Image Classification Method and Device

Abstract

The present application discloses an image classification method and apparatus, belonging to the field of communication technologies. The image classification method includes: receiving a first input from a user; in response to the first input, displaying N category labels corresponding to a target image, where N is an integer greater than or equal to 2; receiving a second input from the user for a target category label, where the target category label is one of the N category labels; and in response to the second input, saving the target image to a target category album corresponding to the target category label. The technical solution provided by the embodiments of the present application can save the target image to the corresponding target category album, achieve accurate classification of the target image that meets the user's needs, and at the same time ensure the diversification of classification.

Description

Technical Field

[0001] This application belongs to the field of communication technologies, and particularly relates to an image classification method and apparatus. Background Art

[0002] With the continuous upgrade of the hardware of electronic devices, the shooting function of electronic devices has been continuously improved, and the image effects obtained by shooting with electronic devices are also getting better and better. At the same time, the album function for storing the captured images has also been continuously improved, and more and more users choose to use electronic devices for shooting. As the content stored in the electronic device album continues to increase, in order to facilitate the effective management of images, classifying images has become the preferred method.

[0003] In the prior art, when performing image classification, it is usually based on an intelligent classification algorithm to identify the content of the image, and the image is classified into the corresponding category according to the recognition result. However, usually, an image may have multiple element labels. When classifying the image according to the content recognition, multiple categories may be determined. At this time, the intelligent classification algorithm usually determines the category with the highest correlation with the image as the image category. This classification method has the problem of inaccurate classification because it only considers the correlation. Summary of the Invention

[0004] The purpose of the embodiments of this application is to provide an image classification method and apparatus, which can, to a certain extent, solve the problem of inaccurate classification existing in the image classification method in the prior art.

[0005] To solve the above technical problems, this application is implemented as follows:

[0006] In a first aspect, the embodiments of this application provide an image classification method, including:

[0007] Receiving a first input from a user;

[0008] In response to the first input, displaying N category labels corresponding to the target image, where N is an integer greater than or equal to 2;

[0009] Receiving a second input from the user for the target category label, where the target category label is one of the N category labels;

[0010] In response to the second input, saving the target image to the target category album corresponding to the target category label.

[0011] In a second aspect, the embodiments of this application provide an image classification apparatus, including:

[0012] A first receiving module, configured to receive a first input from a user;

[0013] A display module, configured to display N category labels corresponding to a target image in response to the first input, where N is an integer greater than or equal to 2;

[0014] A second receiving module, configured to receive a second input from a user for a target category label, where the target category label is one of the N category labels;

[0015] A saving module, configured to save the target image to a target category album corresponding to the target category label in response to the second input.

[0016] In a third aspect, an embodiment of the present application provides an electronic device, including: a processor, a memory, and a program or instruction stored on the memory and executable on the processor, where when the program or instruction is executed by the processor, the steps in the image classification method as described in the first aspect are implemented.

[0017] In a fourth aspect, an embodiment of the present application provides a readable storage medium, where a program or instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, the steps of the image classification method as described in the first aspect are implemented.

[0018] In a fifth aspect, an embodiment of the present application provides a chip, where the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run a program or instruction to implement the image classification method as described in the first aspect.

[0019] In the embodiments of the present application, by displaying N category labels for a target image, at least two category labels can be provided for the user to select. The user determines the target category label from the N category labels, and saves the target image to the target category album corresponding to the target category label, which can achieve accurate classification of the target image through simple operations and meet the user's personalized classification needs. At the same time, since at least two category labels are provided, the diversification of classification can be achieved. Description of the Drawings

[0020] Figure 1 is a schematic flowchart of the image classification method provided by the embodiment of the present application;

[0021] Figure 2 is a schematic diagram of displaying a classification control on a shooting interface provided by the embodiment of the present application;

[0022] Figure 3 is a schematic diagram of controlling a target category label to be prominently displayed provided by the embodiment of the present application;

[0023] Figure 4 is a schematic diagram of displaying a first category label and a second category label provided by the embodiment of the present application;

[0024] Figure 5a It is a schematic diagram of performing a rotation operation on a classification control provided by an embodiment of the present application;

[0025] Figure 5b It is a schematic diagram of displaying the updated classification control provided by an embodiment of the present application;

[0026] Figure 6 It is a schematic diagram of locking a target category label provided by an embodiment of the present application;

[0027] Figure 7 It is an example flowchart of determining a target category label among N first category labels and classifying and saving a target image provided by an embodiment of the present application;

[0028] Figure 8 It is an example flowchart of determining a target category label among a first category label and a second category label and classifying and saving a target image provided by an embodiment of the present application;

[0029] Figure 9 It is a block diagram of an image classification device provided by an embodiment of the present application;

[0030] Figure 10 It is one of the schematic block diagrams of an electronic device provided by an embodiment of the present application;

[0031] Figure 11 It is the second schematic block diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0032] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0033] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same category, and the number of objects is not limited. For example, the first object can be one or multiple. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character " / ", generally represents an "or" relationship between the associated objects before and after.

[0034] The following will combine the accompanying drawings and, through specific embodiments and their application scenarios, elaborate in detail on the image classification method provided by the embodiments of the present application.

[0035] The embodiments of the present application provide an image classification method, as Figure 1 shown, including:

[0036] Step 101: The electronic device receives a first input from the user.

[0037] The image classification method provided by the embodiments of the present application is applied to an electronic device. The electronic device can first receive a first input executed by the user. Here, the first input can be a first input for the target image or an input for the display interface corresponding to the target image, and the first input includes but is not limited to click, press, and slide inputs.

[0038] Step 102: The electronic device, in response to the first input, displays N category labels corresponding to the target image, where N is an integer greater than or equal to 2.

[0039] After receiving the first input, the electronic device can, in response to the first input, display at least two category labels of the target image. Among them, the target image can be a real-time captured image or an unclassified image stored in the local image database. For a real-time captured image, after the capture is completed, N category labels can be displayed according to the user's first input and are displayed through a classification control. Here, the first input can be a first input for the capture button or a first input for the target image obtained by capture. Specifically, after the capture is completed, a blank classification control is displayed, and according to the user's first input, N category labels corresponding to the target image are displayed through the classification control; it is also possible to display a classification control including the category labels corresponding to the previous image after the capture is completed, and according to the user's first input, update the category labels in the classification control, that is, display N category labels corresponding to the target image through the classification control. Optionally, a classification control (which can be a blank classification control or a classification control including the category labels corresponding to the previous image) can also be displayed after the capture is completed. If no input for the current display interface is detected within the first duration, it is triggered to display N category labels corresponding to the target image through the classification control. For an unclassified image stored in the local image database, according to the user's first input for the selected image (target image), a classification control including N category labels corresponding to the target image can be displayed. Before the first input is executed on the target image, a blank classification control or a classification control including the category labels corresponding to the previous image can be displayed.

[0040] Among them, the form of the classification control is not specifically limited and can be circular, rectangular, etc. The classification control can display at least two category labels, and here the category labels are associated with the target image and are the category information of the target image obtained through relevant processing.

