CN111324254A

CN111324254A - Image sorting method and device, electronic equipment and storage medium

Info

Publication number: CN111324254A
Application number: CN202010163597.7A
Authority: CN
Inventors: 李马丁; 郑云飞
Original assignee: Reach Best Technology Co Ltd
Current assignee: Reach Best Technology Co Ltd; Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2020-03-10
Filing date: 2020-03-10
Publication date: 2020-06-23

Abstract

The disclosure relates to an image sorting method, an image sorting device, electronic equipment and a storage medium, relates to the technical field of image processing, and is used for solving the problem of single image arrangement mode in the related technology, and the image sorting method comprises the following steps: acquiring an image set to be ordered, wherein the image set comprises at least two images to be ordered; acquiring color features of each image in the image set, wherein the color features are determined according to a target color channel in a color space; and sorting part or all of the images in the image set according to the color characteristics. Because the method for sequencing the images based on the inherent attribute of the color features of the images is provided by the disclosure, the shooting time of the images does not need to be determined, and the display sequence does not need to be manually determined by a user, so that the operation of the user and the consumption of certain user time can be reduced, and the sequencing mode of the images is enriched while the sequencing efficiency is ensured.

Description

Image sorting method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of image processing technologies, and in particular, to an image sorting method and apparatus, an electronic device, and a storage medium.

Background

With the continuous development of electronic products, mobile terminals with a shooting function are more and more popular, and users can shoot images by using the mobile terminals at any time and any place. The photographed image can record what people see at ordinary times, the scenery along the travel, and the like.

The ordering of many images taken or otherwise obtained is important in determining the presentation order of a batch of images. Such as image ordering of long figures, image ordering of an album or photo album, image ordering of an album, and the like. The related art currently uses the capturing time of images to determine the presentation sequence, which can only be presented in time series.

In summary, the current image sorting method is single.

Disclosure of Invention

The disclosure provides an image sorting method, an image sorting device, an electronic device and a storage medium, which at least solve the problem of single image sorting mode in the related art. The technical scheme of the disclosure is as follows:

according to a first aspect of the embodiments of the present disclosure, there is provided an image sorting method, including:

acquiring an image set to be ordered, wherein the image set comprises at least two images to be ordered;

acquiring color features of each image in the image set, wherein the color features are determined according to a target color channel in a color space;

and sorting part or all of the images in the image set according to the color characteristics.

In an optional embodiment, the sorting the partial or all images in the image set according to the color features includes:

and sorting part or all of the images in the image set according to the sizes of the color features of the images under any one target color channel.

selecting at least one image subset as a target image subset from a plurality of image subsets obtained by dividing the image set according to the color interval;

and aiming at any one target image subset, sequencing all images in the target image subset according to the size of the color features of the images under at least one target color channel.

In an alternative embodiment, the set of images is divided by:

if the target color channel comprises a tone channel and the color features comprise tone components, dividing the images of which the tone components belong to the same color interval in the image set into the same image subset; or

If the target color channel comprises any color channel in the RGB color space, dividing the images of which the color components belong to the same color interval in the image set into the same image subset; or

And classifying the image set according to the shooting mode and/or the shooting content to obtain at least one image subset, wherein different image subsets correspond to different color intervals.

In an alternative embodiment, the color interval is determined according to a preset color circle or a reference color template.

In an alternative embodiment, the color feature includes a first component, which is a saturation component or a luminance component;

the step of sorting the images in the target image subset according to the size of the color features of the images in at least one target color channel includes:

and ordering the images in the target image subset according to the size of the first component.

In an alternative embodiment, the color feature further comprises a second component;

after the step of sorting the images in the target image subset by the size of the first component, the method further includes:

for any one target image subset, reordering a first target image in the target image subset according to the size of a second component, wherein the first target image is an image in the target image subset, the first component of which is ordered in a specified order range;

wherein the first component is a saturation component and the second component is a luminance component; or the first component is a luminance component and the second component is a saturation component.

In an alternative embodiment, the target image subset is a plurality;

the method further comprises the following steps:

and determining the sequence among the target image subsets according to the color intervals corresponding to the target image subsets.

In an alternative embodiment, in the adjacent target image subsets, the first component of each image in one target image subset is from high to low, and the first component of each image in the other target image subset is from low to high; or

The first component of each image in each target image subset is from high to low; or

The first component of each image in each subset of target images is low to high.

In an optional embodiment, the step of acquiring the image set to be sorted includes:

classifying the images in the target image library according to the shooting mode and/or the shooting content to obtain at least one image set;

and taking the image set which meets the preset condition in the at least one image set as the image set to be sorted.

In an alternative embodiment, the color feature includes a third component, which is a saturation component or a luminance component;

the sorting of some or all of the images in the image set according to the color features includes:

and for any image set, sorting the images in the image set according to the size of the third component.

In an alternative embodiment, the color feature further comprises a fourth component;

after the step of sorting the images in the image set according to the size of the third component, the method further includes:

for any image set, reordering a second target image in the image set according to the size of a fourth component, wherein the second target image is an image in the image set, of which the third component is ordered in a specified order range;

wherein the third component is a saturation component and the fourth component is a luminance component; or the third component is a luminance component and the fourth component is a saturation component.

In an alternative embodiment, the target color channel comprises a luminance channel, the color feature comprises a luminance component;

determining a luminance component of any one of the images by:

taking the average value of the brightness values of all pixel points in the image as the brightness component of the image; or

And taking the average value of the brightness values of all target pixel points in the image as the brightness component of the image, wherein the target pixel points are pixel points of which the brightness values are within a specified brightness range.

