Finger movement recognition device, finger spelling output method using the device, and glove-type device for operation in a virtual space

Abstract

The objective is to provide a finger movement recognition device and a finger spelling output method using that device, which enable smooth communication between visually impaired individuals and people in different spaces by accurately recognizing finger and hand movements such as opening, bending, and placing fingers, converting them into finger spelling, and then outputting the results via finger spelling to external devices such as PCs and smartphones in one of the following ways: voice, text, or Braille. [Solution] The present invention provides a finger motion recognition device 1 comprising a motion detection unit 2 that detects a predetermined number of types of human movements using sensors, and a finger spelling information output unit 3 that outputs finger spelling information corresponding to human movements to an external device UT, wherein the motion detection unit 2 is a glove-type device 2 that is worn on the five fingers of the hand and is equipped with sensors that detect the movement of each of the five fingers.

Description

Technical Field

[0004] , , , , ,

[0005] , , , , , ,

[0001] The present invention relates to a finger movement recognition device for recognizing finger movements, a finger character output method using the device, and a glove-type device for an operator to operate their own avatar (such as in a virtual space (metaverse, etc.)). In particular, it relates to a technology for detecting the shape and orientation of the hand and fingers using a glove-type device and recognizing them as finger characters.

Background Art

[0002] Conventionally, technologies for detecting finger movements and using them as input information are known. For example, Patent Document 1 discloses a technology for detecting finger movements using a glove-type device. Also, Patent Document 2 discloses a technology for recognizing a specific movement based on finger movements. <000001​​​​​​​​​​​​​​​​​​​​​​​​​​​​​Therefore, the object of the present invention is to provide a finger movement recognition device and a finger letter output method using the device that can convert finger and hand movements such as opening, bending, and placing fingers into finger letters by using the device, and also enable incidental operations such as confirming or canceling the converted finger letters, and further enable the output of the conversion results as voice via finger letters on external devices such as personal computers and smartphones, thereby facilitating smooth communication between visually impaired and sighted persons. [Means for solving the problem]

[0006] To achieve this objective, the present invention comprises a motion detection unit that detects a predetermined number of types of human movements using sensors, and a finger spelling information output unit that outputs finger spelling information corresponding to human movements to an external device, wherein the motion detection unit is a finger movement recognition device having a glove-type device that is worn on the five fingers of the hand and determines or cancels finger spelling by detecting the movement of the hand or the five fingers.

[0007] Furthermore, the sensor of the glove-type device may include a first to fifth group of sensors attached to the joint positions on the back of each of the five fingers, a sixth sensor attached to either the palm or the back of the hand, and a seventh sensor attached to the wrist, wherein the first to fifth group of sensors are bending sensors that detect the bending and straightening of the fingers, the sixth sensor is a sensor that detects the tilt of the hand, and the seventh sensor is a sensor that detects the direction of hand movement.

[0008] Furthermore, the motion detection unit further includes a leg-mounted device that determines or cancels finger spelling by detecting predetermined foot movements using an acceleration sensor attached to the foot, and the finger spelling information output unit outputs finger spelling information to an external device when foot movement is detected.

[0009] Furthermore, the invention of a finger spelling output method using a finger motion recognition device includes the steps of: detecting the movement of the five fingers as electrical signals using a sensor on a glove-type device while the glove-type device is worn on the hand; transmitting the detected electrical signals from the glove-type device to a finger spelling information output unit; selecting the corresponding finger spelling by analyzing the received electrical signals at the finger spelling information output unit; confirming or canceling the selected finger spelling using the glove-type device by outputting the selected finger spelling as voice from an external device; and transmitting the confirmed finger spelling to an external device by either wireless or wired communication means to output the finger spelling data as voice, text, Braille, or any other means.