[0041] Among them, for the case where the target image is a real-time captured image, by triggering the display of the classification control including N category labels corresponding to the target image after the shooting is completed, the realization of fast classification can be ensured. For example, see Figure 2 As shown, after the target image is captured and obtained, the captured target image is displayed on the shooting interface. At this time, the display of the classification control including N category labels corresponding to the target image can be triggered (such as triggered according to the user's first input). A concentric circular classification control appears centered on the shooting button, and location category labels, sky category labels, travel category labels, and landscape category labels are displayed on the circle, providing guarantee for realizing fast classification.

[0042] For the case where the target image is an unclassified image in the local image database, when the user browses the local image database, after the user selects the target image, the display of the classification control including N category labels corresponding to the target image can be triggered to realize the classification of the stored images.

[0043] Step 103: The electronic device receives a second input from the user for the target category label, and the target category label is one of the N category labels.

[0044] After the N category labels corresponding to the target image are displayed, a second input from the user for the target category label among the N category labels can be received. The second input includes but is not limited to click, press, selection, and sliding input.

[0045] Among them, after receiving the second input from the user for the target category label, the target category label can be controlled to be displayed in a display style different from other category labels, such as controlling the target category label to be highlighted, enlarged, bolded, etc., so that the user can quickly identify the target category label. See Figure 3 As shown, according to the user's sliding input to the position where the sky category label is located, it is determined that the sky category label is the target category label, and the sky category label is controlled to be bolded.

[0046] Step 104: The electronic device responds to the second input and saves the target image to the target category album corresponding to the target category label.

[0047] After receiving the second input executed by the user, the image category of the target image (the image category corresponding to the target category label) can be determined in response to the second input of the user. After determining the image category of the target image, the target image can be saved to the target category album corresponding to the target category label, realizing the classified storage of the target image.

[0048] For example, in response to the user's selection input for a certain category label among N category labels, it is determined that the selected category label is the target category label, and then the image category corresponding to the target category label is determined as the image category of the target image, and the target image is saved to the corresponding location according to the determined image category. Or, in response to the user's sliding input to the location where a certain category label is located, it is determined that the category label is the target category label, and then the image category corresponding to the target category label is determined as the image category of the target image, and the target image is saved to the corresponding location.

[0049] Optionally, it is also possible to receive the click input executed by the user on a specific location of the classification control, select different category labels one by one, and determine the selected category label as the target category label when the user stops clicking, and then determine the image category corresponding to the target category label as the image category of the target image.

[0050] In the embodiments of the present application, by displaying N category labels for the target image, at least two category labels can be provided for the user to select. The user determines the target category label among the N category labels, and saves the target image to the target category album corresponding to the target category label, which can achieve accurate classification of the target image through simple operations and meet the user's personalized classification needs. At the same time, since at least two category labels are provided, the diversification of classification can be realized.

[0051] In an optional embodiment of the present application, the N category labels are determined according to at least one of a preset category division method and an image category matching method;

[0052] The display of the N category labels corresponding to the target image includes one of the following steps:

[0053] Display the N first category labels corresponding to the target image through the classification control;

[0054] Display the N second category labels corresponding to the target image through the classification control;

[0055] Display a classification control including a first sub-control and a second sub-control, where the first sub-control corresponds to the first category label, the second sub-control corresponds to the second category label, and the sum of the number of the first category labels and the second category labels is N;

[0056] Among them, the first category label is a category label determined according to the preset category division method, and the second category label is a category label determined according to the image category matching method.

[0057] In the embodiments of the present application, the N category labels displayed can be determined according to the preset category division method, or can be determined according to the image category matching method, or can also be determined according to the preset category division method and the image category matching method. Among them, the category label determined according to the preset category division method is the first category label, and the category label determined according to the image category matching method is the second category label. When displaying the N category labels, the N first category labels corresponding to the target image can be displayed through the classification control, or the N second category labels corresponding to the target image can be displayed through the classification control, or the first category label and the second category label corresponding to the target image can be displayed through the classification control, where the sum of the number of the first category label and the second category label is N.

[0058] For the case of displaying the first category label and the second category label corresponding to the target image through the classification control, the classification control may include a first sub-control and a second sub-control, and the first sub-control correspondingly displays the first category label, and the second sub-control correspondingly displays the second category label. For example, see Figure 4 As shown, the left half area of the circular classification control is the first sub-control, and the right half area of the circular classification control is the second sub-control. The first category label (scenery category label and travel category label) determined according to the preset category division method is displayed in the first sub-control, and the second category label (portrait category label and emoji category label) determined according to the image category matching method is displayed in the second sub-control. Among them, there may be a situation where the first category label determined based on the preset category division method is the same as the second category label determined based on the image category matching method, but before display, the same category labels need to be filtered, and only one category label is retained to avoid the situation that the classification control displays two identical category labels.

[0059] For the case of displaying the first category label through the classification control, by displaying the first category label determined according to the preset category division method, it is convenient for the user to select the target category label from the N first category labels according to the needs; for the case of displaying the second category label through the classification control, by displaying the second category label determined according to the image category matching method, it is convenient for the user to select the target category label from the N second category labels according to the needs; for the case of displaying the first category label and the second category label corresponding to the target image through the classification control, by displaying the first category label determined according to the preset category division method and the second category label determined according to the image category matching method, the category labels in the classification control are enriched, which is convenient for the user to make a reasonable selection according to the needs.

[0060] In the embodiments of the present application, a classification control corresponding to the first category label, a classification control corresponding to the second category label, or a classification control corresponding to the first category label and the second category label can be displayed, enriching the display content of the classification control.

[0061] Before displaying the N category labels corresponding to the target image in an alternative embodiment of the present application, the following steps are further included:

[0062] Perform content recognition on the target image to obtain a recognition result;

[0063] Obtain the N category labels according to the recognition result.

[0064] Before displaying the N category labels corresponding to the target image, content recognition can be performed on the target image to obtain a corresponding recognition result. After obtaining the recognition result, the N category labels can be obtained based on the obtained recognition result for display through the classification control. Among them, the recognition result corresponding to the target image can include at least one object. When obtaining the N category labels according to the recognition result, one of the following steps is included:

[0065] Determine the category corresponding to the recognition result according to the preset category division method, obtain N first category labels corresponding to the recognition result, and determine the display priority of each first category label;

[0066] Perform similarity matching between the recognition result and the preset image categories, determine N second category labels according to the similarity matching result, and determine the display priority of each second category label;

[0067] Determine the first number of the first category labels corresponding to the recognition result according to the preset category division method, determine the second number of the second category labels according to the similarity matching result between the recognition result and the preset image categories, and obtain the N category labels according to the first number of the first category labels and the second number of the second category labels. Among them, the display priority of each first category label is determined when determining the first number of the first category labels, and the display priority of each second category label is determined when determining the second number of the second category labels.

[0068] When obtaining N category labels according to the recognition result, for the recognition result including at least one object, the corresponding category can be determined based on the attribute features corresponding to the at least one object according to the preset category division method. After obtaining the category, the corresponding N first category labels can be obtained according to the category. Among them, when obtaining the N first category labels, the display priority corresponding to each first category label can also be determined based on the proportion of the object in the image, and the proportion is positively correlated with the display priority, and the greater the proportion, the higher the priority. Of course, determining the display priority based on the proportion is only one implementation method, and other methods (such as setting the display priority according to the importance level of the object, setting the display priority according to the category of the object, etc.) can also be used, which will not be listed and elaborated here.

