KR101982848B1 - Vision aids apparatus for the vulnerable group of sight comprising a removable wearable device and a control device - Google Patents

Abstract

Disclosed is a sight assisting apparatus for a vulnerable social group of sight including a removable wearable device and a control device. According to an embodiment, the sight assisting apparatus includes: a wearable device which is formed in such a form that can be worn on the body of a user who belongs to the vulnerable social group of sight, photographs images from the front surface of the user, and outputs auditory information generated through the control device; the control device which recognizes visual information including at least one of an object, a character and a depth through an artificial intelligence-based mechanical learning from photographed image data, and converts the recognized visual information into the auditory information; and a connection part which connects the wearable device and the control device. The sight assisting apparatus according to an embodiment removes inconvenience felt by the vulnerable social group of sight in daily lives and enables the vulnerable social group of sight to be well adopted to the environment.

Description

[0001] The present invention relates to a vision assist apparatus for a vision-impaired layer comprising a removable wearable device and a control apparatus,

The present invention relates to vision aiding technology for vulnerable groups.

In recent years, 30-40 units have been on the rise, including presbyopia, prime, nearsightedness, and astigmatism due to the use of smartphones, even if they are not visually impaired. In addition, it is said to be a vulnerable group, including primitive, nearsighted, municipal, aged and visually impaired. These vulnerable groups have a lot of discomfort in everyday life. For example, they are reluctant to go out because of the dangers of striking obstacles or other pedestrians while walking. Even if you want to take a bus, it is difficult to read the bus number, so I hesitate to take a bus. Sometimes you can not read a book because it is hard to read the text of the book. Therefore, a technique capable of solving such a visual inconvenience is required.

Korean Patent No. 10-0405636 (Nov. 2003) Korean Registered Patent No. 10-1715472 (Mar.

According to one embodiment, a vision aiding device for a visually impaired layer comprising a detachable wearable device and a control device is proposed.

The wearable device has a wearable device that is wearable on the wearer's body, which is a vulnerable layer of sight, and that captures an image on the front of the user and outputs auditory information generated through the control device. A controller for recognizing the visual information including at least one of the object, the character and the depth through artificial intelligence-based machine learning and converting the recognized visual information into auditory information, and a connection unit for connecting the wearable device and the controller.

A wearable device includes a body, a photographing unit mounted on the body for photographing an actual image along a viewpoint of the user, an output unit installed on the body for transmitting auditory information to the user, Section.

The output may include a bone conduction speaker that transmits auditory information through the bone, not the eardrum. There are a number of bone conduction speakers, at least one of which can be used as a support. The output unit includes a body having a leg structure at least partially inserted into the body and the other body protruding to the outside, and a bone conduction speaker formed in the shape of a diaphragm at one end of the body, and the bone conduction speaker may have a predetermined tension.

The coupling portion may be in the form of a tube having an eyeglass frame of the user's glasses or a receiving hole for receiving the eyeglass legs. The coupling portion may be made of a material having elasticity. The coupling portion may include a magnet for being detached from the spectacles.

The wearable device further includes a power button for turning on and off the power, and a volume control button for adjusting the volume size. The power button and the volume control button include a boss structure or a vibration imparting method, .

The control device may include a processor for recognizing the visual information through artificial intelligence-based machine learning from the photographed image and converting the recognized visual information into auditory information, and a battery for supplying power to the wearable device. The control device may be included in the user terminal. The connection may be wired.

According to one embodiment, it is possible to eliminate the inconvenience experienced by the sight-impaired people in daily life and adapt to the environment. For example, it makes it easier for people with low vision to know things around, things in depth, and text. This cognition is based on vision, recognizing objects, depths, and texts in place of those with weak vision, and voicing them, thus helping vulnerable groups.

Further, by providing a wearable type vision assist device, it is easy to wear, hold, and use it for a vision-impaired layer. It is possible to operate with a simple gesture rather than a device that operates with a complicated operation method, thereby improving convenience of use. The price is low to moderate, and it reduces the economic burden of the sight-poor. It enhances object recognition rate through machine learning based visual information recognition and enables users to use it easily through augmented reality based gesture pointing.

Visual aids can be used in various scenarios using techniques such as augmented reality based gesture recognition, machine learning based object recognition, image processing based depth recognition, and machine learning based character recognition. For example, there are scenarios in which menus are recognized in menus when ordering food at a restaurant / restaurant, scenarios in which books or magazines are read in a living room / library, scenarios in which danger is avoided through distance notice to surrounding objects, Scenarios for informing the traffic light status, scenarios for guiding bus numbers at bus stops, scenarios for informing the subway entrance, and the like.

By disassembling the wearable device and the control device, placing the camera in the wearable device and placing the battery in the control device, the weight of the wearable device can be lightened to enhance the fit. Wearable devices are worn on the spectacles or spectacles of the spectacles, so that the user's sense of rejection can be minimized. In this case, detachment of the wearable device is easy. Furthermore, since the output unit for outputting the auditory information is implemented by the bone conduction speaker, the user's fatigue can be reduced. At this time, the bone conduction speaker maintains proper tension. The control device can be implemented as a user terminal such as a smart phone possessed by a user and can be conveniently used by the user when interfacing with the wearable device.

FIG. 1 is a block diagram of an intelligent vision assistant system for a vision-impaired layer according to an exemplary embodiment of the present invention.
2 is a functional block diagram of a vision assist device according to an embodiment of the present invention.
FIG. 3 is a block diagram of the processor of FIG. 2 according to an embodiment of the present invention;
4 is a configuration diagram of a remote management apparatus according to an embodiment of the present invention;
FIG. 5 is a hardware block diagram of a vision assist device according to an embodiment of the present invention,
6 is a hardware configuration diagram of a vision assist device according to another embodiment of the present invention,
7 to 9 are external views of a wearable device of a vision assist device according to an embodiment of the present invention,
10 and 11 are reference views showing a state in which a user wears the wearable device of the vision assist device,
12 is a conceptual diagram of an intelligent service system for a vulnerable group of eyes according to an embodiment of the present invention;
FIG. 13 is a reference diagram illustrating a scenario combination example of application of an intelligent service system for a vulnerable layer of sight according to an exemplary embodiment of the present invention;
FIG. 14 is a conceptual diagram illustrating a functional concept of the vision assist device according to an embodiment of the present invention;
FIG. 15 is a diagram illustrating scenarios for ordering food at a restaurant / restaurant using the vision assist device of the present invention,
16 illustrates scenarios for reading a book or a magazine in a living room / study room using the vision assist device of the present invention,
FIG. 17 is a view illustrating a scenario in which the risk is prevented through the use of the sight assist device of the present invention,
FIG. 18 is a diagram illustrating a scenario of a traffic light state recognition at an intersection using the vision assist device of the present invention,
FIG. 19 is a view illustrating a scenario in which a bus number is guided at a bus stop using the vision assist device of the present invention,
20 is a scenario for confirming a subway entrance using the vision assist device of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The advantages and features of the present invention and the manner of achieving them will become apparent with reference to the embodiments described in detail below with reference to the accompanying drawings. The present invention may, however, be embodied in many different forms and should not be construed as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the invention to those skilled in the art. Is provided to fully convey the scope of the invention to those skilled in the art, and the invention is only defined by the scope of the claims. Like reference numerals refer to like elements throughout the specification.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS In the following description of the present invention, detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear. , Which may vary depending on the intention or custom of the user, the operator, and the like. Therefore, the definition should be based on the contents throughout this specification.