[0010] Alternatively, the finger spelling output method includes the steps of: wearing a glove-type device on the hand and a leg-mounted device on the foot, detecting the movement of the five fingers as electrical signals using a sensor on the glove-type device; transmitting the detected electrical signals to a finger spelling information output unit; selecting the corresponding finger spelling by analyzing the received electrical signals at the finger spelling information output unit; outputting the selected finger spelling as voice from an external device, allowing the person to confirm or cancel the selected finger spelling using the leg-mounted device; and transmitting the determined corresponding finger spelling to an external device via either wireless or wired communication to output the finger spelling data as voice, text, Braille, or any other means.

[0011] Furthermore, regarding the invention of a glove-type device for operating an avatar of the operator appearing in a virtual space (metaverse, etc.) using the aforementioned glove-type device, the glove-type device for operating in a virtual space has a first to fifth sensor group attached to the joint position on the back of each of the five fingers, a sixth sensor attached to either the palm or the back of the hand, and a seventh sensor attached to the wrist, and the first to fifth sensor groups are bending sensors that sense the bending and straightening of the fingers, the sixth sensor is a sensor that senses the tilt of the hand, and the seventh sensor is a sensor that senses the direction of hand movement, thereby creating a glove-type device for operating in a virtual space that can detect the movement of all five fingers. [Effects of the Invention]

[0012] This invention allows for the detection of finger and hand movements, recognition of these movements as finger spelling, conversion of those movements into finger spelling, and the ability to perform ancillary operations such as confirming or canceling the converted finger spelling. Furthermore, by connecting to an external device, it is possible to output voice messages via finger spelling, thus facilitating smooth communication between visually impaired individuals and people in different locations. [Brief explanation of the drawing]

[0013] [Figure 1] This is a schematic diagram of a hand motion recognition device 1, which is one embodiment of the present invention. [Figure 2] This is a front view of the glove-type device 20 according to the first embodiment. [Figure 3] This is a rear view of the glove-type device 20 of the first embodiment. [Figure 4] This is a left side view of the glove-type device 20 according to the first embodiment. [Figure 5] This is a perspective view of the leg-mounted device 28 of the second embodiment. [Figure 6] This is a perspective view of the leg-mounted device 29 of the second embodiment. [Figure 7] This is a flowchart of the finger spelling output method according to the first embodiment of the present invention. [Modes for carrying out the invention]

[0014] Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. In the following, the same reference numerals will be used for similar elements in all drawings, and redundant explanations will be omitted. In addition, in the descriptions within the text, reference numerals previously mentioned will be used as necessary.

[0015] Figure 1 shows a schematic configuration diagram of a finger movement recognition device 1, which is one embodiment of the present invention. As shown in Figure 1, the finger movement recognition device 1 according to the present invention is broadly composed of a motion detection unit 2 for detecting the movements of a person (operator) and a finger spelling information output unit 3 for outputting information as finger spelling corresponding to the movements detected by the motion detection unit 2 to an external device UT, and these are connected to each other via wiring H1. Furthermore, the finger spelling information output unit 3 can be connected to an external device UT such as a smartphone, personal computer, or tablet terminal via wiring H2 and H3, and output as voice via finger spelling data. In addition, the finger spelling information output unit 3 can also output the information as finger spelling in braille by connecting to a braille output device such as a braille printer or braille display. The details of the motion detection unit 2 and the finger spelling information output unit 3 will be described below.

[0016] <Motion detection unit 2> The motion detection unit 2 is an element of the hand motion recognition device of the present invention that detects predetermined types of movements of a person's hands, feet, etc., using sensors. When the motion detection unit 2 is a glove-type device as shown in Figure 1, it detects the movement of the five fingers of a person's (operator's) hand and collects electrical signals sent from various sensors provided on the glove-type device as data.

[0017] The electrical signals collected as data are transmitted to the finger character information output unit described later via wireless or wired communication means. In addition to the glove-type device described above, the motion detection unit 2 can also use a leg-mounted device that detects predetermined leg motions using sensors attached to the thigh or ankle. Details of the glove-type device 20, which is the first embodiment of the motion detection unit, and the leg-mounted devices 28 and 29, which are the second embodiment, will be described below.