According to a second aspect of the embodiments of the present disclosure, there is provided an image sorting apparatus including:

an image acquisition unit configured to perform acquisition of a set of images to be sorted, wherein the set of images includes at least two images to be sorted;

a feature acquisition unit configured to perform acquiring color features of respective images in the set of images, wherein the color features are determined according to a target color channel in a color space;

a sorting unit configured to perform sorting of some or all of the images in the set of images according to the color features.

In an alternative embodiment, the sorting unit is specifically configured to perform:

In an alternative embodiment, the sorting unit is further configured to perform the dividing of the set of images by:

the sorting unit is specifically configured to perform:

after sorting the respective images of the subset of target images by the size of the first component, the sorting unit is further configured to perform:

In an alternative embodiment, the target image subset is a plurality;

the sorting unit is further configured to perform:

In an alternative embodiment, the image acquisition unit is specifically configured to perform:

the sorting unit is specifically configured to perform:

after sorting the respective images of the set of images by the size of the third component, the sorting unit is further configured to perform:

the feature acquisition unit is further configured to perform determining a luminance component of any one of the images by:

According to a third aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the image ordering method according to any one of the first aspect of the embodiments of the present disclosure.

According to a fourth aspect of the embodiments of the present disclosure, there is provided a non-transitory readable storage medium, wherein instructions of the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the image sorting method according to any one of the first aspect of the embodiments of the present disclosure.

According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product, which, when run on an electronic device, causes the electronic device to perform a method that implements any of the above first aspect and the first aspect of embodiments of the present disclosure may relate to.

The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:

the embodiment of the disclosure provides a method for sorting images based on the inherent attribute of the color features of the images, wherein the color features of the images are determined according to the target color channels in the specific color space, that is, the color features corresponding to the target color channels, and there is no need to determine the shooting time of the images and manually determine the display sequence by the user, so that the operation of the user and the consumption of a certain user time can be reduced, and the sorting mode of the images is enriched while the sorting efficiency is ensured.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.

FIG. 1 is a schematic diagram illustrating an application scenario in accordance with an exemplary embodiment;

FIG. 2 is a flow diagram illustrating a method of image ranking according to an exemplary embodiment;

FIG. 3 is a schematic diagram illustrating a color interval in accordance with an exemplary embodiment;

FIG. 4A is a diagram illustrating a color matching selection method in accordance with an exemplary embodiment;

FIG. 4B is a diagram illustrating another color matching selection method in accordance with an exemplary embodiment;

FIG. 5 is a diagram illustrating an image presentation effect according to an exemplary embodiment;

FIG. 6 is a flowchart illustrating a complete method of image ordering according to an exemplary embodiment;

FIG. 7 is a block diagram illustrating an image sorting apparatus according to an exemplary embodiment;

FIG. 8 is a block diagram illustrating an electronic device in accordance with an exemplary embodiment;

fig. 9 is a block diagram illustrating a terminal device according to an example embodiment.

Detailed Description

In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

Some of the words that appear in the text are explained below:

1. the term "and/or" in the embodiments of the present disclosure describes an association relationship of associated objects, and means that there may be three relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.

2. The term "electronic device" in the embodiments of the present disclosure may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, or the like.

3. The term "color space" also called color model (also called color space or color system) in the embodiments of the present disclosure is used to describe colors in a generally acceptable manner under certain standards. There are many kinds of color spaces, and RGB (Red, Red; Green, Green; Blue, Blue), CMY (Cyan; Magenta, Yellow), HSV (Hue, Hue/Hue; Saturation, Saturation; Value, brightness/Lightness), HSI (Hue, Hue/Hue; Saturation, Saturation; Intensity/brightness), HSL ((Hue, Hue/Hue; Saturation, Saturation; Lightness, brightness), Lab, etc. are commonly used.

RGB is a space defined by colors recognized by human eyes, and can represent most colors. However, the RGB color space is not generally used in scientific research because its details are difficult to digitally adjust. It puts the three quantities of hue, brightness and saturation together to represent, and is difficult to separate. It is the most common hardware-oriented color model. The model is used for color monitors and a large class of color video cameras.

CMY is the color space used for industrial printing. It corresponds to RGB. A simple analog RGB source is that the object emits light, and CMY is based on reflected light.

The three color spaces HSV, HSI and HSL are proposed for better digital processing of colors. There are many HSX color spaces where X may be V, I, or L, etc., depending on the particular application. H is hue, S is saturation, and I is intensity. The HSL color scheme is a color standard in the industry, and various colors are obtained by changing three target color channels of hue (H), saturation (S) and brightness (L) and superimposing them on each other. HSV is a color space created according to the intuitive nature of color, also known as the hexagonal pyramid model (HexconeModel). The HSV color space includes three color channels, a hue channel, a saturation channel, and a brightness channel.

The Lab color space is used for computer tone adjustment and color correction. It is implemented independently of the color model of the device. This method is used to map the device to the model and color distribution quality changes of the model ontology. The L component in the Lab color space is used for representing the brightness of the pixel, the value range is [0, 100], and the L component represents pure black to pure white; a represents the range from red to green, and the value range is [127, -128 ]; b represents the range from yellow to blue, and the value range is [127, -128 ].

4. The term "saturation" in the embodiments of the present disclosure refers to the vividness of a color, also called the purity of the color. The saturation depends on the ratio of the color component and the achromatic component (gray) contained in the color. The larger the color content, the greater the saturation; the larger the achromatic component is, the smaller the saturation is. Pure colors are highly saturated, such as bright red, bright green. Mixed with a white, grey or other shade of color, is an unsaturated color such as magenta, pink, yellow-brown, etc. Fully unsaturated colors have no hue at all, such as various grays between black and white. Generally, the saturation value ranges from 0% to 100%, and the larger the value is, the more saturated the color is.

