WO2021089059A1

WO2021089059A1 - Method and apparatus for smart object recognition, object recognition device, terminal device, and storage medium

Info

Publication number: WO2021089059A1
Application number: PCT/CN2020/138696
Authority: WO
Inventors: 石翔
Original assignee: 昆山提莫智能科技有限公司
Priority date: 2019-11-06
Filing date: 2020-12-23
Publication date: 2021-05-14
Also published as: CN110781861A

Abstract

Provided in the present invention is a smart object recognition method, comprising acquiring an image of an object to be recognized; performing pre-processing on the image of the object to be recognized to obtain image feature data; on the basis of the image feature data, performing recognition in an object database to acquire a recognition result and generate an object content text, and on the basis of the object content text, generating a first audio link; on the basis of the object content text, performing matching in a resource library to acquire resource data corresponding to the recognition text, and on the basis of the resource data, generating a second audio link; and selecting to play the first audio link and/or the second audio link, thus solving the problems of enjoyment, independence, and knowledge limitation when a child is identifying objects.

Description

Intelligent object recognition method and device, object recognition equipment, terminal equipment, storage medium

Technical field

The present invention relates to the technical field of intelligent terminals, in particular to an intelligent object recognition method and device, intelligent object recognition equipment, terminal equipment and computer storage media.

Background technique

At present, there are more and more educational products on the market, either for children’s cognitive enlightenment, or for children’s knowledge teaching. For children who are curious about the world, their desire to understand the things around them has given birth to a series of Education terminal.

For example, in children’s cognition of objects, in the prior art, the main way for children to recognize objects is to print the objects on books. This is the most common way for children to recognize objects by reading text or under the guidance of others. Obviously, on the one hand, this kind of education requires the accompany of parents. On the other hand, based on the limited knowledge of printed publications, this kind of teaching method has great knowledge limitations and lack of interest.

Another way is to set up a recognition card. Each card sets a recognition pressing point. When a recognition pressing point is pressed, the name of the item corresponding to the card is played. This way is for children to operate Sex is a bit complicated, and it is easy for children to lose interest. At the same time, the recognition card is also easy to fail. Compared with the previous method, there is still the problem of knowledge limitations.

Summary of the invention

The purpose of the present invention is to provide an intelligent object-recognition method and device, intelligent object-recognition equipment, terminal equipment and computer storage medium, which are used to solve the problems of knowledge limitation, independence and interest in children's object-recognition.

In order to achieve the above purpose of naming, in one embodiment, the present invention provides an intelligent object recognition method, including:

Obtain an image of the object to be recognized;

Preprocessing the image of the object to be recognized to obtain image feature data;

Perform recognition in an article database according to the image feature data, obtain a recognition result and generate article content text, and generate a first audio link according to the article content text;

Matching in the resource library according to the content text of the article, obtaining resource data corresponding to the recognized text, and generating a second audio link according to the resource data;

Select to play the first audio link and/or the second audio link.

Further, the preprocessing of the image of the object to be recognized to obtain image feature data specifically includes:

Compression, image binarization, gray-scale image processing, SIFT feature extraction, and intersection feature extraction are performed on the image of the object to be recognized to obtain image feature data.

Further, said performing recognition in an article database according to the image feature data, obtaining a recognition result and generating article content text, and generating a first audio link according to the article content text specifically includes:

Extracting the object features corresponding to the core feature point data according to the image feature data;

Search in the article database according to the object feature, obtain the article name corresponding to the object feature, output the recognition result, and generate the article content text;

Synthesize the content text of the article into a first audio link.

Further, the matching in a resource library according to the article content text, obtaining resource data corresponding to the recognized text, and generating a second audio link according to the resource data specifically includes:

A search formula is generated according to the article content text, and a search is performed in the resource library according to the search formula. For example, resource data that exactly matches the search formula is retrieved, and the resource data includes the text corresponding to the article content For video, animation or audio data, one or more of the resource data is selected to generate a second audio link.

Further, the searching in the item database according to the feature of the object and obtaining the item name corresponding to the feature of the object specifically includes:

The article database is set in a remote server, the article database includes a characteristic article mapping table, and the corresponding article name is obtained according to the characteristics of the article;

Wherein, the data interface of the article database is connected with a third-party knowledge base, and the data interface is used to update the characteristic article mapping table in real time.

