Gesture judgment method

Abstract

The invention relates to a gesture judgment method, which comprises the following steps of: (S1) capturing a current image by an image capturing unit; (S2) the gesture recognition unit judges whether the image contains a hand image or not; (S3) when the judgment result of the step (S2) is yes, the gesture recognition unit judges whether the hand image is an effective gesture or not; (S4) when the judgment result of the step (S3) is yes, recording a plurality of positions corresponding to a plurality of fingers of the palm and a plurality of pieces of coordinate information thereof by the gesture recognition unit; (S5) the gesture recognition unit obtains the palm orientation according to the hand image; (S6) the gesture recognition unit calculates the palm width according to the hand image and calculates a dynamic displacement threshold value according to the palm width; (S7) the gesture recognition unit judges whether to start an action command or not according to the palm width, the dynamic displacement threshold value and a judgment condition; and (S8) when the judgment result of the step (S7) is yes, starting an action command.

Description

Technical Field

[0001] This case belongs to the field of gesture judgment, and in particular, refers to a gesture judgment method. Background Art

[0002] Mobile devices are usually controlled by touching the screen or by voice control. In addition to the above two methods, more and more functions are controlled by gestures to control the mobile devices, making it more convenient for users to use.

[0003] Traditional mobile devices use fixed gesture displacement thresholds to judge gestures. However, the offset of gestures will vary depending on the distance between the user and the camera of the mobile device. Therefore, for users at different distances, the same gesture may obtain different offsets and cannot correspond to the gesture displacement threshold, resulting in inaccurate gesture recognition by traditional mobile devices. Furthermore, traditional mobile devices may produce gesture misjudgments. For example, when a user slides his palm to the right, the palm shifts to the left after returning to the initial position, causing the traditional mobile device to misjudge that the user has performed a left sliding gesture. What's worse, when the user's palm moves out of the camera field of view of the traditional mobile device, the traditional mobile device no longer processes the trajectory information of the previous gesture, that is, ignores the trajectory of the previous palm movement, which may cause the user's gesture to be ignored, resulting in an inability to correctly control the mobile device.

[0004] Therefore, how to develop a gesture determination method is an urgent issue in this field. Summary of the invention

[0005] The purpose of this case is to provide a gesture judgment method to solve the defects of traditional mobile devices, such as inaccurate gesture recognition, gesture misjudgment, and the inability to correctly control the mobile device due to the palm moving out of the camera field of view of the traditional mobile device.

[0006] To achieve the above-mentioned purpose, an embodiment of the present case is a gesture determination method, which is suitable for a mobile device. The mobile device includes an image capture unit, a gesture recognition unit and a storage unit. The gesture determination method includes: (S1) the image capture unit captures an image frame within the current field of view; (S2) the gesture recognition unit determines whether the image frame includes a hand image of a palm; (S3) when the judgment result of step (S2) is yes, the gesture recognition unit determines whether the hand image is a valid gesture; (S4) when the judgment result of step (S3) is yes, the gesture recognition unit records multiple positions and multiple coordinate information corresponding to multiple fingers of the palm presented in the current hand image in a finger list, and stores them in the storage unit; (S5) the gesture recognition unit obtains the palm orientation according to the hand image; (S6) The gesture recognition unit calculates the palm width based on the hand image, and calculates the dynamic displacement threshold based on the palm width; (S7) The gesture recognition unit determines whether to start the action command based on the dynamic displacement threshold and the judgment condition, and re-executes step (S1) when the judgment result is no; (S8) When the judgment result of step (S7) is yes, start the action command and re-execute step (S1), and when the judgment result of step (S7) is no, re-execute step (S1); and (S9) When the judgment result of step (S2) is no or the judgment result of step (S3) is no, confirm whether the record of coordinate information in the finger list is empty, and re-execute step (S1) when the judgment result is yes, and execute step (S7) when the judgment result is no. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 This is a flowchart of the steps of the gesture determination method of the preferred embodiment of the present invention;

[0008] Figure 2 for Figure 1 A schematic diagram of the structure of a mobile device to which the gesture determination method is applied;

[0009] Figure 3 for Figure 2 The schematic diagram of obtaining the position coordinates of each finger of the palm is shown;

[0010] Figure 4 for Figure 1 The step flow chart of the sub-steps of step S6 shown;

[0011] Figure 5A-Figure 5B for Figure 1 The step flow chart of the judgment condition in step S7 is shown.