Each block of the accompanying block diagrams and combinations of steps of the flowcharts may be performed by computer program instructions (execution engines), which may be stored in a general-purpose computer, special purpose computer, or other processor of a programmable data processing apparatus The instructions that are executed through the processor of the computer or other programmable data processing equipment will generate means for performing the functions described in each block or flowchart of the block diagram.

These computer program instructions may also be stored in a computer usable or computer readable memory capable of directing a computer or other programmable data processing apparatus to implement the functionality in a particular manner so that the computer usable or computer readable memory It is also possible for the instructions stored in the block diagram to produce an article of manufacture containing instruction means for performing the functions described in each block or flowchart of the flowchart.

And computer program instructions may be loaded onto a computer or other programmable data processing equipment so that a series of operating steps may be performed on a computer or other programmable data processing equipment to create a computer- It is also possible that the instructions that perform the data processing equipment provide the steps for executing the functions described in each block of the block diagram and at each step of the flowchart.

Also, each block or step may represent a portion of a module, segment, or code that includes one or more executable instructions for executing the specified logical functions, and in some alternative embodiments, It should be noted that functions may occur out of order. For example, two successive blocks or steps may actually be performed substantially concurrently, and it is also possible that the blocks or steps are performed in the reverse order of the function as needed.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, the following embodiments of the present invention may be modified into various other forms, and the scope of the present invention is not limited to the embodiments described below. The embodiments of the present invention are provided to enable those skilled in the art to more fully understand the present invention.

FIG. 1 is a block diagram of an intelligent vision assist system for a vision-impaired layer according to an exemplary embodiment of the present invention.

Referring to FIG. 1, the intelligent vision assist system includes a vision assistant 2, and may further include a remote management device 1 and a network 3.

Intelligent vision assistance systems utilize artificial intelligence (AI) to support vulnerable groups of vision. Vision is a layer that is different from normal people with eyesight. It is a group of people who have early vision, primordial vision, myopia, astigmatism due to the use of smartphone, and the existing primitive, near vision, municipal, Concept. The purpose of the intelligent vision assist system is to provide vision aids (2) at an affordable price to overcome the inconvenience of the visually impaired and to live independently.

The vision assistant 2 is a device that can be carried and carried by a user with a sight weakness. Hereinafter, the 'user' and the 'vulnerable layer' may be used in combination for the detailed description. The vision aids device 2 may be in the form of a wearable device that is wearable to the vulnerable layer of sight or that includes it. A wearable device is an accessory that is easy to wear and carry. Examples of the wearable device include a shape which is detached from the eyeglass frame or the eyeglass frame of the glasses worn by the user. A photographing unit is mounted on the front side, and an image can be photographed through the photographing unit. Such a wearable device can be detached also to existing glasses, and it is made to be easy to wear by minimizing the weight. The vision assistant device 2 may be a stand-alone type (see FIG. 5) in which the detachable wearable device and the control device are combined, and may be an interlocking type in which the wearable device and the smartphone are interlocked (see FIG. 6).

The vision assistant 2 recognizes the visual information from the image input to the camera through the AI based machine learning and processes the recognized visual information into auditory information so that the visually impaired layer can hear the visual information . The visual information is an object, a character, and a depth. The auditory information is a voice signal, a warning sound, and the like. This makes it easier for people with visual impairments to recognize things and adapt them to the environment.

The intelligent vision assist system according to one embodiment can be used even when the eyesight is not bad, the eyes are less fatigued, the focus is blurred due to presbyopia, or the time for focusing the eye muscles is slow. For example, it provides an automatic book reading mode and the like, thereby providing ease of use and customer scalability. For example, the visually impaired person A can use the bus as the sight assistant device 2, which can be worn on the glasses, recognizes and informs the bus number in front. It became easy to find a bus to take at a bus stop that several buses stopped. As another example, Mr. B, a low-vision class, fell in the fun of reading books on his commute. This is because the vision assistant (2) worn on the glasses automatically recognizes and reads the contents of the book. Recently, my eyesight suddenly deteriorated and I could not read the book without a magnifying glass. Braille was also unfamiliar.

The core of the vision aid (2) is the object recognition in front. Through artificial intelligence-based machine learning, people are distinguished from animals and objects, and they are notified by voice. Due to the nature of machine learning, the more users there are, the higher the accuracy. The vision assistant 2 also calculates and reports the distance to the front object. Furthermore, warn against bumping. It also extracts character images from camera images and reads them out. Until now, it was a way of transferring images to an acquaintance or an agent and then oral explanation.

When the user specifies an object desired by the user, the vision assistant device 2 can provide the vision assistant service to the object of interest. As a device input method used to specify a desired object, an augmented reality (AR) -based pointer can be used so that the user can immediately recognize the object pointed by the finger. For example, if only the weakest layer of sight is detected, it becomes a pointer in augmented reality. When you point your finger at the menu plate at a restaurant, the camera recognizes and reads the letter. Books and magazines can also be read on their own. If you express your letter 'V' with your finger, you will recognize it automatically with books and magazines. When the palm is extended, it switches to the depth estimation mode so as not to hit the surrounding objects. Image Distortion Processing You can calculate the exact depth with image processing.

