KR102581822B1 - Method and apparatus for recognizing characters in educational programs - Google Patents

Abstract

Embodiments include an optical character recognition method for an electronic device for children's learning according to an embodiment of the present invention to solve the above problem, wherein the electronic device includes a touch display; A database storing a plurality of letter images and Unicode data corresponding to each of the letter images; receiving a target letter image through the touch display, and using a text detection model to Generating a text area image and coordinate data of the text area image from a target text image, and recognizing a character string corresponding to the target text image in the text area image using a text recognition model. Including, the letter recognition model divides the letter area image into a first zone, a second zone, a third zone, and a fourth zone, and assigns different weights to each of the first to fourth zones, Considering each of the weights, a matching rate between the letter area image included in one or more of the first to fourth areas and any one of the letter images is calculated, and based on the matching rate, the letter area One or more letters included in the image can be recognized, and a string corresponding to the target letter image can be output based on the recognized letters and the coordinate data.

Description

{METHOD AND APPARATUS FOR RECOGNIZING CHARACTERS IN EDUCATIONAL PROGRAMS}

The present invention relates to an optical character recognition method for electronic devices for infant learning.

Optical character recognition technology, which converts character images electronically or mechanically, includes a method of classifying character patterns into arrays and comparing them with circular patterns to find similar shapes (template matching), and statistical methods. , Structural analysis methods, etc. have now developed into methods using artificial neural networks.

In addition, recently, various video output devices such as IP TVs, tablet PCs, smartphones, etc. have been produced, and as their penetration rate is rapidly increasing, text learning applications that are easily accessible to children and can arouse interest in children are being released. .

In the method of learning letters for children, a commonly used method is for children to write directly on the touchable display of a video output device, enter the answer to the problem, and compare it with the correct answer. However, the optical character recognition rate of the handwriting of infants who have not yet properly learned English is very low.

According to one embodiment, a method of optical character recognition for an electronic device for infant learning using optical character recognition technology with improved character recognition rate is provided.

Additionally, according to another embodiment, a method for automatically correcting typos in input words entered by a child based on an improved optical character recognition rate is provided.

The technical problems to be solved by the present invention are not limited to the problems mentioned above, and other technical problems not mentioned can be considered by those skilled in the art from the various embodiments described below. You can.

An optical character recognition method for an electronic device for infant learning according to an embodiment of the present invention to solve the above problem includes: a touch display; A database storing a plurality of letter images and Unicode data corresponding to each of the letter images; receiving a target letter image through the touch display, and using a text detection model to Generating a text area image and coordinate data of the text area image from a target text image, and recognizing a character string corresponding to the target text image in the text area image using a text recognition model. Including, the letter recognition model divides the letter area image into a first zone, a second zone, a third zone, and a fourth zone, and assigns different weights to each of the first to fourth zones, Considering each of the weights, a matching rate between the letter area image included in one or more of the first to fourth areas and any one of the letter images is calculated, and based on the matching rate, the letter area One or more letters included in the image can be recognized, and a string corresponding to the target letter image can be output based on the recognized letters and the coordinate data.

The character area detection model includes a feature extraction layer, and the feature extraction layer receives the target character image and generates a plurality of feature maps based on the target character image. and determining whether a letter exists in each of the plurality of feature maps, assigning a feature score to each of the plurality of feature maps, coordinate data of each of the plurality of feature maps, a rotation angle of each of the plurality of feature maps, and The character area image may be output based on the feature score.

The letter recognition model includes an input layer, one or more hidden layers, and an output layer, and includes a plurality of letter area images included in one or more of the first to fourth regions, the match rate, and the correct letter image. Training data is input to the input layer of the letter recognition model, passes through the one or more hidden layers and the output layer to output an output vector, and the output vector is input to a loss function layer connected to the output layer, and the loss function The layer outputs a loss value using a loss function that compares the output vector with the correct answer vector for each training data, and the parameters of the letter recognition model are learned in the direction of decreasing the loss value,

[Equation]

The loss function follows the above equation, where N is the number of the plurality of learning data, n is a natural number identifying the learning data, k is a natural number identifying the value of the nth learning data, and nk is the nth It refers to the kth value of the training data, t refers to the correct word image, y refers to the output vector, and E may refer to the loss value.

Other specific details of the invention are included in the detailed description and drawings.

According to one embodiment, the optical character recognition method of an electronic device for children's learning accurately recognizes letters input by a child using a touch display through a high optical character recognition rate, allowing the child's letter learning to proceed smoothly. .

The effects that can be obtained from the examples are not limited to the effects mentioned above, and other effects not mentioned can be clearly derived and understood by those skilled in the art based on the detailed description below. It can be.

The accompanying drawings, which are included as part of the detailed description to aid understanding of the embodiments, provide various embodiments and together with the detailed description describe technical features of the various embodiments.
1 is a diagram showing the configuration of an electronic device according to an embodiment.
Figure 2 is a diagram showing the configuration of a program according to one embodiment.
Figure 3 is a block diagram showing an electronic device for infant learning according to an embodiment.
Figure 4 is an example of the standard form and handwriting of the alphabet in various fonts.
Figure 5 is a flowchart showing an infant learning process according to an embodiment.
Figure 6 is a diagram showing a first display screen displayed on a touch display.
7 and 8 are diagrams showing a second display screen displayed on a touch display.
Figure 9 is a diagram showing a third display screen displayed on a touch display.
FIG. 10 is an enlarged view of the user input area of FIG. 8.
FIG. 11 is a flowchart for explaining S140 of FIG. 5.
FIG. 12 is an exemplary diagram illustrating feature areas of each character to determine a plurality of areas used for character recognition.

The following embodiments combine elements and features of the embodiments in a predetermined form. Each component or feature may be considered optional unless explicitly stated otherwise. Each component or feature may be implemented in a form that is not combined with other components or features. Additionally, various embodiments may be configured by combining some components and/or features. The order of operations described in various embodiments may change. Some features or features of one embodiment may be included in other embodiments or may be replaced with corresponding features or features of other embodiments.

