Method and device for object recognition

Abstract

The invention provides a method and device for object recognition. The method comprises the steps that an object image is acquired, and the object image comprises one or more to-be-recognized objects; for each to-be-recognized object, generating a recognition result of the to-be-recognized object by adopting a pre-trained object recognition model, and determining a target feature part of the to-be-recognized object according to the recognition result; and displaying a first picture, the first picture including at least a portion of the object image and target feature information associated with the target feature portion.

Description

Technical Field

[0001] The present disclosure relates to the technical field of object recognition, and in particular to a method and device for object recognition. Background Art

[0002] With the development of technologies such as image analysis, object recognition has been increasingly widely used. In some applications, images or videos input by users can be received, and objects to be recognized in the images or videos can be recognized to obtain recognition results of the objects to be recognized. However, in these applications, there are problems of poor interactivity with users and poor user experience. Summary of the invention

[0003] A brief overview of the disclosure is given below in order to provide a basic understanding of some aspects of the disclosure. However, it should be understood that this overview is not an exhaustive overview of the disclosure. It is not intended to identify the key or important parts of the disclosure, nor is it intended to limit the scope of the disclosure. Its purpose is simply to give some concepts of the disclosure in a simplified form as a prelude to a more detailed description given later.

[0004] One of the objectives of the present disclosure is to provide a method and apparatus for object recognition.

[0005] According to a first aspect of the present disclosure, a method for object recognition is provided, comprising: acquiring an object image, wherein the object image includes one or more objects to be recognized; for each object to be recognized, using a pre-trained object recognition model to generate a recognition result of the object to be recognized, and determining a target feature part of the object to be recognized based on the recognition result; and displaying a first picture, wherein the first picture includes at least a portion of the object image and target feature information associated with the target feature part.

[0006] In some embodiments, determining the target feature part of the object to be identified based on the recognition result includes: determining a candidate feature part corresponding to the recognition result based on the recognition result; and using a pre-trained part recognition model to determine the target feature part of the object to be identified that matches the candidate feature part based on the candidate feature part.

[0007] In some embodiments, the target feature information includes: text information describing at least one of the size, shape, and color of the target feature part; and / or image information of the target feature part.

[0008] In some embodiments, the first screen has one or more first areas, wherein the one or more first areas are determined based on a pre-trained area recognition model and the object image, and a corresponding object to be recognized is displayed in each first area.

[0009] In some embodiments, displaying the first screen includes: in response to receiving an operation in the first area, displaying target feature information associated with the target feature part of the corresponding object to be identified.

[0010] In some embodiments, displaying the target feature information associated with the target feature parts of the corresponding object to be identified includes: displaying the target feature information associated with a preset number of target feature parts in descending order of priority of the target feature parts.

[0011] In some embodiments, displaying the target feature information associated with the corresponding target feature part of the object to be identified includes: displaying the priority of the target feature part in the form of at least one of text, numbers and graphics.

[0012] In some embodiments, the first screen has a second area, wherein information associated with the recognition result of the object to be recognized is displayed in the second area.

[0013] In some embodiments, the recognition result is the species classification to which the object to be recognized belongs, and the information associated with the recognition result of the object to be recognized includes at least one of the following: at least one of the name, nickname and image of the species classification to which the object to be recognized belongs; and at least one of the name, nickname and image of the genus classification corresponding to the species classification to which the object to be recognized belongs.

[0014] In some embodiments, the second area includes at least one of a first interactable object, a second interactable object, and a third interactable object, wherein the method further includes: displaying a second screen in response to receiving an operation on the first interactable object; displaying an answer or question to the received operation in response to receiving an operation on the second interactable object; and receiving voice information in response to receiving an operation on the third interactable object.

[0015] In some embodiments, the second screen includes: at least one of growth characteristics, growth status, pest and disease information of the object to be identified, and maintenance guidance for the object to be identified.

[0016] In some embodiments, the first screen has one or more third areas, wherein one third area corresponds to a target feature part, and each third area displays target feature information associated with the corresponding target feature part.

[0017] In some embodiments, the method further includes: in response to receiving an operation in the third area, displaying a third picture, wherein the third picture includes additional information associated with the corresponding target feature part.

[0018] In some embodiments, the additional information associated with the corresponding target feature part includes at least one of the following: image information of the target feature part, the name of the target feature part, additional image information similar to the image information of the target feature part, a prompt requesting input of one or more additional images of the target feature part, and shooting guidance for the target feature part.

[0019] In some embodiments, the third screen includes a fourth interactive object, and the method further includes: in response to receiving one or more additional images about the target feature part based on input of the fourth interactive object, identifying the one or more additional images; and updating the target feature information associated with the corresponding target feature part based on the recognition results of the one or more additional images.

[0020] According to another aspect of the present disclosure, there is provided an apparatus for object recognition, comprising: a processor; and a memory, wherein instructions are stored in the memory, and when the instructions are executed by the processor, the steps of the object recognition method described above are implemented.

[0021] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium is provided, on which instructions are stored. When the instructions are executed by a processor, the steps of the object recognition method described above are implemented.

[0022] According to yet another aspect of the present disclosure, a computer program product is provided, comprising instructions, and when the instructions are executed by a processor, the steps of the object recognition method described above are implemented.

[0023] Other features and advantages of the present disclosure will become more apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings, which constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0025] The present disclosure may be more clearly understood from the following detailed description with reference to the accompanying drawings, in which:

[0026] Figure 1 A schematic flow chart of a method for object recognition according to an exemplary embodiment of the present disclosure is shown;

[0027] Figure 2A schematic diagram of a process for determining a target feature part in a method for object recognition according to an exemplary embodiment of the present disclosure is shown;

[0028] Figures 3 to 5 A schematic diagram showing a first screen according to an exemplary embodiment of the present disclosure is shown;

[0029] Figure 6 A schematic structural diagram of a device for object recognition according to an exemplary embodiment of the present disclosure is shown;

[0030] Figure 7 A schematic diagram of the structure of a computer system that can implement the embodiments of the present disclosure is shown.

[0031] Note that in the embodiments described below, the same reference numerals are sometimes used in common between different drawings to represent the same parts or parts with the same functions, and their repeated descriptions are omitted. In this specification, similar reference numerals and letters are used to represent similar items, so once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0032] For ease of understanding, the positions, sizes, and ranges of various structures shown in the drawings and the like sometimes do not represent actual positions, sizes, and ranges, etc. Therefore, the disclosed invention is not limited to the positions, sizes, and ranges, etc. disclosed in the drawings and the like. In addition, the drawings are not necessarily drawn to scale, and some features may be exaggerated to show details of specific components. DETAILED DESCRIPTION

[0033] Various exemplary embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. It should be noted that unless otherwise specifically stated, the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure.