In another embodiment, the present invention also provides an intelligent object recognition device, the intelligent object recognition device comprising:

The image acquisition unit is used to acquire an image of the object to be identified;

An image preprocessing unit, configured to preprocess the image of the object to be recognized to obtain image feature data;

The recognition unit is used to send the image feature data to the item database for recognition, obtain the recognition result and generate the item content text, generate the first audio link according to the item content text, and perform the process in the resource database according to the item content text Match, obtain resource data corresponding to the recognized text, and generate a second audio link according to the resource data;

The playing unit is configured to receive and select to play the first audio link and/or the second audio link.

Further, the identification unit specifically includes:

The sending module is used to send the image feature data to the item database, wherein the item database is set in a remote server, and the server extracts the object feature corresponding to the core feature point data according to the image feature data, and then According to the object feature search in the article database, the article name corresponding to the object feature is obtained, the recognition result is output, the article content text is generated, and the article content text is synthesized into the first audio link.

In another implementation, the identification unit specifically includes:

A sending module for sending the image feature data to the article database;

The first audio generation module is configured to search and obtain recognition results in the article database according to the image characteristics, generate article content text, and generate a first audio link based on the article content text;

The second audio generating module is configured to perform matching in the resource library according to the article content text, obtain resource data corresponding to the recognized text, and generate a second audio link according to the resource data.

Correspondingly, the present invention further provides an embodiment, in which an intelligent object recognition device based on the aforementioned intelligent object recognition method, the intelligent object recognition device includes:

Comprising a housing, a handle and a camera module, the camera module includes a camera, the camera is used to obtain the image of the object to be identified, the housing has a plurality of installation positions for installing the camera, A camera is installed on at least one of the installation positions, and any two straight lines where the installation positions are located intersect the straight lines where the handles are located, and if there are two installation positions, they are symmetrically arranged on the left and right sides of the children's encyclopedia knowledge device On both sides,

Wherein, the housing includes a front cover, a rear cover, a front housing, and a rear housing. The installation location is located on the front housing, and the rear cover has a through hole through which light can pass through the through hole to reach the The photosensitive area of the camera; the back cover has two symmetrically arranged circular protrusions, and the through hole is provided at the center of the protrusions.

Further, the intelligent object recognition device further includes:

A circuit board, the circuit board includes a main body portion accommodated in the housing and a connecting portion extending from the main body portion to the inside of the handle, the connecting portion is provided with an identification trigger, and the handle includes and The button matched with the object-recognizing trigger can be pressed to drive the object-recognizing trigger to act, and the object-recognizing method can be started.

Preferably, the button part passes through the through hole and is detachably connected to the object triggering member.

Preferably, the intelligent object recognition device further includes a display assembly, the display assembly includes a display panel, a mounting frame for fixing the display panel is provided on the front housing, and the display panel is mounted on the front housing. The body is close to one side of the rear housing, and the display assembly is used for playing the first audio or the second audio.

The embodiment of the present invention also provides a terminal device, including a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor realizes intelligent recognition when the computer program is run. The steps of the physical method.

The embodiment of the present invention also provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the intelligent identification method are realized.

The intelligent object recognition method and device, intelligent object recognition equipment, terminal equipment and computer storage medium provided by the present invention can at least bring about the following beneficial effects:

1. Obtain the image of the object to be recognized through the camera in real time, and obtain the feature of the object to be recognized through image processing to perform feature recognition, obtain the object recognition result, and broadcast it. It is full of fun for children, and the desire for knowledge can be satisfied in time. The real-time performance is high, and the object of recognizing is not limited to the publication or card at hand, and any object is in the recognition range, which increases the breadth of knowledge.

2. In addition to the name of the item to be played, a learning resource library is also provided. For the identified object, the educational resources related to the item are also retrieved in the resource library, such as the historical origin, evolution process, composition, function and distribution of the item, etc. While enriching knowledge, it also enhances the fun of children's learning.