[0012] The reference numerals are described as follows:

[0013] 1: Mobile device

[0014] 2: Image capture unit

[0015] 3: Gesture recognition unit

[0016] 4: Storage unit

[0017] S1~S9: Steps of gesture judgment method

[0018] F1: Thumb

[0019] F2: Index finger

[0020] F3: Middle finger

[0021] F4: Ring finger

[0022] F5: Little finger

[0023] Fa: First fingertip

[0024] Fb: first knuckle

[0025] Fc: second knuckle

[0026] Fd: third finger joint

[0027] Fe: Second fingertip

[0028] Ff: fourth knuckle

[0029] Fg: fifth finger joint

[0030] Fh: Sixth knuckle

[0031] Fi: Third fingertip

[0032] Fj: Seventh knuckle

[0033] Fk: Eighth knuckle

[0034] Fl: ninth knuckle

[0035] Fm: fourth fingertip

[0036] Fn: tenth knuckle

[0037] Fo: Eleventh knuckle

[0038] Fp: 12th finger joint

[0039] Fq: fifth fingertip

[0040] Fr: Thirteenth finger joint

[0041] Fs: Fourteenth knuckle

[0042] Ft: Fifteenth knuckle

[0043] F6: Wrist endpoint

[0044] S60-S61: Sub-steps of step S6

[0045] S70~S80: Steps for judging conditions DETAILED DESCRIPTION

[0046] Some typical embodiments that embody the features and advantages of the present invention will be described in detail in the following description. It should be understood that the present invention can have various variations in different aspects without departing from the scope of the present invention, and the descriptions and drawings are essentially for illustrative purposes rather than for limiting the present invention.

[0047] See also Figure 1 and Figure 2 ,in Figure 1 This is a flow chart of the steps of the gesture determination method of the preferred embodiment of the present invention. Figure 2 for Figure 1 The structure diagram of the mobile device to which the gesture determination method is applied is shown in FIG. Figure 1 and Figure 2 As shown, the gesture judgment method of this case can be applied to Figure 2 In the mobile device 1 shown, the mobile device 1 may be but not limited to a mobile phone or a tablet, etc., and the mobile device 1 includes an image capture unit 2, a gesture recognition unit 3 and a storage unit 4. The image capture unit 2 may be but not limited to a camera, which is used to capture at least one image frame within the current field of view. The gesture recognition unit 3 communicates with the image capture unit 2 to perform hand image recognition of the user's palm for each image frame captured by the image capture unit 2. In some embodiments, the gesture recognition unit 3 uses the Mediapipe library to obtain the position coordinates of each finger of the palm. The storage unit 4 may be but not limited to a memory, which is used to communicate with the gesture recognition unit 3 and provide data storage functions.

[0048] The gesture judgment method of this case includes the following steps.

[0049] In step S1 , the image capturing unit 2 captures image frames within a current field of view.

[0050] In step S2 , the gesture recognition unit 3 determines whether the image frame captured by the image capture unit 2 includes a hand image of a palm.

[0051] Step S3 , when the determination result of step S2 is yes, the gesture recognition unit 3 determines whether the hand image is a valid gesture.

[0052] Step S4, when the judgment result of step S3 is yes, the gesture recognition unit 3 records the multiple positions corresponding to the multiple fingers of the palm presented by the current hand image and the multiple coordinate information and time information in the finger list, and stores the finger list in the storage unit 4. In some embodiments, each coordinate information may include three-dimensional coordinates of X-axis coordinate, Y-axis coordinate and Z-axis coordinate information, and the time information may be a timestamp.

[0053] In step S5 , the gesture recognition unit 3 obtains the palm direction according to the hand image.

[0054] In step S6, the gesture recognition unit 3 calculates the palm width according to the hand image, and calculates the dynamic displacement threshold according to the palm width. Since the distance between the user and the image capture unit 2 of the mobile device 1 is not fixed, and the palm sizes of different users are also different, through step S6, the appropriate dynamic displacement threshold can be dynamically calculated according to the distance between the user and the image capture unit 2 of the mobile device 1 (the farther the distance, the smaller the palm width; conversely, the closer the distance, the larger the palm width) and the palm size. In some embodiments, the larger the palm width, the larger the dynamic displacement threshold. Conversely, the smaller the palm width, the smaller the dynamic displacement threshold.