In the description of the drawings, procedures or steps that may obscure the gist of the various embodiments are not described, and procedures or steps that can be understood at the level of a person with ordinary knowledge in the relevant technical field are not described. did.

Throughout the specification, when a part is said to “comprise or include” a certain element, this means that it does not exclude other elements but may further include other elements, unless specifically stated to the contrary. do. Additionally, the terms “a or an,” “one,” “the,” and similar related terms are used herein in the context of describing various embodiments (particularly in the context of the claims below). Unless otherwise indicated or clearly contradicted by context, it may be used in both singular and plural terms.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected," but also the case where it is "electrically connected" with another element in between. . In addition, when a part is said to "include" a certain component, this does not mean excluding other components unless specifically stated to the contrary, but may further include other components, and one or more other features. It should be understood that it does not exclude in advance the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

In this specification, 'part' includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more pieces of hardware, and two or more units may be realized using one piece of hardware. Meanwhile, '~ part' is not limited to software or hardware, and '~ part' may be configured to reside in an addressable storage medium or may be configured to reproduce one or more processors. Therefore, as an example, '~ part' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and 'parts' may be combined into a smaller number of components and 'parts' or may be further separated into additional components and 'parts'. Additionally, components and 'parts' may be implemented to regenerate one or more CPUs within a device or a secure multimedia card.

In this specification, some of the operations or functions described as being performed by a terminal, apparatus, or device may instead be performed on a server connected to the terminal, apparatus, or device. Likewise, some of the operations or functions described as being performed by the server may also be performed in a terminal, apparatus, or device connected to the server.

In this specification, some of the operations or functions described as mapping or matching with the terminal mean mapping or matching the terminal's unique number or personal identification information, which is identifying data of the terminal. It can be interpreted as

In addition, in this specification, blockchain is a technology in which new transaction records are distributed and stored in all nodes when a block is created, and is a distributed database management system (DBMS) that ensures transparency of transactions by keeping transaction ledgers separate for all parties to the transaction. means. Smart Contract, which forms the basis of the database, is a computer program that automates the consensus process, and is a system that is established as soon as the contract conditions written in the code are satisfied according to the code principle that code is law. .

Hereinafter, embodiments according to various embodiments will be described in detail with reference to the attached drawings. The detailed description set forth below in conjunction with the accompanying drawings is intended to illustrate exemplary embodiments of various embodiments and is not intended to represent the only embodiment.

In addition, specific terms used in various embodiments are provided to aid understanding of the various embodiments, and the use of such specific terms may be changed to other forms without departing from the technical spirit of the various embodiments. .

1 is a diagram showing the configuration of an electronic device according to an embodiment.

1 is a block diagram of an electronic device 101 in a network environment 100, according to various embodiments. Referring to FIG. 1, in the network environment 100, the electronic device 101 communicates with the electronic device 102 through a first network 198 (e.g., a short-range wireless communication network) or a second network 199. It is possible to communicate with at least one of the electronic device 104 or the server 108 through (e.g., a long-distance wireless communication network). According to one embodiment, the electronic device 101 may communicate with the electronic device 104 through the server 108. According to one embodiment, the electronic device 101 includes a processor 120, a memory 130, an input module 150, an audio output module 155, a display module 160, an audio module 170, and a sensor module ( 176), interface 177, connection terminal 178, haptic module 179, camera module 180, power management module 188, battery 189, communication module 190, subscriber identification module 196 , or may include an antenna module 197. In some embodiments, at least one of these components (eg, the connection terminal 178) may be omitted or one or more other components may be added to the electronic device 101. In some embodiments, some of these components (e.g., sensor module 176, camera module 180, or antenna module 197) are integrated into one component (e.g., display module 160). It can be. The electronic device 101 may also be referred to as a client, terminal, or peer.

The processor 120, for example, executes software (e.g., program 140) to operate at least one other component (e.g., hardware or software component) of the electronic device 101 connected to the processor 120. It can be controlled and various data processing or calculations can be performed. According to one embodiment, as at least part of data processing or computation, the processor 120 stores commands or data received from another component (e.g., sensor module 176 or communication module 190) in volatile memory 132. The commands or data stored in the volatile memory 132 can be processed, and the resulting data can be stored in the non-volatile memory 134. According to one embodiment, the processor 120 includes a main processor 121 (e.g., a central processing unit or an application processor) or an auxiliary processor 123 that can operate independently or together (e.g., a graphics processing unit, a neural network processing unit ( It may include a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor). For example, if the electronic device 101 includes a main processor 121 and a secondary processor 123, the secondary processor 123 may be set to use lower power than the main processor 121 or be specialized for a designated function. You can. The auxiliary processor 123 may be implemented separately from the main processor 121 or as part of it.

The auxiliary processor 123 may, for example, act on behalf of the main processor 121 while the main processor 121 is in an inactive (e.g., sleep) state, or while the main processor 121 is in an active (e.g., application execution) state. ), together with the main processor 121, at least one of the components of the electronic device 101 (e.g., the display module 160, the sensor module 176, or the communication module 190) At least some of the functions or states related to can be controlled. According to one embodiment, co-processor 123 (e.g., image signal processor or communication processor) may be implemented as part of another functionally related component (e.g., camera module 180 or communication module 190). there is. According to one embodiment, the auxiliary processor 123 (eg, neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. Artificial intelligence models can be created through machine learning. For example, such learning may be performed in the electronic device 101 itself on which the artificial intelligence model is performed, or may be performed through a separate server (e.g., server 108). Learning algorithms may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but It is not limited. An artificial intelligence model may include multiple artificial neural network layers. Artificial neural networks include deep neural network (DNN), convolutional neural network (CNN), recurrent neural network (RNN), restricted boltzmann machine (RBM), belief deep network (DBN), bidirectional recurrent deep neural network (BRDNN), It may be one of deep Q-networks or a combination of two or more of the above, but is not limited to the examples described above. In addition to hardware structures, artificial intelligence models may additionally or alternatively include software structures.

