KR20210102658A - Asceptic operating system using gaze-tracking, gesture, or voice - Google Patents

Abstract

Embodiments of the present invention provide a non-contact aseptic controlling system capable of realizing a perfect sterile surgical environment by controlling equipment without touch operation such as a mouse or keyboard after processing gaze, gesture (motion), or voice signals with a preset program. According to an embodiment of the present invention, provided is an asceptic operating system using gaze, gesture, or voice. The system comprises: a display unit arranged to display an image; a gaze tracking unit disposed on one side of the display unit to track the user's gaze movement; a gesture sensing unit disposed on one side of the display unit to detect a movement or shape of a user's hand; an eye tracking unit; a control unit that selects and processes a preset image according to a signal detected by the gesture sensing unit, and displays the image through the display unit.

Description

Non-contact aseptic manipulation system using gaze, gesture, or voice {ASCEPTIC OPERATING SYSTEM USING GAZE-TRACKING, GESTURE, OR VOICE}

The present invention relates to a sterile manipulation system, and more particularly, to a sterile manipulation system using a user's gaze, gesture, or voice instead of a traditional method of controlling an image system by manipulating a keyboard or mouse.

In order to manipulate a series of objects displayed on the screen (eg, a web browser or an application, etc.), a keyboard, a mouse, or a remote control is used as a typical input device, and the screen is directly touched.

With the improvement of computer performance, intuitive interface technologies that enhance interaction between humans and computers are emerging. A technology for detecting user's motion information and recognizing operation commands therefrom is also being developed in the medical field.

In particular, in the recent medical field, as many types of procedures and surgeries have been changed to minimally invasive and percutaneous procedures, the location and location of treatment devices and User experiences have emerged to identify, measure, and guide shapes.

In order to perform a surgery or procedure aseptically in such a user environment, an assistant manpower to operate various imaging equipment in addition to the main operator is required.

In particular, the assistant personnel have a good understanding of advanced surgeries and procedures, and track the appropriate images for each special situation and the situation, and show the operator to make an accurate judgment so that the procedure/surgery can be guided safely and accurately. Do what you can to help

However, it is impossible to deal with various and complex situations that occur during the procedure, and the assistant shows the image in the desired direction to fit the various unexpected situations before the procedure and provides the necessary information (position, distance, size, etc. of the target) It is important to quickly and accurately track and show the operator so that the operator can make a decision.

The assistant performs the operation desired by the operator (manipulating imaging equipment, etc.) and the operator decides how to proceed to the next step based on the provided information. Since the silver tools are being held or operated continuously, direct operation is impossible even if the remote control is sterilized. In many cases, since the operator's feet are also using pedals to operate the equipment (mainly video), the operator must communicate the requirements to the assistant mainly through language.

However, in a general hospital environment, it is rare for most assistants to be as proficient as the operator, and even a well-trained assistant may not be able to quickly and accurately perform the operation desired by the operator at once.

Therefore, depending on the type and situation of the procedure, such delay and inaccuracy can seriously affect the safety of the patient and the result of the procedure, so a system that allows the operator to directly and accurately and aseptically operate is needed.

Since the contents described in the above-mentioned background are only written for understanding the background of the present invention, it may include contents other than those already known to those skilled in the art.

Application No. 10-2016-0064946 Application No. 10-2012-0103599 Application No. 10-2015-0144243

Embodiments of the present invention provide a non-contact aseptic operation system that can implement a more perfect sterile surgical environment by processing the gaze, gesture (motion), or voice signal with a preset program and controlling the equipment without touch operation such as a mouse or keyboard. will provide

In addition, a function to search for a desired image during the procedure, a function to repeatedly play a set section in the searched image, a function to search for a desired frame in a searched image, a function to select and enlarge a desired part in the image, a function to An object of the present invention is to provide an aseptic manipulation system capable of performing a function of measuring a length, a function of comparing searched images, and a function of allowing the imaging equipment to perform a desired operation by an operator.

In addition, it is possible to convert to a user interface suitable for images and auxiliary equipment used in various procedures, and it is possible to eliminate potential risk factors by quickly and accurately responding to special situations caused by differences in the skill of assistants in complex procedures/surgeries. The goal is to provide a non-contact aseptic handling system that can help improve patient safety inventory and treatment outcomes.