3. The third-party program interface is connected to the database of the object through the server, and the object of the object is expanded. The object of the object is expanded infinitely, and the capacity of the knowledge base is increased. More importantly, the powerful computing power of the knowledge base can greatly increase the capacity of the knowledge base. Improve the speed of recognizing objects, and the user experience can be greatly improved.

4. Through the pre-set item feature mapping table, the item classification can be quickly located according to the main features of the item, and then the object name can be further identified according to other features. On the one hand, it improves the speed of item recognition, and on the other hand, it also improves the item Accuracy of recognition.

Description of the drawings

Hereinafter, the preferred embodiments will be described in a clear and easy-to-understand manner in conjunction with the accompanying drawings to further illustrate the above-mentioned characteristics, technical features, advantages and implementation methods.

Figure 1 is a schematic diagram of the process of the intelligent object recognition method in the present invention;

2 is a schematic diagram of the structure of an intelligent object recognition device in the present invention;

Figure 3 is a schematic diagram of another intelligent object recognition device in the present invention;

Figure 4 is a schematic diagram of the structure of yet another intelligent object recognition device in the present invention;

5 is a schematic diagram of the front structure of a handheld children's encyclopedia recognition device according to a specific embodiment of the present invention;

6 is an exploded schematic diagram of various components of the handheld children's encyclopedia recognition device according to a specific embodiment of the present invention;

FIG. 7 is a schematic diagram of the front shell structure of the handheld children's encyclopedia recognition device according to a specific embodiment of the present invention;

FIG. 8 is a schematic structural diagram of a camera module of a handheld children's encyclopedia object-recognizing device according to a specific embodiment of the present invention;

9 is a schematic diagram of the front cover and the back cover of the handheld children's encyclopedia recognition device according to a specific embodiment of the present invention;

10 is a schematic diagram of another structure of the front cover and the back cover of the handheld children's encyclopedia recognition device according to a specific embodiment of the present invention;

FIG. 11 is a schematic structural diagram of a terminal device according to a specific embodiment of the present invention.

Detailed ways

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, specific embodiments of the present invention will be described below with reference to the drawings. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative work, other drawings can be obtained based on these drawings and obtained Other embodiments.

As shown in FIG. 1 is an embodiment of the present invention, a method for intelligently identifying objects, including:

S10. Obtain an image of the object to be recognized;

S20. Preprocess the image of the object to be recognized to obtain image feature data;

S30. Perform recognition in an article database according to the image feature data, obtain a recognition result and generate article content text, and generate a first audio link based on the article content text;

S40. Perform matching in the resource library according to the article content text, obtain resource data corresponding to the recognized text, and generate a second audio link according to the resource data;

S50. Select to play the first audio link and/or the second audio link.

When the user needs to recognize an object, he can first press the camera button to focus on the object, and collect a picture of the object through the camera. Since children have not yet set appropriate camera parameters, users can configure the frequency and exposure time of the camera to obtain more suitable pictures through mobile phones, Bluetooth, wifi, or peer-to-peer, etc., so as to obtain more suitable pictures to facilitate follow-up. It is easy to obtain the main feature information of the object during feature recognition.

Based on embodiment 1, in another embodiment 2 of the present invention, the preprocessing of the image of the object to be recognized to obtain image feature data specifically includes:

Preprocess the collected images, including but not limited to compressed pictures, image binarization, grayscale image processing, SIFT feature extraction, and intersection feature extraction. The pre-processing action can be performed by the object-recognizing device, can also be completed by a mobile phone connected to the object-recognizing device, or even sent to a remote server for completion. The above examples do not represent that the embodiments of the present invention limit the implementation subject of the image preprocessing process.

In Embodiment 3 of the present invention, based on the foregoing implementation, the identification in the article database based on the image feature data, obtaining the identification result and generating article content text, and generating the first audio link based on the article content text specifically includes:

Synthesize the content text of the article into a first audio link.

After the feature data is extracted, the collected images have many features, and may even contain features of other objects due to the camera angle. However, the features of the main objects are generally emphasized. Therefore, the embodiment of the present invention waits in advance. Identify the core feature or main feature of the object picture or image, compare it with the object feature in the item database, obtain the object corresponding to the core feature point, and generate the item content text.