Various technologies such as artificial intelligence (AI) technology, augmented reality (AR), and text to speech (TTS) technology are applied to the vision assistant 2. Remote control is also possible. Artificial intelligence technology includes techniques for automatically recognizing visual information such as objects, characters, and distances from images through machine learning. Augmented reality technology is a technology that combines a virtual world with a real world, such as recognizing an object image of a user and notifying the user of the object even if the object is located away from the user. Here, a technique of recognizing a user's gesture as an augmented reality pointer and recognizing a position pointed by the recognized augmented reality pointer is included. The voice conversion technology includes a technique of converting recognized time information, for example, a character image into text information, converting it into audible information that the user can hear, and outputting voice. The remote control includes a technique in which the vision assist device 2 is supported by a remote control device 1 connected via the network 3 and the remote management device 1 monitors the vision assist device 2. [

The remote management apparatus (1) manages the vision assistant (2). In addition, a real-time pre-service (B / S) and a post-service (A / S) are provided so that the user can maintain a normal state when using the sight assistant device 2. If the vision assist device 2 fails or malfunctions in the field, the risk of the user who is a weak vision layer increases. Therefore, the state of the vision assist device 2 is analyzed in advance based on a big data, and an abnormal symptom is grasped in advance. In the event of an anomaly, the risk can be eliminated in advance by notifying the user or dispatching the maintenance personnel to pre-process them. In the event of a problem in the field, maintenance of the device for the vision assist device (2) is also possible via the network (3). Furthermore, the user can also provide a service for storing screen captures and moving pictures on the spot when the user agrees. At this time, monitoring can be provided to support the service.

The network 3 is a wired / wireless network capable of transmitting and receiving data between the remote management apparatus 1 and the vision assistant apparatus 2. The network 3 may use various types of communication networks such as Wi-Fi, WLAN (Wireless LAN), Wibro, Wimax, HSDPA (High Speed Downlink Packet Access), Bluetooth, DSL, LTE, PCS, (Ethernet), xDSL (ADSL, VDSL), Hybrid Fiber Coax (HFC), Fiber to the Curb (FTTC), and the like. And a wired communication method such as FTTH (Fiber To The Home) may be used. The network is not limited to the communication method described above, and may include any other known or later-developed communication methods in addition to the communication methods described above.

2 is a functional block diagram of a vision assist device according to an embodiment of the present invention.

1 and 2, the vision assist apparatus 2 includes a photographing unit 20, an input unit 21, an output unit 22, a processor 23, a battery 24, a client agent 25, a communication unit 26, and a memory 27. [

The photographing section 20 photographs from the front face of the user, which is a layer with weak eyesight. The photographing unit 20 may be, for example, a camera. To recognize the depth of an object, the camera may be a ToF camera. The photographing unit 20 may be disposed so as to face the inside or the outside of the vision assist device 2 to photograph the front of the user. For example, the photographing unit 20 can be mounted on a wearable device that can be worn by a user on the glasses or glasses legs of the glasses, and can take an actual image according to the user's viewpoint.

The input unit 21 receives a user command and provides it to the processor 23. The input unit 21 may include a user interface for inputting. For example, a power button, a volume control button, and the like. The input interface is focused on vulnerable layers, such as embossing the buttons in consideration of the vulnerable layer of sight, or implementing button functions in the sense of the hand, such as giving vibration. The input unit 21 can receive a threshold value as an error criterion and a notification type at the time of error prediction in order to receive the advance service information according to the error prediction.

The output unit 22 outputs information processed by the processor 23 and information received through the communication unit 26 to the outside. The output unit 22 outputs the audible information converted by the processor 23 by voice. The output format may be a voice signal, and the voice signal may include a warning message, a warning sound, and output through a speaker. The speaker may be a bone conduction speaker. This speaker transmits sound waves to the skull through vibration. The main advantage of the bone conduction speaker is that it frees the ear. It reduces damage and fatigue of the eardrum and allows you to hear additional external sounds. Bone conduction speakers can be used in public transport such as libraries, subways, and public places. Optionally, output 22 may include a display. In this case, the photographed image can be displayed through the display. Further, the gesture pointer of the user can be combined and displayed on the photographed image. For display purposes, the vision aids 2 may be implemented in the form of glasses, such as smart glass.

The user can read the food menu designated by the user as the voice signal through the output unit 22 and automatically read the article such as a book or a magazine. If there is a danger in the front, it can be notified by voice or warning sound. For example, "Be careful because there is a risk within 3m ahead", "It is an unexpected situation, please stop." , Or to transmit a warning sound such as " beep ". In the event of a hazard, the danger alert signal is immediately transmitted to proactively respond to the hazardous situation.

The processor 23 recognizes visual information such as an object, a character, and a depth through an artificial intelligence (AI) -based machine learning from the photographed image and converts the recognized visual information into auditory information. If the recognized time information is in a dangerous situation, a danger warning signal is generated. Machine learning is a method of extracting features from photographed image data and distinguishing objects from image data using extracted features. The object type can be a person or an object. In the case of a person, it is possible to recognize whether or not the person is an acquaintance. If the object is a traffic light, whether it is a book or a door, whether it is a subway entrance or a bus. At this time, the outline of the object can be recognized. The processor 23 can recognize characters, which include words, sentences, symbols, numbers, and the like. Machine learning is performed in the vision assistant device 2, and may be performed through collaboration with the remote management device 1 when the processing capability of the vision assistant device 2 is low as necessary.

The processor 23 recognizes the object using the machine learning data on the input image data. For example, the processor 23 compares the image data with a previously stored shape pattern to detect a signal lamp present in the front, compares the detected color pattern with the color pattern of the object stored in the memory 27, And judges the signal by object pattern and color. It also recognizes numeric images in traffic lights. At this time, if the determined traffic light is green light and the numerical image is 20, guidance information such as " green light is 20 seconds remaining " is generated and output through the output unit 22. The detailed configuration of the processor 23 will be described later with reference to Fig.

The battery 24 supplies power for driving the vision assist device 2. When the vision assist device 2 is separated into a wearable device and a control device, the battery 24 may be located in the control device. The weight of the wearable device to be worn by the user can be lightened. When the wearable device is interlocked with a user terminal such as a smart phone, the battery 24 may use the battery of the user terminal. The battery 24 may be replaceable, rechargeable, or both. For example, a rechargeable battery can be used as a standby power source if all of the replaceable batteries are used, with the power being supplied primarily through the replaceable battery.