A non-contact aseptic manipulation system using a gaze, a gesture, or a voice according to an embodiment of the present invention includes a display unit arranged to display an image; a gaze tracking unit disposed on one side of the display unit to track a user's gaze movement; a gesture sensing unit disposed on one side of the display unit to detect a movement or shape of a user's hand; and a control unit that selects and processes a preset image according to the signal detected by the eye tracking unit and the gesture sensing unit, and displays the selected image through the display unit.

In the non-contact aseptic manipulation system using a gaze, a gesture, or a voice according to an embodiment of the present invention, the gaze tracking unit may be of a bar type disposed on one side of the display unit in the direction of movement of the gaze.

In the non-contact aseptic manipulation system using a gaze, a gesture, or a voice according to an embodiment of the present invention, the gaze tracking unit may be disposed on one side of the display unit.

In the non-contact aseptic manipulation system using a gaze, a gesture, or a voice according to an embodiment of the present invention, the gesture sensing unit may include a depth camera, an RBG camera, a stereo camera, or an infrared camera.

In the non-contact aseptic manipulation system using gaze, gesture, or voice according to an embodiment of the present invention, a voice recognition unit disposed on one side of the display unit to detect a user's voice may be further included.

In the non-contact aseptic manipulation system using gaze, gesture, or voice according to an embodiment of the present invention, according to the signal detected by the gaze tracking unit and the gesture sensing unit, at least one of the images stored in the memory unit through the software unit is selected. It may include a control unit to select.

In the non-contact aseptic manipulation system using gaze, gesture, or voice according to an embodiment of the present invention, according to the signal detected by the gaze tracking unit and the gesture detection unit, the control unit repeats a preset section in the selected image and displays can do.

In the non-contact aseptic manipulation system using a gaze, a gesture, or a voice according to an embodiment of the present invention, according to a signal detected by the gaze tracking unit and the gesture sensing unit, the control unit selects at least one of the frames constituting the image. You can select a frame to display.

In the non-contact aseptic manipulation system using a gaze, a gesture, or a voice according to an embodiment of the present invention, according to a signal detected by the gaze tracking unit and the gesture sensing unit, the control unit places a visual mark ( mark), and it can be moved or fixed according to the gaze or gesture.

In the non-contact aseptic manipulation system using a gaze, a gesture, or a voice according to an embodiment of the present invention, according to a signal detected by the gaze tracking unit and the gesture sensing unit, the control unit controls the distance between the at least two marks, The area or volume can be calculated and displayed.

In the non-contact aseptic manipulation system using a gaze, a gesture, or a voice according to an embodiment of the present invention, according to the signal detected by the gaze tracking unit and the gesture sensing unit, the control unit includes the voice signal input through the voice recognition unit and the Marks can be matched to each other.

In the non-contact aseptic manipulation system using gaze, gesture, or voice according to an embodiment of the present invention, according to the signal detected by the gaze tracking unit and the gesture sensing unit, the control unit includes a voice signal input through the voice recognition unit and The matching mark may be searched for, and an image including the searched mark may be displayed.

In the non-contact aseptic manipulation system using a gaze, a gesture, or a voice according to an embodiment of the present invention, the display unit may include a rotating unit that rotates to face the user's eyes or hands.

According to embodiments of the present invention, it is possible to implement a more sterile surgical environment by processing a gaze, a gesture (motion), or a voice signal with a preset program to control the equipment without manipulation of a mouse or keyboard.

In particular, a function to search for a desired image during the procedure, a function to repeatedly play a set section in the searched image, a function to search for a desired frame in a searched image, a function to select and enlarge a desired part in the image, and a function to A function of measuring the length and a function of comparing searched images may be performed.

In addition, it is possible to convert to a user interface suitable for images and auxiliary equipment used in various procedures, and it is possible to eliminate potential risk factors by quickly and accurately responding to special situations caused by differences in the skill of assistants in complex procedures/surgeries. This can help to rethink patient safety and improve treatment outcomes.

The above-mentioned effects according to the embodiments of the present invention are not limited to the described contents, and may further include all effects predictable from the specification and drawings.

1 is a schematic configuration diagram of a non-contact aseptic manipulation system using a gaze, a gesture, or a voice according to an embodiment of the present invention.
2 shows a method of operating an aseptic handling system according to an embodiment of the present invention.
3 is a flowchart showing a process of an aseptic handling system according to an embodiment of the present invention.
4 is a table showing the functions of the aseptic handling system according to an embodiment of the present invention.
5 shows an image of an aseptic manipulation system according to an embodiment of the present invention.
6 is a schematic perspective view of an aseptic handling system according to another embodiment of the present invention.
7 to 12 are schematic views showing embodiments of the present invention.