In another embodiment 5, the article database is also provided with article classification, and a certain kind of article contains category characteristics, which is convenient for quickly searching and locating the name of the article.

By docking with Baidu/Ali/Tencent AI services, the image content is first recognized and the text of the main object name in the image is output. This text is the recognition result; then the text content is synthesized into voice content through TTS voice technology, and this voice content link is the first Audio link; then use the object name text to search in the server's audio, video, animation and other educational resource libraries, with complete overlap as the matching criterion, select the voice, animation, and video content, if the matching is successful. This voice content link is the second audio link.

The generation of the first audio link and the second audio link may be completed by the identification device itself, or completed by the identification device and the server respectively, or all completed by the server.

In one implementation mode, the collected or preprocessed images can be uploaded to the server via wifi or 4G/5G network, and the server can complete the feature recognition and search, and then obtain the article name text. Preferably, the article database is set in the remote The server also includes a feature item mapping table, which directly maps object names from features to achieve rapid identification of items.

As shown in FIG. 2, Embodiment 6 of the present invention provides an intelligent object-recognizing device 100, and the intelligent object-recognizing device includes:

The image acquisition unit 110 is used to acquire an image of the object to be identified;

The image preprocessing unit 120 is configured to preprocess the image of the object to be recognized to obtain image feature data;

The recognition unit 130 is configured to send the image feature data to the article database for identification, obtain the recognition result and generate article content text, generate a first audio link according to the article content text, and store the article content text in the resource database according to the article content text Performing matching, obtaining resource data corresponding to the recognized text, and generating a second audio link according to the resource data;

The playing unit 140 is configured to receive and select to play the first audio link and/or the second audio link.

For example, the image acquisition unit includes: a camera; a processor, a camera button (which can be a physical button or a touch screen button), a speaker, an LCD display and an LED indicator, and the processor uses a wifi or bluetooth module or 4G The /5G network is connected to the mobile phone, the camera and the camera button are connected to the input end of the processor, and the output end of the processor is connected to the speaker, LCD display and LED indicator.

As shown in FIG. 3, in Embodiment 7, the identification unit specifically includes:

The sending module 1301 is configured to send the image feature data to an item database, where the item database is set in a remote server, and the server extracts the object feature corresponding to the core feature point data according to the image feature data, and Search in the article database according to the object feature, obtain the article name corresponding to the object feature, output the recognition result, generate the article content text, and synthesize the article content text into the first audio link.

In embodiment 7, the article database and the resource library are both located in the server, the retrieval formula is generated according to the article content text, and the retrieval is performed in the resource database according to the retrieval formula. If the retrieval formula is completely retrieved, Matching resource data, where the resource data includes video, animation, or audio data corresponding to the content text of the article, then one or more of the resource data is selected to generate a second audio link.

In Embodiment 8, the resource library is located in an object recognition device or a third-party mobile phone, a search formula is generated according to the content text of the article, and the resource library is searched according to the search formula. If the resource data that exactly matches the search formula, the resource data includes video, animation, or audio data corresponding to the content text of the article, then one or more of the resource data is selected to generate a second audio link.

In Embodiment 9, as shown in FIG. 4, the identification unit specifically includes:

The sending module 1301 is used to send the image feature data to the article database;

The first audio generating module 1302 is configured to search and obtain a recognition result in the article database according to the image feature, generate article content text, and generate a first audio link according to the article content text;

The second audio generating module 1303 is configured to perform matching in the resource library according to the article content text, obtain resource data corresponding to the recognized text, and generate a second audio link according to the resource data.

As shown in FIG. 5, the present invention further provides Embodiment 10. In this embodiment, an intelligent object recognition device based on the foregoing intelligent object recognition method includes:

Further, the intelligent object recognition device further includes:

As shown in FIG. 5, it is a schematic diagram of the front structure of a smart object-recognizing device. The smart object-recognizing device is a child's smart encyclopedia object-recognizing device or a child's camera device.

As shown in Figures 5, 6, 7, and 8, the children’s smart encyclopedia knowledge device includes a housing 20, a handle 10, and a camera module 60. The camera module 60 includes a camera 61. The camera 61 can be a color camera, a black and white camera, and a wide-angle camera. For a camera or a zoom camera, the housing 20 has a plurality of installation positions for installing the camera, at least one of the installation positions is equipped with a camera, and the line where any two installation positions are located intersects the line where the handle 10 is located, and the housing 20 and the handle 10 are formed T-shaped.