[0018] (Glove-type device 20) A front view of the glove-type device 20, which is the first embodiment of the motion detection unit, is shown in FIG. 2, a rear view of the glove-type device 20 is shown in FIG. 3, and a left side view of the glove-type device 20 is shown in FIG. 4. The glove-type device 20, which is the first embodiment of the motion detection unit, is a device equipped with a function of accurately detecting the motions of the five fingers of the hand by attaching various sensors to a glove body made of a material with durability such as fiber-reinforced plastic or Kevlar fiber. By the functions of the various sensors attached to these glove bodies, for example, the bending sensor measures the degree of finger bending, and the acceleration sensor captures the movement of the entire hand, so that fine motions such as finger bending and stretching and wrist movement can be accurately captured as information of electrical signals. Here, the bending sensor is, for example, a combination of two thin plate-shaped elastic bodies each having a strain gauge or the like formed on the surface. By detecting the dimensional change of the strain gauge generated on the front surface side and the back surface side when the elastic body bends as a resistance value, the degree of bending of the elastic body can be detected. In addition, the acceleration sensor, for example, includes a weight and a sensor element inside, and when the weight moves, a compressive force or a tensile force is generated in the sensor element. Using a predetermined calculation formula for the change in the resonance frequency due to these compressive forces and tensile forces, vibrations, tilts, and linear motions generated in the object can be detected.

[0019] The glove-shaped device 20 is a glove-shaped device with a plurality of sensors distributed and worn as shown in FIGS. 2 to 4, and can be used by inserting a hand inside. The sensors worn on the glove-shaped device 20 are, as shown in FIGS. 2 to 4, at least the first to fifth sensor groups 21 to 25 worn at the joint positions on the dorsal side of each of the five fingers (thumb, index finger, middle finger, ring finger, and little finger), the sixth sensor 26 worn at the position of the palm or the back of the hand, and the seventh sensor 27 worn at the position of the wrist.

[0020] Regarding the first to fifth sensor groups, as shown in FIG. 2, the first sensor group 21 is worn on the thumb (so-called parent finger) of the hand, the second sensor group 22 is worn on the index finger (so-called pointer finger) of the hand, the third sensor group 23 is worn on the middle finger of the hand, the fourth sensor group 24 is worn on the ring finger (so-called medicine finger) of the hand, and the fifth sensor group 25 is worn on the little finger of the hand, respectively. Further, each sensor worn on each finger is divided into three types of sensors for each joint position of each finger.

[0021] For example, the first sensor group 21 worn on the thumb is divided into three types of sensors: the first upper-end sensor 21A worn at the position of the first joint (the joint at the tip) of the thumb, the first central sensor 21B worn at the position of the second joint of the thumb, and the first lower-end sensor 21C worn at the position of the third joint of the thumb, as shown in FIG. 2. These first upper-end sensor 21A, first central sensor 21B, and first lower-end sensor 21C are connected to each other by a wiring W21 as shown in FIG. 2, and the wiring W21 is connected to a wiring H1 that is connected to a finger character information output unit 3 described later.

[0022] Therefore, the degree of bending of the thumb is detected for each sensor and transmitted as an electrical signal to the finger character information output unit 3 described later, which is connected via the wiring H1 shown in FIG. 2. Since the second to fifth sensor groups 22 to 25 worn on the other four fingers, namely the index finger, middle finger, ring finger, and little finger, have the same configuration, detailed description is omitted.