It should be understood that the present invention is not limited to the specific embodiments described below, and includes all modifications, equivalents and substitutes included in the spirit and scope of the present invention.

The terms used herein are used to describe specific embodiments, and are not intended to limit the present invention. A singular expression may include a plural expression unless the context clearly dictates otherwise.

Terms such as “include” or “have” mean that there is a possibility to further include other components or actions in addition to the components or actions described in the specification. Terms such as first, second, etc. are not intended to limit the components, and are for the purpose of distinguishing one component from other components.

Hereinafter, an embodiment of a non-contact aseptic manipulation system using a gaze, a gesture, or a voice according to the present invention will be described in detail with reference to the accompanying drawings.

1 is a schematic configuration diagram of a non-contact aseptic manipulation system using a gaze, a gesture, or a voice according to an embodiment of the present invention.

Referring to FIG. 1 , the aseptic manipulation system includes an eye tracking unit 100 , a gesture sensing unit 105 , a voice recognition unit 110 , a display unit 115 , an input/output unit 120 , an operation control unit 130 , and a memory. It includes a unit 135 and a software unit 140 , and a keyboard 122 , a mouse 124 , or a pedal 126 may be connected to the input/output unit 120 by wire/wireless. First, the gaze tracking unit 100 may track the gaze 210 by irradiating infrared or light into the human eye, tracking the pupil position of the eye, and estimating the movement of the eye using this, and The direction of the gaze 210 may be estimated by photographing the entire appearance. By setting the estimated gaze direction as a virtual line, the position on the 2D flat monitor or the direction and area in 3D space can be estimated.

The eye tracking unit 100 according to an embodiment of the present invention may be configured as a bar type attached to the lower end of the display unit 115, and through this structure, a specific point or area in the image the user is looking at is detected. faster and more accurate selection.

In addition, the gesture detection unit 105 recognizes the movement or shape of a finger, and may include a camera, and the gesture detection unit 105 may track the movement of a finger in a non-contact manner using a camera. .

The camera of the gesture sensing unit 105 may largely include a type using a depth image and a type using a color (RBG) image or infrared light, and in an embodiment of the present invention, a type using a depth image is relatively A better tracking performance may be exhibited, but a type using a color image may also be employed.

In the present invention, it is considered that the finger motion tracking method in the third person view is suitable, and if the user is a surgeon, a depth image type camera can be used for stability of performance because he is wearing gloves stained with blood. have. In addition, as a method of quickly detecting a user's hand, well-known programs, operating devices, and methods may be suitably applied according to embodiments.

In addition, the voice recognition unit 110 uses a voice recognition technology to draw a point or select a point at a desired point in the image using an annotation using a voice in a state where the gaze is fixed at a specific position, A name is given to this, and if necessary, the same point can be referred to or searched for through voice.

In an embodiment of the present invention, the display unit 115 displays an image, and is an electronic device such as plasma, light emitting diode, liquid crystal, etc. can be applied.

The operation control unit 130 may be implemented as one or more microprocessors operated by preset software or programs, and such a set program or software executes a series of instructions for performing each operation and function according to an embodiment of the present invention. may include

In the memory unit 135 , preset images may be stored, arranged, and updated, which may be connected to an external system by wire or wireless, and the software unit 140 may include a keyboard, mouse, or A user's instruction or command input through the pedal or input through the eye tracking unit 100, the gesture sensing unit 105, or the voice recognition unit 110 may be performed through the operation control unit 130, , functions performed through the operation control unit 130 and the software unit 140 will be described with reference to FIGS. 1 to 6 .

2 shows a method of operating an aseptic handling system according to an embodiment of the present invention.

Referring to FIG. 2 , the bar-type gaze tracking unit 100 is mounted on the lower end of the display unit 115 in the horizontal direction. In an embodiment of the present invention, the bar-type gaze tracking unit 100 may be horizontally disposed on the upper end of the display unit 115 , or may be configured separately from the display unit 115 .

The gesture sensing unit 105 may be disposed left and right at the upper end of the display unit 115 , which may be a depth camera or a color camera, and its installation position may be variable, and the gesture sensing unit 105 may be configured separately from the display unit 115 .