[0069] The above process will be illustrated by examples below. For example, after content recognition of the target image, the recognition result including a human object, a grassland object, and a house object is obtained, and the proportion of the human object is 60%, the proportion of the grassland object is 25%, and the proportion of the house object is 15%. Then, the human category can be determined according to the human object, the landscape category can be determined according to the grassland object, and the building category can be determined according to the house object. Then, N first category labels (human category label, landscape category label, and building category label) are obtained. Since the proportions of the human object, the grassland object, and the house object decrease in turn, the human category label is determined as the highest display priority, the landscape category label is determined as the second display priority, and the building category label is determined as the lowest display priority. Or, after content recognition of the target image, the recognition result including a human object is obtained. Then, N first category labels can be determined according to the relevant features of the human object. For example, the female category can be determined according to the gender of the human object, the adult category can be determined according to the age of the human object, and the short hair category can be determined according to the hairstyle of the human object. Then, N first category labels (female category label, adult category label, short hair category label) are obtained. Among them, according to the preset rules, the attention levels (importance levels) of gender, age, and hairstyle decrease in turn. Therefore, the female category label is determined as the highest display priority, the adult category label is determined as the second display priority, and the short hair category label is determined as the lowest display priority.

[0070] In the above process, by obtaining N first category labels according to the preset category division method and determining the display priority of each first category label, the first category labels can be displayed in the classification control according to the display priority, ensuring the orderliness of the display.

[0071] When obtaining N category labels according to the recognition result, the recognition result can also be matched with a preset image category (the preset image category is each image category corresponding to the local album of the electronic device) in accordance with the image category matching method to obtain a similarity matching result, and N second category labels are determined based on the obtained similarity matching result. When determining the N second category labels, a corresponding display priority can be determined for each second category label. Among them, when determining the display priority, it can be determined based on the similarity level, and the similarity is positively correlated with the display priority, that is, the greater the similarity, the higher the priority. Of course, determining the display priority based on the similarity is only one implementation method, and other methods (such as setting the display priority according to the importance level of the image category) can also be adopted, which will not be listed and elaborated here.

[0072] The following is an example to illustrate this process. For example, after content recognition of a target image, a recognition result including a face object and a pool object is obtained. The recognition result is matched with each local image category (emoji category, tree category, pet category, and scenic spot category) for similarity. Among them, the similarity between the recognition result and the emoji category is 60%, and the similarity between the recognition result and the scenic spot category is 30%. Then, N second category labels (emoji category label, scenic spot category label) are obtained. Since the similarity between the recognition result and the emoji category is greater than that with the scenic spot category, it is determined that the display priority of the emoji category label is higher than that of the scenic spot category label.

[0073] It should be noted that when determining N second category labels based on the image category matching method, the frequency coefficient corresponding to the shooting frequency can also be considered. Here, the frequency coefficient is determined according to the shooting time interval. For example, image A is shot first, image B is shot after an interval of 10s, and image C is shot after an interval of 2s. Then, the frequency coefficient corresponding to the shooting frequency of image B associated with image A can be determined based on 10s, and the frequency coefficient corresponding to the shooting frequency of image C associated with image B can be determined based on 2s. And the shooting time interval is negatively correlated with the frequency coefficient, that is, the shorter the shooting time interval, the greater the frequency coefficient.

[0074] Then, determine N second category labels and the display priorities of each second category label according to the frequency coefficient corresponding to the shooting frequency and the similarity matching result between the recognition result and each image category. Specifically: when performing similarity matching between the recognition result and each image category, determine the corresponding frequency coefficient for each image category (the frequency coefficient corresponding to the time interval between the shooting time of the image corresponding to the last storage of each image category and the shooting time of the current target image), calculate the product of the frequency coefficient and the first weight and the product of the similarity matching result and the second weight, accumulate the sum of the two products to obtain the first value, sort the multiple first values in descending order, filter out the first N values in the sorting (which can also be understood as filtering out the first values less than the set value), and then determine N second category labels, and determine the display priorities of the N second category labels from high to low according to the order of the N first values from high to low.

[0075] Among them, considering the shooting time interval is for the scenario of continuous shooting by the user. For example, the user continuously shoots multiple images for the same scene, and these multiple images need to be classified into a new category. After storing the first image in the new category, when displaying the classification control for the subsequent images, providing the second category label based on the similarity and the shooting interval can ensure the accuracy of classification.

[0076] The following elaborates on this process through an example. The local image categories include the person category, the tree category, and the scenic spot category. The shooting time of the current target image is 10:30. As of 10:30, the shooting time of the last stored image A in the tree category is 10:29, the shooting time of the last stored image B in the scenic spot category is 10:28, and the shooting time of the last stored image C in the person category is 10:25. The frequency coefficient associated with the target image and image A is 0.9, the frequency coefficient associated with the target image and image B is 0.8, and the frequency coefficient associated with the target image and image C is 0.5. The similarity matching result between the target image and the tree category is 60%, the similarity matching result between the target image and the scenic spot category is 50%, and the similarity matching result between the target image and the person category is 80%. When the first weight is 0.4 and the second weight is 0.6, the first value corresponding to the tree category is (0.4 * 0.9 + 0.6 * 60% = 0.72), the first value corresponding to the scenic spot category is (0.4 * 0.8 + 0.6 * 50% = 0.62), and correspondingly, the first value corresponding to the person category is (0.4 * 0.5 + 0.6 * 80% = 0.68). Since all three first values are greater than the set value (0.5), three second category labels (the tree category label, the person category label, and the scenic spot category label) can be determined, as well as the display priorities of the three second category labels: the display priorities of the tree category label, the person category label, and the scenic spot category label decrease in turn.

[0077] In the above process, by obtaining N second-category labels according to the image category matching method and determining the display priorities of the second-category labels, the second-category labels can be displayed in the classification control according to the display priorities, ensuring the orderliness of the display. At the same time, by screening and sorting the second-category labels based on the shooting time interval and the similarity matching result, the accuracy of determining the second-category labels and the rationality of the display priority sorting can be ensured.

[0078] When obtaining N category labels according to the recognition result, the corresponding category can be determined based on the attribute features corresponding to at least one object for the recognition result including at least one object according to the preset category division method. After obtaining the category, the first number of first-category labels can be obtained according to the category. Among them, when obtaining the first number of first-category labels, the display priority corresponding to each first-category label can be determined. The recognition result can also be matched with each image category on the local device of the electronic device to obtain a similarity matching result, and then the second number of second-category labels can be determined based on the obtained similarity matching result. When determining the second number of second-category labels, the display priority corresponding to each second-category label can be determined. Among them, when obtaining the second-category labels, the shooting time interval can be considered for the continuous shooting scenario. For details, refer to the above process and will not be elaborated here.

[0079] After obtaining the first number of first-category labels and the second number of second-category labels, the first number of first-category labels and the second number of second-category labels can be combined to obtain N category labels. When combining, the category labels with the same content are filtered, and only one is retained. It is also possible to screen out some first-category labels with higher display priorities from the first number of first-category labels, screen out some second-category labels with higher display priorities from the second number of second-category labels, filter out the same category labels, and then combine them to obtain N category labels. Among them, the first number and the second number can be the same or different, and no specific limitation is made here.

