JP2008040075A - Robot apparatus and control method of robot apparatus - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a robot apparatus and its operation control method improving a voice recognition rate. <P>SOLUTION: The robot apparatus includes: voice input and output paths A1 to A4 with priority set; a voice signal switching device 11 for switchably and selecting voice input and output paths A1 to A4 based on the priority; a voice recognition module 12 for recognizing input voice; a voice generation module 13 for generating voice based on the voice recognition result. The voice recognition module 12 includes: an S/N ratio determination section for determining whether or not the S/N ratio of the voice from the voice input and output paths is a predetermined threshold value or more; and a recognition ratio determination means for determining whether the voice recognition ratio of the voice is a predetermined threshold value or more. The voice signal switching device 11 includes a priority updating means for updating the priority of the voice input and output paths A2 to A4 having variable priority in voice input and output paths A1 to A4, based on a determination result of the S/N ratio determination means and the recognition ratio determination means. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to a robot apparatus that operates autonomously based on a voice recognition result and a method for controlling the robot apparatus.

  2. Description of the Related Art Conventionally, some autonomously moving robots use speech as a teaching signal, cause the robot to recognize speech, and perform operations such as movement based on the speech recognition result. However, with the current speech recognition technology, depending on the surrounding environment, speech recognition accuracy may not be improved, and speech may not be recognized or may be erroneously recognized. Therefore, it is necessary to sufficiently suppress background noise in order to improve the recognition rate. is there. Therefore, a technique for suppressing noise by signal processing using a microphone array or the like has been developed, but even in this case, the recognition rate is lowered only by being several meters away from the microphone. Thus, in order to give an appropriate instruction to the robot by voice regardless of the environment, there is a limit to performing voice recognition using only the microphone built in the robot.

  Therefore, if the robot's built-in microphone cannot recognize it, a separate microphone (hereinafter referred to as an external microphone) is installed around the robot to collect background noise or collect sound at a position away from the robot. It is possible. However, in this case, if the installation location of the external microphone is fixed, the movement range of the robot is limited, so that the operator's voice is wirelessly transmitted to the robot.

  However, if the robot's voice instruction is given only by the operator, the operator's voice input may be directly input to the robot by radio or the like. However, this method cannot accept voice input from other than the operator. Therefore, it is desirable to be able to recognize the voice of both the operator and the person near the robot, but conventionally there has not been established a means for switching between the voice signal transmitted wirelessly to the robot and the built-in microphone. Switching was done manually.

On the other hand, Patent Document 1 discloses a robot apparatus that performs voice recognition based on input from a built-in microphone and voice information received via wireless communication. In the robot apparatus described in Patent Document 1, in place of the voice content input from the receiving means for receiving the user's utterance content transmitted via wireless communication and the built-in microphone device incorporated in the robot device, or Voice recognition means for recognizing the utterance contents based on the voice information received from the receiving means is provided together with the voice contents. With this configuration, a robot apparatus is provided that can smoothly and naturally interact with a user.
Japanese Patent Laying-Open No. 2005-202075

  However, in the robot apparatus of Patent Document 1, when there are a plurality of built-in microphones, it is impossible to determine which built-in microphone should be used for voice recognition. For example, a selection method such as sequentially selecting and using the built-in microphone if the voice can be recognized can be considered, but if the optimum microphone can be determined and selected, the voice recognition rate can be improved.

  The present invention has been made in view of such circumstances, and an object of the present invention is to provide a robot apparatus and a control method thereof that can improve a speech recognition rate.

  The robot apparatus according to the present invention is a robot apparatus that operates autonomously based on a voice recognition result, wherein the first and second voice input means set with priority and the first or second based on the priority are set. Voice signal switching means for switching and selecting input from the second voice input means, and voice recognition means for recognizing voice input from the first or second voice input means switched and selected by the voice signal switching means And an action selection means for selecting an action based on the voice recognition result of the voice recognition means, wherein the voice signal switching means determines whether the signal-to-noise ratio of the voice from the voice input means is equal to or greater than a predetermined threshold value. Based on the determination result, the priority of the first voice input means and / or the second voice input means is updated.

  In the present invention, since the priority for selecting the voice input means is updated based on the signal-to-noise ratio (S / N ratio), it is possible to automatically select the voice input means having a good S / N ratio. it can.