5. The term "brightness" in the embodiments of the present disclosure is also called brightness, and represents the brightness of a color. The shade may be different for colors of the same hue. For example, magenta and pink both contain red, but the former appears dark and the latter appears bright. Typically, the brightness ranges from 0% (black) to 100% (white).

6. The term "hue", also referred to as hue in the embodiments of the present disclosure, refers to the relative brightness of an image, and represents a color on a color image, and the value ranges from 0 ° to 360 ° measured by an angle, and is calculated from red in a counterclockwise direction, where red is 0 °, green is 120 °, and blue is 240 °. Specifically, hue is the primary characteristic of color, and is the most accurate standard for distinguishing various colors. Virtually any color other than black, white and gray has the attribute of hue, i.e., consisting of primary, secondary and multiple colors. Hue and color can present the texture and appearance. In nature, different hues are infinite and abundant, such as purplish red, silvery grey, orange yellow and the like. Hue is the appearance of various colors.

7. The term "color circle" in the embodiments of the present disclosure refers to a circular arrangement of color spectra (spectra), the colors being arranged in the order in which the spectra appear in nature. The WARM COLOR (WARM COLOR) is contained within the semicircle containing the COLORs red and yellow, and the cool COLOR is contained within the semicircle containing the COLORs green and violet. Complementary colors (complementary colors) appear at positions opposite to each other.

The color circle is divided into a twelve-color circle, a twenty-four-color circle, a thirty-six-color circle, a forty-eight-color circle, and the like. The twelve-color phase ring is formed by combining primary colors (primary hues), secondary colors (secondary hues) and tertiary colors (tertiary hues). The three primary colors in the hue ring are red, yellow and blue, which are equal in potential to each other and form an equilateral triangle in the ring. The secondary colors are orange, purple and green, and are located among the three primary colors to form another equilateral triangle. The six colors of red orange, yellow green, blue violet and red violet are three primary colors. The tertiary color is formed by mixing primary color and secondary color. The well-ordered color cycle allows the user to clearly see the result of color balance and blending.

The application scenario described in the embodiment of the present disclosure is for more clearly illustrating the technical solution of the embodiment of the present disclosure, and does not form a limitation on the technical solution provided in the embodiment of the present disclosure, and as a person having ordinary skill in the art knows, with the occurrence of a new application scenario, the technical solution provided in the embodiment of the present disclosure is also applicable to similar technical problems. Wherein, in the description of the present disclosure, unless otherwise indicated, "plurality" means.

Fig. 1 is a schematic view of an application scenario of the embodiment of the present disclosure. The application scenario diagram includes two terminal devices 110 and a server 130, and the terminal devices 110 can log in the related interface 120. The terminal device 110 and the server 130 can communicate with each other through a communication network.

In an alternative embodiment, the communication network is a wired network or a wireless network.

In the embodiment of the present disclosure, the terminal device 110 is an electronic device used by a user, and the electronic device may be a computer device having a certain computing capability and running instant messaging software and a website or social software and a website, such as a personal computer, a mobile phone, a tablet computer, a notebook, an e-book reader, and the like. Each terminal device 110 is connected to a server 130 through a wireless network, and the server 130 is a server or a server cluster or a cloud computing center formed by a plurality of servers, or is a virtualization platform.

Optionally, the server 130 may also have an image database that may store a large number of images.

In the embodiment of the present disclosure, the terminal device 110 may directly sort the local images according to the color features of the images and display the images to the user through the interface 120; or, when receiving a sorting request triggered by a user, the terminal device 110 sends the local image to the server 130, the server 130 obtains the color features of the received image and sorts the color features, the sorting result is sent to the terminal device 110, and then the terminal device 110 displays the sorting result to the user. Optionally, when the terminal device 110 detects an image search request triggered by a user, the terminal device 110 may also send a request to the server 130, the server 130 searches for an image, obtains color features of the searched image, sorts the image according to the color features, sends a sorting result to the terminal device 110, and displays the sorting result to the user by the terminal device 110, and so on.

FIG. 2 is a flowchart illustrating a method of image ranking, as shown in FIG. 1, including the following steps, according to an exemplary embodiment.

In step S21, acquiring a set of images to be sorted, wherein the set of images includes at least two images to be sorted;

in step S22, acquiring color features of each image in the image set, wherein the color features are determined according to a target color channel in a color space;

wherein, the color space includes but is not limited to some or all of the following:

HSV color space, HSI color space, HSL color space, RGB color space, CMY color space, Lab color space.

In the embodiment of the present disclosure, the target color channel refers to any one or more color channels in the color space, for example, an R color channel, a G color channel, and a B color channel in an RGB color space, a hue channel, a saturation channel, and a brightness channel in an HSV color space.

Accordingly, the color feature is determined according to the color channel in the color space, and the general color feature is based on the feature of the pixel point, and all the pixels belonging to the image or the image area have respective contributions. For example, when the target color channel is a saturation channel, the color feature is a feature representing color saturation in the image, and is referred to as a saturation component in the embodiment of the present disclosure, that is, the average value of the saturation of each pixel point in the saturation channel of the image in the HSV color space is also similar when the target color channel is another channel other than the saturation channel.

In step S23, some or all of the images in the image set are sorted according to color characteristics.

In the embodiment of the present disclosure, a method for sorting images based on an inherent attribute of color features of images is provided, where the color features of the images are determined according to a target color channel in a specific color space, that is, the color features corresponding to the target color channel, and there is no need to determine the capturing time of the images and manually determine the display order by a user, so that the operations of the user and the consumption of a certain user time can be reduced, and the sorting method of the images is enriched while the sorting efficiency is ensured.