There are two installation positions on the housing 20. The line where the two installation positions are located is perpendicular to the line where the handle 10 is located. In this application, there are two installation positions and are symmetrically arranged on the left and right sides of the children's encyclopedia object recognition device. The line connecting the center points of the position forms a straight line L1, which extends in the horizontal direction, and the straight line L2 where the handle 10 is located extends in the vertical direction.

The children’s smart encyclopedia object recognition equipment of this application may include one camera or multiple cameras, but at least two camera installation positions can be installed. Cameras can be installed in both installation positions or only one of them can be installed according to actual needs. , The other mounting position can be equipped with a magnifying glass, flashlight or flashlight. The two mounting positions form two eyes of the children’s encyclopedia knowledge device in appearance, which is convenient for the design of cartoon characters or animals that children like. The two mounting positions are symmetrically arranged More beautiful.

Further refer to FIG. 6, which is an exploded schematic diagram of the components of the children's encyclopedia identification device of a specific embodiment of the present invention. The children's encyclopedia identification device of the present application further includes a circuit board 30, which includes a main body 31 housed in a housing And the connecting portion 32 extending from the main body portion 31 to the inside of the handle 10, the connecting portion 32 is provided with an object-sensing trigger, the handle 10 includes a button 11 matched with the object-sensing trigger, pressing the button 11 can drive the object-sensing trigger to act , Start the smart identification device to work. The object recognition trigger is an electronic component. The camera module 60 is electrically connected to the circuit board 30. Specifically, the camera module 60 includes a camera 61, a soft board 62, and a connector 63. The camera 61 is mounted on the housing 20, and the connector 63 is electrically connected to the circuit board 30.

A battery 80 is provided in the handle 10, and the battery provides power to the circuit board 30.

It also includes a display assembly 40 and a player 50. The display assembly 40 includes a display panel 41, a protective foam 42, a display panel fixing member 43, and a front cover 44 for protecting the display panel. The installation frame of the display panel 41, the display panel 41 is installed on the side of the front casing 21 close to the rear casing 22, and the front cover 44 is installed on the side of the front casing 21 away from the rear casing 22 to protect the foam 42 is adhered to a circumference of the mounting frame to protect the display panel. The display panel 41 is mounted on the display panel fixing member 43 and then fixed to the mounting frame to better protect the display panel from damage. That is, the children’s encyclopedia identification device of the present application further includes a display panel 41, a protective foam 42, and a display panel fixing member 43. A mounting frame for fixing the display panel 41 is provided on the housing, and the protective foam adheres to the circumference of the mounting frame. , To protect the display panel, the display panel 41 is installed on the display panel fixing member, and then fixed to the mounting frame, which better protects the display panel from damage. The display panel can only have display functions, or it can integrate display and touch Control function. The display panel may be a liquid crystal display panel (Liquid Crystal Display, LCD) or an organic light-emitting diode display panel (Organic light-emitting diode, OLED).

The housing 20 includes a front cover 24, a rear cover 23, a front housing 21 and a rear housing 22. The handle 10 includes a handle front shell 12, a handle rear shell 13 and a silicone rear hand guard 14. The front shell 21 and the handle front shell 12 The front case is integrally formed, and the rear case 22 and the handle rear case 13 are integrally disposed to form a rear case. The front cover 24, the rear cover 23, the front case and the rear case are connected in sequence. The front cover 24 and the rear cover 23 can be integrally formed, or Through the integrated structure of the assembled form, the front shell and the rear shell are fixedly connected by screws. The front shell and the rear shell are jointly enclosed to form an accommodating cavity. The circuit board 30, the battery 80, and the display panel 41 are all located in the accommodating cavity. The battery 80 is electrically connected to the circuit board to provide power for the circuit board 30.