[0034] The following description of at least one exemplary embodiment is in fact merely illustrative and is in no way intended to limit the present disclosure and its application or use. That is, the structures and methods herein are shown in an exemplary manner to illustrate different embodiments of the structures and methods in the present disclosure. However, those skilled in the art will appreciate that they merely illustrate exemplary ways of the present disclosure that can be implemented, rather than exhaustive ways. In addition, the drawings need not be drawn to scale, and some features may be enlarged to illustrate the details of specific components.

[0035] Technologies, methods, and apparatus known to ordinary technicians in the relevant field may not be discussed in detail, but where appropriate, such technologies, methods, and apparatus should be considered part of the authorization specification.

[0036] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0037] In order to identify an object, the user can provide an image containing the object to be identified, and the corresponding object identification program or equipment will perform identification processing on the image and obtain the identification result of the object to be identified. For example, when the object to be identified is a biological organism, the identification result obtained can be the biological classification of the object to be identified, and the unit of biological classification can be, for example, family, genus or species.

[0038] In some cases, users may not be satisfied with knowing the recognition results of the objects to be recognized. In addition, when, for example, a large language model is used to identify the species of a plant object provided by a user (a process called species determination), it is difficult to reflect the professionalism of the recognition results only by using text descriptions, which makes users have low trust in the recognition results. In addition, after the user provides the image, the recognition results are described in the form of a dialogue page, which is separated from the image provided by the user, resulting in poor interactivity with the user and a poor user experience.

[0039] In order to solve the above problems, the present disclosure proposes a method and device for object recognition, which determines the target feature part of the object to be recognized and displays at least a part of the image and target feature information associated with the target feature part, so that the recognition result can be interpreted from at least two aspects of the image and the target feature information, thereby enhancing the interactivity with the user, improving the user experience, and increasing the user's trust in the recognition result.

[0040] like Figure 1 As shown, in an exemplary embodiment of the present disclosure, a method for object recognition is provided, which may include:

[0041] Step S110, acquiring an object image.

[0042] The object image may include one or more objects to be identified. In some embodiments below, the technical solution of the present disclosure will be described in detail by taking the object to be identified as a plant as an example. It can be understood by those skilled in the art that the object to be identified may also be other types of objects besides plants, for example, the object to be identified may also be an animal, a commemorative coin, etc., which is not limited here.

[0043] In some embodiments, the object image uploaded by the user may be directly obtained. In other examples, after receiving the user's instruction, corresponding prompt information may be generated and output to prompt the user to upload the object image. Furthermore, the prompt information may include specific requirements for the object image, for example, the user may be prompted to upload at least one image of the whole plant or upload an image of a specified part of the plant. Alternatively, the prompt information may also include information prompting the user that the image uploaded is not clear enough and the user needs to re-photograph the object to be identified.

[0044] The object image usually includes at least a part of the object to be identified. For example, when the object to be identified is a plant, the object image may include any one or a combination of multiple items of the root, stem, leaf, flower, fruit, and seed of the plant to be identified, wherein each item included may be the whole or part of the item. The object image may be previously stored by the user, captured in real time, or downloaded from the Internet. The object image may include any form of visual presentation, such as a static image, a dynamic image, etc. The object image may be captured using an electronic device including a camera, such as a mobile phone, a tablet computer, etc.

[0045] In some embodiments, the acquired object image may be preprocessed, for example, the image may be denoised, so as to better identify the object to be identified in the image later. For another example, the object to be identified in the object image may be marked. In a specific example, the image may be segmented to generate the area where each object to be identified in the object image is located, so as to mark the object to be identified, so as to identify each object to be identified separately and improve the accuracy of identification.

[0046] Continue to refer to Figure 1 In an exemplary embodiment of the present disclosure, the method for object recognition may further include:

[0047] Step S120 , for each object to be identified, a pre-trained object recognition model is used to generate a recognition result of the object to be identified, and a target feature part of the object to be identified is determined according to the recognition result.

[0048] At least a portion of the object image can be input into a pre-trained object recognition model. For example, a whole object image can be input into a pre-trained object recognition model, or a portion of the object image containing the object to be recognized can be input into a pre-trained object recognition model. The object recognition model can output one or more classifications of the object to be recognized, which can usually be sorted from high to low according to the confidence level. The classification with the highest confidence level can be considered as the recognition result of the object to be recognized. In some embodiments, the classification unit of the recognition result generated by the pre-trained object recognition model can be "species". Further, the classification unit of the recognition result can be obtained based on the correspondence between "species" and "genus". In some embodiments, the classification unit of the recognition result generated by the pre-trained object recognition model can also be a classification unit of a higher level than "species" such as "genus". In this article, the classification with the classification unit of species is referred to as "species classification", and the classification with the classification unit of genus is referred to as "genus classification".

[0049] In some embodiments, the object recognition model can be trained based on a neural network model, for example, it can be trained based on a convolutional neural network model or a deep residual network model. The convolutional neural network model can be a deep feedforward neural network, which uses a convolution kernel to scan the object image, extracts the features to be identified in the object image, and then identifies the features to be identified of the object. In addition, in the process of identifying the object image, the original object image can be directly input into the convolutional neural network model without preprocessing the object image. Compared with other object recognition models, the convolutional neural network model has a higher recognition accuracy and recognition efficiency. Compared with the convolutional neural network model, the deep residual network model has an additional identity mapping layer, which can avoid the phenomenon of accuracy saturation or even decrease caused by the increase of network depth (the number of stacked layers in the network). The identity mapping function of the identity mapping layer in the deep residual network model needs to satisfy: the sum of the identity mapping function and the input of the deep residual network model is equal to the output of the deep residual network model. After the introduction of the identity mapping, the change of the output of the deep residual network model is more obvious, so the recognition accuracy and recognition efficiency of the object can be greatly improved.

[0050] In some embodiments, the specific training process of the object recognition model can be described as follows.

[0051] Prepare a sample set including a preset number of object images annotated with recognition results. In order to improve the training effect, a corresponding number of object images can be prepared for each possible recognition result, and the number of object images corresponding to each recognition result can be equal or unequal. Object images taken by users and related information (including shooting location, shooting time or shooting environment, etc.) can be collected to enrich the samples in the sample set, so as to further optimize the object recognition model based on these collected samples in the later stage.

[0052] Further, a part of the object images in the sample set is determined as a test set, and another part of the object images is determined as a training set. The test set and the training set can be determined manually or automatically, and the determination process can be random.