In an optional implementation manner, after the image set to be sorted is obtained, each image in the image set may be scaled first, and the resolution of the image is reduced, so that the processing speed may be increased, and the sorting efficiency may be improved.

In the embodiment of the present disclosure, since there are many target color channels, there are many actual sorting manners after determining the color features of the image according to the target color channels, and the following details are described below:

in an alternative embodiment, some or all of the images in the image set are sorted according to the size of the color features of the images in any one of the target color channels.

For example, when the target color channel is a hue channel in the HSV color space, the color feature of the image under the hue channel is a hue component H. Specifically, for any image, the image is converted into HSV space, and an average value of hues of pixels in the image under a hue channel, that is, a hue component of the image, is obtained. All images in the image set may be sorted according to the size of the hue component. It is also possible to only apply to a part of the images in the image set, such as images from a certain software in a gallery, images taken by a cell phone in a gallery, etc.

There are various ways of sorting according to the size of the hue component, for example, sorting according to the hue component H from high to low; ordering the hue components H in order from low to high, and so on.

In another optional implementation, the image set is divided to obtain a plurality of image subsets, and then at least one image subset is selected as a target image subset from the plurality of image subsets divided from the image set according to the color interval; and aiming at any one target image subset, sequencing all the images in the target image subset according to the size of the color features of the images under at least one target color channel.

Each image subset has a corresponding color interval, and when at least one image subset is selected from the plurality of image subsets as a target image subset according to the color interval, actually, the selection modes are various, and automatic selection or manual selection can be performed. For example, an image subset corresponding to the yellow interval is selected as a target image subset, and when only one target image subset is selected, only images in the target image subset need to be sorted.

In an alternative embodiment, the color interval is determined according to a preset hue circle or a reference color template.

The preset color circle may be a twelve-color circle, a twenty-four-color circle, a thirty-six-color circle, etc., for example, the twelve-color circle shown in fig. 3 includes 12 color intervals, which are: yellow, orange red, purplish red, purple, blue-green, yellow-green, yellow. The reference color template may be a gradient color template, or a color template for design, etc., such as a color template for web page design, a color template for making a picture album, etc.

The above-mentioned color section determination method is only an example, and other methods are also applicable to the embodiment of the present disclosure, for example, determination is performed based on other gradient colors, and a color gradient is divided into several different color sections.

In the embodiment of the present disclosure, when a plurality of image subsets are selected as the target image subsets, a plurality of color intervals may be selected, and the image subsets corresponding to the selected color intervals are used as the target image subsets. Specifically, when the color interval is selected, color matching selection can be performed by using modes such as complementary colors, similar colors, triangular opponent color matching and the like.

For example, the selected color regions are complementary, and the complementary colors of the colors are complementary to each other, such as red and green, blue and orange, and purple and yellow, as shown in fig. 4A. In optics, two colors of light are mixed in a proper proportion to generate a white color feeling, and the two colors are called complementary colors. The complementary colors have very strong contrast, and under the condition of very high color saturation, many quite shocking visual effects can be created, so that the matching effect is easy to blend, and the user can be rich in change, brightness and brightness.

Or, the selected color intervals are similar, three adjacent hues with an included angle of 60 degrees on the hue circle are called as the same color or similar colors, and the matching of the similar colors is harmonious. For example: red-red orange-orange, yellow-yellow green-green, blue-blue violet-violet, etc. are all similar colors. The same color can make the user feel calm and comfortable due to the poor hue contrast, can make abundant texture and level in the same hue, and can express the natural, steady, written and elegant feeling.

Or, the selected color intervals are opposite, for example, as shown in fig. 4B, positions of the red, yellow and blue colors on the color circle just form an equilateral triangle, which belongs to the opposite color of the triangle; similarly, the positions of the three colors of green, orange and purple on the color ring just form an equilateral triangle, and the equilateral triangle also belongs to the opposite color of the triangle. In the disclosed embodiment, to find three mutually balanced colors, any three triangularly opposable colors on the twelve-color circle can be selected. The color matching is performed by using the colors on the triangular positions, so that the user can be provided with an open feeling without disorder. The color matching type is a stable color matching type and has visual sense of security.

It should be noted that, when the images in the target image subset are sorted according to the size of the color feature of the image in the at least one target color channel, the at least one target color channel may also be an R color channel, a G color channel, a B color channel in an RGB color space, a hue channel, a saturation channel, a brightness channel, and the like in an HSV color space.

For example, when the target color channels include an R color channel, a G color channel, and a B color channel, the images in the target image subset may be sorted by the size of the R color component.

When the target color channel includes both the saturation channel and the luminance channel, the corresponding color feature is a saturation component and a luminance component, and at this time, the images in the target image subset may be sorted according to the size of the saturation component and/or according to the size of the luminance component, which will be described in detail later.

In the embodiment of the present disclosure, there are many ways when the image set is divided into a plurality of image subsets, and the following methods are listed as follows:

the method comprises the following steps that if a target color channel comprises a tone channel and color features comprise tone components, images of which the tone components belong to the same color interval in an image set are divided into the same image subset.

In this way, the color space may be determined according to a preset color circle, taking the twelve color circle shown in fig. 3 as an example, when dividing images in an image set, firstly, a hue component H of each image needs to be obtained, a set formed by images of which H belongs to the same color interval is taken as an image subset, and assuming that an image subset a corresponding to a yellow interval, an image subset B corresponding to an orange interval, an image subset C corresponding to an orange interval, and image subsets D and … corresponding to an orange-red interval, a total of twelve image subsets may be obtained.