The memory 130 may store various data used by at least one component (eg, the processor 120 or the sensor module 176) of the electronic device 101. Data may include, for example, input data or output data for software (e.g., program 140) and instructions related thereto. Memory 130 may include volatile memory 132 or non-volatile memory 134.

The program 140 may be stored as software in the memory 130 and may include, for example, an operating system 142, middleware 144, or application 146.

The input module 150 may receive commands or data to be used in a component of the electronic device 101 (e.g., the processor 120) from outside the electronic device 101 (e.g., a user). The input module 150 may include, for example, a microphone, mouse, keyboard, keys (eg, buttons), or digital pen (eg, stylus pen).

The sound output module 155 may output sound signals to the outside of the electronic device 101. The sound output module 155 may include, for example, a speaker or a receiver. Speakers can be used for general purposes such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. According to one embodiment, the receiver may be implemented separately from the speaker or as part of it.

The display module 160 can visually provide information to the outside of the electronic device 101 (eg, a user). The display module 160 may include, for example, a display, a hologram device, or a projector, and a control circuit for controlling the device. According to one embodiment, the display module 160 may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of force generated by the touch.

The audio module 170 can convert sound into an electrical signal or, conversely, convert an electrical signal into sound. According to one embodiment, the audio module 170 acquires sound through the input module 150, the sound output module 155, or an external electronic device (e.g., directly or wirelessly connected to the electronic device 101). Sound may be output through the electronic device 102 (e.g., speaker or headphone).

The sensor module 176 detects the operating state (e.g., power or temperature) of the electronic device 101 or the external environmental state (e.g., user state) and generates an electrical signal or data value corresponding to the detected state. can do. According to one embodiment, the sensor module 176 includes, for example, a gesture sensor, a gyro sensor, an air pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, It may include a temperature sensor, humidity sensor, or light sensor.

The interface 177 may support one or more designated protocols that can be used to connect the electronic device 101 directly or wirelessly with an external electronic device (eg, the electronic device 102). According to one embodiment, the interface 177 may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

The connection terminal 178 may include a connector through which the electronic device 101 can be physically connected to an external electronic device (eg, the electronic device 102). According to one embodiment, the connection terminal 178 may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (eg, a headphone connector).

The haptic module 179 can convert electrical signals into mechanical stimulation (e.g., vibration or movement) or electrical stimulation that the user can perceive through tactile or kinesthetic senses. According to one embodiment, the haptic module 179 may include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

The camera module 180 can capture still images and moving images. According to one embodiment, the camera module 180 may include one or more lenses, image sensors, image signal processors, or flashes.

The power management module 188 can manage power supplied to the electronic device 101. According to one embodiment, the power management module 188 may be implemented as at least a part of, for example, a power management integrated circuit (PMIC).

The battery 189 may supply power to at least one component of the electronic device 101. According to one embodiment, the battery 189 may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

Communication module 190 is configured to provide a direct (e.g., wired) communication channel or wireless communication channel between electronic device 101 and an external electronic device (e.g., electronic device 102, electronic device 104, or server 108). It can support establishment and communication through established communication channels. Communication module 190 operates independently of processor 120 (e.g., an application processor) and may include one or more communication processors that support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module 190 is a wireless communication module 192 (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module 194 (e.g., : LAN (local area network) communication module, or power line communication module) may be included. Among these communication modules, the corresponding communication module is a first network 198 (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network 199 (e.g., legacy It may communicate with an external electronic device 104 through a telecommunication network such as a cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., LAN or WAN). These various types of communication modules may be integrated into one component (e.g., a single chip) or may be implemented as a plurality of separate components (e.g., multiple chips). The wireless communication module 192 uses subscriber information (e.g., International Mobile Subscriber Identifier (IMSI)) stored in the subscriber identification module 196 within a communication network such as the first network 198 or the second network 199. The electronic device 101 can be confirmed or authenticated.

The wireless communication module 192 may support 5G networks after 4G networks and next-generation communication technologies, for example, NR access technology (new radio access technology). NR access technology provides high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and access to multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low latency). -latency communications)) can be supported. The wireless communication module 192 may support high frequency bands (eg, mmWave bands), for example, to achieve high data rates. The wireless communication module 192 uses various technologies to secure performance in high frequency bands, for example, beamforming, massive array multiple-input and multiple-output (MIMO), and full-dimensional multiplexing. It can support technologies such as input/output (FD-MIMO: full dimensional MIMO), array antenna, analog beam-forming, or large scale antenna. The wireless communication module 192 may support various requirements specified in the electronic device 101, an external electronic device (e.g., electronic device 104), or a network system (e.g., second network 199). According to one embodiment, the wireless communication module 192 supports Peak data rate (e.g., 20 Gbps or more) for realizing eMBB, loss coverage (e.g., 164 dB or less) for realizing mmTC, or U-plane latency (e.g., 164 dB or less) for realizing URLLC. Example: Downlink (DL) and uplink (UL) each of 0.5 ms or less, or round trip 1 ms or less) can be supported.

The antenna module 197 may transmit or receive signals or power to or from the outside (eg, an external electronic device). According to one embodiment, the antenna module 197 may include an antenna including a radiator made of a conductor or a conductive pattern formed on a substrate (eg, PCB). According to one embodiment, the antenna module 197 may include a plurality of antennas (eg, an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network such as the first network 198 or the second network 199 is connected to the plurality of antennas by, for example, the communication module 190. can be selected Signals or power may be transmitted or received between the communication module 190 and an external electronic device through the at least one selected antenna. According to some embodiments, in addition to the radiator, other components (eg, radio frequency integrated circuit (RFIC)) may be additionally formed as part of the antenna module 197.

According to various embodiments, the antenna module 197 may form a mmWave antenna module. According to one embodiment, a mmWave antenna module includes: a printed circuit board, an RFIC disposed on or adjacent to a first side (e.g., bottom side) of the printed circuit board and capable of supporting a designated high frequency band (e.g., mmWave band); And a plurality of antennas (e.g., array antennas) disposed on or adjacent to the second side (e.g., top or side) of the printed circuit board and capable of transmitting or receiving signals in the designated high frequency band. can do.