[0053] Further, the object recognition model is trained using the training set, and the trained object recognition model is tested using the test set, so as to obtain the accuracy of the object recognition model. Among them, the training process specifically includes adjusting each model parameter in the object recognition model. By comparing the accuracy of the object recognition model with the preset accuracy, it can be determined whether it is necessary to continue training. Specifically, when the accuracy of the trained object recognition model is greater than or equal to the preset accuracy, it can be considered that the accuracy of the object recognition model has met the requirements, so the training can be terminated, and the trained object recognition model can be used for object recognition. When the accuracy of the trained object recognition model is less than the preset accuracy, it can be considered that the object recognition model needs further optimization. At this time, the object recognition model can be further trained by increasing the number of samples in the training set, specifically by expanding the sample set and / or the training set, or increasing the proportion of the number of samples in the training set to the number of samples in the entire sample set. Alternatively, the object recognition model itself can be adjusted, and the adjusted object recognition model can be trained until an object recognition model that meets the requirements is obtained.

[0054] In some embodiments, Figure 2 As shown, determining the target characteristic part of the object to be identified according to the identification result may include:

[0055] Step S121, determining a candidate feature part corresponding to the recognition result according to the recognition result;

[0056] Step S122, using a pre-trained part recognition model, and determining a target feature part of the object to be recognized that matches the candidate feature part based on the candidate feature part.

[0057] When the recognition result of the object to be recognized is obtained, the corresponding candidate characteristic parts can be determined. In some embodiments, the candidate characteristic parts corresponding to the recognition result can be obtained from the content management database by, for example, a processor of the electronic device according to the recognition result. The candidate characteristic parts can be parts of the object to be recognized that have corresponding characteristic information to reflect the corresponding recognition result. For example, the morphology of the flowers and leaves of the cherry tree is usually different from that of other species. When the plant object is recognized as a cherry tree, the candidate characteristic parts can be determined to be flowers and leaves.

[0058] By using a pre-trained part recognition model, it can be determined whether there is a target feature part matching the candidate feature part in the object to be recognized. Specifically, an image containing the object to be recognized (for example, an image of the entire object or an image of the area where the object to be recognized is located in the object image) can be input into a pre-trained part recognition model. In some embodiments, the image containing the object to be recognized can be recognized according to the candidate feature parts to identify whether there is a corresponding part in the object to be recognized, and when a part matching the candidate feature part is recognized, the recognized part is determined as the target feature part. For example, when the candidate feature part is determined to be a flower or a leaf, the image containing the corresponding plant object can be recognized according to the pre-trained part recognition model to identify whether there are flowers and leaves in the image, and when flowers and / or leaves are recognized, flowers and / or leaves are determined as target feature parts. In this way, the part of the object to be recognized can be targetedly recognized and the target feature part can be determined according to the candidate feature parts, so that the influence of interference information such as non-candidate feature parts and external environment on the recognition result can be reduced, the amount of data to be processed can be reduced, and the recognition efficiency can be improved. In other embodiments, a pre-trained part recognition model can be used to recognize the parts of the object to be recognized, and the parts of the recognized parts of the object to be recognized that match the candidate feature parts are determined as target feature parts based on the candidate feature parts. For example, it can be recognized that the parts of the object to be recognized include fruits, flowers, and leaves based on the pre-trained part recognition model, and the candidate feature parts are flowers and leaves, then the flowers and leaves can be determined as target feature parts. In this way, the parts contained in the image to be recognized in the image can be recognized and the target feature parts that match the candidate feature parts can be determined from the recognized parts based on the candidate feature parts, so that the target feature parts can be updated in time when the candidate feature parts are updated.

[0059] In some embodiments, the part recognition model can be trained based on a neural network model, for example, it can be trained based on a convolutional neural network model or a deep residual network model. The part recognition model can be, for example, a plant part recognition model to recognize the parts of a plant object. In some embodiments, the specific training process of the part recognition model can refer to the training process of the object recognition model above, which will not be repeated here. In some embodiments, the part recognition model and the corresponding image processing algorithm (such as an edge detection algorithm) can be combined to better recognize the parts of the object to be recognized. In some embodiments, the recognition of the object to be recognized and the recognition of the parts of the object to be recognized can also be achieved by the same pre-trained model, that is, the model can integrate the functions of the above-mentioned object recognition model and the part recognition model. For example, the recognition results of the object to be recognized and the recognition results of the parts of the object to be recognized can be pre-marked on the training samples of the training set, so that the trained model can simultaneously recognize the object to be recognized and the parts of the object to be recognized.

[0060] return Figure 1 , refer to Figures 3 to 5 In an exemplary embodiment of the present disclosure, the method for object recognition may further include:

[0061] Step S130: display the first picture.

[0062] The first picture 300 may include at least a portion of the object image 310 and target feature information 320 associated with the target feature part 311 a .

[0063] The processor of one or more electronic devices may be configured to execute the method for object recognition disclosed herein, so as to display the first screen 300 and the second screen and the third screen described below on the user interface (UI) of one or more electronic devices, for example. One or more electronic devices may include one or more cameras for capturing still images or recording video streams, and all components for connecting these elements to each other. One or more electronic devices may each include a full-size personal computing device, or a mobile computing device that wirelessly exchanges data with a server via a network such as the Internet. For example, one or more electronic devices may be mobile phones, or may be mobile devices such as handheld computers, tablets, wearable devices, or devices that can obtain information via the Internet that can communicate wirelessly.

[0064] In some embodiments, the first picture 300 may include the entire object image 310 , or may include a partial image of the object image 310 including one or more objects 311 to be identified. Figures 3 to 5It is exemplarily shown that the first picture 300 includes a whole object image 310 , and the object image 310 has an object 311 to be recognized.

[0065] As described above, the target characteristic part 311a of the object to be identified 311 can be determined according to the pre-trained part recognition model. In some embodiments, the target characteristic information 320 associated with the target characteristic part 311a can also include image information 322 of the target characteristic part 311a. In some embodiments, the target characteristic information 320 associated with the target characteristic part 311a can include text information 321 describing at least one of the size, shape, and color of the target characteristic part 311a.

[0066] In this way, the basis for the corresponding recognition result of the object to be identified (such as the basis for species determination) can be displayed to the user in a multimodal form (such as text, images, etc.). Compared with outputting the recognition result only in text form, the interactivity with the user is enhanced, the user experience is improved, and the user's trust in the recognition result is increased.

[0067] In some embodiments, the first screen 300 may have one or more first areas, wherein the one or more first areas may be determined based on a pre-trained area recognition model and an object image 310, and an object to be identified 311 may correspond to a first area, or in other words, a corresponding object to be identified 311 may be displayed in each first area.

[0068] In some embodiments, one or more object regions of one or more objects to be identified 311 in the object image 310 may be determined based on a pre-trained region recognition model and the object image 310, and the image of the object region may be displayed in the corresponding first region of the first screen.

[0069] It is worth noting that, in a specific example, a first region may only display the corresponding object to be identified 311, and in another specific example, a first region may display not only the corresponding object to be identified 311, but also parts of other objects to be identified 311 corresponding to adjacent first regions. In other words, any two first regions may partially overlap, or may not have overlapping parts.