The voice recognition unit 110 may be installed on the side of the display unit 115 to detect the user's voice from the outside, the installation position of the voice recognition unit 110 may be variable, and the display unit ( 115) and may be configured separately.

In a state in which the user's eyes gaze at the screen of the display unit 115 , the eye tracking unit 100 detects the direction of the user's eye gaze 210 , and the gesture detection unit 105 detects the user's hand It is possible to detect the movement path of 200 and the shape of the hand. In addition, the user may input an instruction signal through the keyboard 122 , the mouse 124 , or the pedal 126 .

3 is a flowchart showing a process of an aseptic handling system according to an embodiment of the present invention.

Referring to FIG. 3 , the power of the aseptic manipulation system is turned on in S300, the eye tracking unit 100 tracks the user's gaze in S310, and the gesture sensing unit 105 detects the movement and shape of the user's hand in S320. , and the voice sensing unit 105 detects the user's voice in S330.

In S340, the operation control unit 130 processes the signals detected by the eye tracking unit 100, the gesture sensing unit 105, and the voice sensing unit 105, and generates a command signal corresponding thereto, and in S350, the software unit 140 receives the command signal generated by the operation control unit 130, and performs a function corresponding thereto.

4 is a table showing the functions of the aseptic handling system according to an embodiment of the present invention.

Referring to FIG. 4 , the aseptic manipulation system may perform a function of searching for an image stored in the memory unit 135 in S400 . Here, it is possible to search for an image through the title of the image, and the title of the image may be recognized as a voice.

In addition, the aseptic manipulation system may perform a function of searching for a frame in the image searched for in S410, and may search for a frame by inputting a name corresponding to the frame to be selected by voice.

In addition, the aseptic manipulation system may perform a function of repeatedly reproducing the image searched for in S420, and the user may set a section to be repeated in the searched image, and this section can be played repeatedly.

In addition, the aseptic manipulation system may perform a function of measuring the length/diameter/volume of a specific region in the image in S430. A user may search for an image or frame through gaze, gesture, or voice, select a specific region, and measure its length, diameter, or volume.

In addition, the aseptic manipulation system may perform a function of enlarging or reducing a specific area in the image in S440 . The user may search for an image or a frame through a gaze, a gesture, or a voice, select a specific region of the image, and enlarge or reduce the selected region.

In addition, the aseptic manipulation system may perform a function of forming a mark on a specific area or point in the image in S450. A user may select a specific area or point of an image through a gaze, a gesture, or a voice, and may form a preset mark in the selected area or point. Here, the user can variously select the shape of the mark and the like.

In addition, the aseptic manipulation system may perform a function of forming a mark on a specific area or point in the image searched in S460, and giving a text name or an audio name to the mark, and the user selects a specific area or point of the image and , a preset mark may be formed in a selected area or point, and a text name or a voice name may be assigned to the formed mark.

In addition, the aseptic manipulation system may perform a function of giving a text name or a voice name to the mark formed in advance in S470. Accordingly, the user can quickly and accurately search for an image or frame through a text name or an audio name.

5 shows an image of an aseptic manipulation system according to an embodiment of the present invention.

Referring to FIG. 5 , a user searches for an image and a frame expressed on the display unit 115 through a gaze, a gesture, or a voice, forms a mark 500 in a specific area, and a length between the marks 500 . (L) can be found. In addition, the user can give the mark 500 a text name or a voice name, and then quickly search for images and frames through the text name or voice name later, which can be visually confirmed through the display unit 115 . have.

In an embodiment of the present invention, a user may give a text name or an audio name to a specific image and a specific frame, and the name may be visually expressed in the image. can be searched for.

6 is a schematic perspective view of an aseptic handling system according to another embodiment of the present invention.

Referring to FIG. 6 , a pedestal 610 is disposed below the display unit 115 , and a rotating unit 600 is configured on the pedestal 610 , and the rotating unit 600 includes the display unit 115 . can be rotated to a set angle.

Here, the rotating unit may rotate the display unit in a left-right direction or a vertical direction, and may move in a three-dimensional space. Accordingly, the direction/height can be changed to suit the operator by comfortably and accurately recognizing the gaze and motion.

The voice recognition unit 110 , the gesture detection unit 105 , or the eye tracking unit 100 detects a preset main user's position, and the operation control unit 130 controls the rotation unit ( 130 ) according to the detected position. 600 ) so that the screen of the display unit 115 can be easily seen by the user's eyes, and the detection accuracy of the eye tracking unit 100 and the gesture sensing unit 105 can be improved.