The client agent 25 acquires the device state information of the vision assistant device 2 and processes the pre-service information received from the remote management device 1. [ The device state information may include device-specific device information and sensing information measured through the device. The device information is device information that can be obtained from the vision assist device 2 itself, for example, a battery remaining amount, a CPU, a memory, a heating value, a device temperature, and a shot image. The photographed image is photographed using the photographing section 20 of the visual aid device 2. [ The sensing information is information obtained through a sensor, and is information obtained through various sensors such as a GPS sensor, an acceleration sensor, an air pressure sensor, and a geomagnetic sensor. The sensor may or may not be mounted to the vision aids 2. The above-described device state information is not limited to this, and can be used without limitation as long as it is information that can indicate the operation state of the vision assist device 2. [ State information analysis can use Big Data Analysis to quickly process large amounts of data. The dictionary service information is information for preventing an error that may occur according to the state of the device in advance and includes at least one of an error prediction history, a warning message for blocking an error occurrence, and error transferring action information.

The communication unit 26 receives information from outside or transmits information to the outside. The communication unit 26 can use the network 3. [ And the outside may be the remote management apparatus 1. [ The communication unit 26 according to one embodiment is connected to the network 3 and communicates with the remote management device 1 and transmits the device status information of the vision assist device 2 to the remote management device 1, 1 according to the state of the apparatus.

The memory 27 stores information necessary for performing operations in the vision assist device 2 and information generated according to the performance of the operation. For example, in the memory 27, a machine-learned data for a pattern such as a shape pattern, a color pattern, and a signal pattern of an object are stored in advance in order to recognize the object in the photographed image .

3 is a block diagram of the processor of FIG. 2 according to an embodiment of the present invention.

1 to 3, the processor 23 of the visual aid apparatus 2 includes a first image processing unit 231, a second image processing unit 232, a signal processing unit 233, a gesture sensing unit 234, A device control unit 235 and a remote control processing unit 236. [

The first image processing unit 231 recognizes an object image or character image through machine learning from photographed image data. At this time, a commonly used character recognition algorithm such as an optical character recognition method can be additionally used. The second image processor 232 recognizes the depth through image analysis of the photographed image data. For example, depth is recognized based on distortion of image data. Since the image taken by the camera is distorted as it goes to the edge, the distance between the object and the user is calculated according to the extent of the distortion. The ToF camera has a disadvantage that the disturbance occurs, and the ToF camera and the distortion-based image processing technique can be used in parallel.

The image data received by the first image processing unit 231 and the second image processing unit 232 may be a noise-eliminated image. For example, it is possible to remove unnecessary top, bottom, right and left marginal regions from the image data and to process and receive image data corresponding to a region of interest (ROI).

The signal processing unit 233 converts the recognized object image, character image or depth information into character information through the respective image processing units 231 and 232, converts the converted character information into auditory information, and provides the converted information to the output unit 22. For example, if the recognized object is " green light of traffic light " and " 30 ", it converts it into character information " green light is 30 seconds remaining ", and converts the converted character information into auditory information.

The gesture sensing unit 234 senses the user gesture from the photographed image. The gesture sensing unit 234 can recognize an object image including a user's hand shape and an operation through artificial intelligence (AI) based machine learning from the image data. The device control unit 235 recognizes the user gesture sensed through the gesture sensing unit 234 as an augmented reality-based gesture, determines an operation mode corresponding to the augmented reality-based gesture, matches the augmented reality- . The remote control processing unit 236 requests the remote management apparatus 1 to perform remote control and remotely shares the capture screen of the sight assist system in accordance with the remote control of the remote management apparatus 1, Lt; / RTI >

4 is a configuration diagram of a remote management apparatus according to an embodiment of the present invention.

1 and 4, the remote management apparatus 1 includes an authentication management unit 10, a monitoring unit 11, a network connection unit 12, a remote control unit 13, a data processing unit 14, a client management unit 15 ), A protocol processing unit 16, and a data analysis unit 17.

The authentication management unit 10 verifies the validity of the user information of the requested vision assist device 2. [ And authenticates who is the subject of the request received by the remote management apparatus 2 as needed. The monitoring unit 11 monitors the capture screen through the vision assistant 2. At this time, a monitoring result is provided to an administrator terminal or a function for assisting an administrator operation is provided. The remote control unit 13 receives the remote control request from the vision assist apparatus 2 and transmits a remote control command to the sight assistant apparatus 2 to perform remote engineering.

The data processing unit 14 carries out a machine learning on the actual image received from the vision assist device 2 through the network connection unit 12 and then generates the final result according to the performance of the vision assistant 2, (12). At this time, the network connection unit 12 provides the final result to the vision assist apparatus 2. [ The machine learning-based visual information recognition of the remote management apparatus 1 can be selectively performed according to the apparatus processing capability of the vision assist apparatus 2. [ For example, when the device processing capability of the vision assist device 2 is low, a request to the remote management device 1 can be followed by machine learning in the remote management device 1. [

The client management unit 15 monitors the device state information of the vision assist device 2 to predict an error in advance and generates advance service information for processing an error before an error occurs. The error prediction may use a method of comparing the received device state information with a preset threshold value. For example, a battery state is classified into a normal state and a dangerous state, and the battery state is classified into a battery residual value threshold. It is determined whether the remaining battery level, which is the received device status information, is included in the steady state threshold value and the critical state threshold value, thereby predicting an error. If it corresponds to the critical state threshold value, it can be judged as error prediction.

The advance service information includes at least one of error prediction history, warning message for blocking an error occurrence, and error transferring action information. The error prediction details indicate the error prediction state, and include the device name or identifier for identifying the vision assist device 2 in which the error is predicted, the device basic information, the device position information, the time information about the error prediction, can do. A warning message is a signal to warn of an error. A warning message can be output through voice, text, and alarm sound. Error handling information includes methods for troubleshooting errors, contact points, link information, and so on. Examples of methods for troubleshooting errors include replacing a problematic part, charging, and the like.

The network connection unit 12 transmits and receives information to and from the vision assist device 2 and an administrator terminal. When an error is predicted through the client management unit 15, the network connection unit 12 according to the embodiment notifies the manager of the warning message through the administrator terminal before an error occurs. For example, the result can be sent to the administrator so that the situation can be responded to immediately. The notification method can utilize all existing communication means such as E-mail, SMS, and ARS. The network connection unit 12 may be configured to receive the device status information of the vision assist device 2 while communicating with the vision assist device 2 and to receive the device status information generated by the client management unit 15 in accordance with the device status of the vision assist device 2. [ And transmits the dictionary service information to the sight assistant device 2. [ The advance service information includes at least one of error prediction history, warning message for blocking an error occurrence, and error transferring action information.