[0070] In some embodiments, the region recognition model can be trained based on a neural network model, for example, it can be trained based on a convolutional neural network model or a deep residual network model. The region recognition model can be, for example, a plant region recognition model to identify the region where the plant object is located in the plant image. In some embodiments, the specific training process of the region recognition model can refer to the training process of the object recognition model above, which will not be repeated here. In some embodiments, the recognition of the object to be recognized, the recognition of the part of the object to be recognized, and the recognition of the region where the object to be recognized is located can also be achieved by the same pre-trained model, that is, the model can integrate the functions of the above-mentioned object recognition model, the part recognition model and the region recognition model. For example, the recognition results of the object to be recognized, the recognition results of the part of the object to be recognized and the recognition results of the region where the object to be recognized is located can be pre-marked on the training samples of the training set, so that the trained model can simultaneously recognize the object to be recognized, the part of the object to be recognized and the region where the object to be recognized is located.

[0071] The region recognition model can be used to obtain the regions where different objects to be recognized are located and displayed in the corresponding first region. Furthermore, the first region can be interactive so that the user can operate in the first region of interest to switch the current object to be recognized of interest. Then, the first screen can be updated or displayed according to the user's operation, as will be described in detail later. In a specific example, the operation in the first region can include, for example, clicking, pressing, dragging, smearing, etc.

[0072] In some embodiments, in response to receiving an operation in the first area, the image of the corresponding object area can be input into a pre-trained object recognition model to generate a recognition result of the corresponding object to be recognized 311, so that subsequent recognition and screen display can be carried out in a targeted manner according to the user's operation, thereby saving computing resources and improving recognition efficiency. In other embodiments, the image of each object area can be input into a pre-trained object recognition model respectively, so as to generate recognition results of each object to be recognized 311 respectively, so that when the user switches the current object to be recognized by operating in the first area, the corresponding recognition result can be obtained in time, so as to facilitate the subsequent timely update or display of the first screen, thereby improving the efficiency of responding to user operations.

[0073] In some embodiments, displaying the first screen 300 may include: in response to receiving an operation in the first area, displaying target feature information 320 associated with the target feature part 311a of the corresponding object to be identified 311. That is, when the user performs an operation in the first area, the first screen 300 may display the target feature information 320 of the object to be identified 311 corresponding to the first area operated by the user. In this way, when the operation in the corresponding first area is received, only the target feature information of the corresponding object to be identified 311 may be displayed, so that the current object to be identified 311 is switched according to the user's operation and the corresponding target feature information 320 is displayed, reducing the possibility of confusion in the first screen 300 caused by the first screen 300 displaying target feature information 320 of multiple objects to be identified 311, so that the user can timely and clearly know the target feature information 320 of each object to be identified 311. In other embodiments, displaying the first screen 300 may include displaying the target feature information 320 of each object to be identified 311 in the object image 310, so that the user can timely know the target feature information 320 of each object to be identified 311 without performing an operation in the first area.

[0074] In some embodiments, in response to receiving an operation in the first area, displaying the target feature information 320 associated with the target feature part 311a of the corresponding object to be identified 311 may include: displaying the target feature information associated with the previous preset number of target feature parts 311a (for example, the first three target feature parts 311a with the highest priority) in order of the priority of the target feature parts 311a from high to low. In the case where the number of target feature parts 311a is greater than the preset number, the target feature information 320 associated with the previous preset number of target feature parts 311a with the highest priority may be displayed. In the case where the number of target feature parts 311a is less than or equal to the preset number, the target feature information 320 associated with each target feature part 311a may be displayed. In this way, the target feature information 320 of the previous preset number of target feature parts 311a with the highest priority may be displayed, reducing the possibility of the first screen 300 being displayed in a more chaotic manner due to displaying too much target feature information 320, avoiding the target feature information 320 from occupying too much screen space, and improving the display effect of the first screen 300 while displaying the target feature information 320 with a higher priority.

[0075] In a specific example, taking the recognition result of the object to be recognized 311 as a cherry tree as an example, the flower of the cherry tree has more obvious characteristics than the leaves, so as to be distinguished from other species, so for the object to be recognized whose recognition result is a cherry tree, the priority of the flower is greater than the priority of the leaves. In some embodiments, the priority of the target feature part 311a can be obtained from a pre-created content management system by a processor of the electronic device according to the recognition result.

[0076] In some embodiments, the target feature parts 311 a and / or the target feature information 320 associated with the target feature parts 311 a may be marked to distinguish different target feature parts 311 a and / or target feature information 320 .

[0077] In some embodiments, the priority of the target feature part 311a can be displayed in the form of at least one of text, numbers and graphics, so that the user can promptly know the priority order of the target feature part 311a. For example, the target feature part 311a with a higher priority can be marked with more "*" graphic symbols.

[0078] In some embodiments, Figures 3 to 5 As shown, the first screen 300 may include information 330 associated with the recognition result of the object to be recognized 311, that is, the information 330 associated with the recognition result of the object to be recognized 311 may be displayed on the same screen as the target feature information 320. For example, the planting result and the planting basis may be displayed simultaneously in the first screen 300. In other embodiments, the information 330 associated with the recognition result of the object to be recognized 311 in the object image 310 may be displayed before the first screen 300 is displayed, and then the first screen 300 including the target feature information 320 may be displayed. For example, the user may be informed of the species to which the plant in the input plant image belongs first, and then the first screen 300 including the target feature information 320 may be displayed, that is, the planting result may be displayed first and then the planting basis may be displayed.

[0079] In some embodiments, when the recognition result is the species classification to which the object to be recognized 311 belongs, the information 330 associated with the recognition result of the object to be recognized 311 may include at least one of the name, alias, and image of the species classification to which the object to be recognized 311 belongs. In some embodiments, the information 330 associated with the recognition result of the object to be recognized 311 may also include at least one of the name, alias, and image of the genus classification corresponding to the species classification to which the object to be recognized 311 belongs.

[0080] In some embodiments, Figures 3 to 5 As shown, the first screen 300 may have a second area 340, wherein information 330 associated with the recognition result of the object to be recognized 311 may be displayed in the second area 340. In a specific example, Figures 3 to 5 As shown, the second area 340 may be located below the first screen 300 , for example, may be located below the target feature information 320 .

[0081] In some embodiments, the second area 340 may display information 330 associated with the recognition result of each object to be recognized 311 in the object image 310. In other embodiments, as described above, in response to receiving the operation in the first area, the recognition result of the corresponding object to be recognized 311 may be generated, and accordingly, only the information 330 associated with the recognition result of the current object to be recognized 311 may be displayed in the second area 340, so that the user can obtain the information 330 associated with the recognition result of the object to be recognized 311 of interest in a timely manner, thereby improving the user experience.