[0080] In the above process, by determining the category labels in two ways, the category labels in the classification control are enriched, facilitating the user to make a reasonable selection according to the needs.

[0081] In the embodiment of the present application, by obtaining N category labels according to at least one of the image category matching method and the preset category division method and determining the display priorities of the category labels, the display content of the classification control is enriched, and the orderliness of the display can be ensured.

[0082] In an optional embodiment of the present application, the classification control corresponds to M sub-regions, where M is an integer greater than or equal to 1, and each of the sub-regions corresponds to one of the first category labels. When M is less than N, displaying the N first category labels corresponding to the target image through the classification control includes:

[0083] Displaying M of the first category labels through the classification control;

[0084] When a trigger condition is detected, updating at least one of the M first category labels according to the hidden first category labels;

[0085] Wherein, the display priority of the hidden first category labels is lower than that of the displayed first category labels.

[0086] The classification control may correspond to M sub-regions, where the sizes of the M sub-regions may be the same or different. In the case where the sizes of the M sub-regions are the same, the display can be ensured to be regular, improving the user's visual experience. In the case where the sizes of the M sub-regions are different, appropriate sub-regions can be selected for display according to the length of the content of the category labels, avoiding waste of regions.

[0087] For the case where the category labels in the classification control are first category labels and M is less than N, when displaying the first category labels through the classification control, M first category labels can be displayed, that is, M first category labels are screened out from the N first category labels for priority display. After displaying the M first category labels, if the user does not select any of the first category labels, the trigger condition can be monitored. When the trigger condition is detected, at least one of the M first category labels that have been displayed is updated according to at least one of the N - M hidden first category labels.

[0088] The trigger condition may be a third input executed by the user on the classification control, such as a click, a swipe input, etc., or the trigger condition can be determined when no input to the current display interface is detected within a second duration, and at this time, at least one of the M first category labels can be automatically updated.

[0089] The display priority of the N - M first - category labels in the hidden state is lower than that of the M first - category labels that are already displayed. Each of the N first - category labels can correspond to a display priority respectively. When the M first - category labels are displayed, they can be displayed in a certain direction in the classification control in the order from the highest to the lowest display priority. When updating at least one of the M first - category labels according to at least one of the N - M first - category labels, for the N - M first - category labels, at least some of the M first - category labels can be updated according to the order from the highest to the lowest display priority. When updating the M first - category labels, the first - category label with the highest or lowest display priority can be updated preferentially.

[0090] It should be noted that after updating the M first - category labels, the display of the M first - category labels can also be restored. The display priority corresponding to each of the N first - category labels can be determined by the electronic device according to a preset policy during display, or can be directly determined when determining the first - category labels. This situation corresponds to the process of obtaining the N first - category labels according to the recognition result and determining the display priority described above.

[0091] The following uses a specific example to elaborate on the above - mentioned process. Refer to Figure 5a As shown, the circular classification control corresponds to 4 sub - regions, and the 4 sub - regions respectively display landscape - category labels, location - category labels, sky - category labels, and travel - category labels. The value of N is 5, and the 5 first - category labels in the order from the highest to the lowest display priority are landscape - category labels, location - category labels, sky - category labels, travel - category labels, and night - scene - category labels. The already - displayed landscape - category labels, location - category labels, sky - category labels, and travel - category labels are displayed counter - clockwise in sequence. When receiving a clockwise rotation operation from the user, as Figure 5b shown, the landscape - category label is hidden, and the night - scene - category label is displayed. At this time, the location - category label, sky - category label, travel - category label, and night - scene - category label are displayed counter - clockwise in sequence.

[0092] In the embodiments of the present application, by using the M first - category labels with high display priority, when there is no first - category label that meets the user's requirements among the M first - category labels, the display of the first - category labels can be updated according to the trigger condition, which can achieve presenting different first - category labels in batches, facilitating the user to select from the N first - category labels. And by preferentially displaying the first - category labels with high display priority, the rate of determining the target category label can be improved.

[0093] In an alternative embodiment of the present application, the classification control corresponds to M sub-regions, where M is an integer greater than or equal to 1, and each of the sub-regions corresponds to one of the second category labels. When M is less than N, displaying the N second category labels corresponding to the target image through the classification control includes:

[0094] Displaying M of the second category labels through the classification control;

[0095] When a trigger condition is detected, updating at least one of the M second category labels according to the hidden second category labels;

[0096] Wherein, the display priority of the hidden second category labels is lower than that of the displayed second category labels.

[0097] The classification control may correspond to M sub-regions, and each sub-region corresponds to and displays one second category label. For the case where M is less than N, M second category labels can be displayed. After displaying the M second category labels, if the user does not select any of the second category labels, the trigger condition can be monitored. When the trigger condition is detected, at least one of the M already displayed second category labels can be updated according to at least one of the N - M hidden second category labels.

[0098] The display priority of the N - M hidden second category labels is lower than that of the M displayed second category labels, and each of the N second category labels can correspond to a display priority respectively. When the M second category labels are displayed, they can be sequentially displayed in a certain direction in the classification control in the order of decreasing display priority. When performing display updates, for the N - M second category labels, at least some of the M second category labels can be updated according to the order of decreasing display priority, and when updating the M second category labels, the second category label with the highest or lowest display priority can be preferentially updated.

[0099] It should be noted that the display priority corresponding to each of the N second category labels can be determined by the electronic device according to a preset policy during display, or can be directly determined when determining the second category labels. This situation corresponds to the process of obtaining the N second category labels according to the recognition result and determining the display priority described above.

[0100] In the embodiments of the present application, by displaying M second-category labels with high display priorities, and when there are no second-category labels that meet the user's requirements among the M second-category labels, updating the display of the second-category labels according to the trigger condition, different second-category labels can be presented in batches, facilitating the user to select among N second-category labels. Moreover, by preferentially displaying the second-category labels with high display priorities, the rate of determining the target category label can be improved.

[0101] In an alternative embodiment of the present application, the classification control corresponds to M sub-regions, and each sub-region corresponds to one of the first-category labels or one of the second-category labels. When M is less than N, the classification control that displays the first sub-control and the second sub-control includes:

[0102] Displaying the first sub-control corresponding to K of the first-category labels and the second sub-control corresponding to L of the second-category labels, where K is an integer greater than or equal to 1, L is an integer greater than or equal to 1, and the sum of K and L is equal to M;

[0103] When a trigger condition is detected, updating at least one of the K first-category labels according to the hidden first-category labels, and / or updating at least one of the L second-category labels according to the hidden second-category labels;

[0104] Among them, the display priority of the hidden first-category labels is lower than the display priority of the displayed first-category labels, and the display priority of the hidden second-category labels is lower than the display priority of the displayed second-category labels.

[0105] The classification control of the target image may correspond to M sub-regions, and each sub-region correspondingly displays one first-category label or one second-category label. When M is less than N, the first sub-control corresponding to K first-category labels and the second sub-control corresponding to L second-category labels can be displayed, where the sum of K and L is equal to M, and K and L may be equal or unequal. When K and L are equal, it is possible to achieve that half of the M sub-regions display first-category labels and the other half display second-category controls. Among the N category labels, there are E first-category labels and F second-category labels, and the value of E is greater than or equal to K, and the value of F is greater than or equal to L.