[0023] Furthermore, it is preferable that the sensors applied to the first to fifth sensor groups 21-25 be bend sensors that can detect the degree of finger bending (how much each finger is bent) by placing them at the dorsal (nail-side) joint of each finger. In addition, although the first sensor group 21 attached to the thumb is shown in Figure 2 as an example where all three types of sensors, the first upper sensor 21A, the first central sensor 21B, and the first lower sensor 21C, are attached to the dorsal (nail-side), attaching them to the lateral or ventral (palm-side) of the thumb will cause the strain gauges inside the attached bend sensors to deform, changing the resistance value and allowing for the detection of the degree of thumb bending, i.e., fine movements such as opening the thumb outward or placing it against the index finger. Moreover, by attaching bend sensors at the joint positions of the fingers, for example, if the index finger is bent at 90 degrees, it can be pre-set as a gesture representing a specific finger letter, and the degree of finger bending can be converted into a specific finger letter.

[0024] As shown in Figures 3 and 4, the sixth sensor 26 is attached to the palm of the hand to detect the tilt and twist of the hand (from the wrist to the fingertips). The sixth sensor 26 is connected to the seventh sensor 27, which will be described later, via wiring W26.

[0025] Furthermore, the sixth sensor 26 can be pre-configured, for example, to represent a gesture such as confirming or canceling a specific input by moving only the hand without bending the fingers. This allows the tilt of the hand, such as bending the wrist forward or backward, and the twisting of the wrist, such as rotating the wrist left or right, to be used as a function for inputting or outputting finger spelling.

[0026] Therefore, it is preferable to use a bend sensor or an acceleration sensor. Although Figures 3 and 4 show the sixth sensor attached to the palm of the hand, it may also be attached to the back of the hand.

[0027] The seventh sensor 27, as shown in Figures 3 and 4, is a sensor that is attached to the wrist to detect movements such as tilting the hand (or forearm) towards the user (operating side) or away from the user (opponent side), or bending the hand (or forearm) to the left or right. The seventh sensor 27 is connected to the aforementioned sixth sensor 26 via wiring W26, and at the same time, it is connected to wiring H1, which is connected to the finger spelling information output unit, via a separate wiring W27. It is preferable that the seventh sensor be an acceleration sensor or a vibration sensor. Here, a vibration sensor is, for example, a sensor equipped with a piezoelectric element sandwiched between two weights. When an object vibrates, the piezoelectric element deforms in accordance with the movement of the two weights and outputs an electrical signal, and the vibration of the object can be detected from the measured voltage.

[0028] Based on the above, the glove-type device is equipped with the various sensors mentioned above, and can capture the bending and straightening of each of the five fingers and the up, down, left, and right movements of the wrist as electrical signal information. Therefore, for example, based on fine operations such as opening, supporting, and bending the thumb (thumb) as described above, a series of steps such as displaying characters, numbers, and punctuation marks corresponding to the 50 sounds of finger spelling, as well as confirming or canceling characters, can be handled by a single glove-type device.

[0029] (Leg-mounted devices 28, 29) Figure 5 shows a perspective view of the leg-mounted device 28 of the second embodiment of the motion detection unit, wrapped around and fixed to the thigh, and Figure 6 shows a perspective view of the leg-mounted device 29 of the same embodiment, fixed to the ankle. The leg-mounted device, which is the second embodiment of the motion detection unit, is equipped with various sensors such as an acceleration sensor and is a device that is fixed to a person's leg for use. For example, as shown in Figure 5, there is a type in which a belt-type component is wrapped around and fixed to the thigh (leg-mounted device 28), and as shown in Figure 6, there is a type in which a ring-shaped component is attached to the ankle (leg-mounted device 29).

[0030] Furthermore, as shown in Figure 5, the leg-mounted device 28 is equipped with wiring W28, which is connected to wiring H1 connected to the finger-spelling information output unit 3. Similarly, the leg-mounted device 29 is equipped with wiring W29, as shown in Figure 6, which is connected to wiring H1 connected to the finger-spelling information output unit. Moreover, as shown in Figures 5 and 6, the leg-mounted devices 28 and 29 are devices that can be attached to the thigh or ankle to accurately detect movements such as swinging the leg up (or down) or kicking up. Through the operation of various sensors attached to these devices, for example, the acceleration sensor can grasp the instantaneous vertical movement of the thigh, and such movements can be accurately captured as electrical signal information.