[0055] In step S7, the gesture recognition unit 3 determines whether to activate the motion command according to the palm direction, the dynamic displacement threshold and the judgment condition, and re-executes step S1 if the judgment result is no. In some embodiments, when the motion command is activated, the application in the mobile device 1 can be run.

[0056] Step S8: When the judgment result of step S7 is yes, start the action command.

[0057] Step S9, when the judgment result of step S2 is no or the judgment result of step S3 is no, confirm whether the record of coordinate information in the finger list is empty, and re-execute step S1 when the judgment result is yes, and execute step S7 when the judgment result is no.

[0058] As can be seen from the above, since the gesture recognition method of this case determines the palm direction of the hand and calculates the dynamic displacement threshold according to the palm width of the palm, and then determines whether to start the action command based on the palm direction, dynamic displacement threshold and judgment conditions, this can make the mobile device more accurate in gesture recognition.

[0059] See also Figure 3 , which is for Figure 2Schematic diagram of obtaining the position coordinates of each finger of the palm. In some embodiments, the gesture recognition unit 3 can recognize the thumb F1, index finger F2, middle finger F3, ring finger F4, little finger F5 and wrist endpoint F6 of the palm, and divide the thumb F1 into multiple positions, the multiple positions of the thumb include the first fingertip Fa, the first knuckle Fb, the second knuckle Fc and the third knuckle Fd from top to bottom, divide the index finger F2 into multiple positions, the multiple positions of the index finger include the second fingertip Fe, the fourth knuckle Ff, the fifth knuckle Fg and the sixth knuckle Fh from top to bottom, and divide the middle finger F The middle finger F3 is divided into multiple positions, the multiple positions of the middle finger F3 include the third fingertip Fi, the seventh knuckle Fj, the eighth knuckle Fk and the ninth knuckle Fl from top to bottom, the ring finger F4 is divided into multiple positions, the multiple positions of the ring finger F4 include the fourth fingertip Fm, the tenth knuckle Fn, the eleventh knuckle Fo and the twelfth knuckle Fp from top to bottom, the little finger F5 is divided into multiple positions, the multiple positions of the little finger F5 include the fifth fingertip Fq, the thirteenth knuckle Fr, the fourteenth knuckle Fs and the fifteenth knuckle Ft from top to bottom.

[0060] In some embodiments, in step S3, the gesture recognition unit 3 determines whether the bending angle of the fifth finger joint Fg is less than a preset threshold, and determines whether the bending angle of the eighth finger joint Fk is less than a preset threshold. When the bending angle of the fifth finger joint Fg is less than the preset threshold and the bending angle of the eighth finger joint Fk is less than the preset threshold, the gesture recognition unit 3 determines that the hand image is a valid gesture. On the contrary, when the bending angle of the fifth finger joint Fg is equal to or greater than the preset threshold and the bending angle of the eighth finger joint Fk is equal to or greater than the preset threshold, it means that the index finger and the middle finger of the palm are over-bent, so the gesture recognition unit 3 determines that the hand image is not a valid gesture.

[0061] In some embodiments, in step S5 , the gesture recognition unit 3 determines the palm direction according to the relative positions of the index finger F2 and the middle finger F3 .

[0062] Since the palm may be tilted instead of facing upward, downward, leftward or rightward, in some embodiments, in step S5, the gesture recognition unit 3 selects one of the second fingertip Fe, the fourth finger joint Ff, the fifth finger joint Fg and the sixth finger joint Fh of the index finger F2 as the first selection point, and the gesture recognition unit 3 selects one of the third fingertip Fi, the seventh finger joint Fj, the eighth finger joint Fk and the ninth finger joint Fl of the middle finger F3 as the second selection point, and the position of the first selection point on the index finger F2 corresponds to the position of the second selection point on the middle finger F3. Position, for example, if the first selection point is the second fingertip Fe, then the second selection point corresponds to the third fingertip Fi, and the gesture recognition unit 3 subtracts the X-axis coordinate in the coordinate information corresponding to the first selection point from the X-axis coordinate in the coordinate information corresponding to the second selection point to obtain the X-axis coordinate deviation value. The gesture recognition unit 3 also subtracts the Y-axis coordinate in the coordinate information corresponding to the first selection point from the Y-axis coordinate in the coordinate information corresponding to the second selection point to obtain the Y-axis coordinate deviation value, and determines the palm direction according to the X-axis coordinate deviation value and the Y-axis coordinate deviation value.