[0082] like Figures 3 to 5 As shown, the second area 340 may include a first interactive object 341, wherein, in response to receiving an operation on the first interactive object 341, a second screen may be displayed. The first interactive object 341 may be, for example, a button having a preset shape, etc. The operation on the first interactive object 341 may be, for example, click, press, drag, smear, etc. The second screen may contain additional information about the object to be identified 311, for example, the second screen may include at least one of the growth characteristics, growth status, pest and disease information of the object to be identified 311, and maintenance guidance for the object to be identified 311. In this way, the user can operate the first interactive object 341 to display the second screen containing additional information about the object to be identified 311. In some embodiments, the information 330 associated with the recognition result of the object to be identified 311 and / or the additional information about the object to be identified 311 may be obtained, for example, by a processor of the electronic device from a pre-created content management system according to the recognition result of the object to be identified 311. In order to facilitate the user to promptly know the object 311 to be identified for which the additional information about the object 311 to be identified is directed, the identification result of the object 311 to be identified and the corresponding detailed introduction may also be displayed in the second screen.

[0083] like Figures 3 to 5As shown, the second area 340 may include a second interactive object 342, wherein, in response to receiving an operation on the second interactive object 342, an answer or question to the received operation may be displayed. The second interactive object 342 may be, for example, a dialog box. The operation on the second interactive object 342 may be, for example, clicking, pressing, dragging, smearing, etc. In addition, the operation on the second interactive object 342 may also be inputting relevant text information into the second interactive object 342 (e.g., a dialog box). For example, when the user feels that the recognition result and / or a certain target feature information does not match the current object to be recognized 311, the user may input the corresponding question or supplementary information into the second interactive object 342.

[0084] In some embodiments, answers or questions to the received operation may be displayed on an additional screen different from the first screen 300. The answers or questions to the received operation may be generated based on a pre-trained large language model, wherein the large language model may be trained based on a neural network model, for example, may be trained based on a deep learning model (e.g., a transformer model) based on a self-attention mechanism.

[0085] like Figures 3 to 5 As shown, the second area 340 may include a third interactive object 343, wherein, in response to receiving an operation on the third interactive object 343, voice information may be received. The third interactive object 343 may be, for example, a button having a preset shape, etc. The operation on the third interactive object 343 may be, for example, clicking, pressing, dragging, smearing, etc. Further, the voice information may be recognized, and subsequently the received voice information may be answered or asked questions based on a pre-trained large language model, or the voice information may be converted into text information and the converted text information may be input into, for example, the second interactive object 342.

[0086] In some embodiments, Figures 3 to 5 As shown, the first screen 300 may have one or more third regions 350, wherein one third region 350 may correspond to one target characteristic part 311a, and each third region may display target characteristic information 320 associated with the corresponding target characteristic part 311a, so as to display the target characteristic information 320 in a more orderly manner and improve the display effect of the screen. In a specific example, the third region 350 may be located near the corresponding target characteristic part 311a displayed in the first screen 300.

[0087] In a specific example, there may be no overlapping part between any two third areas 350, or they may partially overlap, and there is no limitation here, as long as each third area 350 can display the corresponding target feature information 320 relatively clearly. For example, each third area 350 can be arranged at a corresponding preset position in the first screen 300 so that the target feature information 320 displayed in each third area 350 is not blocked by other target feature information 320, so that the user can clearly know the corresponding target feature information 320, thereby improving the screen display effect.

[0088] In some embodiments, in the first screen 300, at least a portion of the displayed object image 310, at least two of the second area 340 and the third area 350 can be set with different transparency to enhance the layering of the screen and enhance the display effect. In a specific example, the transparency of at least a portion of the displayed object image 310 can be set to a lower transparency than that of the third area 350, so as to better display the target feature information 320 in the third area 350, reduce the possibility that the target feature information 320 is blocked by the object image 310 and displayed unclearly, and enhance the user experience.

[0089] In some embodiments, in response to receiving an operation in the third area 350, a third screen may be displayed, wherein the third screen may include additional information associated with the corresponding target feature part 311a. That is, the third area 350 may be interactive, and the user may operate in the third area 350 of interest to display additional information associated with the corresponding target feature part 311a. In a specific example, the operation in the third area 350 may include, for example, clicking, pressing, dragging, smearing, etc.

[0090] In some embodiments, the additional information associated with the corresponding target characteristic part 311a may include at least one of the image information of the target characteristic part 311a, the name of the target characteristic part, additional image information similar to the image information of the target characteristic part 311a, a prompt requesting input of one or more additional images of the target characteristic part 311a, and shooting guidance for the target characteristic part 311a. The additional information associated with the corresponding target characteristic part 311a may also include distinguishing features between the target characteristic part 311a and similar characteristic parts.

[0091] In a specific example, the additional information associated with the corresponding target characteristic part 311a can be obtained from the content management system by the processor of the electronic device according to the recognition result of the object to be recognized 311 and / or the corresponding target characteristic part 311a. The content management system can be pre-created, and the content management system can include multiple groups of names, nicknames, and images of similar object types and / or characteristic parts that are easily confused. The content management system can also include distinguishing features between these similar object types and / or characteristic parts, optimized shooting parameters for these distinguishing features, shooting guidance, and other information.

[0092] In a specific example, information (e.g., the results of image recognition model input and / or information obtained from a content management system) can be integrated and extracted based on a pre-trained image recognition model (e.g., the object recognition model and part recognition model mentioned above) and a large language model to display additional information associated with the corresponding target feature part 311a.

[0093] In some embodiments, the third screen may further include a fourth interactive object. The fourth interactive object may be, for example, a button with a preset shape, or a dialog box in which information may be input. When the user feels that the corresponding target feature information 320 does not match the current object to be identified 311 or is interested in the corresponding target feature part 311a, the user may ask questions and / or provide additional information based on the fourth interactive object. In a specific example, one or more additional images about the target feature part 311a may be input based on the fourth interactive object. For example, the additional images may be input by performing operations such as clicking, pressing, dragging, and smearing on the fourth interactive object.

[0094] In some embodiments, in response to receiving one or more additional images about the target feature part 311a based on the fourth interactive object input, one or more additional images can be identified. Among them, a pre-trained object recognition model and / or part recognition model can be used to recognize the additional images. Then, the target feature information 320 associated with the corresponding target feature part 311a can be updated based on the recognition results of the one or more additional images to improve the accuracy of the displayed target feature information 320. Accordingly, in some embodiments, the corresponding information 330 associated with the recognition results can also be updated based on the recognition results of the one or more additional images to improve the accuracy of the displayed information 330 associated with the recognition results. In this way, the corresponding displayed screen can be updated based on the recognition results of one or more additional images, thereby enhancing user participation, enhancing interactivity with users, and improving user experience.

[0095] In some embodiments, the associated task can be generated and displayed to the user based on the content in at least one of the first screen, the second screen, and the third screen. In the case of a device that can execute the task being connected, the corresponding device can also be automatically and / or manually controlled to execute the task.