The handle 10 is roughly cylindrical, which is convenient to hold. The handle 10 also includes a silicone front hand guard 15. Both the silicone front hand guard 15 and the silicone rear hand guard 14 have anti-slip structures. The anti-slip structure in the present invention is an anti-slip stripe; at the same time, The handle 10 also includes a supporting part for supporting the intelligent object recognition device to stand. The bottom of the handle 10 is a flat surface, and the flat bottom forms the supporting part.

The camera module 60 is electrically connected to the circuit board 30. Specifically, the camera module 60 further includes a soft board 62 and a connector 63. The connector 63 is electrically connected to the circuit board 30. The camera module 60 is used to collect images to form Corresponding to the image signal, the circuit board 30 is provided with a chip for processing the image signal. The chip preprocesses the image and uploads the image to the server via WiFi or 4G/5G. The server first outputs the object name in text form after identifying the content of the image. Then, the text content is synthesized into voice content and output. Next, the object name is matched with the optimal animation content of the server's educational resource library. If the matching is successful, the animation content is output, and the handheld electronic device plays the voice content and the animation content in sequence.

Further referring to Figures 7 and 8, Figure 7 is a schematic diagram of the front shell structure of the children's encyclopedia recognition device in a specific embodiment of the present invention, and Figure 8 is a schematic diagram of the camera module structure of the children's encyclopedia recognition device in a specific embodiment of the present invention, and the camera 61 is installed On the side of the front housing 21 away from the rear housing 22, two installation positions are provided on one side of the front housing 21 where the camera is installed. The center connection of the two installation positions forms a straight line L1, which is along the length direction of the housing 20 Extend, the camera is installed on one of the installation positions in the present application. Specifically, the installation position is set as a receiving groove 211 with side walls on all sides. The camera is fixed at the bottom of the receiving groove. During assembly, the camera 61 is fixed in the receiving groove 211 , The soft board 62 passes through the opening 212, and the connector 63 is electrically connected to the circuit board 30 located in the accommodating cavity.

Further referring to Figures 9 and 10, Figure 9 is a schematic diagram of the front cover and the back cover of the children's encyclopedia recognition device in a specific embodiment of the present invention, and FIG. 10 is another front cover and back cover of the children's encyclopedia recognition device in a specific embodiment of the present invention A schematic structural diagram. In the present application, the back cover 23 has a through hole 232 through which light can reach the photosensitive area of the camera 61. The back cover 23 has two symmetrically arranged circular protrusions 231, and the through hole 232 is provided with At the center of the protrusion 231, the back cover 23 has a groove 233 for accommodating the microphone, and the bottom of the groove has a hole through which external sound can pass. Accordingly, the front cover 24 includes a circular protrusion 231 for passing through For the round hole 241 that has passed, a small hole is also opened on the front cover 24 at a position corresponding to the bottom hole of the groove 233, so that the microphone can sensitively receive external sounds.

The children’s encyclopedia knowledge device has a convenient handle, and the camera has multiple optional installation positions, which is convenient to choose the appropriate installation position according to different shapes. Most children like animals or cartoon characters, and the camera can be used as an animal in shape Or the eyes of cartoon characters are novel in shape, which enhances the fun, and the handle is convenient for children to hold.

As shown in Figure 11, the embodiment of the present invention also provides a terminal device, including a memory, a processor, and a computer program that is stored in the memory and can run on the processor. When the processor runs the computer program, Steps to realize the method of intelligent object recognition.

FIG. 11 is a schematic structural diagram of a terminal device provided in an embodiment of the present invention. As shown, the terminal device 200 includes: a processor 220, a memory 210, and a computer program stored in the memory 210 and running on the processor 220 211, such as: intelligent object recognition program. When the processor 220 executes the computer program 211, the steps in the foregoing embodiments of the smart object recognition method are implemented, or when the processor 220 executes the computer program 211, the functions of the modules in the foregoing embodiments of the smart object recognition device are implemented.

The terminal device 200 may be a notebook, a palmtop computer, a tablet computer, a mobile phone, and other devices. The terminal device 200 may include, but is not limited to, a processor 220 and a memory 210. Those skilled in the art can understand that FIG. 11 is only an example of the terminal device 200, and does not constitute a limitation on the terminal device 200. It may include more or less components than those shown in the figure, or a combination of certain components, or different components. For example, the terminal device 200 may also include input and output devices, display devices, network access devices, buses, and so on.