[0063] In some embodiments, in step S5, when the X-axis coordinate deviation value is a positive value, and the absolute value of the X-axis coordinate deviation value is greater than the absolute value of the Y-axis coordinate deviation value, the gesture recognition unit 3 determines that the palm is facing upward. When the X-axis coordinate deviation value is a negative value, and the absolute value of the X-axis coordinate deviation value is greater than the absolute value of the Y-axis coordinate deviation value, the gesture recognition unit 3 determines that the palm is facing downward. When the Y-axis coordinate deviation value is a positive value, and the absolute value of the Y-axis coordinate deviation value is greater than the absolute value of the X-axis coordinate deviation value, the gesture recognition unit 3 determines that the palm is facing left, and when the Y-axis coordinate deviation value is a negative value, and the absolute value of the Y-axis coordinate deviation value is greater than the absolute value of the X-axis coordinate deviation value, the gesture recognition unit 3 determines that the palm is facing right.

[0064] See also Figure 4 , which is for Figure 1 The step flow chart of the sub-steps of step S6 is shown. In some embodiments, step S6 further includes the following sub-steps.

[0065] In step S60 , the gesture recognition unit 3 uses the coordinate information corresponding to the sixth joint Fh of the index finger F2 and the coordinate information corresponding to the fifteenth joint Ft of the little finger F5 to calculate the distance between the two to obtain the palm width.

[0066] In step S61 , the gesture recognition unit 3 calculates the dynamic displacement threshold value by multiplying the palm width by the preset adjustable multiple, wherein the preset adjustable multiple is not a fixed value and can be adjusted according to actual needs.

[0067] See also Figure 5A-Figure 5B , which is for Figure 1The step flow chart of the determination condition in step S7 is shown. In some embodiments, the determination condition in step S7 includes the following steps.

[0068] In step S70, the gesture recognition unit 3 compares the difference between the last and the second to last coordinate information corresponding to the multiple coordinate information recorded in the finger list to determine whether the palm orientation is the same as the palm movement direction. In step S70, the palm movement direction is estimated by using the difference between one of the multiple coordinate information recorded in the last time in the finger list and the corresponding coordinate information in the multiple coordinate information recorded in the second to last time in the finger list.

[0069] Step S71 , when the determination result of step S70 is yes, the reverse flag (ReverseFlag) is set to false (SetReverseFlag=False) and recorded in the storage unit 4 .

[0070] In step S72 , the gesture recognition unit 3 determines whether the palm is still within the field of view of the image capture unit 2 according to the currently captured image frame.

[0071] Step S73, when the judgment result of step S72 is yes, the gesture recognition unit 3 calculates the displacement speed of the palm movement by using the time difference obtained from the multiple coordinate information and time information recorded for the last N times in the finger list, where N is an integer greater than 2.

[0072] Step S74, determining whether the displacement speed of the palm is greater than a speed threshold, and when the determination result is yes, it means that the gesture action is not completed, so step S1 is executed again.

[0073] In some embodiments, the determination condition in step (S7) further includes the following steps.

[0074] Step S75, when the judgment result of step S72 is no (i.e., the palm leaves the range of the image capture unit 2) or the judgment result of step S74 is no (i.e., the palm displacement speed is less than the speed threshold), the total unidirectional displacement of the palm movement is calculated from the first and last recorded multiple coordinate information in the finger list. In some embodiments, the total unidirectional displacement of the palm movement can be calculated from the coordinates of a specific dimension in the first and last recorded multiple coordinate information in the finger list, such as the X-axis coordinate or the Y-axis coordinate.

[0075] Step S76, clearing the information in the finger list stored in the storage unit 4. In step S76, all the coordinate information recorded in the finger list at any time will be cleared.

[0076] Step S77, determine whether the unidirectional total displacement is greater than the dynamic displacement threshold. When the determination result is yes, execute step S8; when the determination result is no, re-execute step S1.

[0077] In some embodiments, the determination condition in step (S7) further includes the following steps.

[0078] Step S78, determine whether the reverse change setting is true.

[0079] Step S79, when the judgment result of step S78 is negative, the reverse flag is set to true (Set ReverseFlag=True), and step S75 is executed.

[0080] Step S80: When the judgment result of step S78 is yes, the information in the finger list stored in the storage unit 4 is cleared, and step S1 is executed again.