[0106] The K first-category labels displayed are the first-category labels with higher display priorities among the E first-category labels (i.e., K are selected from the E first-category labels according to the order from the highest to the lowest display priority), and the L second-category labels displayed are the second-category labels with higher display priorities among the F second-category labels (i.e., L are selected from the F second-category labels according to the order from the highest to the lowest display priority).

[0107] After the K first-category labels and the L second-category labels are displayed, if the user does not select any category label, the trigger condition can be monitored. When the trigger condition is detected, at least one of the K first-category labels that have been displayed is updated according to at least one of the E - K first-category labels in the hidden state. Or, at least one of the L second-category labels that have been displayed is updated according to at least one of the F - L second-category labels in the hidden state. Or, at least one of the K first-category labels that have been displayed is updated according to at least one of the E - K first-category labels in the hidden state, and at the same time, at least one of the L second-category labels that have been displayed is updated according to at least one of the F - L second-category labels in the hidden state.

[0108] The display priorities of the E - K first-category labels in the hidden state are lower than the display priorities of the K first-category labels that have been displayed, and each first-category label among the E first-category labels can respectively correspond to a display priority. When the K first-category labels are displayed, they can be sequentially displayed in a certain direction in the first sub-control according to the order from the highest to the lowest display priority. When updating at least one of the K first-category labels according to at least one of the first-category labels in the E - K first-category labels, at least part of the K first-category labels can be updated according to the order from the highest to the lowest display priority for the E - K first-category labels, and when updating the K first-category labels, the first-category label with the highest or lowest display priority can be preferentially updated.

[0109] Correspondingly, the display priority of the F - L second - category labels in the hidden state is lower than that of the L second - category labels that have been displayed. Each of the F second - category labels can correspond to a display priority. When the L second - category labels are displayed, they can be sequentially displayed in a certain direction in the second sub - control in the order of decreasing display priority. When updating at least one of the L second - category labels according to at least one of the F - L second - category labels, for the F - L second - category labels, at least part of the L second - category labels can be updated in the order of decreasing display priority, and when updating the L second - category labels, the second - category label with the highest or lowest display priority can be preferentially updated.

[0110] In the embodiments of the present application, by displaying the first sub - control corresponding to the first - category label and the second sub - control corresponding to the second - category label, when the user - required category label does not exist among the displayed category labels, the display of the first - category label and / or the second - category label can be updated according to the trigger condition, which can achieve presenting different first - category labels and second - category labels in batches, facilitating the user to select among the E first - category labels and the F second - category labels. Moreover, by preferentially displaying the category label with a high display priority, the rate of determining the target category label can be improved.

[0111] In an alternative embodiment of the present application, when saving the target image to the target - category album corresponding to the target - category label, according to the second input of the user, the target - category label can be set to the locked state, and the target image can be saved to the target - category album corresponding to the target - category label. Since the target - category label has been set to the locked state, for subsequent target images, they can also be directly saved to the target - category album corresponding to the target - category label.

[0112] It is also possible to select the target - category label and set the target - category label to the locked state before receiving the second input of the user. The target - category label in the locked state can be prominently displayed. Then, according to the second input (such as clicking) performed by the user on the target - category label, the target image can be saved to the target - category album corresponding to the target - category label. For subsequent target images, they can also be directly saved to the target - category album according to the locked state of the target - category label.

[0113] Among them, by setting the target - category label to the locked state, it can be applied to the scenario of continuously shooting for a certain scene, and can also be applied to the scenario of classifying multiple images corresponding to the same scene in the local image database.

[0114] When the target category label is in a locked state, the user does not need to select the target category label for each image taken (or each image to be classified), and accurate and convenient image classification and saving can be achieved quickly.

[0115] For example, if a user takes photos of scenery in a certain area and wants to store all the photos in the same folder, he can lock a category label for a period of time and store all the photos in the same album (which can be a new album). Figure 6 As shown in the figure, before or after taking a photo, the user can slide from the shooting button to a category label (the landscape category label in the figure) and continue to slide to the outside of the concentric circle. At this time, the category label will be locked, so that the image can be automatically saved to the corresponding album, thus achieving a fast and convenient classification effect. The images taken subsequently can also be automatically saved to the album corresponding to the category label. When the user needs to cancel the lock, just do the reverse operation and slide from the outside to the inside of the concentric circle to unlock the target category label.

[0116] In an embodiment of the present application, by locking the target category label and saving multiple target images to the target category album corresponding to the target category label, accurate and convenient image classification storage can be achieved without the user having to select from multiple category labels, thereby ensuring the speed of image saving.

[0117] The following takes the target image as an example of an image captured in real time to illustrate the process of determining the target category label from N first category labels and classifying and saving the target image. Figure 7 As shown, including:

[0118] Step 701: receiving a user click on a shooting button on a shooting interface, and displaying a target image to be shot.

[0119] Step 702: Display a blank category control in a concentric circular shape with the capture button as the center.

[0120] Step 703: The electronic device performs content recognition on the target image to obtain a recognition result, determines N first category labels corresponding to the recognition result according to a preset category classification method, and displays M first category labels on the classification control according to a user trigger, where M is less than N.

[0121] Step 704: Detect whether the user selects a target category label from the M first category labels, if so, execute step 707, otherwise execute step 705. The selection here may be that the user directly slides to a category label, and then determines that the category label is the target category label.

[0122] Step 705: Receive the user's clockwise rotation operation on the classification control, display the remaining first-category labels, and according to the user's counterclockwise rotation operation on the classification control, display the previous first-category labels, and then execute Step 706.

[0123] Step 706: Receive the user's selection operation among the N first-category labels to determine the target category label.

[0124] Step 707: Save the target image to the target category album corresponding to the target category label.

[0125] In the above implementation process, by displaying the classification control corresponding to the target image, displaying M first-category labels in the classification control, and updating the display of the category labels when the category label required by the user does not exist among the M first-category labels, it is possible to provide N first-category labels for the user to select, facilitating the user to accurately classify the target image.

[0126] Next, taking the target image as a real-time captured image as an example, the process of determining the target category label from the first-category labels and the second-category labels in the present application and classifying and saving the target image will be illustrated by way of example. Refer to Figure 8 As shown, it includes:

[0127] Step 801: Receive the user's click on the shooting button in the shooting interface and display the captured target image.

[0128] Step 802: According to the user's trigger on the target image, display a concentric circular ring-shaped classification control centered on the shooting button, and the classification control displays the first-category labels.

[0129] Step 803: According to the user's input in the right half area of the classification control, display the second-category labels in the right half area of the classification control and display the first-category labels in the left half area of the classification control. Among them, the second-category labels can be updated by rotating the right half area, the first-category labels can be updated by rotating the left half area, and the previous display can be restored by rotating in the opposite direction. The second-category labels are category labels determined based on the image category matching method, and the first-category labels are category labels determined based on the preset category division method.