At least some of the components are connected to each other through a communication method between peripheral devices (e.g., bus, general purpose input and output (GPIO), serial peripheral interface (SPI), or mobile industry processor interface (MIPI)) and signal ( (e.g. commands or data) can be exchanged with each other.

According to one embodiment, commands or data may be transmitted or received between the electronic device 101 and the external electronic device 104 through the server 108 connected to the second network 199. Each of the external electronic devices 102 or 104 may be of the same or different type as the electronic device 101. According to one embodiment, all or part of the operations performed in the electronic device 101 may be executed in one or more of the external electronic devices 102, 104, or 108. For example, when the electronic device 101 needs to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device 101 may perform the function or service instead of executing the function or service on its own. Alternatively, or additionally, one or more external electronic devices may be requested to perform at least part of the function or service. One or more external electronic devices that have received the request may execute at least part of the requested function or service, or an additional function or service related to the request, and transmit the result of the execution to the electronic device 101. The electronic device 101 may process the result as is or additionally and provide it as at least part of a response to the request. For this purpose, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology can be used. The electronic device 101 may provide an ultra-low latency service using, for example, distributed computing or mobile edge computing. In another embodiment, the external electronic device 104 may include an Internet of Things (IoT) device. Server 108 may be an intelligent server using machine learning and/or neural networks. According to one embodiment, the external electronic device 104 or server 108 may be included in the second network 199. The electronic device 101 may be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

The server 108 is connected to the electronic device 101 and can provide services to the connected electronic device 101. In addition, the server 108 may perform a membership registration process, store and manage various information of users who have registered as members, and provide various purchase and payment functions related to the service. Additionally, the server 108 may share execution data of service applications running on each of the plurality of electronic devices 101 in real time so that services can be shared between users. This server 108 may have the same hardware configuration as a typical web server or WAP server. However, in terms of software, it may be implemented through any language such as C, C++, Java, Visual Basic, and Visual C, and may include program modules that perform various functions. In addition, the server 108 is generally connected to an unspecified number of clients and/or other servers through an open computer network such as the Internet, and receives work performance requests from clients or other servers and derives and provides work results in response. It refers to a computer system and the computer software (server program) installed for it. In addition, in addition to the server program described above, the server 108 includes a series of application programs running on the server 108 and, in some cases, various databases (DBs) built internally or externally, hereinafter " It should be understood as a broad concept including “DB”). Accordingly, the server 108 classifies membership registration information and various information and data about games, stores them in a DB, and manages this DB, which may be implemented inside or outside the server 108. In addition, the server 108 uses a variety of server programs provided depending on the operating system such as DOS, Windows, Linux, UNIX, and Macintosh on general server hardware. Representative examples include Website, IIS (Internet Information Server) used in a Windows environment, and CERN, NCSA, and APPACH used in a Unix environment. Additionally, the server 108 may be linked with an authentication system and payment system for user authentication of the service or payment for purchases related to the service.

The first network 198 and the second network 199 are a connection structure that allows information exchange between each node, such as terminals and servers, or a network connecting the server 108 and the electronic devices 101 and 104. It means (Network). The first network 198 and the second network 199 are the Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), and 3G. , 4G, LTE, 5G, Wi-Fi, etc., but are not limited to these. The first network 198 and the second network 199 may be closed, such as a LAN or WAN, but are preferably open, such as the Internet. The Internet uses the TCP/IP protocol and several services existing at its upper layer, namely HTTP (HyperText Transfer Protocol), Telnet, FTP (File Transfer Protocol), DNS (Domain Name System), SMTP (Simple Mail Transfer Protocol), and SNMP ( It refers to a worldwide open computer first network (198) and second network (199) structure that provides Simple Network Management Protocol (NFS), Network File Service (NFS), and Network Information Service (NIS).

A database can have a general data structure implemented in the storage space (hard disk or memory) of a computer system using a database management program (DBMS). A database may have a data storage format that allows for free search (extraction), deletion, editing, addition, etc. of data. Databases are relational database management systems (RDBMS) such as Oracle, Infomix, Sybase, and DB2, or object-oriented database management such as Gemston, Orion, and O2. It can be implemented according to the purpose of an embodiment of the present disclosure using a system (OODBMS) and an XML native database such as Excelon, Tamino, and Sekaiju, and has its own functions. To achieve this, you can have appropriate fields or elements.

Figure 2 is a diagram showing the configuration of a program according to one embodiment.

Figure 2 is a block diagram 200 illustrating program 140 according to various embodiments. According to one embodiment, the program 140 includes an operating system 142, middleware 144, or an application 146 executable on the operating system 142 for controlling one or more resources of the electronic device 101. It can be included. Operating system 142 may include, for example, AndroidTM, iOSTM, WindowsTM, SymbianTM, TizenTM, or BadaTM. At least some of the programs 140 are preloaded into the electronic device 101, for example, at the time of manufacture, or are stored in an external electronic device (e.g., the electronic device 102 or 104, or a server) when used by a user. It can be downloaded or updated from 108)). All or part of the program 140 may include a neural network.

The operating system 142 may control management (eg, allocation or retrieval) of one or more system resources (eg, process, memory, or power) of the electronic device 101 . Operating system 142 may additionally or alternatively operate on other hardware devices of electronic device 101, such as input module 150, audio output module 155, display module 160, and audio module 170. , sensor module 176, interface 177, haptic module 179, camera module 180, power management module 188, battery 189, communication module 190, subscriber identification module 196, or It may include one or more driver programs for driving the antenna module 197.

The middleware 144 may provide various functions to the application 146 so that functions or information provided from one or more resources of the electronic device 101 can be used by the application 146. The middleware 144 includes, for example, an application manager 201, a window manager 203, a multimedia manager 205, a resource manager 207, a power manager 209, a database manager 211, and a package manager 213. ), connectivity manager (215), notification manager (217), location manager (219), graphics manager (221), security manager (223), call manager (225), or voice recognition manager (227). You can.