  The robot apparatus according to the present invention is a robot apparatus that autonomously moves based on a voice recognition result, wherein the first and second voice input means set with priority and the first or second based on the priority are set. Voice signal switching means for switching and selecting input from the second voice input means, and voice recognition means for recognizing voice input from the first or second voice input means switched and selected by the voice signal switching means And an action selection means for selecting an action based on a voice recognition result of the voice recognition means, wherein the voice signal switching means determines whether or not the voice recognition rate of the voice from the voice input means is equal to or higher than a predetermined threshold value. The priority of the first voice input means and / or the second voice input means is updated based on the determination result.

  In the present invention, since the priority for selecting the voice signal input means is updated based on whether the voice recognition rate is good or not, it is possible to automatically select the voice input means to which the voice having a good voice recognition rate is input.

  The robot apparatus according to the present invention is a robot apparatus that autonomously moves based on a voice recognition result, wherein the first and second voice input means set with priority and the first or second based on the priority are set. Voice signal switching means for switching and selecting input from the second voice input means, and voice recognition means for recognizing voice input from the first or second voice input means switched and selected by the voice signal switching means An action selection unit that selects an action based on a voice recognition result of the voice recognition unit; and an S / N ratio determination that determines whether a signal-to-noise ratio of a voice from the voice input unit is equal to or greater than a predetermined threshold value And a recognition rate determination unit that determines whether or not a voice recognition rate of the voice from the voice input unit is equal to or greater than a predetermined threshold, and a determination result of the S / N ratio determination unit and the recognition rate determination unit Based on the first Those having a priority updating means for updating the priority of the voice input means and / or second audio input means.

  In the present invention, since the priority for selecting the voice input means is updated based on the quality of the S / N ratio and the quality of the voice recognition rate, it is possible to automatically select a voice input means having a high voice recognition rate. it can.

  Further, the priority update means can update the priority when the S / N ratio is less than a predetermined threshold and when the speech recognition rate is less than a predetermined threshold. It is possible to lower the priority of the voice input means having a low probability of voice recognition.

  Further, the first voice input means is a voice reception means for receiving a radio signal, and the second voice input means is one or a plurality of microphones, and the priority of the first voice input means. Is set higher than the initial value of the priority of the second voice input means. Thereby, at the time of initial setting, it is possible to always select an input by a radio signal.

  Furthermore, the priority set in the voice receiving means is a fixed value, and the priority update means is based on a signal-to-noise ratio and / or a voice recognition rate of voice signals input from the plurality of microphones. The priority set for the plurality of microphones can be updated within a range not exceeding the fixed value. Thus, for example, an important instruction can be sent by a radio signal that is always selected if there is an input.

  The priority set in the voice input means can be reset to the initial value when a reset signal is input or at a predetermined timing.

  A control method for a robotic device according to the present invention is a control method for a robotic device that moves autonomously based on a voice recognition result, and is based on the priority set in the first and second voice input means. Alternatively, a voice input selection step for switching and selecting an input from the second voice input means, a voice recognition step for recognizing a voice inputted from the first or second voice input means selected for switching, and the voice An action selection step of selecting an action based on a voice recognition result in the recognition step, wherein the voice input selection step determines whether or not the signal-to-noise ratio of the voice from the voice input means is greater than or equal to a predetermined threshold value. An S / N ratio determination step, and / or a recognition rate determination step of determining whether or not a voice recognition rate of the voice from the voice input means is equal to or higher than a predetermined threshold, and the S / N ratio determination step and / or Recognition rate judgment Based on the extent of the determination result and a priority updating step of updating the priority of the first audio input unit and / or second audio input means.

  In the present invention, the priority order for selecting one of a plurality of voice input means can be changed according to the S / N ratio or the recognition rate, and the one having a good S / N ratio or recognition rate is automatically selected. Can be selected.

  ADVANTAGE OF THE INVENTION According to this invention, the robot apparatus which can improve a speech recognition rate, and its operation | movement control method can be provided.

  Hereinafter, specific embodiments to which the present invention is applied will be described in detail with reference to the drawings. FIG. 1 is a perspective view showing a biped walking type robot according to an embodiment of the present invention. As shown in FIG. 1, in the robot 1, a head unit 1a, two left and right arm units 1b, and two right and left leg units 1d are connected to a predetermined position of the trunk unit 1c. In this embodiment, the robot is described as a biped walking type robot, but it may be a quadruped walking or the like, or the leg may be composed of wheels or the like.