The protocol processor 16 is a software module that receives and parses the normal signal of the vision assist device 2 and implements a communication protocol for processing the signal.

The data analysis unit 17 acquires and analyzes the big data and provides the analysis information to the client management unit 15 for the advance service. The data analysis unit 17 according to an embodiment generates and manages statistical information from the analysis result of the data analysis unit 17 or the prediction result of the client management unit 15. The administrator can easily grasp the error prediction result through statistical information.

The data analyzer 17 can flexibly set standard data based on the environment of the vision assistant 2 by collecting the device status information for a predetermined period and extracting valid standard data from the collected device status information. Since the amount of state information collected during a predetermined period is large, a large data analysis can be performed so that a large amount of collected data can be processed quickly. For example, it collects state information according to weather information and weather, and extracts valid standard data from the collected state information.

For example, if the battery remaining amount among the status information of the vision assist device 2 is in the range of the preset threshold value, for example, 10% It is predicted to be a replacement step and a warning message is generated and notified to the sight assistant device 2 before the sight assistant device 2 is turned off due to battery consumption.

5 is a hardware block diagram of a vision assist device according to an embodiment of the present invention.

Referring to Figs. 2, 3 and 5, the vision assist device 2 includes a detachable wearable device 6 and a control device 7-1. The wearable device 6 may include the photographing unit 20, the input unit 21, and the output unit 22 shown in Fig. The control device 7-1 may include the processor 23, the battery 24, the client agent 25, the communication unit 26 and the memory 27 in Fig. The control device 7-1 is coupled to the wearable device 6 via the connection part 8. [

The reason why the wearable device 6 and the control device 7-1 are separated is that the battery 24 enters the control device 7-1. When the wearable device 6 and the control device 7-1 are integrated, the feeling of fit is reduced due to the weight of the battery 24, which makes it difficult to use the wearable device 6 for a long time. At this time, the connection portion 8 may be wired. Of course, wireless communication methods such as Bluetooth and Wi-Fi are also possible. The battery 24 is mounted on the control device 7-1 and the wearable device 6 is connected to the wearable device 6 by wire, since the battery 24 must be mounted even when the wearable device 6 is linked to the wearable device 6 by the wireless communication method. . If necessary, wireless communication such as Bluetooth can be applied as an option.

The control device 7-1 operates based on the existing OS such as Linux, Windows, Android, and iOS so that the machine learning library has sufficient performance to operate. The control device 7-1 must be able to grasp the state of the device through a communication function such as Wi-Fi / LTE in case of emergency, and the client device 25 is installed in the control device 7-1. The control device 7-1 first considers operating systems such as Linux, Windows, Android, and iOS so that the general-purpose user terminal, for example, a smart phone can be substituted.

Since the wearable device 6 needs to be mounted separately on the user's body, a frame that can be fixed to the head is required. The wearable device 6 should be configured to be easy to attach and detach to a general eyeglass leg, and at the same time an appropriate tension must be maintained to utilize the function of the bone conduction speaker. The wearable device 6 is attached to the wearer's feet and the actual image is photographed through the photographing unit attached to the front side of the wearable device 6 so that the user can obtain the actual image at a point of view of the user, Can be eliminated.

6 is a hardware block diagram of a visual acuity assisting apparatus according to another embodiment of the present invention.

Referring to Fig. 6, the vision assistant 2 can replace the control device 7-1 of Fig. 5 with a user terminal 7-2. The function of the user terminal 7-2 is similar to that of the control device 7-1, and a detailed description thereof will be omitted.

7 to 9 are external views of a wearable device of a vision assist device according to an embodiment of the present invention.

7 to 9, the wearable device 6 includes a body 60, a camera 62, a bone conduction speaker 64, a coupling portion 66, a power button 68, and a volume control button 69, . The camera 62 corresponds to the photographing unit 20 in Fig. 2, the bone conduction speaker 64 corresponds to the output unit 22 in Fig. 2, the power button 68 and the volume control button 69 correspond to the 2 < / RTI >

The camera 62 is installed in the body 60 to photograph an actual image along a user's viewpoint. The photographed image is used to recognize the machine learning based vision information in the photographed image and further to recognize the user gesture. The camera 62 may be attached to the front side of the body 60, as shown in Figs. In this case, an actual image can be photographed at a point of view of the user.

The bone conduction speaker 64 is installed in the body 60 to output auditory information. The bone conduction speaker 64 is a method for transmitting auditory information through the bone, not the eardrum. The bone conduction speaker 64 transmits auditory information to the user in close contact with the user's face or around the ear. As shown in FIGS. 7 to 9, the bone conduction speaker 64 may be formed in the shape of a diaphragm at one end of the body of the leg structure. The body is a leg structure in which at least a part is inserted into the body (60) and the rest is projected to the outside. In Figs. 7 to 9, the leg structure is divided into two. The diaphragm may be of a round shape. So that the diaphragm has a predetermined tension. The predetermined tension is such a tension that it is not unreasonable when the human body is worn. The number of bone conduction speakers 64 may be plural. In Figs. 7 to 9, two are shown. In the case of a plurality, at least one can be used as a support.

The engaging portion 66 has a structure for wearing the body 60 on the user's body. The engaging portion 66 may be provided on a side surface of the body 60, and may be provided on a side surface different from the camera 62. The engaging portion 66 may be in the form of a tube having an eyeglass frame of a spectacle worn by a user or a receiving hole for accommodating the legs of a spectacle. The engaging portion 66 may be made of a material having elasticity. For example, it may be a synthetic resin or a rubber material. As another example, the engaging portion 66 may include a magnet for desorption to the spectacles.

The power button 68 and the volume control button 69 may be structured considering that the user is a vulnerable layer of sight. For example, the power button 68 and the volume control button 69 provide a sense of hand to the user, such as a bracing structure, a vibrating structure.

10 and 11 are reference views showing a state in which a user wears the wearable device of the vision assist device.

Referring to FIGS. 10 and 11, a user's eye leg is fitted into a receiving hole of a tube-shaped coupling portion 66, and a camera 62 of the front side captures an image. And the bone conduction speaker 64 is positioned around the ear so that the user can hear the sound output through the bone conduction speaker 64.