The application manager 201 may, for example, manage the life cycle of the application 146. The window manager 203 may, for example, manage one or more GUI resources used on the screen. For example, the multimedia manager 205 identifies one or more formats required for playing media files, and encodes or decodes the corresponding media file using a codec suitable for the selected format. It can be done. The resource manager 207 may, for example, manage the source code of the application 146 or the memory space of the memory 130. The power manager 209 manages, for example, the capacity, temperature, or power of the battery 189, and may use this information to determine or provide related information necessary for the operation of the electronic device 101. . According to one embodiment, the power manager 209 may interface with a basic input/output system (BIOS) (not shown) of the electronic device 101.

Database manager 211 may create, search, or change a database to be used by application 146, for example. The package manager 213 may, for example, manage the installation or update of applications distributed in the form of package files. The connectivity manager 215 may manage, for example, a wireless connection or direct connection between the electronic device 101 and an external electronic device. For example, the notification manager 217 may provide a function for notifying the user of the occurrence of a designated event (eg, an incoming call, message, or alarm). The location manager 219 may, for example, manage location information of the electronic device 101. The graphics manager 221 may, for example, manage one or more graphic effects to be provided to the user or a user interface related thereto.

Security manager 223 may provide, for example, system security or user authentication. The telephony manager 225 may manage, for example, a voice call function or a video call function provided by the electronic device 101. For example, the voice recognition manager 227 transmits the user's voice data to the server 108 and provides a command corresponding to a function to be performed in the electronic device 101 based at least in part on the voice data, Alternatively, text data converted based at least in part on the voice data may be received from the server 108. According to one embodiment, the middleware 244 may dynamically delete some existing components or add new components. According to one embodiment, at least a portion of the middleware 144 may be included as part of the operating system 142 or may be implemented as separate software different from the operating system 142.

The application 146 includes, for example, home 251, dialer 253, SMS/MMS (255), instant message (IM) 257, browser 259, camera 261, and alarm 263. , Contacts (265), Voice Recognition (267), Email (269), Calendar (271), Media Player (273), Album (275), Watch (277), Health (279) (such as exercise amount or blood sugar) It may include applications that measure biometric information) or environmental information 281 (e.g., measure atmospheric pressure, humidity, or temperature information). According to one embodiment, the application 146 may further include an information exchange application (not shown) that can support information exchange between the electronic device 101 and an external electronic device. The information exchange application may include, for example, a notification relay application configured to deliver designated information (e.g., calls, messages, or alarms) to an external electronic device, or a device management application configured to manage the external electronic device. there is. The notification relay application, for example, transmits notification information corresponding to a specified event (e.g., mail reception) generated in another application (e.g., email application 269) of the electronic device 101 to an external electronic device. You can. Additionally or alternatively, the notification relay application may receive notification information from an external electronic device and provide it to the user of the electronic device 101.

The device management application, for example, controls the power (e.g., turn-on or turn-off) of an external electronic device or some component thereof (e.g., a display module or camera module of the external electronic device) that communicates with the electronic device 101. ) or functions (such as brightness, resolution, or focus). A device management application may additionally or alternatively support installation, deletion, or update of applications running on external electronic devices.

Throughout this specification, neural network, neural network, and network function may be used with the same meaning. A neural network may consist of a set of interconnected computational units, which may generally be referred to as “nodes.” These “nodes” may also be referred to as “neurons.” A neural network is composed of at least two or more nodes. Nodes (or neurons) that make up neural networks may be interconnected by one or more “links.”

Within a neural network, two or more nodes connected through a link can relatively form a relationship as an input node and an output node. The concepts of input node and output node are relative, and any node in an output node relationship with one node may be in an input node relationship with another node, and vice versa. As described above, input node to output node relationships can be created around links. One or more output nodes can be connected to one input node through a link, and vice versa.

In a relationship between an input node and an output node connected through one link, the value of the output node may be determined based on data input to the input node. Here, nodes connecting the input node and the output node may have weights. Weights may be variable and may be varied by a user or algorithm in order for the neural network to perform a desired function. For example, when one or more input nodes are connected to one output node by respective links, the output node is set to the values input to the input nodes connected to the output node and the links corresponding to each input node. The output node value can be determined based on the weight.

As described above, in a neural network, two or more nodes are interconnected through one or more links to form an input node and output node relationship within the neural network. The characteristics of the neural network may be determined according to the number of nodes and links in the neural network, the correlation between the nodes and links, and the value of the weight assigned to each link. For example, if there are two neural networks with the same number of nodes and links and different weight values between the links, the two neural networks may be recognized as different from each other.

In addition, memory includes ROM, RAM, non-volatile memory, volatile memory, hard disk drive (HDD), solid state drive (SSD), USB memory, flash memory card, and various portable and portable storage devices corresponding thereto. It includes media (e.g., SD (Secure Digital) memory cards, microSD memory cards, ISO 7816 standard storage devices, etc.), but is not limited thereto and may include all types of storage devices that store data. Memory may be referred to as a storage device.

Figure 3 is a block diagram showing an electronic device for infant learning according to an embodiment.

Referring to FIG. 3 , the electronic device 300 for infant learning may include a database 310, a touch display 320, a processor 330, and a memory 340.

The database 310 can store word images for letters used in English and Unicode data corresponding to the letter images. The database 310 can store letter images showing the shape and form of each letter. Additionally, Unicode data corresponding to each letter image can be stored. Unicode is an industry standard established by the Unicode Consortium designed to consistently express and handle all characters around the world on computers. The Unicode standard includes the ISO 10646 character set, character encoding, character information database, and algorithms for manipulating characters.

The touch display 320 may be a liquid crystal display (LCD) panel, an organic light emitting diode (OLED) panel, or the like. The touch display 320 may also include a touch screen panel (TSP) including touch electrodes for detecting touches on the display panel. In one embodiment, the touch display 320 may be an in-cell type in which a display panel and a touch panel are integrated into one piece. However, this is illustrative, and embodiments of the present invention are not limited thereto. The touch display 320 can electrically recognize contact with a finger, pen, etc., generate an electrical signal, and transmit it to a processor to be described later.