[0081] From the step flow of the judgment condition in the above step S7, it can be known that there are three situations for executing step S8, which are described as follows. The first situation is that the user's palm pauses during the movement, but the previous displacement speed of the palm is greater than the speed threshold, and the total unidirectional displacement is also greater than the dynamic displacement threshold. The second situation is that the user's palm exceeds the field of view of the image capture unit 2, but the previous displacement speed of the palm is greater than the speed threshold, and the total unidirectional displacement is also greater than the dynamic displacement threshold. The third situation is that the user's palm begins to change from forward movement to reverse movement, and the total unidirectional displacement is also greater than the dynamic displacement threshold.

[0082] In summary, the present invention provides a gesture judgment method and a mobile device. The gesture judgment method judges the direction of the palm and calculates the dynamic displacement threshold according to the width of the palm. Then, the method judges whether to start the action command according to the direction of the palm, the dynamic displacement threshold and the judgment conditions. In this way, the mobile device can recognize gestures more accurately. In addition, the gesture judgment method of the present invention does not use a fixed gesture displacement threshold to judge whether the user has completed an action, but also considers whether the direction of the palm is the same as the direction of the palm movement and whether the displacement speed of the palm is greater than the speed threshold. Therefore, it is not easy to misjudge the gesture. What's more, when the user's palm moves out of the field of view of the image capture unit 2 of the mobile device, the gesture judgment method of the present invention will still judge whether the user has completed the gesture according to the previous displacement speed of the palm and the total displacement in one direction. Therefore, it can avoid the gesture used by the user from being ignored. In this way, the user can correctly control the mobile device.

Claims

1. A gesture determination method, suitable for a mobile device, the mobile device comprising an image capture unit, a gesture recognition unit and a storage unit, the gesture determination method comprising: (S1) The image capture unit captures an image frame within the current field of view; (S2) the gesture recognition unit determines whether the image frame includes a hand image of a palm; (S3) When the determination result of step (S2) is yes, the gesture recognition unit determines whether the hand image is a valid gesture; (S4) When the judgment result of step (S3) is yes, the gesture recognition unit records the multiple positions and multiple coordinate information corresponding to the multiple fingers of the palm presented by the current hand image in a finger list, and stores them in the storage unit; (S5) the gesture recognition unit obtains a palm direction according to the hand image; (S6) the gesture recognition unit calculates a palm width according to the hand image, and calculates a dynamic displacement threshold according to the palm width; (S7) the gesture recognition unit determines whether to initiate an action command according to the dynamic displacement threshold value and a determination condition, and re-executes step (S1) when the determination result is no; (S8) when the judgment result of step (S7) is yes, start the action command and re-execute step (S1); when the judgment result of step (S7) is no, re-execute step (S1); and (S9) When the judgment result of step (S2) is no or the judgment result of step (S3) is no, confirm whether the record of the coordinate information in the finger list is empty, and re-execute step (S1) when the judgment result is yes, and execute step (S7) when the judgment result is no.

2. The gesture determination method as claimed in claim 1, wherein the gesture recognition unit recognizes that the multiple fingers include a thumb, an index finger, a middle finger, a ring finger, a little finger and a wrist endpoint, and the multiple positions of the thumb include a first fingertip, a first knuckle, a second knuckle and a third knuckle from top to bottom, the multiple positions of the index finger include a second fingertip, a fourth knuckle, a fifth knuckle and a sixth knuckle from top to bottom, the multiple positions of the middle finger include a third fingertip, a seventh knuckle, an eighth knuckle and a ninth knuckle from top to bottom, the multiple positions of the ring finger include a fourth fingertip, a tenth knuckle, an eleventh knuckle and a twelfth knuckle from top to bottom, and the multiple positions of the little finger include a fifth fingertip, a thirteenth knuckle, a fourteenth knuckle and a fifteenth knuckle from top to bottom.

3. The gesture judgment method as described in claim 2, wherein in the step (S3), the gesture recognition unit determines whether the bending angle of the fifth knuckle is less than a preset threshold, and determines whether the bending angle of the eighth knuckle is less than the preset threshold; when the bending angle of the fifth knuckle is less than the preset threshold and the bending angle of the eighth knuckle is less than the preset threshold, the gesture recognition unit determines that the hand image is a valid gesture; when the bending angle of the fifth knuckle is equal to or greater than the preset threshold and the bending angle of the eighth knuckle is equal to or greater than the preset threshold, the gesture recognition unit determines that the hand image is an invalid gesture.