In the non-contact aseptic manipulation system using gaze, gesture, or voice according to an embodiment of the present invention, the user's gesture command is comprehensively analyzed to allow the auxiliary equipment to perform the desired operation (forward/backward/left/right movement, rotation, etc.) You can make it take as many as you want (angle, distance, height/height, etc.), and algorithms such as machine learning can be used to more accurately perform the user's desired action in the process of executing the command.

Referring to FIG. 6 , the rotating unit is thought to be necessary in order to track the user's gaze and to accurately recognize the user's gaze, and appropriately height and vertical rotation are possible according to the height and position of the user.

In the non-contact aseptic manipulation system using gaze, gesture, or voice according to an embodiment of the present invention, commands are comprehensively analyzed to allow auxiliary equipment to perform desired operations (forward/backward/left/right movement, rotation, etc.) as much as desired (angle , distance, height / height, etc.) can be taken, and algorithms such as machine learning can be used so that the user can perform the desired action more precisely in the process of executing the command.

7 to 12 are schematic views showing embodiments of the present invention.

7, for fluoroscopy, the equipment finds an appropriate position in the moving direction as it goes up, recognizes according to the shape/thickness/electrode arrangement of various catheters, and the operator says "Go" to the catheter When operating, the instrument can be recognized by naming it "a". After the lock-on becomes "is", you can follow the device and show the image.

By gaze tracking the bottom of the monitor, you can move at an appropriate speed so that 70% of the blank space is maintained in the moving direction. In addition, by utilizing the function of machine learning, improvements such as improved images and smooth operation can be expected depending on the operator/type of procedure.

In addition, by attaching a marker to the back of the hand of the sterile glove, the push-in distance during hand movement can be accurately measured, and the distance to be moved to the machine can be predicted and transmitted. can

8 shows the overall contour of the heart, and as a naming possible application example, when naming "right coronary artery" during coronary angiography, focusing and moving to the right, naming "left coronary artery", focusing to the left In order to prevent blood vessels from going out of the screen by machine learning the outline/motion of the heart, the vertical, horizontal, and vertical positions of the screen and the height and angle of the X-ray fluoroscopy equipment can be adjusted.

Referring to FIG. 9 , as angiographic measurement, frame selection/video clip selection may be performed. First, call "machine name" (eg machine name "angio") and then say "show me video clip list". Then, as shown in (a) of FIG. 9 , the display is configured in a state in which the thumbnail list is played.

Then, if the hand gesture is scrolled left/right, the selected thumbnail becomes larger than the surrounding according to the gaze, and if it is determined that it is correct, call “ok” or select it with a hand gesture. Then, the selected clip is changed to the full screen, ready to be displayed, and the desired frame is selected by moving the frame position left and right in the frame view area below as shown in FIG. 9(b). Then, in the selected frame, the front and rear 1 to 3 frames are merged, the boundary of the display target is sharpened, and the process is performed before measurement in the margin enhanced state.

Referring to FIG. 10 , for angiographic measurement, examples of the assistant's mechanical measurement are d1', d2', and d3', and the operator's intentional treatment plan, d1, d2, d3. When the user calls “A-view”, the name of the device to be activated by voice, enters the standby input mode, and calls “distance measurement” as a function to use, the gaze tracking area is displayed on the screen It is enlarged to the shape of a target, etc.

Then, when "Point1" hits the target, it is called "stop" at this point. If, after "unintentional eye movement" or "stop", you can take your eyes off for a while or use blinking to check and correct whether the marker is fixed at the correct point. In the same way, after fixing "point2", you can call "Measure distance" between two points [name of the function you want to perform] and measure the distance.

11, for the measurement and analysis function of the electrocardiogram (EGM) and pacing record in the heart, in the corresponding part when the desired page is scrolled, "book mark If you call ", it is displayed in the log, and if you call "book mark number" on the review screen, it moves to that screen. Here, since a desired signal may be in a corner of the screen, a desired portion can be found by scrolling. In the present embodiment, scrolling may be performed by moving a mouse mark according to voice/hand gesture (left/right movement, distance/speed)/. In addition, you can freely command forward/backward, by second/page/half page, etc., and say “next” after the first command to move in the same scale and direction.