[0031] Therefore, by using the leg-mounted device in conjunction with the aforementioned glove-type device 20, for example, steps such as confirming or canceling characters can be individually handled by actions such as swinging the leg equipped with the leg-mounted device in response to finger spelling displayed using the glove-type device. As a result, it is possible to perform a series of steps from displaying to confirming finger spelling with one hand and foot (for example, the right hand and right foot) while using the other hand (for example, the left hand) to operate external devices such as smartphones, personal computers, and tablet terminals, such as sending emails.

[0032] <Finger Spelling Information Output Unit 3> The finger spelling information output unit 3 is a device that generates finger spelling information corresponding to the human movements detected by the aforementioned motion detection unit and outputs it to an external device. It analyzes the data sent from the motion detection unit, generates finger spelling information based on a predetermined correspondence between movements and finger spellings, and transmits it to the external device.

[0033] The finger spelling information output unit 3 analyzes motion data, maps motion to finger spelling, generates finger spelling information, and transmits it to an external device as finger spelling data via wired or wireless means. Although the finger spelling information output unit 3 is shown as a separate and independent device from the motion detection unit 2 as shown in Figure 1, it can also be integrated by embedding it in the aforementioned glove-type device or leg-mounted device of the motion detection unit 2.

[0034] Next, an embodiment of a finger spelling output method using a finger motion recognition device will be described. The finger spelling output method using a finger motion recognition device of the present invention mainly consists of the following steps 1 to 9. • Step 1: Sensor motion detection based on hand movements • Step 2: Transmission of the motion-detected electrical signal • Step 3: Check whether or not an electrical signal is received. • Step 4: Selection of corresponding finger spelling based on analysis of electrical signals • Step 5: Confirmation of finger spelling selection through analysis of electrical signals • Step 6: Audio output of selected finger spelling on an external device • Step 7: Confirmation of selected finger spelling • Step 8: Confirming the selected finger spelling. Step 9: Output of finger spelling data to external devices in voice, text, and braille. The details of steps 1 through 9 when using the glove-type device shown in Figures 2 through 4 or the leg-mounted device shown in Figures 5 and 6 as the motion detection unit will be explained below with reference to the drawings. Figure 7 shows a flowchart of a finger spelling output method using a finger motion recognition device, which is one embodiment of the present invention.

[0035] (Step 1: Sensor motion detection based on hand movements) First, a person (operator) puts a glove-type device on one hand. This glove-type device is equipped with several types of sensors, such as a bend sensor and an accelerometer, to detect the movement of the hand and the five fingers (first step S001 shown in Figure 7).

[0036] The bending sensor accurately detects the bending direction and angle of each finger joint, and measures the degree of finger flexion by capturing the change in resistance value of the strain gauge inside the sensor in response to the finger movement. The acceleration sensor detects the direction and speed of hand movement, and determines the speed and direction of the movement by measuring the acceleration associated with the hand movement.

[0037] Furthermore, by continuously monitoring the output of these sensors, calibration can be performed as needed to maintain measurement accuracy. For example, recalibration during initial use and at regular intervals can correct sensor misalignment and errors, ensuring that accurate data is always obtained.

[0038] (Step 2: Transmission of the detected electrical signal) In the second step, the electrical signal detected in the first step is transmitted from the glove-type device 20 to the finger-spelling information output unit 3 (second step S002 shown in Figure 7). The glove-type device 20 can quickly and reliably transmit the electrical signal to the finger-spelling information output unit via wired or wireless communication means.

[0039] Specifically, by using Bluetooth® or Wi-Fi® as wireless communication, rapid information transmission becomes possible without the physical constraints of wired communication such as cables. Furthermore, by using recording media such as USB for wired communication, high-speed and stable communication becomes possible.