4. The gesture determination method as claimed in claim 2, wherein in step (S5), the gesture recognition unit determines the direction of the palm according to the relative positions of the index finger and the middle finger.

5. The gesture determination method as claimed in claim 4, wherein in the step (S5), the gesture recognition unit selects one of the second fingertip, the fourth knuckle, the fifth knuckle and the sixth knuckle of the index finger as a first selection point, and the gesture recognition unit selects one of the third fingertip, the seventh knuckle, the eighth knuckle and the ninth knuckle of the middle finger as a second selection point, the position of the first selection point on the index finger corresponds to the position of the second selection point on the middle finger, and the gesture recognition unit subtracts the X-axis coordinate in the coordinate information corresponding to the first selection point from the X-axis coordinate in the coordinate information corresponding to the second selection point to obtain an X-axis coordinate deviation value, the gesture recognition unit subtracts the Y-axis coordinate in the coordinate information corresponding to the first selection point from the Y-axis coordinate in the coordinate information corresponding to the second selection point to obtain a Y-axis coordinate deviation value, and determines the palm orientation according to the X-axis coordinate deviation value and the Y-axis coordinate deviation value.

6. The gesture determination method as claimed in claim 5, wherein in the step (S5), when the X-axis coordinate deviation value is a positive value and the absolute value of the X-axis coordinate deviation value is greater than the absolute value of the Y-axis coordinate deviation value, the gesture recognition unit determines that the palm is facing upward; when the X-axis coordinate deviation value is a negative value and the absolute value of the X-axis coordinate deviation value is greater than the absolute value of the Y-axis coordinate deviation value, the gesture recognition unit determines that the palm is facing downward; when the Y-axis coordinate deviation value is a positive value and the absolute value of the Y-axis coordinate deviation value is greater than the absolute value of the X-axis coordinate deviation value, the gesture recognition unit determines that the palm is facing left; when the Y-axis coordinate deviation value is a negative value and the absolute value of the Y-axis coordinate deviation value is greater than the absolute value of the X-axis coordinate deviation value, the gesture recognition unit determines that the palm is facing right.

7. The gesture determination method as claimed in claim 5, wherein in step (S6), further comprising the following sub-steps: (S60) the gesture recognition unit calculates the palm width by using the distance between the coordinate information corresponding to the sixth knuckle of the index finger and the coordinate information corresponding to the fifteenth knuckle of the little finger; and (S61) The gesture recognition unit calculates the dynamic displacement threshold using the product of the palm width and a preset adjustable multiple.

8. The gesture determination method as claimed in claim 1, wherein the determination condition in step (S7) comprises the following steps: (S70) the gesture recognition unit compares the difference between the coordinate information corresponding to the last and the second to last coordinate information recorded in the finger list to determine whether the palm direction is the same as a moving direction of the palm; (S71) when the determination result of step (S70) is yes, a reverse variable is set to false and recorded in the storage unit; (S72) the gesture recognition unit determines whether the palm is still within the field of view of the image capture unit according to the currently captured image frame; (S73) When the determination result of step (S72) is yes, the gesture recognition unit calculates a displacement speed of the palm movement using the multiple coordinate information recorded for the last N times in the finger list, where N is an integer greater than 2, and N corresponds to the number of frames per second that can be captured by the image capture unit; and (S74) Determine whether the displacement speed of the palm is greater than a speed threshold, and when the determination result is yes, re-execute step (S1).

9. The gesture determination method as claimed in claim 8, wherein the determination condition in step (S7) comprises the following steps: (S75) when the judgment result of step (S72) is no or the judgment result of step (S74) is no, calculating a total displacement of the palm in one direction based on the plurality of coordinate information recorded each time in the finger list; (S76) clearing the information in the finger list stored in the storage unit; and (S77) Determine whether the unidirectional total displacement is greater than the dynamic displacement threshold. When the judgment result is yes, execute step (S8) to start the action command. When the judgment result is no, re-execute step (S1).

10. The gesture determination method as claimed in claim 9, wherein the determination condition in step (S7) comprises the following steps: (S78) determining whether the reverse variable setting is true; (S79) When the result of the judgment in step (S78) is negative, the inversion variable is set to true, and step (S75) is executed; and (S80) When the judgment result of step (S78) is yes, the information in the finger list stored in the storage unit is cleared and step (S1) is executed again.

Images