The processor 330 may control other components of the electronic device 300 for infant learning connected to the processor 330 and may perform various data processing or calculations. In addition, the processor 330 corresponds to the target character image input through the touch display 320 and converted into an electrical signal using a text detection model and a text recognition model. You can create a string that says The processor 330 may have the same or similar structure as the processor 120 of FIG. 1.

The memory 340 may store various data used by components of the electronic device 300 for infant learning. The data may include, for example, image data to be learned and word data to be learned for infant learning. Memory 340 may include volatile memory or non-volatile memory.

Next, with reference to FIGS. 5 to 9 , the process of children learning English words using the electronic device 300 for children learning will be described. In the following, a method of showing picture fairy tale content to a child through the electronic device 300 for learning, previewing the learning target word and images corresponding to the learning target word, and checking whether the learning target word is remembered will be explained as an example. do. In order to elicit children's interest, learning target words can be provided to infants through picture fairy tale content with a plot along with images corresponding to the learning target words. In other words, the technical idea regarding optical character recognition of the present invention may be included as part of the method of operating an early childhood education application.

Figure 4 is an example of the standard form and handwriting of the alphabet in various fonts.

Referring to FIG. 4, the letter image 401 is a standard form of the first alphabet of the first font. The first font is an arbitrary font among various fonts, and the first alphabet is one of arbitrary English alphabets, which is the letter A in FIG. 4.

The letter image group 410 is a group of handwriting data of the first alphabet of the second font. The letter image group 410 includes learning data 411 and learning data 412. Learning data 411 and learning data 412 are handwriting data.

The letter image group 420 is a group of handwriting data of the first alphabet of the first font. The letter image group 420 includes training data 421. Learning data 421 is handwriting data.

This is not a problem if there is ample learning data for handwriting for each font, but if learning data for handwriting of specific characters for a specific font is insufficient, it may be advantageous to use learning data for handwriting of specific characters for other fonts. there is. The electronic device can first determine whether cross-use of learning data is possible based on the similarity of handwriting in different fonts for a specific character.

Figure 5 is a flowchart showing an infant learning process according to an embodiment. Figure 6 is a diagram showing a first display screen displayed on a touch display. 7 and 8 are diagrams showing a second display screen displayed on a touch display. Figure 9 is a diagram showing a third display screen displayed on a touch display.

Referring to FIGS. 5 and 7 , first, a learning target image is output to the learning target image area 322_1 of the first display screen 322 (S100). The learning target image may be previously stored in the memory 340. The processor 330 may control the learning target image stored in the memory 340 to be output to the learning target image area 322_1 of the touch display 320.

Figure 6 exemplarily shows a playback screen of picture fairy tale content. The learning target word and the learning target image corresponding to the learning target word may be output in advance through the first display screen 321, as shown in FIG. 6. In other words, through picture fairy tale content, the learning target word and the learning target image corresponding to the learning target word can be output in advance so that the child can remember them.

For example, referring to FIG. 6, in order to teach a child the word 'Apple', the word 'Apple' and an image of 'Apple' can be output in advance. In addition, a song related to 'Apple' (for example, the song 'My face like an apple') is played and played, or a fairy tale animation using 'Apple' as the main object (for example, a fairy tale 'Snow White') is played. ), it is possible to provide picture fairy tale content so that children watching it can recognize 'Apple' in various ways.

Afterwards, a learning confirmation screen can be displayed as shown in FIG. 7 to check whether the child who watched the picture fairy tale content remembers the word 'Apple'. Referring to FIG. 7, the 'Apple' image corresponding to the learning target word 'Apple' may be displayed in the learning target image area 322_1 of the second display screen 322, and the learning target word description area 322_3. Appropriate hints related to picture fairy tale content can be displayed to help children think of 'Apple'.

The infant can see this and input the correct word into the user input area 322_2 of the second display screen 322 through the touch display 320, as shown in FIG. 8. That is, the target character image (image_text) is input into the user input area 322_2 (S120).

The processor 330 uses a text detection model to generate a text area image and coordinate data from the target text image (image_text) (S130).

The processor 330 uses a text recognition model to recognize a character string corresponding to the target text image in the text area image (S140). A method of recognizing and outputting a character string corresponding to the target character image will be described in detail later.

The processor 330 determines whether the recognized string matches the correct word of the learning target word (S150).

In S150, if the string matches the correct word, the processor 330 outputs the correct answer screen through the touch display 320 (S170) and displays the learning target image on the third display screen 323 shown in FIG. 9. Save it in <my room> (S180). The learning target image can be implemented in the form of an item that can decorate <my room>. In other words, it is possible to encourage children's motivation to learn by providing learning target images as a reward for learning target words.

In S150, if the character string does not match the correct word, the processor 330 outputs a correction screen on the touch display 320 that specifies the character that does not match the correct word and displays a correction guide (S160). The method of outputting the correction screen will be described later.

Next, a method for recognizing characters will be described with reference to FIGS. 10 to 12.

FIG. 10 is an enlarged view of the user input area of FIG. 8.

Referring to FIG. 10, the character area detection model may include a feature extraction layer. The feature extraction layer may receive a target character image (image_text) and generate a plurality of feature maps based on the target character image (image_text).

The feature map may be smaller than the size of the target text image (image_text). In one embodiment, the feature map may be 1/16 the size of the target text image (image_text). The feature map may be rectangular. In other words, the feature extraction layer can receive a target character image (image_text) as input and output 16 feature maps.

The feature extraction layer can generate feature scores, axis-aligned bounding box (AABB), and rotation angle for each feature map. The feature score may be a score that numerically indicates whether the target character image (image_text) is included in each feature map. AABB may be data that predicts the area box of the character area image. The rotation angle may represent the rotation angle of AABB. The feature extraction layer can output coordinate data of the character area image based on AABB and rotation angle.