The processor 220 may be a central processing unit (Central Processing Unit, CPU), or other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), on-site Field-Programmable GateArray (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor 220 may be a microprocessor or the processor may also be any conventional processor or the like.

The memory 210 may be an internal storage unit of the terminal device 200, such as a hard disk or memory of the terminal device 200. The memory 210 may also be an external storage device of the terminal device 200, such as a plug-in hard disk equipped on the terminal device 200, a smart memory card (SmartMedia Card, SMC), a Secure Digital (SD) card, and a flash memory card (Flash). Card) and so on. Further, the memory 210 may also include both an internal storage unit of the terminal device 200 and an external storage device. The memory 210 is used to store the computer program 211 and other programs and data required by the terminal device 200. The memory 210 may also be used to temporarily store data that has been output or will be output.

In the above-mentioned embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in an embodiment, reference may be made to related descriptions of other embodiments.

The intelligent object recognition method and device, intelligent object recognition equipment, terminal equipment and computer storage medium provided by the present invention can at least bring the following beneficial effects:

Those skilled in the art can clearly understand that for the convenience and conciseness of the description, only the division of the above-mentioned program modules is used as an example. In practical applications, the above-mentioned functions can be allocated by different program modules as needed, namely The internal structure of the device is divided into different program units or modules to complete all or part of the functions described above. The program modules in the embodiments can be integrated in one processing unit, or each unit can exist alone physically, or two or more units can be integrated in one processing unit. The above-mentioned integrated units can be implemented in the form of hardware. It can also be implemented in the form of a software program unit. In addition, the specific names of the program modules are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the present invention.

A person of ordinary skill in the art may realize that the units and algorithm steps of the examples described in the embodiments disclosed in the present invention can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraint conditions of the technical solution. Professionals and technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered as going beyond the scope of the present invention.

In the embodiments provided by the present invention, it should be understood that the disclosed terminal device and method may be implemented in other ways. For example, the terminal device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be Combined or can be integrated into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

In addition, the functional units in the various embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.

If the integrated module/unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment methods, and can also be completed by sending instructions to the relevant hardware through the computer program 211. The computer program 211 can be stored in a computer-readable storage medium. When executed by the processor 220, 211 may implement the steps of the foregoing method embodiments. Wherein, the computer program 211 includes: computer program code, and the computer program code may be in the form of source code, object code, executable file, or some intermediate forms. The computer-readable storage medium may include: any entity or device capable of carrying the computer program 211 code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random Access memory (RAM, Random Access Memory), electric carrier signal, telecommunications signal, software distribution medium, etc. It should be noted that the content contained in the computer-readable storage medium can be appropriately added or deleted according to the requirements of the legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to the legislation and patent practice, the computer-readable medium Does not include electrical carrier signals and telecommunication signals.

It should be noted that the above embodiments can be freely combined as required. The above are only preferred embodiments of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and modifications can be made, and these improvements and modifications are also It should be regarded as the protection scope of the present invention.

Claims

A method of intelligent object recognition, which is characterized in that it includes:

Obtain an image of the object to be recognized;

Preprocessing the image of the object to be recognized to obtain image feature data;

Perform recognition in an article database according to the image feature data, obtain a recognition result and generate article content text, and generate a first audio link according to the article content text;

Performing matching in the resource library according to the article content text, obtaining resource data corresponding to the article content text, and generating a second audio link according to the resource data;

Select to play the first audio link and/or the second audio link.
The intelligent object recognition method of claim 1, wherein preprocessing the image of the object to be recognized to obtain image feature data specifically includes:

Compression, image binarization, gray-scale image processing, SIFT feature extraction, and intersection feature extraction are performed on the image of the object to be recognized to obtain image feature data.
The intelligent object recognition method according to claim 1, wherein the recognition is performed in the article database according to the image feature data, the recognition result is obtained and the article content text is generated, and the first audio link is generated according to the article content text Specifically:

Extracting the object features corresponding to the core feature point data according to the image feature data;

Search in the article database according to the object feature, obtain the article name corresponding to the object feature, output the recognition result, and generate the article content text;