And if the target color channel comprises any color channel in the RGB color space, dividing the images of which the color components belong to the same color interval in the image set into the same image subset.

In this way, each image in the image set may be divided according to any one of the three color components, and the color interval may be determined according to a reference color template. Each color interval corresponds to the value ranges of the corresponding R color component, G color component, and B color component, and at this time, the image set can be divided into a plurality of image subsets according to the G color component.

And thirdly, classifying the image set according to the shooting mode and/or the shooting content to obtain at least one image subset, wherein different image subsets correspond to different color intervals.

In the embodiment of the present disclosure, there are many shooting modes, such as time-delay shooting, panoramic shooting, and the like; or when the image is shot through the mobile phone, the method can be divided into the following steps according to the placing mode of the mobile phone: horizontal shooting, vertical shooting and the like; or may be classified into a wide variety of photographing modes according to settings of various parameters (e.g., exposure, sensitivity, white balance, focus, etc.) when an image is photographed, and the like. The shooting contents may refer to people, animals, scenery, buildings, etc., and are not listed here.

For example, dividing the landscape picture into a subset, specifically including images of grassland, sea, blue sky, etc.; dividing the building picture into a subset, specifically comprising images of tall buildings, old foreign houses and the like; the gourmet pictures are divided into a subset, and specifically comprise images of various foods.

It should be noted that, in this manner, the color interval matched with each image subset may be determined according to a preset correspondence, for example, as shown in table 1, where it can be known that the landscape matches with a certain color interval of blue or green, and the architectural lighting matches with a certain color interval of red or brown according to the correspondence.

TABLE 1 Preset correspondences

Image sub-collection	Color interval
		Landscape picture	Blue and green
Building lamp	Red, brown
		Food photo	Yellow colour
…	…

It should be noted that the division methods listed in the embodiments of the present disclosure are also only examples, and in fact, besides the color components in the hue component H or RGB color space, other color-related features may also be used, such as color components in CMY color space, and any method of dividing the image is actually applicable to the embodiments of the present disclosure, and is not listed here.

The following describes in detail the steps of sorting the images in the target image subset according to the size of the color features of the images in at least one target color channel:

in an alternative embodiment, the color feature includes a first component, and the first component is a saturation component or a brightness component, and the images in the target image subset are sorted according to the size of the first component. In this manner, the target color channel includes a saturation channel and/or a brightness channel.

When the first component is a saturation component, for any image, the saturation component S of the image is an average value of the saturation of each pixel of the image in a saturation channel.

When the first component is a luminance component, for any one image, the luminance component V of the image can be determined in two ways:

determining a first mode, and taking the average value of the brightness values of all pixel points in the image as the brightness component of the image.

And determining a second mode, wherein the mean value of the brightness values of all target pixel points in the image is used as the brightness component of the image, wherein the target pixel points are pixel points of which the brightness values are within a specified brightness range, namely pixel points of which the brightness values are greater than a first threshold value and/or less than a second threshold value, and the first threshold value is less than the second threshold value.

For example, the first threshold is 5%, when the luminance component of the image a is calculated, the pixel points with the luminance value less than 5% are removed, and the average value of the luminance values of the remaining pixel points is used as the luminance component of the image a.

Or, for example, when the second threshold is 95%, when calculating the luminance component of the image B, eliminating the pixel points whose luminance values are greater than 95%, and taking the average value of the luminance values of the remaining pixel points as the luminance component of the pixel B.

In this way, areas that are too bright or too dark in the luminance channel can be excluded, so that the sorting effect is better.

Specifically, when the images in the target image subset are sorted according to the size of the first component, the images in the target image subset may be sorted according to the order from high to low or from low to high of the first component.

Another optional embodiment is that, on the basis that the color feature includes the first component, if the color feature further includes the second component, after the step of sorting the images in the target image subset according to the size of the first component, for any one target image subset, the first target image in the target image subset is reordered according to the size of the second component, where the first target image is an image in the target image subset whose first component is sorted within a specified order range.

It should be noted that, when the first component is a saturation component, the second component is a luminance component; or when the first component is a luminance component, the second component is a saturation component.

For example, there are 30 images in the target image subset, the first component being a saturation component and the second component being a luminance component. The 30 images in the target image subset are first sorted in order of high to low saturation. Assuming that the specified order range is the top 1/3 images when sorted from high to low in saturation, when the first target image is sorted according to the magnitude of the luminance component, only the top 10 images of the 30 images need to be sorted again, the top 10 images are the first target images, and the remaining 20 images do not need to be sorted again according to the luminance component.

In the above embodiment, if a plurality of target image subsets are combined, in addition to sorting the images in each target image subset, each target image subset may be further sorted. Optionally, the order between the target image subsets is determined according to the color intervals corresponding to the target image subsets.

For example, the image set is divided into 12 image subsets according to the hue component H, and the 12 image subsets correspond to 12 color segments in a twelve-hue ring. Suppose that the four selected target image subsets are: the image subset a, the image subset B, and the image subset C are image subsets D, the color intervals corresponding to the four image subsets are yellow, orange, and orange red, respectively, and at this time, the order between each target image subset can be determined according to the positions of the color intervals in the twelve-color hue ring, for example, the order is: an image subset A corresponding to a yellow section, an image subset B of an orange section, an image subset C of an orange section and an image subset D of an orange section.