That is, the feature extraction layer determines whether a letter exists in each of the plurality of feature maps, assigns a feature score to each of the plurality of feature maps, and creates a plurality of character regions based on the coordinate data and feature scores of each of the plurality of feature maps. Images (image_1, image_2) can be output.

FIG. 11 is a flowchart for explaining S140 of FIG. 5.

Referring to FIG. 11, first, the character area image (image_1) is divided into a plurality of zones, for example, first to fourth zones (quad_1 to quad_4) (S141). In one embodiment, the character area image (image_1) may have a square shape including a monosyllable character image included in the target character image (image_text).

Next, considering each weight, the match rate between the letter area image (image_1) included in one or more of the first to fourth regions (quad_1 to quad_4) and any one of the letter images stored in the database 310 Calculate (S143).

One or more letters included in the character area image (image_1) are recognized based on the calculated match rate (S144).

FIG. 12 is an exemplary diagram illustrating feature areas of each character to determine a plurality of areas used for character recognition.

The electronic device can determine the matching rate of each area for each standard alphabet in the alphabet handwriting divided into a plurality of areas and recognize letters. For example, electronic devices have a, b, c, d ?? The standard form for each alphabet can be stored in the database. When the user's handwriting is input, the electronic device can compare the handwriting with the standard form for each alphabet in each of a plurality of predetermined zones through learning. The electronic device can calculate the match rate for each zone. The electronic device can determine the alphabet corresponding to the input handwriting based on the matching rate of each zone.

The plurality of zones may be predetermined by an electronic device. Electronic devices can extract feature regions for each alphabet using a character feature region extraction model, a type of neural network. For example, the electronic device may determine a first feature area and a second feature area as feature areas that distinguish alphabet a from alphabet b.

The electronic device can compare a plurality of feature areas and set boundaries between feature areas. The electronic device can determine multiple zones by overlapping boundary lines. For example, the electronic device may determine a first boundary line from the first feature area and the second feature area. The boundary between feature areas may be displayed as a solid line the closer it is to the feature area, and may be displayed as a dotted line as it moves away from the feature area. As you move away from the feature area, the spacing between dotted lines can become increasingly distant.

To this end, the electronic device can learn alphabet data of handwriting in various fonts.

This is not a problem if there is ample learning data for handwriting for each font, but if learning data for handwriting of specific characters for a specific font is insufficient, it may be advantageous to use learning data for handwriting of specific characters for other fonts. there is. The electronic device can first determine whether cross-use of learning data is possible based on the similarity of handwriting in different fonts for a specific character.

When learning data is input, the electronic device can compare the learning data with a standard form for each alphabet of a specific font. Here, a specific font may be a font that lacks learning data. The electronic device can apply multiple comparison areas for each alphabet. For example, for alphabet A, five comparison areas may be applied. For example, in the case of the alphabet A, five comparison areas can be applied: long line segments on the left and right, two points where each long line segment meets the horizontal line, and the upper area where the two long lines bend.

According to one embodiment, the electronic device may obtain a difference value by comparing the standard type and learning data for the alphabet of a specific font for each comparison area. The difference value can be calculated through criteria defined for each comparison area. For example, in alphabet A, the difference between the left and right long line segments can be calculated based on the relative length of the line segments, the slope of the line segments, and the width between the line segments.

According to another embodiment, the electronic device may output a plurality of difference values using a difference value extraction model, which is a type of pre-trained neural network. The difference value extraction model can configure vector elements for each of the plurality of comparison areas defined for each alphabet. For example, in the case of alphabet A, each element of an output vector having a 5-dimensional vector may represent a difference value. The difference value extraction model can be trained in advance through a large amount of learning data to increase the accuracy of character recognition.

According to one embodiment, the electronic device may calculate a feature score for learning data of handwriting of the first alphabet in a first font for which there is insufficient learning data. Learning data of handwriting of the first alphabet in the first font for which there is insufficient learning data may be referred to as the first group. The electronic device may calculate a feature score for the learning data of the handwriting of the first alphabet in the second font with abundant learning data. The learning data of the handwriting of the first alphabet in the second font, which is rich in learning data, may be referred to as the second group.

The electronic device may calculate the difference between the feature score for the first font and the feature score for the second font. The electronic device can determine whether the calculated result meets the conditions. If the condition is satisfied, the electronic device may use learning data for the first alphabet of the second font as learning data for the first alphabet of the first font.

For example, the electronic device calculates the feature score for the first alphabet of each font through Equation 2, and provides learning data for a group with many samples based on the feature score for the first alphabet of each font. You can decide whether to use it for small groups or not.

The weight reflected in the feature score may be determined according to the grade grouped based on the weight of the feature that represents the difference from the standard type for the first alphabet. For example, in the case of the alphabet A, among the five comparison areas of the long line segments on the left and right, the two points where each long line segment meets the horizontal line, and the upper area where the two long lines bend, there are more differences from the standard type for the alphabet A. Grades for each comparison area can be determined in order of greatest contribution. For example, when grade i = 1, 2, 3, 4, 5, weights of 1, 2, 4, 8, 16 may be applied.

[Equation 2]

In Equation 2, the feature score for the first group, which is a small sample group, is It can be defined as: Here, m is the number of sample data (handwriting data) for each grade, j is the identification number of the sample data, and xi,j is the difference value calculated by comparing the standard form of the alphabet and the training data to the comparison area corresponding to the grade. . n is the number of grades, for example, n = 5 (i is the grade identification number, 5=A, 4=B ?? 1 =E), is the set of sample data of the ith class, means the standardization of the value of each sample data as the maximum value of the set of sample data of the i-th grade, and cannot exceed the maximum of 1. represents the feature score for each grade as the average value of the standardized values of the sample data. In, n differs by 1 for each grade, Since cannot exceed a maximum of 1, the higher the feature score of a high grade, the larger the value becomes. in other words, means the weight for the grade.