[0130] Step 804: Detect whether the user selects the target category label from the currently displayed first-category labels and second-category labels. If so, execute Step 807; otherwise, execute Step 805.

[0131] Step 805: Receive the user's clockwise rotation operation on the right half area of the classification control to display the remaining second-category labels, and / or receive the user's clockwise rotation operation on the left half area of the classification control to display the remaining first-category labels.

[0132] Step 806: Receive the selection operation of the user to determine the target category label.

[0133] Step 807: Save the target image to the target category album corresponding to the target category label.

[0134] In the above implementation process, by displaying the classification control corresponding to the target image, displaying the first category label in the classification control, and when the category label required by the user does not exist in the first category label, displaying the first category label and the second category label, more choices can be provided for the user, which is convenient for accurately classifying the target image.

[0135] The above is the implementation process of the image classification method provided by the embodiment of the present application. By displaying N category labels for the target image, at least two category labels can be provided for the user to select. The user determines the target category label from the N category labels, and saves the target image to the target category album corresponding to the target category label. It can realize accurate classification of the target image through simple operations and meet the personalized classification needs of users. At the same time, since at least two category labels are provided, the diversification of classification can be realized.

[0136] Furthermore, by displaying the first category label and / or the second category label, the display content of the classification control is enriched; by determining the display priority of each category label, the orderliness of the display is ensured; by updating the category labels, the complete category labels can be presented in batches, which is convenient for the user to select; by preferentially displaying the category labels with higher priority, the speed of determining the target category label can be improved; by locking the category labels, accurate, convenient and fast image classification and saving of multiple target images can be realized.

[0137] It should be noted that for the image classification method provided by the embodiment of the present application, the execution subject can be an image classification device or a control module in the image classification device for executing the image classification method. In the embodiment of the present application, taking the image classification device executing the image classification method as an example, the image classification device provided by the embodiment of the present application is described.

[0138] Figure 9 It is a schematic block diagram of an image classification device provided by the embodiment of the present application. This image classification device is applied to an electronic device.

[0139] As Figure 9 shown, the image classification device includes:

[0140] A first receiving module 901, configured to receive the first input of the user;

[0141] A display module 902, configured to display N category labels corresponding to the target image in response to the first input, where N is an integer greater than or equal to 2;

[0142] A second receiving module 903, configured to receive a second input from a user for a target category label, where the target category label is one of the N category labels;

[0143] A saving module 904, configured to save the target image to a target category album corresponding to the target category label in response to the second input.

[0144] Optionally, the N category labels are determined according to at least one of a preset category division method and an image category matching method;

[0145] The display module includes one of the following sub-modules:

[0146] A first display sub-module, configured to display N first category labels corresponding to the target image through a classification control;

[0147] A second display sub-module, configured to display N second category labels corresponding to the target image through a classification control;

[0148] A third display sub-module, configured to display a classification control including a first sub-control and a second sub-control, where the first sub-control corresponds to a first category label, the second sub-control corresponds to a second category label, and the sum of the number of the first category labels and the second category labels is N;

[0149] Wherein, the first category label is a category label determined according to the preset category division method, and the second category label is a category label determined according to the image category matching method.

[0150] Optionally, the apparatus further includes:

[0151] An identification module, configured to perform content identification on the target image before the display module displays N category labels corresponding to the target image, to obtain an identification result;

[0152] An obtaining module, configured to obtain the N category labels according to the identification result.

[0153] Optionally, the obtaining module includes one of the following sub-modules:

[0154] A first processing sub-module, configured to determine the category corresponding to the identification result according to the preset category division method, obtain N first category labels according to the category corresponding to the identification result, and determine the display priority of each first category label;

[0155] A second processing sub-module, configured to perform similarity matching between the identification result and a preset image category, determine N second category labels according to the similarity matching result, and determine the display priority of each second category label;

[0156] A third processing sub-module, configured to determine a first number of the first category labels corresponding to the recognition result according to the preset category division method, determine a second number of the second category labels according to the similarity matching result between the recognition result and a preset image category, and obtain the N category labels according to the first number of the first category labels and the second number of the second category labels, wherein, when determining the first number of the first category labels, determine the display priority of each of the first category labels, and when determining the second number of the second category labels, determine the display priority of each of the second category labels.

[0157] Optionally, the classification control corresponds to M sub-regions, where M is an integer greater than or equal to 1, each of the sub-regions corresponds to one of the first category labels, and in the case where M is less than N, the first display sub-module includes:

[0158] A first display unit, configured to display M of the first category labels through the classification control;

[0159] A first update unit, configured to update at least one of the M first category labels according to the hidden first category labels when a trigger condition is monitored;

[0160] Wherein, the display priority of the hidden first category labels is lower than that of the displayed first category labels.

[0161] Optionally, the classification control corresponds to M sub-regions, where M is an integer greater than or equal to 1, each of the sub-regions corresponds to one of the second category labels, and in the case where M is less than N, the second display sub-module includes:

[0162] A second display unit, configured to display M of the second category labels through the classification control;

[0163] A second update unit, configured to update at least one of the M second category labels according to the hidden second category labels when a trigger condition is monitored;

[0164] Wherein, the display priority of the hidden second category labels is lower than that of the displayed second category labels.

[0165] Optionally, the classification control corresponds to M sub-regions, each of the sub-regions corresponds to one of the first category labels or one of the second category labels, and in the case where M is less than N, the third display sub-module includes:

[0166] A third display unit, configured to display the first sub-controls corresponding to the K first category labels and the second sub-controls corresponding to the L second category labels, where K is an integer greater than or equal to 1, L is an integer greater than or equal to 1, and the sum of K and L is equal to M;

[0167] A third update unit, configured to, when a trigger condition is detected, update at least one of the K first category labels according to the hidden first category labels, and / or update at least one of the L second category labels according to the hidden second category labels;

[0168] Wherein, the display priority of the hidden first category labels is lower than that of the displayed first category labels, and the display priority of the hidden second category labels is lower than that of the displayed second category labels.

[0169] The image classification device in the embodiments of the present application may be a device, or a component, an integrated circuit or a chip in a terminal. The device may be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device may be a mobile phone, a tablet computer, a laptop computer, a handheld computer, a vehicle-mounted electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a personal digital assistant (PDA), etc., and the non-mobile electronic device may be a server, a Network Attached Storage (NAS), a personal computer (PC), a television (TV), a teller machine or a self-service machine, etc. The embodiments of the present application do not make specific limitations.

[0170] The image classification device in the embodiments of the present application may be a device with an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems. The embodiments of the present application do not make specific limitations.

[0171] The image classification device provided in the embodiments of the present application can implement Figure 1 each process implemented by the image classification method embodiments shown. To avoid repetition, it will not be elaborated here.

[0172] Optionally, as Figure 10As shown in the figure, an embodiment of the present application further provides an electronic device 1000, including a processor 1001, a memory 1002, a program or instruction stored on the memory 1002 and executable on the processor 1001. When the program or instruction is executed by the processor 1001, it implements each process of the above image classification method embodiment and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0173] It should be noted that the electronic device in the embodiment of the present application includes the above-mentioned mobile electronic device and non-mobile electronic device.

[0174] Figures 5a - 5b It is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present application.