In the above embodiment, since the color intervals corresponding to the target image subsets are selected in color matching manners such as complementary colors, triangular opposite colors, similar colors, and the like, after the order between the target image subsets is determined according to the color intervals corresponding to the target image subsets, the color transformation between the images obtained according to the order is very soft, the form of the similar gradient color is close, or the contrast is very obvious, the display effect is relatively beautiful, and the user experience can be enhanced.

It should be noted that, when the images in the target image subset are sorted according to the size of the first component, there may be many sorting manners in consideration of the order between the target image subsets, and the following may be listed as follows:

in the first sorting mode, in the adjacent target image subsets, the first component of each image in one target image subset is from high to low, and the first component of each image in the other target image subset is from low to high.

Taking the four target image subsets as an example, taking the image subset a and the image subset B as examples, assuming that the first component is a saturation component, if the saturation component of each image in the image subset a is from high to low, the saturation component of each image in the image subset B is from low to high. The image subset B is adjacent to the image subset C, the saturation component of each image in the image subset B is from low to high, and the saturation component of each image in the image subset C is from high to low. Next, the image subset C is adjacent to the image subset D, the saturation component of each image in the image subset C is from high to low, the saturation component of each image in the image subset D is from low to high, and the display effect is as shown in fig. 5.

In this way, if the color feature further includes a second component, where the second component is a luminance component, the first target images in each target image subset are sorted again according to the second component, and finally, the image in the border between the two target image subsets is either lower in saturation, lighter in color, or lower in luminance, and darker in this way, the color transition of the image can be relaxed, and the effect is better and more beautiful.

And in the second sorting mode, the first components of all the images in each target image subset are from high to low.

Taking the above four subsets of target images as an example, the saturation components of each image in the image subset A, B, C, D are all from high to low.

And in the third sorting mode, the first components of all the images in each target image subset are all from low to high.

Taking the above four subsets of target images as an example, the saturation components of each image in the image subset A, B, C, D are all from low to high.

The same is true when the first component is a luminance component and the second component is a saturation component, which is not described herein again.

It should be noted that, the sorting manner of the first components of the images in the several target image subsets listed in the foregoing embodiments is only an example, and any other sorting manner according to the size of the first components is applicable to the embodiments of the present disclosure, for example, the first components of the images in a smaller part of the target image subsets are all from high to low, the first components of the images in a larger part of the target image subsets are all from low to high, and so on.

In the embodiment of the present disclosure, depending on the application, all images may be sorted, and a part of the images may be sorted. When selecting the images, an optional implementation is as follows:

classifying the images in the target image library according to the shooting mode and/or the shooting content to obtain at least one image set; and taking the image set meeting the preset condition in at least one image set as an image set to be sorted.

In the embodiment of the present disclosure, the target image library may be an album of a mobile phone of a user, an gallery/album on a computer, or an album, etc., wherein the images may be images of long images, photos, albums, etc. For example, when analyzing all or a large number of images in a user's mobile phone album, the images may be divided according to some clustering rules, for example, the images shot horizontally are divided into an image set called image set 1, and the images shot vertically are divided into an image set called image set 2. Or, dividing the images in the photo album into several image sets such as photos for holiday tour, photos away from the ordinary residence, landscape photos, architectural photos and the like according to the shooting contents.

After the target image library is divided into at least one image set, at least one image set meeting a preset condition may be used as an image set to be sorted, for example, if the preset condition is a horizontal shot image, the image set to be sorted is an image set 1. For example, the preset condition is an image whose shooting time is X months and X days after X months, and assuming that the images meeting the preset condition are all the photos in the target image library, the image set to be sorted may include all the photos, or may include only some of the photos, such as landscape photos and architectural photos.

Then, the images may be sorted according to their color characteristics, and several sorting methods are described below:

in an alternative embodiment, the color feature includes a third component, the third component being a saturation component or a luminance component; and for any image set, sorting the images in the image set according to the size of the third component.

Assuming that the image sets to be sorted include landscape photographs and architectural photographs, actually representing that there are two image sets to be sorted, the sorting may be performed in the above manner for any one of the landscape photographs and the architectural photographs.

For example, for a landscape shot, the third component is a saturation component, and the landscape shots may be sorted according to the magnitude of the saturation component.

In an alternative embodiment, the color feature further comprises a fourth component; for any image set, after the images in the image set are sorted according to the size of the third component, the second target image in the image set is reordered according to the size of the fourth component, wherein the second target image is the image in the image set, and the third component of the second target image is sorted in a specified order range; wherein, the third component is a saturation component, and the fourth component is a brightness component; or the third component is a luminance component and the fourth component is a saturation component.

Still taking landscape shots as an example, the third component is a saturation component, the fourth component is a brightness component, and after the respective landscape shots are sorted from high to low according to the saturation component, the image at the top 1/3 is taken as the second target image, and the second target image is re-sorted according to the brightness component again, for example, the image at the top 1/3 is re-sorted according to the brightness component from high to low.

It should be noted that before the images are sorted according to the size of the saturation component, the images may be classified again and divided into a plurality of image subsets, where the classification may be performed by any one of the first, second, and third division methods listed above, and repeated details are omitted here. Of course, the same applies to the case where the third component is a luminance component and the fourth component is a saturation component.

In the embodiment of the present disclosure, after the image set to be sorted is obtained, the corresponding color interval may be matched for the image set according to the clustering result, most of general landscape photographs are blue or green, and architectural photographs are matched with hues such as red or brown, that is, the corresponding color interval is matched for the image set according to the results of scene classification, target identification, and the like, and then the images are sorted … … according to the saturation component S, the brightness component V, and the like, and repeated parts are not described again. The order between the image sets may be determined according to the color intervals corresponding thereto, for example, when a landscape photograph is displayed and then a building photograph is displayed, the saturation components of the landscape photographs may be ranked from high to low and the saturation components of the building photographs may be ranked from low to high, so that the display effect is from a first color from deep to light and then from light to deep from a second color, and the like.