[0096] In a specific example, a processor of an electronic device may generate a maintenance task and / or treatment task for the object to be identified 311 based on at least one of the identification result of the object to be identified 311, the target feature information 320, the additional information about the object to be identified 311, and the additional information associated with the target feature part 311a, and output the corresponding maintenance task and / or treatment task. Maintenance tasks may include, for example, irrigation, fertilization, light adjustment, pruning, etc., and treatment tasks may include, for example, pesticide spraying, weeding, loosening the soil, etc. The maintenance tasks and / or treatment tasks may also include various parameters of the tasks, such as the time, interval, and amount of watering, the dosage, time, and interval of fertilization, the location of pruning, the dosage and location of pesticide spraying, etc.

[0097] Further, the identification of the maintenance device and / or treatment device for performing the corresponding maintenance task and / or treatment task can also be output, so that, for example, the processor of the electronic device controls the corresponding maintenance device and / or treatment device according to the identification of the maintenance device and / or treatment device to complete the corresponding maintenance task and / or treatment task. For example, the maintenance devices such as the irrigation device, the fertilization device, the light adjustment device, and the pruning device can be controlled to perform the maintenance tasks such as irrigation, fertilization, light adjustment, and pruning on the object to be identified 311. For another example, the treatment devices such as the pesticide spraying device, the weeding device, and the loosening device can be controlled to perform the treatment tasks such as pesticide spraying, weeding, and loosening on the object to be identified 311.

[0098] The identification of the maintenance device and / or treatment device can be determined, for example, by a processor of the electronic device according to the maintenance task and / or treatment task from a content management database storing identifications of devices communicatively coupled to the electronic device.

[0099] Since the maintenance device and / or treatment device usually has a communication function, commands can be transmitted to the maintenance device (eg, via Bluetooth protocol, Zigbee protocol, etc.).

[0100] In a specific example, a command instructing the corresponding maintenance device and / or treatment device to perform the maintenance task and / or treatment task can be sent according to the determined identifier of the device for performing the task, thereby controlling the corresponding device to automatically complete the corresponding maintenance task and / or treatment task, thereby reducing the burden on the user and improving the efficiency of maintenance and / or treatment. In this way, after the object image is taken and uploaded by the electronic device, not only the corresponding screen (first screen, second screen or third screen) can be displayed, but also the maintenance task and / or treatment task for the object to be identified in the object image can be displayed, and the corresponding device can also be automatically controlled to perform the corresponding task, thereby realizing fully automatic monitoring, maintenance and treatment of the object to be identified.

[0101] In another specific example, after displaying a maintenance task and / or a treatment task to the user, the user may be further asked whether to confirm the execution of the corresponding maintenance and / or treatment, and after the user confirms the execution, the corresponding device is controlled to execute the corresponding task according to the maintenance task and / or the treatment task.

[0102] According to another aspect of the present disclosure, a device for object recognition is also provided. Figure 6 As shown, the apparatus 400 for object recognition may include a processor 410 and a memory 420. The memory 420 stores instructions, which, when executed by the processor 410, implement the steps of the method for object recognition described in any of the foregoing embodiments of the present disclosure.

[0103] The processor 410 may be an integrated circuit chip having the ability to process signals. The processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, to implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present disclosure. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc., and may be an X86 architecture or an ARM architecture, etc.

[0104] The memory 420 may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronously connected dynamic random access memory (SLDRAM), and direct memory bus random access memory (DRRAM). It should be noted that the memory described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0105] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium is provided, on which instructions are stored. When the instructions are executed, the steps of the method for object recognition described in any of the foregoing embodiments of the present disclosure can be implemented.

[0106] Similarly, the non-transitory computer-readable storage medium in the embodiments of the present disclosure may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory. It should be noted that the non-transitory computer-readable storage medium described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0107] According to another aspect of the present disclosure, a computer program product is further provided. The computer program product includes a computer program. When the computer program is executed by a processor, the steps of the method for object recognition described in any of the aforementioned embodiments of the present disclosure can be implemented.

[0108] The instructions may be any set of instructions to be executed directly by one or more processors, such as machine code, or any set of instructions to be executed indirectly, such as a script. The terms "instructions", "applications", "processes", "steps" and "programs" (including "computer programs") herein may be used interchangeably herein. The instructions may be stored in an object code format for direct processing by one or more processors, or as a script or collection of independent source code modules in any other computer language, including those interpreted on demand or compiled in advance. The instructions may include instructions that cause one or more processors, such as to act as the various neural networks herein. The functions, methods and routines of the instructions are explained in more detail elsewhere herein.

[0109] Figure 7A schematic block diagram of a computer system 500 on which an embodiment of the present disclosure may be implemented is shown. The computer system 500 includes a bus 510 or other communication mechanism for transmitting information, and a processing device 520 coupled to the bus 510 for processing information. The computer system 500 also includes a memory 530 coupled to the bus 510 for storing instructions to be executed by the processing device 520, which may be a random access memory (RAM) or other dynamic storage device. The memory 530 may also be used to store temporary variables or other intermediate information during the execution of instructions to be executed by the processing device 520. The computer system 500 may also include a read-only memory (ROM) 540 or other static storage device coupled to the bus 510 for storing static information and instructions for the processing device 520. A storage device 550 such as a magnetic disk or optical disk is provided and coupled to the bus 510 for storing information and instructions. The computer system 500 may be coupled to an output device 560 via a bus 510 for providing output to a user, such as, but not limited to, a display (such as a cathode ray tube (CRT) or a liquid crystal display (LCD)), a speaker, etc. An input device 570 such as a keyboard, a mouse, a microphone, etc. is coupled to the bus 510 for transmitting information and command selections to the processing device 520. The computer system 500 may perform embodiments of the present disclosure. Consistent with certain implementations of the present disclosure, the results are provided by the computer system 500 in response to the processing device 520 executing one or more sequences of one or more instructions contained in the memory 530. Such instructions may be read from another computer-readable medium such as a storage device 550 into the memory 530. The execution of the sequence of instructions contained in the memory 530 causes the processing device 520 to perform the methods described herein. Alternatively, hard-wired circuitry may be used instead of software instructions or in combination with software instructions to implement the present teachings. Therefore, implementations of the present disclosure are not limited to any specific combination of hardware circuitry and software. In various embodiments, computer system 500 can be connected to one or more other computer systems like computer system 500 across a network via network interface 580 to form a networked system. The network can include a private network or a public network such as the Internet. In a networked system, one or more computer systems can store data and supply data to other computer systems. The term "computer-readable medium" as used herein refers to any medium that participates in providing instructions to processing device 520 for execution. Such media can take many forms, including but not limited to non-volatile media, volatile media, and transmission media. Non-volatile media include, for example, optical or magnetic disks such as storage device 550. Volatile media include dynamic memories such as memory 530. Transmission media include coaxial cables, copper wires, and optical fibers, including wiring that includes bus 510.Common forms of computer-readable media or computer program products include, for example, floppy disks, flexible disks, hard disks, tapes, or any other magnetic media, CD-ROMs, digital video disks (DVDs), Blu-ray disks, any other optical media, thumb drives, memory cards, RAMs, PROMs and EPROMs, flash EPROMs, any other memory chips or cartridges, or any other tangible media from which a computer can read. Various forms of computer-readable media may be involved when carrying one or more sequences of one or more instructions to processing device 520 for execution. For example, the instructions may initially be carried on a disk of a remote computer. The remote computer may load the instructions into its dynamic memory and send the instructions over a telephone line using a modem. A modem local to computer system 500 may receive data over the telephone line and convert the data into an infrared signal using an infrared transmitter. An infrared detector coupled to bus 510 may receive the data carried in the infrared signal and place the data on bus 510. Bus 510 carries the data to memory 530, and processing device 520 retrieves the instructions from memory 530 and executes the instructions. Optionally, the instructions received by memory 530 may be stored on storage device 550 either before or after execution by processing device 520 .