[0175] The electronic device 1100 includes but is not limited to: a radio frequency unit 1101, a network module 1102, an audio output unit 1103, an input unit 1104, a sensor 1105, a display unit 1106, a user input unit 1107, an interface unit 1108, a memory 1109, a processor 1110 and other components.

[0176] Those skilled in the art can understand that the electronic device 1100 may further include a power supply (such as a battery) for supplying power to each component. The power supply can be logically connected to the processor 1110 through a power management system, so as to implement functions such as management of charging, discharging, and power consumption management through the power management system. Figure 11 The structure of the electronic device shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0177] Among them, the user input unit 1107 is used for: receiving a first input from the user; the display unit 1106 is used for: in response to the first input, displaying N category labels corresponding to the target image, where N is an integer greater than or equal to 2; the user input unit 1107 is further used for: receiving a second input from the user for the target category label, and the target category label is one of the N category labels; the processor 1110 is used for: in response to the second input, saving the target image to the target category album corresponding to the target category label.

[0178] Optionally, the N category labels are determined according to at least one of a preset category division method and an image category matching method; the display unit 1106 is further used to display the N category labels in one of the following ways:

[0179] Displaying N first category labels corresponding to the target image through a classification control;

[0180] Display N second category labels corresponding to the target image through a classification control;

[0181] Display a classification control including a first sub-control and a second sub-control, where the first sub-control corresponds to a first category label, the second sub-control corresponds to a second category label, and the sum of the number of the first category labels and the number of the second category labels is N;

[0182] Wherein, the first category label is a category label determined according to the preset category division method, and the second category label is a category label determined according to the image category matching method.

[0183] Optionally, before the display unit 1106 displays N category labels corresponding to the target image, the processor 1110 is further configured to: perform content recognition on the target image to obtain a recognition result; and obtain the N category labels according to the recognition result.

[0184] Optionally, the processor 1110 is further configured to: determine the category corresponding to the recognition result according to the preset category division method, obtain N first category labels corresponding to the recognition result and determine the display priority of each first category label; or

[0185] Perform similarity matching between the recognition result and a preset image category, determine N second category labels according to the similarity matching result and determine the display priority of each second category label; or

[0186] Determine a first number of the first category labels corresponding to the recognition result according to the preset category division method, determine a second number of the second category labels according to the similarity matching result between the recognition result and the preset image category, and obtain the N category labels according to the first number of the first category labels and the second number of the second category labels, wherein the display priority of each first category label is determined when determining the first number of the first category labels, and the display priority of each second category label is determined when determining the second number of the second category labels.

[0187] Optionally, the classification control corresponds to M sub-regions, where M is an integer greater than or equal to 1, and each sub-region corresponds to a first category label. When M is less than N, the display unit 1106 is further configured to: display M first category labels through the classification control; the processor 1110 is further configured to: update at least one of the M first category labels according to the hidden first category label when a trigger condition is detected; wherein the display priority of the hidden first category label is lower than the display priority of the displayed first category label.

[0188] Optionally, the classification control corresponds to M sub-regions, where M is an integer greater than or equal to 1, and each of the sub-regions corresponds to one of the second category labels. When M is less than N, the display unit 1106 is further configured to: display M of the second category labels through the classification control; the processor 1110 is further configured to: when a trigger condition is detected, update at least one of the M second category labels according to the hidden second category labels; wherein, the display priority of the hidden second category labels is lower than the display priority of the displayed second category labels.

[0189] Optionally, the classification control corresponds to M sub-regions, and each of the sub-regions corresponds to one of the first category labels or one of the second category labels. When M is less than N, the display unit 1106 is further configured to: display the first sub-control corresponding to K of the first category labels and the second sub-control corresponding to L of the second category labels, where K is an integer greater than or equal to 1, L is an integer greater than or equal to 1, and the sum of K and L is equal to M; the processor 1110 is further configured to: when a trigger condition is detected, update at least one of the K first category labels according to the hidden first category labels, and / or update at least one of the L second category labels according to the hidden second category labels; wherein, the display priority of the hidden first category labels is lower than the display priority of the displayed first category labels, and the display priority of the hidden second category labels is lower than the display priority of the displayed second category labels.

[0190] In the embodiments of the present application, by displaying N category labels for the target image, at least two category labels can be provided for the user to select. The user determines the target category label from the N category labels and saves the target image to the target category album corresponding to the target category label, which can achieve accurate classification of the target image through simple operations and meet the user's personalized classification needs. At the same time, since at least two category labels are provided, the diversification of classification can be realized.

[0191] Furthermore, by displaying the first category labels and / or the second category labels, the display content of the classification control is enriched; by determining the display priority of each category label, the orderliness of the display is ensured; by updating the category labels, the complete category labels can be presented in batches, which is convenient for the user to select; by preferentially displaying the category labels with high display priority, the speed of determining the target category label can be improved.

[0192] It should be understood that in the embodiments of the present application, the input unit 1104 may include a Graphics Processing Unit (GPU) 11041 and a microphone 11042. The graphics processor 11041 processes the image data of static pictures or videos obtained by an image capturing device (such as a camera) in the video capturing mode or the image capturing mode. The display unit 1106 may include a display panel 11061, and the display panel 11061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 1107 includes a touch panel 11071 and other input devices 11072. The touch panel 11071 is also called a touch screen. The touch panel 11071 may include two parts: a touch detection device and a touch controller. The other input devices 11072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be elaborated here. The memory 1109 can be used to store software programs and various data, including but not limited to application programs and operating systems. The processor 1110 may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, user interface, application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor may not be integrated into the processor 1110.

[0193] The embodiments of the present application further provide a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, it implements each process of the above-mentioned embodiment of the image classification method and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0194] Among them, the processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer-readable storage medium, such as a computer Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disc, etc.

[0195] The embodiments of the present application further provide a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run a program or instruction to implement each process of the above-mentioned embodiment of the image classification method and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0196] It should be understood that the chip mentioned in the embodiments of the present application may also be referred to as a system-on-chip, a system chip, a chip system, or a system-on-chip, etc.

[0197] It should be noted that, in this text, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article or device. Without more limitations, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or device including such element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, but may also include performing functions in a substantially simultaneous manner or in the reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0198] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described example methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in various embodiments of the present application.

[0199] The embodiments of the present application have been described above with reference to the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Those of ordinary skill in the art, under the inspiration of the present application and without departing from the purpose of the present application and the scope protected by the claims, can still make many forms, all of which fall within the protection scope of the present application.

Claims

1. An image classification method, characterized in that, Including: Receiving a first input from a user; In response to the first input, displaying N category labels corresponding to a target image, where N is an integer greater than or equal to 2; Receiving a second input from the user for a target category label, where the target category label is one of the N category labels; In response to the second input, saving the target image to a target category album corresponding to the target category label; The N category labels are displayed by a classification control; the classification control is a circular classification control, and sub-regions of the circular classification control are used to display corresponding category labels; when a rotation operation on the circular classification control is received, the displayed category labels are updated; After receiving the second input from the user for the target category label, controlling the target category label to be displayed in a display style different from other category labels; Determining the N category labels according to at least one of a preset category division method and an image category matching method; The displaying the N category labels corresponding to the target image includes one of the following steps: Displaying N first category labels corresponding to the target image through the classification control; Displaying N second category labels corresponding to the target image through the classification control; Displaying a classification control including a first sub-control and a second sub-control, where the first sub-control corresponds to a first category label and the second sub-control corresponds to a second category label, and the sum of the number of the first category labels and the number of the second category labels is N; Wherein, the first category labels are category labels determined according to the preset category division method, and the second category labels are category labels determined according to the image category matching method.