12 is a conceptual diagram of an intelligent service system for a visually impaired layer according to an embodiment of the present invention.

Referring to FIG. 12, the vision assist device 2 converts the visual information displayed on the front face of the user 4 into auditory information, and assists the visual acuity of the user 4 by outputting the visual information. The user 4 can be extended to individuals, corporations, and public institutions as a vulnerable layer of sight.

The vision assistant device 2 may be separated into a wearable device 6 and a control device 7-1. The wearable device 6 may be in the form of being detached from the glasses leg of the user's glasses as shown in Fig. The connection unit 8 connects the wearable device 6 and the control device 7-1. The connection unit 8 can connect the wearable device 6 and the control device 7-1 by wire as shown in FIG. It is also possible to use a wireless connection or a wireless connection in parallel. The photographing unit may be mounted on the wearable device 6 and the battery may be mounted on the control device 7-1.

As another example, the wearable device 6 may be in a form associated with a user terminal (e.g., smartphone) 7-2. The connection unit 8 connects the wearable device 6 and the user terminal 7-2. The connection unit 8 can connect the wearable device 6 and the user terminal 7-2 by wire as shown in FIG. It is also possible to use a wireless connection or a wireless connection in parallel. The photographing unit may be mounted on the wearable device 6 and the battery of the user terminal 7-2 may be used.

The vision assistant device 2 grasps a user's intention through a user gesture, for example, a palm or fist clenching operation, and provides a vision assistant service according to the intent that is grasped. For example, if the user 4 shows a gesture showing the palm of his hand, he or she estimates the distance between the user and the surrounding risk factors and provides a service to guide the user. The augmented reality technique is applied in that the user 4 recognizes a distant object through a gesture.

The vision assistant 2 distinguishes objects from the photographed images through artificial intelligence (AI) -based machine learning and informs them by voice. The vision assistant 2 also calculates and communicates the distance to the front object. When the object is recognized, a voice conversion technique for converting it into character information and converting it back to a voice signal is applied. The voice signal can be transmitted to the user 4 via the bone conduction speaker.

The remote management apparatus 1 collects log data from the vision assist apparatus 2 and performs monitoring to grasp the state of the apparatus. At this time, when the action is required according to the monitoring result, the action is taken, and the vision assist device 2 can be remotely controlled. Monitoring and remote control can be done in real time. The remote management apparatus 1 can collect user images, moving images, and the like, and store them in a database.

The remote management apparatus 1 provides an advance service to take action before an error occurs according to an error prediction. At this time, the manager 5 can be instructed to remove the error state by monitoring and warning the error state. The manager (5) may be a center person or a local engineer. The person in charge of the center is the person who has the authority for general affairs. The local engineer is a local engineer who can take action on site in case of failure. The remote management apparatus 1 monitors the defective parts of the vision assist device 2, the defective unit, the exhaustion of the battery, the occurrence of an emergency, and instructs the manager 5 to take measures. And warns the manager (5) when an emergency occurs in the vision assistant (2). If a trouble occurs in the device itself or the parts of the vision assist device 2, the administrator 5 is instructed to replace the problematic device or parts in advance.

As another example of the measure, the device 2 is directly controlled by transmitting a device control command to the vision assist device 2. For example, if the battery remaining amount of the vision assistant device 2 is less than a predetermined value, a control command to replace the battery is sent so that the user of the vision assistant device 2 can replace the battery.

The manager 5 confirms the information provided through the remote management apparatus 1 as a person who uses the remote management apparatus 1. At this time, the manager 5 recognizes the error of the vision assist device 2 in advance while monitoring the error prediction result through various manager terminals, for example, a computer, a desk top, a tablet PC, a smart phone or the like. When the administrator 5 recognizes an error in advance, the remote assistant can perform remote diagnosis and repair on the vision assist device 2.

The manager 5 can receive a warning message according to the error prediction for the vision assist device 2 from the remote management apparatus 1 in a predetermined manner. The predetermined method may be a call, a text message (MMS), an email (E-mail), or the like. When the manager 5 is notified of the warning message, the manager 5 can immediately take an action on the vision assist device 2 in which an error is predicted, or can check the vision assist device 2 at a predetermined time, for example, have.

As an example of the dictionary service, a user of the vision assistant device 2 may connect with the remote management device 1 via a Wi-Fi connection with the sight assistant device 2 at home, (2) to the remote management apparatus (1). Taking the remaining battery level as an example, the remote management apparatus 1 determines that the remaining battery level in the received device status information is normal if it is a predetermined threshold value, for example, 60% or more, and informs the user that the remaining battery level is normal. When the user enters the cafe and connects to the remote management apparatus 1 via the Wi-Fi connection, the remote management apparatus 1 determines that the remaining battery level in the received device status information is a predetermined threshold value, for example, 30% If it is below, please tell the user "Please change the battery." Or "Please charge the battery." And the like. In response to the warning signal, the user solves the battery problem by charging or charging the battery.

A threshold value can be set in advance for the advance service according to the error prediction. Then, the error can be predicted by comparing the preset threshold value with the device state information value received from the visual aid auxiliary device 2. The threshold value can be set by the user of the sight assistant device 2, and the remote management device 1 can preset it through the big data base analysis. As an example of the user setting, the user can set the remote management apparatus 1 to automatically notify the user when the remaining battery power reaches 30% or less.

The advance service of the remote management apparatus 1 can be performed at a predetermined cycle, for example, once every three minutes. Or when an event, for example, a battery needs to be replaced, occurs during monitoring, advance service can be performed.

FIG. 13 is a reference diagram showing an example of a combination of application scenarios of an intelligent service system for a vulnerable group of eyesight according to an embodiment of the present invention.

12 and 13, the vision assistant 2 recognizes the gesture of the user (610). The shape of the gesture can be an action shape, a stop shape, or a mixture of motion and stop. An example of an action type is a gesture that shakes the hand side to side, and an example of the stop type is a gesture with the hand held.

The vision assistant 2 recognizes the object in the photographed image through artificial intelligence (AI) based machine learning 620. Object recognition includes object recognition and contour recognition. Classification recognizes whether a person is a person or an object, or whether a person is a dog or a chair. People can be distinguished through outline recognition. Furthermore, fingerprint recognition can be implemented.