[0040] (Step 3: Check whether or not an electrical signal is received) The finger spelling information output unit 3 checks whether it has received an electrical signal from the glove-type device 20. If the finger spelling information output unit 3 has not received an electrical signal, it sends a command to the glove-type device 20 to retransmit the electrical signal (retransmission command: third step S003).

[0041] At this time, the timestamp of the received signal and sensor identification information are also transmitted, making it possible to identify the time of signal generation and the source of the signal. In this way, the signal transmitted from the glove-type device 20 is appropriately managed and processed by the finger spelling information output unit 3, allowing for a smooth transition to the next step.

[0042] Furthermore, to enhance the reliability of communication, security protocols such as encryption technology can be introduced for communication between the glove-type device 20 and the finger-spelling information output unit 3. This prevents interception and tampering of electrical signals by third parties, ensuring highly confidential communication. In this way, in the second step, electrical signals are transmitted from the glove-type device to the finger-spelling information output unit 3, and it is ensured that these signals are received accurately and securely.

[0043] (Step 4: Selection of corresponding finger spelling based on analysis of electrical signals) (Step 5: Confirmation of finger spelling selection by analyzing electrical signals) In the fourth and fifth steps, the finger spelling information output unit 3 analyzes the electrical signal received in the second step (fourth step S004 shown in Figure 7) to select the finger spelling corresponding to that electrical signal (fifth step S005 shown in Figure 7). The finger spelling information output unit 3 includes multiple processes for analyzing the received electrical signal. This analysis process consists of a signal preprocessing process, a feature extraction process, and a finger spelling matching process.

[0044] First, the signal preprocessing process involves denoising and normalizing the received electrical signal. Denoising uses filtering techniques to remove noise from the external environment and the device itself. For example, applying a low-pass filter removes high-frequency and low-frequency components from the electrical signal, improving its quality. Normalization is performed to unify the range and scale of the electrical signal obtained from the sensor, and is an important process for improving the accuracy of the analysis.

[0045] Next, in the feature extraction process, important features are extracted from the pre-processed electrical signals. Feature extraction includes the flexion angle of each finger, the speed and direction of hand movement, and the pressure applied to the fingertips. These features are analyzed using machine learning algorithms or existing finger spelling recognition technologies. For example, algorithms such as neural networks can be used to accurately identify the corresponding finger spelling from the extracted features. If, as a result of the analysis in step 4 S004 shown in Figure 7, the corresponding finger spelling cannot be selected in step 5 S005, a command is sent to the finger spelling information output unit 3 to re-analyze the electrical signals (re-analysis command).

[0046] (Step 6: Audio output of selected finger spelling on an external device) Finally, in the finger spelling correspondence process, a pre-trained model is used to select the corresponding finger spelling based on the extracted features. This model is pre-trained so that specific finger flexion patterns and hand movements correspond to specific finger spellings.

[0047] For example, machine learning technology is used to build a highly accurate model based on a large amount of data. This allows for the rapid and accurate selection of finger spelling corresponding to the operator's hand and finger movements. Subsequently, the selected finger spelling is displayed on the screen of an external device such as a PC or smartphone connected to the finger spelling information output unit via wired or wireless communication, and at the same time, it is output as audio using an application (app) and speaker with a text-to-speech function on the external device (step 6 S006 shown in Figure 7).

[0048] (Step 7: Confirm the selected finger spelling) In step 7, the operator performs a confirmation action to finally determine the finger spelling selected in step 5 (step 7, S007, shown in Figure 7). Specifically, the finger spelling selected in step 5 is displayed on an external device connected to the finger spelling information output unit 3, and at the same time, it is output as audio using an application (app) and speaker equipped with the external device's reading function. If the audio output of the finger spelling matches the finger spelling intended by the operator, the operator confirms it by performing a specific action using their hand or fingers. This confirmation action can be performed using predetermined action patterns, such as tilting the hand forward, raising the hand (arm), or moving the hand (arm) to the side of the body, to make a decision on which finger spelling has been selected.