In Equation 2, for the second group, which is a group with many samples, for example, the grades can be classified into 5, and when grade i = 1, 2, 3, 4, 5, 1, 2, 4, 8 , a weight of 16 may be applied.

The feature score for the second group is It can be defined as: q is the number of sample data (handwriting data) for each grade, l is the identification number of the sample data, and xk,l are the difference values calculated by comparing the standard form of the alphabet and the learning data to the comparison area corresponding to the grade. p is the number of grades, and p = 5 (k is the grade identification number, 5 = A, 4 = B ?? 1 = E). is the set of sample data of the kth class, is the maximum value of the set of sample data of the kth grade, which is a value that normalizes the value of each sample data, and cannot exceed a maximum of 1. represents the feature score for each grade as the average value of the standardized values of the sample data. In, p differs by 1 for each grade, Since cannot exceed a maximum of 1, the higher the feature score of a high grade, the larger the value becomes. in other words, means the weight for the grade.

In equation 2, means the absolute value of the difference between the feature score for the first group and the feature score for the second group. The functions of y and z are as follows.

Depending on the value of y, z is distributed between 0.5 and 1.5. The electronic device can calculate z for the feature score between the group with a small sample and the group with a large sample. When z is a certain value, for example, 1.0 or less, the electronic device determines that the handwriting learning data is similar to each other and can use the learning data interchangeably.

The embodiments described above may be implemented with hardware components, software components, and/or a combination of hardware components and software components. For example, the devices, methods, and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, and a field programmable gate (FPGA). It may be implemented using one or more general-purpose or special-purpose computers, such as an array, programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. A processing device may execute an operating system (OS) and one or more software applications that run on the operating system. Additionally, a processing device may access, store, manipulate, process, and generate data in response to the execution of software. For ease of understanding, a single processing device may be described as being used; however, those skilled in the art will understand that a processing device includes multiple processing elements and/or multiple types of processing elements. It can be seen that it may include. For example, a processing device may include a plurality of processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are possible.

Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing unit to operate as desired, or may be processed independently or collectively. You can command the device. Software and/or data may be used on any type of machine, component, physical device, virtual equipment, computer storage medium or device to be interpreted by or to provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on the medium may be specially designed and configured for the embodiment or may be known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -Includes optical media (magneto-optical media) and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include machine language code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Although the embodiments have been described with limited drawings as described above, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques are performed in a different order than the described method, and/or components of the described system, structure, device, circuit, etc. are combined or combined in a different form than the described method, or other components are used. Alternatively, appropriate results may be achieved even if substituted or substituted by an equivalent.

Therefore, other implementations, other embodiments, and equivalents of the claims also fall within the scope of the claims described below.

Claims (7)

In the optical character recognition method of an electronic device for infant learning,
The electronic device is,
touch display;
A database storing a plurality of letter images and Unicode data corresponding to each of the letter images,
An operation of receiving a target character image through the touch display;
An operation of generating a text area image and coordinate data of the text area image from the target text image using a text detection model;
An operation of recognizing a character string corresponding to the target text image in the text area image using a text recognition model,
The letter recognition model is,
Dividing the text area image into a plurality of regions,
Assigning different weights to each of the plurality of zones,
Considering each weight, calculating a matching rate between the letter area image included in one or more of the plurality of regions and any one of the plurality of letter images,
Based on the match rate, recognize one or more letters included in the letter area image,
Outputting a string corresponding to the target letter image based on the recognized letter and the coordinate data,
By the electronic device,
An operation of determining one or more feature regions for each character using a character feature region extraction model;
An operation of determining a boundary line between the determined one or more feature areas for each character; and
An operation of determining one or more zones based on the determined boundary lines
It further includes,
By the electronic device,
Further comprising training the character feature area extraction model using learning data of handwriting in various fonts,
If the number of learning data for the first character of the second font is less than the threshold and the number of learning data for the first character of the first font is greater than or equal to the threshold,
An operation of determining, by the electronic device, whether to train the character feature area extraction model for the first character of the second font using learning data of the first character of the first font using Equation 2. It further includes,
[Equation 2]


In Equation 2 above, m is the number of sample data (handwriting data) for each grade, j is the identification number of the sample data, and xi, j are calculated by comparing the standard form of the alphabet and the learning data to the comparison area corresponding to the grade. This is the difference value. n is the number of grades, is the set of sample data of the ith grade, q is the number of sample data (handwriting data) of each grade, l is the identification number of the sample data, is the difference value calculated by comparing , p is the number of grades, is a set of sample data of the kth rank,
Optical character recognition method for electronic devices for early childhood learning.
According to paragraph 1,
The character area detection model is,
Includes a feature extraction layer,
The feature extraction layer is,
Receive the target character image as input,
Based on the target letter image, a plurality of feature maps are generated,
Determine whether a letter exists in each of the plurality of feature maps and assign a feature score to each of the plurality of feature maps,
Outputting the letter area image based on the coordinate data of each of the plurality of feature maps and the feature score,
Optical character recognition method for electronic devices for early childhood learning. According to paragraph 1,
The letter area image is a rectangular shape containing the letter image of the letter included in the target letter image.
Optical character recognition method for electronic devices for early childhood learning. According to paragraph 1,
The character recognition model includes an input layer, one or more hidden layers, and an output layer,
A plurality of learning data consisting of the letter area image, the match rate, and the correct letter image included in one or more of the plurality of regions are input to the input layer of the letter recognition model and pass through the one or more hidden layers and the output layer. outputs an output vector, and the output vector is input to a loss function layer connected to the output layer, and the loss function layer calculates a loss value using a loss function that compares the output vector with the correct vector for each training data. Outputs, and the parameters of the letter recognition model are learned in the direction of decreasing the loss value,
[Equation]

The loss function follows the above equation,
In the above equation, N is the number of the plurality of learning data, n is a natural number identifying the learning data, k is a natural number identifying the value of the nth learning data, nk is the kth value of the nth learning data, t refers to the correct word image, y refers to the output vector, and E refers to the loss value.
Optical character recognition method for electronic devices for early childhood learning. delete delete delete

Images