It should be noted that the luminance component mentioned in any of the embodiments of the present disclosure may be calculated by using one of the two determination methods listed in the above embodiments.

Fig. 6 is a flowchart illustrating a complete method for image sorting according to an exemplary embodiment, which specifically includes the following steps:

s61: acquiring an image set to be sorted;

s62: scaling each image in the image set to a smaller resolution;

s63: converting each zoomed image into an HSV color space;

s64: acquiring hue components H, saturation components S and brightness components V of each image;

s65: dividing the images of which the tone components H in each image fall within the same color interval into an image subset, wherein the color intervals are divided according to a twelve-tone color ring;

s66: and selecting four color intervals from the twelve-color phase ring, and sequencing the images in the image subset corresponding to each color interval according to the saturation, and then sequencing the images in the partial image with higher saturation according to the brightness V mean value.

The image subsets corresponding to the four color intervals are target image subsets, and the order between the target image subsets may be determined according to the color intervals, for example, the order listed in the above embodiment is as follows: an image subset A corresponding to a yellow section, an image subset B of an orange section, an image subset C of an orange section and an image subset D of an orange section.

Fig. 7 is a block diagram illustrating an image sorting apparatus 700 according to an exemplary embodiment. Referring to fig. 7, the apparatus includes an image acquisition unit 701, a feature acquisition unit 702, and a sorting unit 703.

An image acquisition unit 701 configured to perform acquiring a set of images to be sorted, wherein the set of images includes at least two images to be sorted;

a feature obtaining unit 702 configured to perform obtaining color features of respective images in the image set, wherein the color features are determined according to a target color channel in a color space;

a sorting unit 703 configured to perform sorting of some or all of the images in the image set according to color characteristics.

In an optional implementation, the sorting unit 703 is specifically configured to perform:

and sorting part or all of the images in the image set according to the size of the color features of the images under any one target color channel.

selecting at least one image subset as a target image subset from a plurality of image subsets obtained by dividing an image set according to a color interval;

and aiming at any one target image subset, sequencing all the images in the target image subset according to the size of the color features of the images under at least one target color channel.

In an alternative embodiment, the sorting unit 703 is further configured to perform the dividing of the image set by:

In an alternative embodiment, the color feature includes a first component, the first component being a saturation component or a luminance component;

the sorting unit 703 is specifically configured to perform:

the images in the target image subset are ordered by the size of the first component.

after sorting the respective images of the target subset of images by the size of the first component, the sorting unit 703 is further configured to perform:

for any one target image subset, reordering the first target images in the target image subset according to the size of the second component, wherein the first target images are images in the target image subset, the first components of which are ordered in a specified order range;

In an alternative embodiment, the target image subset is a plurality;

the sorting unit 703 is further configured to perform:

In an alternative embodiment, the image acquisition unit 701 is specifically configured to perform:

and taking the image set meeting the preset condition in at least one image set as an image set to be sorted.

In an alternative embodiment, the color feature includes a third component, the third component being a saturation component or a luminance component;

the sorting unit 703 is specifically configured to perform:

after sorting the respective images of the image set by the size of the third component, the sorting unit 703 is further configured to perform:

for any image set, reordering a second target image in the image set according to the size of the fourth component, wherein the second target image is an image in the image set, the third component of which is ordered in a specified order range;

wherein, the third component is a saturation component, and the fourth component is a brightness component; or the third component is a luminance component and the fourth component is a saturation component.

the feature acquisition unit 702 is further configured to perform determining a luminance component of any one of the images by:

And taking the average value of the brightness values of all target pixel points in the image as the brightness component of the image, wherein the target pixel points are pixel points of which the brightness values are within the specified brightness range.

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

Fig. 8 is a block diagram illustrating an electronic device 800 according to an example embodiment, the apparatus comprising:

a processor 801;

a memory 802 for storing instructions executable by the processor 801;

wherein the processor 801 is configured to execute instructions to implement any one of the image ordering methods in the embodiments of the present disclosure.

In an exemplary embodiment, a storage medium comprising instructions, such as the memory 802 comprising instructions, executable by the processor 801 of the electronic device 800 to perform the above-described method is also provided. Alternatively, the storage medium may be a non-transitory computer readable storage medium, 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.

In an embodiment of the present disclosure, there is also provided a terminal device, a structure of which is shown in fig. 9, and a terminal 900 for image sorting according to an embodiment of the present disclosure includes: a Radio Frequency (RF) circuit 910, a power supply 920, a processor 930, a memory 940, an input unit 950, a display unit 960, a camera 970, a communication interface 980, and a Wireless Fidelity (Wi-Fi) module 990. Those skilled in the art will appreciate that the configuration of the terminal shown in fig. 9 is not intended to be limiting, and that embodiments of the present disclosure provide terminals that include more or less components than those shown, or that combine certain components, or that are arranged in different components.

The various components of terminal 900 are described in detail below with reference to fig. 9:

the RF circuit 910 may be used for receiving and transmitting data during a communication or conversation. In particular, RF circuit 910 sends the downlink data of the base station to processor 930 for processing; and in addition, sending the uplink data to be sent to the base station. In general, RF circuit 910 includes, but is not limited to, an antenna, at least one Amplifier, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like.

In addition, the RF circuit 910 may also communicate with networks and other terminals through wireless communication. The wireless communication may use any communication standard or protocol, including but not limited to Global System for mobile communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), etc.