[0049] If the selected finger spelling is different from the finger spelling intended by the operator, an action can be taken to cancel that finger spelling (step 7, S007, shown in Figure 7). For example, when using a glove-type device 20 as the motion detection unit, an electrical signal to cancel the selected finger spelling can be transmitted by performing specific actions such as bending the hand towards the user, lowering the hand (arm), or moving the hand (arm) inward.

[0050] Furthermore, when using a leg-mounted device as the motion detection unit 2, it is possible to send an electrical signal to cancel the selected finger spelling by performing actions such as swinging the thigh up or kicking (a ball, etc.). This prevents incorrect finger spelling from being selected and allows for accurate finger spelling input again. After the finger spelling is input again, a command is sent to redisplay the re-entered finger spelling on the external device's screen and simultaneously output it as audio (redisplay command).

[0051] (Step 8: Confirming the selected finger spelling) When the operator performs a confirmation action, the glove-type device transmits an electrical signal corresponding to that action back to the finger spelling information output unit (step 8, S008, shown in Figure 7). This electrical signal is used to finally confirm the previously selected finger spelling and indicates that the confirmation action was performed correctly. At this time, the glove-type device detects the action with high sensitivity and applies filtering processing to prevent misrecognition, so that the confirmation action is detected correctly.

[0052] Once the verification process is successfully completed and the selected finger spelling is finally confirmed, that finger spelling is prepared to be output to an external device in the next step, step 5. In this way, step 4 meticulously manages the process by which the selected finger spelling is finally determined through the verification process.

[0053] (Step 9: Outputting finger spelling data to external devices via voice, text, and Braille) In step 9, the finger spelling data finalized in step 8 is displayed as text from the finger spelling information output unit to an external device, and at the same time, output as voice, text, Braille, or any other means (step 9 S009 shown in Figure 7). This output step is performed via wired or wireless communication between the finger spelling information output unit and the external device. External devices include a wide variety of devices such as computers, smartphones, tablets, and various internet-connected devices.

[0054] Bluetooth® and Wi-Fi® are commonly used as wireless communication technologies. Bluetooth® is suitable for short-distance data transmission with low power consumption and provides stable communication between paired devices. Wi-Fi, on the other hand, enables high-speed data transfer over a wide area and allows communication via the internet using home networks and public Wi-Fi networks. For wired communication, USB and serial cables are used, achieving high-speed and stable data transfer.

[0055] Error checking and encryption technologies are applied to the transmission of finger spelling data to ensure the reliability and integrity of the transmitted data. For example, by adding a checksum to the transmitted data, the receiving end can detect errors in the data and request retransmission if necessary. Furthermore, the use of encryption technology ensures the confidentiality of the transmitted data and the security of the communication.

[0056] The transmitted finger spelling data can be used by various applications and software on external devices. For example, it can be used as real-time finger spelling input in text editors, messaging applications, and email clients. This also enables rapid and efficient information exchange between different users and realizes an intuitive finger spelling input interface through hand movements.

[0057] Furthermore, the process for transmitting finger spelling data can be customized according to the user's needs. It can accommodate a variety of usage scenarios, such as a mode for direct input to a specific application or a mode for sending data to a cloud service and synchronizing it with a remote device.

[0058] Thus, in the final ninth step, the process of transmitting the finger spelling data, which was finalized in the eighth step, to external devices via wireless or wired communication and using it in various applications and software is meticulously managed.