Synthesize the content text of the article into a first audio link.
The intelligent object recognition method according to claim 3, wherein the article content text is matched in a resource library to obtain resource data corresponding to the recognized text, and generate according to the resource data The second audio link specifically includes:

A search formula is generated according to the article content text, and a search is performed in the resource library according to the search formula. For example, resource data that exactly matches the search formula is retrieved, and the resource data includes the text corresponding to the article content For video, animation or audio data, one or more of the resource data is selected to generate a second audio link.
The intelligent object recognition method according to claim 3, wherein the searching in an object database according to the object feature and obtaining the object name corresponding to the object feature specifically includes:

The article database is set in a remote server, the article database includes a characteristic article mapping table, and the corresponding article name is obtained according to the characteristics of the article;

Wherein, the data interface of the article database is connected with a third-party knowledge base, and the data interface is used to update the characteristic article mapping table in real time.
An intelligent object-recognizing device, characterized in that, the intelligent object-recognizing device includes:

The image acquisition unit is used to acquire an image of the object to be identified;

An image preprocessing unit, configured to preprocess the image of the object to be recognized to obtain image feature data;

The recognition unit is used to send the image feature data to the item database for recognition, obtain the recognition result and generate the item content text, generate the first audio link according to the item content text, and perform the process in the resource database according to the item content text Match, obtain resource data corresponding to the recognized text, and generate a second audio link according to the resource data;

The playing unit is configured to receive and select to play the first audio link and/or the second audio link.
The intelligent object recognition device according to claim 6, wherein the recognition unit specifically comprises:

The sending module is used to send the image feature data to the item database, wherein the item database is set in a remote server, and the server extracts the object feature corresponding to the core feature point data according to the image feature data, and then According to the object feature search in the article database, the article name corresponding to the object feature is obtained, the recognition result is output, the article content text is generated, and the article content text is synthesized into the first audio link.
The intelligent object recognition device according to claim 6, wherein the recognition unit specifically comprises:

A sending module for sending the image feature data to the article database;

The first audio generation module is configured to search and obtain recognition results in the article database according to the image characteristics, generate article content text, and generate a first audio link based on the article content text;

The second audio generating module is configured to perform matching in the resource library according to the article content text, obtain resource data corresponding to the recognized text, and generate a second audio link according to the resource data.
An intelligent object recognition device based on any one of claims 1-5, wherein the intelligent object recognition device comprises:

Comprising a housing, a handle and a camera module, the camera module includes a camera, the camera is used to obtain the image of the object to be identified, the housing has a plurality of installation positions for installing the camera, A camera is installed on at least one of the installation positions, and any two straight lines where the installation positions are located intersect the straight lines where the handles are located, and if there are two installation positions, they are symmetrically arranged on the left and right sides of the children's encyclopedia knowledge device On both sides,

Wherein, the housing includes a front cover, a rear cover, a front housing, and a rear housing. The installation location is located on the front housing, and the rear cover has a through hole through which light can pass through the through hole to reach the The photosensitive area of the camera; the back cover has two symmetrically arranged circular protrusions, and the through hole is provided at the center of the protrusions.
The intelligent object recognition device of claim 9, wherein the intelligent object recognition device further comprises:

A circuit board, the circuit board includes a main body portion accommodated in the housing and a connecting portion extending from the main body portion to the inside of the handle, the connecting portion is provided with an identification trigger, and the handle includes and The button matched with the object-recognizing trigger can be pressed to drive the object-recognizing trigger to act, and the object-recognizing method can be started.
The intelligent object recognition device of claim 10, wherein the button part passes through the through hole and is detachably connected to the object recognition trigger.
The intelligent object recognition device of claim 11, wherein the intelligent object recognition device further comprises a display component, the display component comprises a display panel, and the front housing is provided with a fixing device for fixing the display panel. A mounting frame, the display panel is mounted on a side of the front housing close to the rear housing, and the display assembly is used for playing the first audio or the second audio.
A terminal device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program as claimed in claim 1- Steps of any one of the intelligent object recognition methods described in 5.
A computer-readable storage medium, the computer-readable storage medium stores a computer program, wherein the computer program is executed by a processor to implement the intelligent identification method according to any one of claims 1-5 A step of.