The vision assistant 2 recognizes the depth between the recognized object and the user (630). Depth perception can be achieved through a ToF camera. Or image processing of the photographed image. For example, depth is recognized based on distortion of image data. Since the image taken by the camera is distorted as it goes to the edge, the distance between the object and the user is calculated according to the extent of the distortion. The ToF camera has a disadvantage that the disturbance occurs, and the ToF camera and the distortion-based image processing technique can be used in parallel. The vision assistant 2 recognizes characters in the shot image through artificial intelligence (AI) based machine learning 640. Characters include words, sentences, numbers, symbols, and so on.

As described above, by using techniques such as augmented reality-based gesture recognition 610, machine learning based object recognition 620, image processing based depth recognition 630, and machine learning based character recognition 640, 2) can be used for various scenarios. For example, there are scenarios (see FIG. 15) for recognizing menus on menu plates when ordering food at restaurants / restaurants (see FIG. 15), scenarios for reading books or magazines (See FIG. 18), a scenario (see FIG. 19) for guiding the bus number at the bus stop (see FIG. 19), and a scenario for notifying the subway entrance See Fig. 20).

FIG. 14 is a conceptual diagram illustrating the functional concept of the vision assist device according to an embodiment of the present invention.

14, a user wears the wearable device 6 of the vision assistant device 2, for example, and takes a gesture 1400 for mounting the palm of the eyeglass on the eyeglass leg of the eyeglasses. Then, the palm-opening gesture 1400 is recognized as an augmented reality-based object pointer, and the operation mode corresponding thereto is started to recognize the visual information. Examples of visual information recognition include machine learning based object recognition (1410), distance recognition (1420), and character recognition (1430). When the visual information is recognized, the recognized visual information is converted into character information, and the converted character information is converted into voice and output. For example, as shown in Fig. 14, when a user recognizes objects (chairs, desks, etc.) through machine learning in a photographed image and converts them into sounds at a level that the user can immediately recognize, It is a desk. "

15 to 20 are views illustrating various scenarios that can be implemented using the vision assist device according to an embodiment of the present invention. 16 is a scenario for reading a text in a living room / study area, FIG. 17 is a risk prevention scenario for noticing a distance to nearby objects, FIG. 18 is a scenario for preventing a traffic light at an intersection FIG. 19 shows a bus number guidance scenario at a bus stop, and FIG. 20 shows a scenario for confirming a subway entrance.

Referring to Fig. 15, in order to order food at a restaurant / restaurant, a user looks at a menu plate and points to a menu called " vegetable gibbet " with one finger. The visual aids recognize the finger point based on the augmented reality and recognize the pointing position in the shot image. Then, a character image called 'vegetable kimbap 2000' at the recognized position is recognized by using machine learning, and the recognized character image is converted into speech and outputted. The user orders food after listening to it. Furthermore, if the user indicates another position with the finger after waiting for the augmented reality pointing, recognition of the directing position, recognition of the character image at the recognized position, conversion of the recognized character image into voice, and output process are repeated.

In such a method, a pointer recognition technique using an augmented reality technique, a technique of recognizing a character of a menu plate by applying artificial intelligence (AI) based machine learning, .

Referring to Figure 16, the user takes a V gesture toward the book for reading in the living room / study. Articles can be books, newspapers, magazines, and so on. The sight assistant recognizes the V gesture and recognizes the recognized V gesture as an action for reading the text and enters the text reading mode. At this time, the character image of book / magazine in the photographed image is sequentially recognized by using machine learning, and the recognized character image is converted into voice and outputted.

The user can read books / magazines while listening without having to continue pointing. In other words, if letters or numbers are frequently used in newspapers, magazines, etc., the continuous mode can be used and the continuous mode instructions can be read and processed. Shopping, and pharmacies to handle very small letters that are difficult to read on the product.

Such methods include a technique of recognizing characters of a book / magazine by applying a pointer recognition technique using an augmented reality technique, an AI based machine learning, a technique of converting a book / A technique of continuously recognizing a character and outputting it as a voice is used.

Referring to FIG. 17, in order to be aware of the danger from nearby objects, the user takes a palm gesture when approaching the door. The sight assistant recognizes the palm gesture, recognizes the depth of the recognized palm gesture so that it does not hit the surrounding objects, and recognizes it as an operation to warn it, and enters the depth estimation mode. At this time, a risk element, for example, a 'door' object is recognized in the photographed image, and the distance between the risk element and the user is calculated through image processing. For example, the distance between the risk factor and the user can be calculated according to the distortion degree of the photographed image. Subsequently, the vision assistant outputs a warning signal including the calculated distance by voice. For example, a warning message "Be careful because there is an obstacle ahead of you" is displayed.

Such a method can be classified into a pointer recognition technique using augmented reality technology, a technique of recognizing an object by applying an AI-based machine learning, a technique of estimating a depth through image distortion processing image processing, Transformation and output techniques are used.

Referring to Fig. 18, in order to grasp the traffic light condition at an intersection, the user indicates a traffic light across from the intersection. The visual aids recognize the finger point based on the augmented reality and recognize the pointing position in the shot image. Then, it recognizes the object image of the signal light, green, and 60 at the recognized position using machine learning, and converts the recognized object image into speech and outputs it. For example, a sound of "green light and 60 seconds remaining" is output. The user moves after listening.

In this method, a pointer recognition technique using augmented reality technology, a technique of recognizing an object of a traffic light by applying an AI-based machine learning, and a conversion and output technology of a signal after recognizing an object are used.

Referring to Fig. 19, in order to receive the bus number guidance at the bus stop, the user instructs the bus with four fingers. The vision assistant recognizes the instructions of the four fingers as a bus number guide, recognizes the numerical image of the bus and the bus using machine learning, and converts the recognized numerical image into speech and outputs it. For example, the voice output is "The bus is now number 5619". The user then listens to it and board the bus.

Referring to FIG. 20, in order to confirm the subway entrance, the user performs a double action of grasping the fist after instructing with four fingers. The sight assistant recognizes the action of gripping the punch after four fingers as a gesture for informing the subway entrance information, recognizes the character / color of the subway entrance using machine learning, and converts the recognized image into voice and outputs it . For example, "Blue line 1 is Jonggak station 2 exit."

In this method, a pointer recognition technique using an augmented reality technology, a technique of recognizing an object at a subway entrance by applying an AI-based machine learning, and a technique of converting and outputting a voice after recognizing an object at a subway entrance are used .

