obscuring the main foreground part of the photo, and the Ox that comes in will have a link attribute pointing to the photo of the Ox object; by iteratively, After the group photo processing is completed, a set photo Pa with index function is formed, and the link of each object on the Pa can be very convenient for the user to browse the specific photos of different objects in the background.

It should be noted that, in the process of selecting a photo, the user may select multiple images that the user needs to group in the photo that has completed the camera function, and the terminal may automatically classify all the images saved in the terminal. It may be that the user automatically reminds the user whether to perform image classification after the new photo shooting is completed, and if so, the classification of the current photo is completed according to the image management method of the above embodiment.

The second case: the background is different and the foreground is the same

For a selected set of photos, the set of photos is analyzed using artificial intelligence's pattern recognition technology. In the embodiment of the present invention, the image can be analyzed by: if most of the spatial pixels of the set of photos are inconsistent, only A small part of the data is the same, if the main character or the scene is the same, and the background is basically different, you can consider this choice, choose one of the photos as the main photo P (the main photo selection background is simple but the foreground is obvious), then The background portion of the other photos that is different from the photo is read as the object Ox, and finally placed in the spatial redundant portion of the main photo P, without obscuring the main foreground portion of the photo, and the Ox will have a link Attribute, the link points to the photo of the Ox object; by iteratively, after the group of photos is processed, a set photo Pa with index function is formed, and the link of each object on the Pa can be conveniently browsed by the user. Specific photos of different objects under the foreground.

By describing the two cases, it can be seen that the index photo obtained in the first case is natural and realistic, while the photo in the second mode may be obvious, but it can give the user an intuitive but fast management. The method of the photo.

It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should understand that the present invention is not limited by the described action sequence. Because certain steps may be performed in other sequences or concurrently in accordance with the present invention. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

An image management apparatus is also provided in the embodiment to implement the above-mentioned embodiments and preferred embodiments. The descriptions of the modules involved in the apparatus are described below. As used below, the term "module" may implement a combination of software and/or hardware of a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware, is also possible and contemplated. 2 is a block diagram showing the structure of an image management apparatus according to an embodiment of the present invention. As shown in Figure 2, the device comprises:

The obtaining module 20 is configured to acquire pixel feature information of the image to be grouped, wherein the pixel feature information is used to represent a pixel characteristic corresponding to the specified image content in the image to be grouped;

The dividing module 22 is connected to the obtaining module 20 and configured to divide the image to be grouped with the same pixel feature information into the same category group.

Through the comprehensive application of the above modules, the images containing the same pixel feature information can be divided into one group, and the related art has no effective technical solution to effectively manage a large number of photos taken by the user. Provides a convenient and fast image management mode, greatly improving the user experience.

Optionally, the obtaining module 20 is configured to acquire image background information of the image to be grouped; and/or obtain image foreground information of the image to be grouped.

In order to achieve the above technical solution, FIG. 3 is another structural block diagram of an image management apparatus according to an embodiment of the present invention. As shown in FIG. 3, the apparatus further includes: a generating module 24 configured to generate an index picture according to the pixel feature information. And the different identifiers of the index image are used to link to different images in the category group, wherein the generating module 24 includes: an extracting unit 240 configured to extract part or all of the image content corresponding to the other image content, where The other image content is image content other than the specified image content corresponding to the pixel feature information in the image to be grouped; the generating unit 242 is connected to the extracting unit 240, and is configured to arrange the part or all of the image content according to a specified arrangement rule. Generate the above index image.

As shown in FIG. 3, the foregoing apparatus further includes: a saving module 26 configured to save attribute information corresponding to the category group, wherein the attribute information includes: the number of images included in the category group.

In order to better understand the above image management method and apparatus, the following combination and preferred embodiments are described:

Preferred embodiment 1

The same background, different prospects, as shown in Figure 4:

4 is a schematic view of a splicing according to a preferred embodiment of the present invention. The five slashed rectangles in FIG. 4 indicate that the background of the photograph is the same, and the triangles, diamonds, squares, and ellipses in the figure indicate the foreground of the image. In part, after analyzing and processing the data of the photo, for a part of different foreground data having most of the same background data, different foreground data can be extracted and stitched onto one picture, and a link attribute of the object can be directly Link to the image corresponding to this object.

Step 1. Select a group of photos and analyze the photos. You can use the artificial intelligence pattern recognition method. Through this technology, you can analyze that the photos to be processed are a group of photos with similar backgrounds and different foregrounds.

Step 2. According to the results of the above analysis, select a photo as the main photo, and the main foreground part of the other photos is extracted and stitched to the non-foreground area of the main photo;

Step 3. When the extracted foreground portion is spliced, a link is formed according to the position of the photo;

Step 4. When the photo is formed after processing, the different foreground parts have different links. Through these links, you can directly browse the corresponding photos.