Wi-Fi technology belongs to short distance wireless transmission technology, terminal 900 can connect Access Point (AP) through Wi-Fi module 990, thus realize the visit of the data network. The Wi-Fi module 990 may be used for receiving and transmitting data during communication.

Terminal 900 can be physically connected to other terminals via communication interface 980. Optionally, the communication interface 980 is connected to a communication interface of another terminal through a cable, so as to implement data transmission between the terminal 900 and the other terminal.

Since the terminal 900 can implement a communication service to send information to other contacts in the embodiment of the present disclosure, the terminal 900 needs to have a data transmission function, that is, the terminal 900 needs to include a communication module inside. Although fig. 9 illustrates communication modules such as RF circuitry 910, Wi-Fi module 990, and communication interface 980, it will be understood that at least one of the above-described components or other communication modules (e.g., bluetooth modules) for enabling communication may be present in terminal 900 for data transmission.

For example, when the terminal 900 is a cellular phone, the terminal 900 can include the RF circuit 910 and can also include the Wi-Fi module 990; when the terminal 900 is a computer, the terminal 900 can include a communication interface 980 and can also include a Wi-Fi module 990; when the terminal 900 is a tablet, the terminal 900 can include a Wi-Fi module.

Memory 940 may be used to store software programs and modules. The processor 930 executes various functional applications and data processing of the terminal 900 by executing software programs and modules stored in the memory 940, and part or all of the processes in fig. 2 of the embodiments of the present disclosure can be implemented when the processor 930 executes the program codes in the memory 940.

Alternatively, the memory 940 may mainly include a program storage area and a data storage area. The storage program area can store an operating system, various application programs (such as communication application), a face recognition module and the like; the storage data area may store data (such as various multimedia files like pictures, video files, etc., and face information templates) created according to the use of the terminal, etc.

Further, memory 940 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.

The input unit 950 may be used to receive numeric or character information input by a user and generate key signal inputs related to user settings and function control of the terminal 900.

Alternatively, the input unit 950 may include a touch panel 951 and other input terminals 952.

Among other things, the touch panel 951, also referred to as a touch screen, can collect touch operations of a user (e.g., operations of a user on or near the touch panel 951 using any suitable object or accessory such as a finger or a stylus) and drive a corresponding connection device according to a preset program. Alternatively, the touch panel 951 may include two parts, a touch detection device and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device, converts it into touch point coordinates, and then sends the touch point coordinates to the processor 930, and can receive and execute commands sent from the processor 930. In addition, the touch panel 951 may be implemented in various types such as a resistive type, a capacitive type, an infrared ray, and a surface acoustic wave.

Optionally, other input terminals 952 may include, but are not limited to, one or more of a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.

The display unit 960 may be used to display information input by or provided to a user and various menus of the terminal 900. The display unit 960 is a display system of the terminal 900, and is used for presenting an interface and implementing human-computer interaction.

The display unit 960 may include a display panel 961. Alternatively, the Display panel 961 may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like.

Further, the touch panel 951 may cover the display panel 961, and when the touch panel 951 detects a touch operation thereon or nearby, the touch panel 951 transmits the touch operation to the processor 930 to determine the type of the touch event, and then the processor 930 provides a corresponding visual output on the display panel 961 according to the type of the touch event.

Although in fig. 9, the touch panel 951 and the display panel 961 are two separate components to implement the input and output functions of the terminal 900, in some embodiments, the touch panel 951 and the display panel 961 may be integrated to implement the input and output functions of the terminal 900.

The processor 930 is a control center of the terminal 900, connects the respective components using various interfaces and lines, performs various functions of the terminal 900 and processes data by operating or executing software programs and/or modules stored in the memory 940 and calling data stored in the memory 940, thereby implementing various terminal-based services.

Optionally, processor 930 may include one or more processing units. Alternatively, processor 930 may integrate an application processor that handles primarily operating systems, user interfaces, application programs, etc. and a modem processor that handles primarily wireless communications. It is to be appreciated that the modem processor described above may not be integrated into processor 930.

And a camera 970 for implementing a shooting function of the terminal 900 and shooting a picture or a video. The camera 970 can also be used to implement a scanning function of the terminal 900 to scan a scanning object (two-dimensional code/barcode).

Terminal 900 also includes a power supply 920 (e.g., a battery) for powering the various components. Optionally, the power supply 920 may be logically connected to the processor 930 through a power management system, so as to manage charging, discharging, and power consumption functions through the power management system.

It is noted that the processor 930 of the embodiment of the disclosure may perform the functions of the processor 801 in fig. 8, and the memory 940 stores the contents of the memory 802.

The embodiments of the present disclosure further provide a computer program product, which when run on an electronic device, causes the electronic device to execute any one of the image sorting methods described above in the embodiments of the present disclosure or any one of the methods that may be involved in any one of the image sorting methods.

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

It will be understood that the present disclosure 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 disclosure is limited only by the appended claims.

Claims

1. A method of image ranking, comprising:

2. The method of claim 1, wherein the ordering of some or all of the images in the set of images according to the color feature comprises:

3. The method of claim 1, wherein the ordering of some or all of the images in the set of images according to the color feature comprises:

4. The method of claim 3, wherein the set of images is partitioned by:

5. The method of claim 4, wherein the color interval is determined according to a preset color circle or a reference color template.

6. The method of claim 3, wherein the color feature comprises a first component, the first component being a saturation component or a luminance component;

7. The method of claim 6, wherein the color feature further comprises a second component;

8. An image sorting apparatus, comprising:

9. An electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the image ordering method of any one of claims 1 to 7.

10. A storage medium, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the image sorting method of any one of claims 1 to 7.