2. The image classification method according to claim 1, characterized in that Before displaying the N category labels corresponding to the target image, further including: Performing content recognition on the target image to obtain a recognition result; According to the recognition result, obtaining the N category labels.

3. The image classification method according to claim 2, wherein The obtaining the N category labels according to the recognition result includes one of the following steps: Determining the category corresponding to the recognition result according to the preset category division method, obtaining N of the first category labels corresponding to the recognition result, and determining the display priority of each of the first category labels; Performing similarity matching between the recognition result and preset image categories, determining N of the second category labels according to the similarity matching result, and determining the display priority of each of the second category labels; Determining a first number of the first category labels corresponding to the recognition result according to the preset category division method, determining a second number of the second category labels according to the similarity matching result between the recognition result and the preset image categories, and obtaining the N category labels according to the first number of the first category labels and the second number of the second category labels, where the display priority of each of the first category labels is determined when determining the first number of the first category labels, and the display priority of each of the second category labels is determined when determining the second number of the second category labels.

4. The image classification method according to claim 1 or 3, characterized in that, The classification control corresponds to M sub-regions, where M is an integer greater than or equal to 1, and each of the sub-regions corresponds to one of the first category labels. When M is less than N, displaying the N first category labels corresponding to the target image through the classification control includes: Displaying M of the first category labels through the classification control; When a trigger condition is detected, updating at least one of the M first category labels according to the hidden first category labels; Among them, the display priority of the hidden first category labels is lower than that of the displayed first category labels.

5. The image classification method according to claim 1 or 3, characterized in that The classification control corresponds to M sub-regions, where M is an integer greater than or equal to 1, and each of the sub-regions corresponds to one of the second category labels. When M is less than N, displaying the N second category labels corresponding to the target image through the classification control includes: Displaying M of the second category labels through the classification control; When a trigger condition is detected, updating at least one of the M second category labels according to the hidden second category labels; Among them, the display priority of the hidden second category labels is lower than that of the displayed second category labels.

6. The image classification method according to claim 1 or 3, characterized in that, The classification control corresponds to M sub-regions, and each of the sub-regions corresponds to one of the first category labels or one of the second category labels. When M is less than N, displaying the classification control including a first sub-control and a second sub-control includes: Displaying the first sub-control corresponding to K of the first category labels and the second sub-control corresponding to L of the second category labels, where K is an integer greater than or equal to 1, L is an integer greater than or equal to 1, and the sum of K and L is equal to M; When a trigger condition is detected, updating at least one of the K first category labels according to the hidden first category labels, and / or updating at least one of the L second category labels according to the hidden second category labels; Among them, the display priority of the hidden first category labels is lower than that of the displayed first category labels, and the display priority of the hidden second category labels is lower than that of the displayed second category labels.

7. An image classification device, characterized in that, Including: A first receiving module for receiving a first input from a user; A display module for displaying N category labels corresponding to a target image in response to the first input, where N is an integer greater than or equal to 2; A second receiving module for receiving a second input from the user for a target category label, where the target category label is one of the N category labels; A saving module for saving the target image to a target category album corresponding to the target category label in response to the second input. The N category labels are displayed by a classification control; the classification control is a circular classification control, and sub-regions of the circular classification control are used to display corresponding category labels; when a rotation operation on the circular classification control is received, the displayed category labels are updated; The device is further configured to, after receiving a second input from a user for the target category label, display the target category label in a display style different from other category labels; Determine the N category labels according to at least one of a preset category division method and an image category matching method; The display module includes one of the following sub-modules: A first display sub-module, configured to display N first category labels corresponding to the target image through a classification control; A second display sub-module, configured to display N second category labels corresponding to the target image through a classification control; A third display sub-module, configured to display a classification control including a first sub-control and a second sub-control, the first sub-control corresponding to a first category label, the second sub-control corresponding to a second category label, and the sum of the number of the first category labels and the number of the second category labels being N; Wherein, the first category labels are category labels determined according to the preset category division method, and the second category labels are category labels determined according to the image category matching method.

8. The image classification device according to claim 7, characterized in that, The device further includes: An identification module, configured to perform content identification on the target image before the display module displays N category labels corresponding to the target image, to obtain an identification result; An acquisition module, configured to acquire the N category labels according to the identification result.

9. The image classification device according to claim 8, characterized in that, The acquisition module includes one of the following sub-modules: A first processing sub-module, configured to determine a category corresponding to the identification result according to the preset category division method, acquire N of the first category labels according to the category corresponding to the identification result, and determine a display priority for each of the first category labels; A second processing sub-module, configured to perform a similarity match between the identification result and a preset image category, determine N of the second category labels according to a similarity match result, and determine a display priority for each of the second category labels; A third processing sub-module, configured to determine a first number of the first category labels corresponding to the identification result according to the preset category division method, determine a second number of the second category labels according to a similarity match result between the identification result and the preset image category, acquire the N category labels according to the first number of the first category labels and the second number of the second category labels, wherein a display priority for each of the first category labels is determined when determining the first number of the first category labels, and a display priority for each of the second category labels is determined when determining the second number of the second category labels.

10. The image classification device according to claim 7 or 9, characterized in that, The classification control corresponds to M sub-regions, where M is an integer greater than or equal to 1, each of the sub-regions corresponds to one of the first category labels, and when M is less than N, the first display sub-module includes: A first display unit, configured to display M of the first category labels through the classification control; A first update unit, configured to update at least one of the M first category labels according to the hidden first category labels when a trigger condition is detected; Wherein, the display priority of the hidden first category labels is lower than that of the displayed first category labels.

11. The image classification device according to claim 7 or 9, characterized in that, The classification control corresponds to M sub-regions, where M is an integer greater than or equal to 1, and each of the sub-regions corresponds to a second category label. When M is less than N, the second display sub-module includes: A second display unit, configured to display the M second category labels through the classification control; A second update unit, configured to update at least one of the M second category labels according to the hidden second category labels when a trigger condition is detected; Wherein, the display priority of the hidden second category labels is lower than that of the displayed second category labels.

12. The image classification device according to claim 7 or 9, characterized in that, The classification control corresponds to M sub-regions, and each of the sub-regions corresponds to a first category label or a second category label. When M is less than N, the third display sub-module includes: A third display unit, configured to display the first sub-control corresponding to K first category labels and the second sub-control corresponding to L second category labels, where K is an integer greater than or equal to 1, L is an integer greater than or equal to 1, and the sum of K and L is equal to M; A third update unit, configured to update at least one of the K first category labels according to the hidden first category labels, and / or update at least one of the L second category labels according to the hidden second category labels when a trigger condition is detected; Wherein, the display priority of the hidden first category labels is lower than that of the displayed first category labels, and the display priority of the hidden second category labels is lower than that of the displayed second category labels.

Images