In addition, it is called "stimulation", and when a desired command is entered, it performs a stimulation function, for example, straight pacing at the cycle length of 500ms at a specific point "A1-2/site" at a set period. function can be performed.

In Fig. 12, when we say "trace v1-2", we change the v1-2 signal to a different color, activate it to enlarge the screen, and the "X" marker is displayed along the line along the line of sight, and when measuring the vertex When "peak" is said, a marker is displayed at the signal peak point. And, when it comes to the desired place, "point 1, there are several peaks in the same way," "first peak" and "second peak", determine p1 and p2, and through this "measure time between p1 and p2", two You can measure the time between points.

In addition, when measuring something on a line different from "A1-2", after determining p1, refer to "change channel to V1-2", fix p2 in the same way, and then use "measure p1 and p2" between two points It measures the time of , selects the "peak"/"take off" of the cardiac electrocardiogram using the "take off"/"beginning" commands, and can accurately perform signal definition through machine learning.

Although the embodiments of the present invention have been described above, the spirit of the present invention is not limited to the embodiments presented herein, and those skilled in the art who understand the spirit of the present invention can add components, Other embodiments may be easily proposed by changes, deletions, additions, etc., but these will also fall within the scope of the present invention.

100: eye tracking unit 105: gesture detection unit
110: voice recognition unit 115: display unit
120: input/output unit 130: control unit
135: memory unit 140: software unit
122: keyboard 124: mouse
126: pedal 200: hand
210: eye 500: mark
600: rotating unit 610: pedestal

Claims (13)

a display unit arranged to display an image;
a gaze tracking unit disposed on one side of the display unit to track a user's gaze movement;
a gesture sensing unit disposed on one side of the display unit to detect a movement or shape of a user's hand; and
a control unit for selecting and processing a preset image according to the signal detected by the eye tracking unit and the gesture sensing unit, and displaying the selected image through the display unit;
A non-contact aseptic manipulation system using a gaze, a gesture, or a voice, comprising a. The method of claim 1,
The non-contact aseptic manipulation system using a gaze, a gesture, or a voice, characterized in that the gaze tracking unit is a bar type disposed on one side of the display unit in the direction of movement of the gaze. 3. The method of claim 2,
The non-contact aseptic manipulation system using a gaze, a gesture, or a voice, characterized in that the gaze tracking unit is disposed on one side of the display unit. The method of claim 1,
The gesture detection unit is a non-contact aseptic manipulation system using a gaze, a gesture, or a voice, characterized in that it includes a depth camera, an RBG camera, a stereo camera, or an infrared camera. The method of claim 1,
Aseptic manipulation system using gaze, gesture, or voice, characterized in that it further comprises a voice recognition unit disposed on one side of the display unit to detect the user's voice. The method of claim 1,
a control unit configured to select at least one of the images stored in the memory unit through a software unit according to the signal detected by the eye tracking unit and the gesture sensing unit;
A non-contact aseptic manipulation system using a gaze, a gesture, or a voice, comprising a. 7. The method of claim 6,
According to the signal detected by the eye tracking unit and the gesture sensing unit,
The control unit is a non-contact aseptic manipulation system using a gaze, a gesture, or a voice, characterized in that it repeatedly displays a preset section in the selected image. 7. The method of claim 6,
According to the signal detected by the eye tracking unit and the gesture sensing unit,
The control unit selects and displays at least one frame from among the frames constituting the image. 7. The method of claim 6,
According to the signal detected by the eye tracking unit and the gesture sensing unit,
The control unit forms a visual mark at at least one point in the image, and moves it according to the gaze or gesture. 10. The method of claim 9,
According to the signal detected by the eye tracking unit and the gesture sensing unit,
The control unit calculates the distance, area, or volume formed by at least two of the marks, and displays them. 10. The method of claim 9,
According to the signal detected by the eye tracking unit and the gesture sensing unit,
The control unit is a non-contact aseptic manipulation system using a gaze, a gesture, or a voice, characterized in that matching the mark with the voice signal received through the voice human. 12. The method of claim 11,
According to the signal detected by the eye tracking unit and the gesture sensing unit,
The control unit searches for the mark matching the voice signal input through the voice recognition unit, and displays an image including the searched mark. The method of claim 1,
a rotating unit for rotating the display unit to face the user's eyes or hands; A non-contact aseptic manipulation system using a gaze, a gesture, or a voice, comprising a.

Images