[0110] According to various embodiments, instructions configured to be executed by the processing device 520 to perform the method are stored on a computer-readable medium. A computer-readable medium may be a device that stores digital information. For example, a computer-readable medium includes a compact disk read-only memory (CD-ROM) as known in the art for storing software. The computer-readable medium is accessed by a processor adapted to execute the instructions configured to be executed.

[0111] In the technical solution of the present disclosure, by determining the target feature part of the object to be identified, displaying at least a part of the object image and the target feature information associated with the target feature part, the recognition result is explained from multiple aspects, and the interactivity with the user is enhanced, just like a professional explaining the object to be identified, which not only provides an immersive experience, but also reflects the professionalism of object identification, thereby improving the user's recognition and trust in the recognition result and improving the user experience. In addition, the present disclosure can also display the basis for the object to be identified as the corresponding recognition result (such as the basis for the determination of plant objects) in a multimodal manner to further enhance the interactivity with the user and improve the user experience. According to some embodiments of the present disclosure, it can be combined with a content management system to display similar legends of the corresponding parts to the user in order to further gain the trust of the user.

[0112] The words "left", "right", "front", "back", "top", "bottom", "up", "down", "high", "low", etc., in the specification and claims, if present, are used for descriptive purposes and are not necessarily used to describe an unchanging relative position. It should be understood that the words so used are interchangeable under appropriate circumstances, so that the embodiments of the present disclosure described herein, for example, can operate in other orientations than those shown or otherwise described herein. For example, when the device in the drawings is turned over, features originally described as "above" other features may now be described as "below" the other features. The device may also be oriented in other ways (rotated 90 degrees or in other orientations), and the relative spatial relationships will be interpreted accordingly.

[0113] In the specification and claims, when an element is referred to as being "on", "attached", "connected", "coupled", or "contacting" another element, the element may be directly on, directly attached, directly connected, directly coupled, or directly contacting another element, or one or more intermediate elements may be present. In contrast, when an element is referred to as being "directly" "on", "directly attached", "directly connected", "directly coupled", or "directly contacting" another element, there will be no intermediate elements. In the specification and claims, a feature being arranged "adjacent" to another feature may refer to a feature having a portion that overlaps with an adjacent feature or a portion that is located above or below an adjacent feature.

[0114] As used herein, the word "exemplary" means "serving as an example, instance, or illustration" rather than as a "model" to be exactly copied. Any implementation described as an example herein is not necessarily to be construed as preferred or advantageous over other implementations. Furthermore, the present disclosure is not to be limited by any expressed or implied theory given in the technical field, background, summary, or detailed description.

[0115] As used herein, the term "substantially" is intended to include any minor variations due to design or manufacturing imperfections, device or component tolerances, environmental influences, and / or other factors. The term "substantially" also allows for deviations from a perfect or ideal situation due to parasitic effects, noise, and other practical considerations that may exist in actual implementations.

[0116] In addition, the terms "first", "second" and the like may also be used herein for reference purposes only and are not intended to be limiting. For example, the terms "first", "second" and other such numerical terms referring to structures or elements do not imply a sequence or order unless the context clearly indicates otherwise.

[0117] It should also be understood that when the term “include / comprises” is used in this document, it indicates the presence of the specified features, integers, steps, operations, units and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, units and / or components and / or their combinations.

[0118] In this disclosure, the term "provide" is used in a broad sense to cover all ways of obtaining an object, and thus "providing an object" includes but is not limited to "purchasing", "preparing / manufacturing", "arranging / setting up", "installing / assembling", and / or "ordering" an object, etc.

[0119] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items. The terms used herein are for the purpose of describing specific embodiments only and are not intended to limit the present disclosure. As used herein, the singular forms "a", "an", and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0120] Those skilled in the art will appreciate that the boundaries between the above operations are merely illustrative. Multiple operations can be combined into a single operation, a single operation can be distributed in additional operations, and operations can be performed at least partially overlapping in time. Moreover, alternative embodiments may include multiple instances of a specific operation, and the order of operations may be changed in various other embodiments. However, other modifications, variations, and replacements are equally possible. Aspects and elements of all embodiments disclosed above may be combined in any manner and / or in combination with aspects or elements of other embodiments to provide multiple additional embodiments. Therefore, this specification and accompanying drawings should be considered illustrative, not restrictive.

[0121] In addition, the embodiments of the present disclosure may also include the following examples:

[0122] 1. A method for object recognition, wherein the method comprises:

[0123] Acquire an object image, wherein the object image includes one or more objects to be identified;

[0124] For each object to be identified, a pre-trained object recognition model is used to generate a recognition result of the object to be identified, and a target feature part of the object to be identified is determined according to the recognition result; and

[0125] A first picture is displayed, wherein the first picture includes at least a portion of the object image and target feature information associated with the target feature part.

[0126] 2. The method according to item 1, wherein determining the target characteristic part of the object to be identified according to the identification result comprises:

[0127] Determining, according to the recognition result, a candidate feature part corresponding to the recognition result; and

[0128] A pre-trained part recognition model is used to determine the target feature parts of the object to be recognized that match the candidate feature parts based on the candidate feature parts.

[0129] 3. The method according to 1, wherein the target feature information includes:

[0130] Text information describing at least one of the size, shape, and color of the target feature part; and / or

[0131] Image information of the target characteristic part.

[0132] 4. The method according to 1, wherein the first screen has one or more first areas, wherein the one or more first areas are determined based on a pre-trained area recognition model and the object image, and a corresponding object to be recognized is displayed in each first area.

[0133] 5. The method according to claim 4, wherein displaying the first screen comprises:

[0134] In response to receiving an operation in the first area, target feature information associated with the target feature part of the corresponding object to be identified is displayed.