Preferred embodiment two

Different backgrounds, same prospects, as shown in Figure 5:

5 is a schematic view of a splicing according to a preferred implementation of the present invention. The foreground portion of the image in FIG. 5 (indicated by a triangle in FIG. 5) is the same, and the intermediate index image combines the background of four different background images as the background of the intermediate drawing. After analyzing and processing the data of the photo, for most of the different background data, a small part of the same foreground data, different background data can be extracted and stitched onto one picture, and a link attribute of the object can be directly linked. Go to the picture corresponding to this object.

Step 1. Select a group of photos, analyze the photos, and use the artificial intelligence pattern recognition method. Through this technical means, it can be analyzed that the photo to be processed is a set of photos having substantially the same foreground and different backgrounds;

Step 2. According to the results of the above analysis, select a photo as the main photo, and the main background part of the other photos is extracted and stitched to the non-foreground area of the main photo;

Step 3. When the extracted background portion is spliced, a link is formed according to the position of the photo;

Step 4. When the photo is processed, the different background parts have different links. Through these links, you can directly browse the corresponding photos.

In summary, the embodiments of the present invention achieve the following technical effects: solving the related art, solving the problem in the related art that there is no effective technical solution to effectively manage a large number of photos taken by the user, and providing a convenient The fast image management mode greatly enhances the user experience.

In another embodiment, software is also provided for performing the technical solutions described in the above embodiments and preferred embodiments.

In another embodiment, a storage medium is further provided, wherein the software includes the above-mentioned software, including but not limited to: an optical disk, a floppy disk, a hard disk, an erasable memory, and the like.

It is to be understood that the terms "first", "second" and the like in the specification and claims of the present invention are used to distinguish similar objects, and are not necessarily used to describe a particular order or order. It is to be understood that the objects so used are interchangeable, where appropriate, so that the embodiments of the invention described herein can be carried out in a sequence other than those illustrated or described herein. In addition, the terms "comprises" and "comprises" and "the" and "the" are intended to cover a non-exclusive inclusion, for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to Those steps or units may include other steps or units not explicitly listed or inherent to such processes, methods, products or devices.

It will be apparent to those skilled in the art that the various modules or steps of the present invention described above can be implemented by a general-purpose computing device that can be centralized on a single computing device or distributed across a network of multiple computing devices. Alternatively, they may be implemented by program code executable by the computing device such that they may be stored in the storage device by the computing device and, in some cases, may be different from the order herein. The steps shown or described are performed, or they are separately fabricated into individual integrated circuit modules, or a plurality of modules or steps thereof are fabricated as a single integrated circuit module. Thus, the invention is not limited to any specific combination of hardware and software.

The above description is only the preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes can be made to the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and scope of the present invention are intended to be included within the scope of the present invention.

Industrial applicability

The above technical solution provided by the present invention can be applied to an image processing process, and by dividing an image containing the same pixel feature information into one group, the related technology is solved, and there is no effective technical solution for effective management. The problem of a large number of photos taken by the user provides a convenient and fast image management mode.

Claims

An image management method comprising:

Obtaining pixel feature information of the image to be grouped, wherein the pixel feature information is used to represent pixel characteristics corresponding to the specified image content in the image to be grouped;

The images to be grouped having the same pixel feature information are divided into the same category group.
The method of claim 1, wherein the acquiring pixel feature information of the image to be grouped comprises:

Obtaining image background information of the image to be grouped; and/or

Obtaining image foreground information of the image to be grouped.
The method according to claim 1, wherein after the image to be grouped having the same pixel feature information is divided into the same category group, the method further includes:

Generating an index picture according to the pixel feature information, wherein different identifiers of the index picture are used to link to different images in the category group.
The method of claim 3, wherein generating an index picture according to the pixel feature information comprises:

Extracting part or all of the image content corresponding to the other image content, wherein the other image content is image content other than the specified image content corresponding to the pixel feature information in the image to be grouped;

The part or all of the image content is generated according to a specified arrangement rule.
The method according to claim 1, wherein after the image to be grouped having the same pixel feature information is divided into the same category group, the method further includes:

The attribute information corresponding to the category group is saved, where the attribute information includes: the number of images included in the category group.
An image management device comprising:

An acquiring module, configured to acquire pixel feature information of the image to be grouped, wherein the pixel feature information is used to represent a pixel characteristic corresponding to the specified image content in the image to be grouped;

And a dividing module, configured to divide the image to be grouped with the same pixel feature information into the same category group.
The apparatus according to claim 6, wherein the obtaining module is configured to acquire image background information of the image to be grouped; and/or acquire image foreground information of the image to be grouped.
The device according to claim 6, wherein the device further comprises:

And a generating module, configured to generate an index picture according to the pixel feature information, wherein different identifiers of the index picture are used to link to different images in the category group.
The device of claim 8, wherein the generating module comprises:

The extracting unit is configured to extract part or all of the image content corresponding to the other image content, wherein the other image content is the image content other than the specified image content corresponding to the pixel feature information in the image to be grouped ;

And a generating unit, configured to generate the index picture according to a specified arrangement rule by using the part or all of the image content.
The device according to claim 6, wherein the device further comprises:

The saving module is configured to save the attribute information corresponding to the category group, where the attribute information includes: the number of images included in the category group.