Hereinafter, the process of the vision assistant for performing the various scenarios of FIGS. 15 to 20 described above will be described in detail below.

15 to 20, the vision assisting method includes the steps of photographing an image on the front face of a user with a weak vision layer, detecting a predetermined user gesture on the photographed image, performing a predetermined operation on the detected predetermined user gesture Determining a predetermined operation mode corresponding to the recognized user gesture for the augmented reality based gesture pointer for the determined operation mode, recognizing the visual information through artificial intelligence based machine learning from the photographed image for each determined operation mode, Into audible information and outputting the audible information.

In the case of the food ordering scenario in the restaurant / restaurant of FIG. 15, in the step of determining the predetermined operation mode, the sight assistant device recognizes the sensed user gesture as a gesture pointer for information guidance and enters the information guidance mode, Recognizing a finger of the sensed user gesture as an augmented reality pointer in the photographed image, recognizing a character image at a position pointed by the augmented reality pointer in the photographed image, converting the sensed user gesture into auditory information, The character image at the position indicated by the augmented reality pointer can be converted into character information, and the converted character information can be converted into auditory information and output.

16, in the step of determining a predetermined operation mode, the vision assist device recognizes the sensed user gesture as a gesture pointer for performing a book reading operation, enters a writing reading mode, In the step of recognizing the visual information, the step of recognizing the character image in the text, converting the text image into auditory information and outputting the converted image, converts the character image recognized in the text into character information, converts the converted character information into auditory information Can be output. Here, the text reading mode is a continuous mode, and the vision assistant recognizes the character image in the text sequentially by machine learning without continuously pointing the user, and converts the recognized character image to speech in turn and outputs it .

In the case of the risk avoidance scenario through the distance notice to the surrounding object in FIG. 17, in the step of determining the predetermined operation mode, the vision assist device recognizes the detected user gesture as a gesture pointer for depth estimation, In the step of recognizing the visual information, the object image on the front face is recognized on the photographed image, the distance between the object and the user is recognized through image analysis, and the converted image is converted into auditory information, The distance information may be converted into character information, and the converted character information may be converted into auditory information and output.

18, in the step of determining a predetermined operation mode, the vision assist device recognizes the detected user gesture as a gesture pointer for guiding the traffic light, enters the traffic light guiding mode, Recognizes a finger of the detected user gesture as augmented reality pointer in the photographed image, recognizes the signal light state including the signal color color information and the remaining time information of the position pointed by the augmented reality pointer, converts it into auditory information In the outputting step, the recognized state of the traffic lights can be converted into character information, and the converted character information can be converted into auditory information and output.

In the case of the bus number guidance scenario in Fig. 19, in the step of determining the predetermined operation mode, the vision assist device recognizes the detected user gesture as a gesture pointer for bus number guidance, enters the bus number guidance mode, Recognizing the position indicated by the gesture pointer in the photographed image and recognizing the numerical image of the recognized position in the step of recognizing the visual information, converting the recognized numeric image into character information And convert the converted character information into auditory information and output it.

20, in the step of determining a predetermined operation mode, the vision assist device recognizes the detected user gesture as a gesture pointer for guiding the subway, enters the subway guide mode, and recognizes the time information Recognizes the position indicated by the gesture pointer in the photographed image, recognizes the color image and the character image at the recognized position, converts the recognized color image and the character image into the character information Converts the converted character information into auditory information, and outputs the converted information.

The embodiments of the present invention have been described above. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the disclosed embodiments should be considered in an illustrative rather than a restrictive sense. The scope of the present invention is defined by the appended claims rather than by the foregoing description, and all differences within the scope of equivalents thereof should be construed as being included in the present invention.

1: remote management device 2: vision assist device
3: Network 4: User
5: Manager 6: Wearable device
7-1: Control device 7-2: User terminal
10: authentication management unit 11: monitoring unit
12: network connection unit 13: remote control unit
14: data processor 15: client manager
16: protocol processing unit 17: data analysis unit
20: photographing section 21: input section
22: output unit 23: processor
24: Battery 25: Client Agent
26: communication unit 26: memory
60: Body 62: Camera
64: bone conduction speaker 66:
68: Power button 69: Volume control button
231: first image processing unit 232: second image processing unit
233: Signal processing unit 234: Gesture detection unit
235: Device control section 236: Remote control processing section

Claims (12)

A wearable device having a form that can be worn on a general eyeglass of a user, which is a vulnerable layer of sight which can be worn in a general eyeglass of a user who is a vulnerable layer of sight, and outputs auditory information generated by a control device;
A controller for recognizing visual information including at least one of an object, a character and a depth from artificial intelligence based machine learning from photographed image data and converting the recognized visual information into auditory information; And
A connection unit connecting the wearable device and the control device; / RTI >
The wearable device
A camera for capturing an image, an output unit for transmitting auditory information, and a coupling unit for attaching and detaching the eyeglass frame or the eyepiece of the user's general eyeglass to the body. delete The apparatus of claim 1, wherein the output section
And a bone conduction speaker for transmitting auditory information through the bone, not the eardrum. The method of claim 3,
Wherein the plurality of bone conduction speakers are used, and at least one of them is used as a support. The apparatus of claim 1, wherein the output section
At least a part of which is inserted into the body and the remainder is projected to the outside; And
A bone conduction speaker formed in the form of a diaphragm at one end of the body; / RTI >
Wherein the bone conduction speaker has a predetermined tension. The apparatus of claim 1,
Wherein the eyepiece is in the form of a tube having a spectacle frame for the user's glasses or a receiving hole for receiving the spectacle legs. The apparatus of claim 1,
Wherein the visual acuity assisting device is made of a material having elasticity. The apparatus of claim 1,
And a magnet for being detached from the spectacles. The wearable device of claim 1, wherein the wearable device
A power button for turning the power on and off; And
Volume control buttons to adjust volume; Further comprising:
Wherein the power button and the volume control button provide a sense of hand to the user, including a bracing or vibrating manner. The control device according to claim 1, wherein the control device
A processor for recognizing the visual information through artificial intelligence based machine learning from the photographed image and converting the recognized visual information into auditory information; And
A battery for supplying power to the wearable device;
Wherein the visual acuity assisting device comprises: The control device according to claim 1, wherein the control device
And is included in the user terminal. The connector according to claim 1,
Wherein the visual acuity assisting device is wired.

Images