[0135] 6. The method according to 5, wherein displaying the target feature information associated with the target feature part of the corresponding object to be identified comprises:

[0136] The target feature information associated with the first preset number of target feature parts is displayed in descending order of priority of the target feature parts.

[0137] 7. The method according to 5, wherein displaying the target feature information associated with the target feature part of the corresponding object to be identified comprises:

[0138] The priority of the target feature part is displayed in at least one form of text, numbers and graphics.

[0139] 8. The method according to 1, wherein the first screen has a second area, wherein information associated with the recognition result of the object to be recognized is displayed in the second area.

[0140] 9. The method according to 8, wherein the recognition result is a category to which the object to be recognized belongs, and the information associated with the recognition result of the object to be recognized includes at least one of the following:

[0141] at least one of a name, an alias, and an image of the category to which the object to be identified belongs; and

[0142] At least one of the name, alias and image of the genus category corresponding to the species category to which the object to be identified belongs.

[0143] 10. The method according to 8, wherein the second area includes at least one of a first interactable object, a second interactable object, and a third interactable object, wherein the method further comprises:

[0144] In response to receiving an operation on the first interactable object, displaying a second screen;

[0145] In response to receiving an operation on the second interactable object, displaying an answer or question to the received operation; and

[0146] In response to receiving an operation on the third interactable object, voice information is received.

[0147] 11. The method according to 10, wherein the second screen includes: at least one of growth characteristics, growth status, pest and disease information, and maintenance guidance for the object to be identified.

[0148] 12. The method according to 1, wherein the first screen has one or more third areas, wherein one third area corresponds to a target feature part, and each third area displays target feature information associated with the corresponding target feature part.

[0149] 13. The method according to 12, wherein the method further comprises:

[0150] In response to receiving an operation in the third area, a third picture is displayed, wherein the third picture includes additional information associated with the corresponding target characteristic part.

[0151] 14. The method according to 13, wherein the additional information associated with the corresponding target feature part includes at least one of the following:

[0152] The image information of the target characteristic part, the name of the target characteristic part, the additional image information similar to the image information of the target characteristic part, the prompt requesting to input one or more additional images about the target characteristic part and the shooting guidance of the target characteristic part.

[0153] 15. The method according to 13, wherein the third screen includes a fourth interactable object, and the method further includes:

[0154] In response to receiving one or more additional images of the target feature based on the fourth interactable object input, identifying the one or more additional images; and

[0155] The target feature information associated with the corresponding target feature part is updated based on the recognition result of the one or more additional images.

[0156] 16. A device for object recognition, wherein the device comprises a processor and a memory, wherein the memory stores instructions, and when the instructions are executed by the processor, the steps of the method described in any one of 1 to 15 are implemented.

[0157] 17. A non-transitory computer-readable storage medium, wherein instructions are stored on the non-transitory computer-readable storage medium, and when the instructions are executed by a processor, the steps of the method described in any one of 1 to 15 are implemented.

[0158] 18. A computer program product, wherein the computer program product comprises instructions, and when the instructions are executed by a processor, the steps of the method according to any one of 1 to 15 are implemented.

[0159] Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. The various embodiments disclosed herein may be combined in any manner without departing from the spirit and scope of the present disclosure. It should also be understood by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A method for object recognition, characterized in that The method comprises: Acquire an object image, wherein the object image includes one or more objects to be identified; For each object to be identified, a pre-trained object recognition model is used to generate a recognition result of the object to be identified, and a target feature part of the object to be identified is determined according to the recognition result; and A first picture is displayed, wherein the first picture includes at least a portion of the object image and target feature information associated with the target feature part.

2. The method according to claim 1, characterized in that: Determining the target characteristic part of the object to be identified according to the recognition result includes: determining a candidate characteristic part corresponding to the recognition result according to the recognition result, and using a pre-trained part recognition model to determine the target characteristic part of the object to be identified that matches the candidate characteristic part according to the candidate characteristic part; and / or The target feature information includes: text information describing at least one of the size, shape, and color of the target feature part; and / or image information of the target feature part; and / or The first screen has one or more first areas, wherein the one or more first areas are determined based on a pre-trained area recognition model and the object image, and a corresponding object to be recognized is displayed in each first area; and / or Displaying the first picture includes: in response to receiving an operation in the first area, displaying target feature information associated with the target feature part of the corresponding object to be identified.

3. The method according to claim 2, characterized in that Displaying target feature information associated with the target feature part of the corresponding object to be identified includes: Displaying target feature information associated with a preset number of target feature parts in descending order of priority of the target feature parts; and / or The priority of the target feature part is displayed in at least one form of text, numbers and graphics.

4. The method according to claim 1, characterized in that The first screen has a second area, wherein information associated with a recognition result of the object to be recognized is displayed in the second area.

5. The method according to claim 4, characterized in that: The recognition result is the species classification to which the object to be recognized belongs, and the information associated with the recognition result of the object to be recognized includes at least one of the following: at least one of the name, alias and image of the species classification to which the object to be recognized belongs; and at least one of the name, alias and image of the genus classification corresponding to the species classification to which the object to be recognized belongs; and / or The second area includes at least one of a first interactable object, a second interactable object, and a third interactable object, wherein the method further includes: in response to receiving an operation on the first interactable object, displaying a second screen; in response to receiving an operation on the second interactable object, displaying an answer or question to the received operation; and in response to receiving an operation on the third interactable object, receiving voice information; and / or The second picture includes: at least one of the growth characteristics, growth status, pest and disease information of the object to be identified, and maintenance guidance for the object to be identified.

6. The method according to claim 1, characterized in that: The first picture has one or more third areas, wherein one third area corresponds to one target characteristic part, and each third area displays target characteristic information associated with the corresponding target characteristic part; and / or The method further includes: in response to receiving an operation in the third area, displaying a third picture, wherein the third picture includes additional information associated with the corresponding target feature part.

7. The method according to claim 6, characterized in that: The additional information associated with the corresponding target characteristic part includes at least one of the following: image information of the target characteristic part, the name of the target characteristic part, additional image information similar to the image information of the target characteristic part, a prompt requesting input of one or more additional images of the target characteristic part, and shooting guidance for the target characteristic part; and / or The third screen includes a fourth interactable object, and the method further includes: in response to receiving one or more additional images about the target feature part input based on the fourth interactable object, identifying the one or more additional images; And updating the target feature information associated with the corresponding target feature part based on the recognition result of the one or more additional images.

8. A device for object recognition, characterized in that: The device comprises a processor and a memory, wherein instructions are stored in the memory, and when the instructions are executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

9. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores instructions, and when the instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product, characterized in that The computer program product comprises instructions which, when executed by a processor, implement the steps of the method according to any one of claims 1 to 7.

Images