[0059] By using the above-described finger movement recognition device, any finger spelling can be expressed. Furthermore, the finger spelling output method using this device allows the device to accurately detect finger and hand movements, recognize them as finger spelling, convert those movements into finger spelling, and perform incidental operations such as confirming or finalizing the converted finger spelling. By connecting to an external device, the finger spelling data can be output as voice. Therefore, smooth communication can be facilitated between visually impaired individuals and people in different spaces. [Explanation of Symbols]

[0060] 1. Hand motion recognition device 2. Motion detection unit 3. Finger spelling information output unit 20 Glove-type devices 21-25 Sensor Groups 1-5 21A~21C First (upper, center, lower) sensor group 22A~22C Second (upper, center, lower) sensor group 23A~23C Third (upper, center, lower) sensor group 24A~24C Fourth (upper, center, lower) sensor group 25A~25C Fifth (Upper, Center, Lower) Sensor Group 26. Sensor No. 6 27 7th Street 28,29 Leg-mounted devices H1~H3 wiring S001~S009 Steps 1~9 UT external equipment W21~W29 Wiring

Claims

1. A finger motion recognition device comprising: a motion detection unit that detects a predetermined number of types of human movements using sensors; and a finger spelling information output unit that outputs finger spelling information to an external device for inputting finger spelling corresponding to the human movements, wherein the motion detection unit has a glove-type device that is worn on the five fingers of the hand, detects the movements of the five fingers to recognize them as finger spelling, and then confirms or cancels the finger spelling.

2. A finger motion recognition device according to claim 1, wherein the sensor of the glove-type device comprises a group of first to fifth sensors attached to the joint positions on the back of each of the five fingers, a sixth sensor attached to either the palm or the back of the hand, and a seventh sensor attached to the wrist, wherein the group of first to fifth sensors are bending sensors that sense the bending and straightening of the fingers, the sixth sensor is a sensor that senses the tilt of the hand, and the seventh sensor is a sensor that senses the direction of movement of the hand.

3. A finger movement recognition device according to claim 2, characterized in that the sixth sensor and the seventh sensor are used to determine or cancel the finger characters.

4. A finger motion recognition device according to claim 1, wherein the motion detection unit further comprises a leg-mounted device that determines or cancels the finger characters by detecting predetermined foot movements using an acceleration sensor attached to the foot, and the finger character information output unit outputs the finger character information to an external device when the foot movement is detected.

5. A finger spelling output method using a finger motion recognition device according to claim 2 or 3, comprising the steps of: detecting the movement of the hand or the five fingers as an electrical signal using the first to fifth sensor group and the sixth and seventh sensors while the glove-type device is worn on the hand; transmitting the detected electrical signal from the glove-type device to the finger spelling information output unit; selecting a corresponding finger spelling by analyzing the received electrical signal at the finger spelling information output unit; outputting the selected finger spelling as voice from the external device so that the person can decide or cancel the selected finger spelling using the glove-type device; and transmitting the decided finger spelling to the external device by either wireless or wired communication means to output the finger spelling data as voice, text, braille, or any other means.

6. A finger spelling output method using the finger movement recognition device described in claim 4, comprising the steps of: attaching the glove-type device to the hand and the leg-mounted device to the foot, detecting the movement of the five fingers as an electrical signal using a sensor on the glove-type device; transmitting the detected electrical signal to the finger spelling information output unit; analyzing the received electrical signal at the finger spelling information output unit to select a corresponding finger spelling; outputting the selected finger spelling as sound from the external device, allowing the person to detect the movement of the foot using the leg-mounted device to determine or cancel the selected finger spelling; and transmitting the determined corresponding finger spelling to the external device via wireless or wired communication means to output the finger spelling data as sound, text, Braille, or any other means.

7. A glove-type device for operating a virtual avatar in a virtual space while being worn on the five fingers of the operator, wherein the glove-type device has a first to fifth sensor group attached to the joint position on the back of each of the five fingers, a sixth sensor attached to either the palm or the back of the hand, and a seventh sensor attached to the wrist, and wherein the first to fifth sensor groups are bending sensors that sense the bending and straightening of the fingers, the sixth sensor is a sensor that senses the tilt of the hand, and the seventh sensor is a sensor that senses the direction of movement of the hand, thereby enabling the detection of the movement of the five fingers.

Images