  FIG. 2 is a block diagram showing the robot according to the present embodiment. The robot 1 includes a control unit 101, an input / output unit 102, a drive unit 103, a power supply unit 104, an external storage unit 105, and the like.

  The input / output unit 102 includes a camera 121 such as a CCD (Charge Coupled Device) for acquiring surrounding video, one or a plurality of built-in microphones 122 for collecting surrounding sounds, and outputs audio to the user. A speaker 123 for performing a dialogue and the like, an LED 124 for expressing a response to the user, emotions, and the like, a sensor unit 125 including a touch sensor, and the like are provided.

  The drive unit 103 includes a motor 131 and a driver 132 that drives the motor, and operates the leg unit 1d and the arm unit 1b according to a user instruction. The power supply unit 104 includes a battery 141 and a battery control unit 142 that controls discharging and charging thereof, and supplies power to each unit.

  The external storage unit 105 includes a removable HDD, an optical disk, a magneto-optical disk, and the like, stores various programs and control parameters, and stores the programs and data in a memory (not shown) in the control unit 101 as necessary. To supply.

  The control unit includes a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), a wireless communication interface, and the like, and controls various operations of the robot 1. And this control part 101 analyzes the image | video acquired by the speech recognition module 12 which performs speech recognition according to the control program stored, for example in ROM, the speech utterance module 13 which speaks to a user based on a recognition result, and the camera 121 The image recognition module 14 includes an action determination module 15 that selects an action to be taken based on various recognition results.

  Here, the robot 1 according to the present embodiment recognizes a voice such as a user or operator call and operates based on the voice recognition result. Next, the operation control method of the robot 1 according to the present embodiment will be described in detail.

  FIG. 3 is a block diagram showing only a portion related to speech recognition in the robot according to the present embodiment. As shown in FIG. 3, the robot 1 has a voice input / output path including a plurality of built-in microphones and speakers as an input / output unit as described above. That is, in this embodiment, the voice input / output path A2 using the front built-in microphone 21 and the speaker 22, the left built-in microphone 41 and the voice input / output path A3 using the speaker, and the right built-in microphone 51 and the speaker are used. There are three voice input / output paths A2 to A4 of the voice input / output path A4. Note that the number of voice input / output paths is not limited to three. Further, the robot 1 has a wireless LAN 31 and also has a voice input / output path A1 through which an operator can input voice from the outside via the wireless LAN 31.

  Further, the control unit 101 of the robot 1 has an audio signal switch 11 that selects which of these audio input / output paths A1 to A4 is used. The voice signal switching unit 11 selects any one of the voice input / output paths A1 to A4 and connects the path and the voice recognition module 12.

  In the present embodiment, a case will be described in which a customer inputs voice from the built-in microphones 21, 41, 51, and an operator inputs voice via the wireless LAN 31. The operator controls the wireless LAN 73 using, for example, a remote operation PC (Personal Computer) 71 having a microphone 74 and a speaker 75 and inputs a teaching signal to the robot 1. For example, the operator inputs voice information using a headset connected to the PC 71 for remote operation, input means such as a tie pin microphone and earphone, or inputs character information using an input means such as a keyboard. Thus, a teaching signal can be input to the robot 1. On the other hand, the robot 1 can interact with the customer using the built-in microphones 21, 41, 51 and the speakers 22, 42, 52.

  The voice signal switching unit 11 in the robot 1 selects one of the voice input / output paths A1 to A4 based on the priority set for each path A1 to A4. Here, in the present embodiment, the priority of the voice input / output path A1 through which voice is input via the wireless LAN 31 is fixed and set to the highest priority. On the other hand, the priorities of the voice input / output paths A2 to A4 by the built-in microphone are variable.

  FIG. 4 is a block diagram showing details of the voice signal switching unit 11 and the voice recognition module 12. As shown in FIG. 4, the audio signal switching unit 11 has a priority update unit 201 as shown in FIG. Update with

  The speech recognition module 12 includes an S / N ratio determination unit 211 and a speech recognition rate determination unit 212. The S / N ratio determination unit 211 determines the quality of the S / N ratio of the input voice. In addition, the voice recognition rate determination unit 212 determines whether the recognition rate of the input voice is good or bad. The priority update unit 201 updates the priorities of the voice input / output paths A2 to A4 based on the S / N ratio determination result of the S / N ratio determination unit 211 and the voice recognition rate determination result of the voice recognition rate determination unit 212. .

  If there is a voice input from the operator according to the priority set in this way, the voice input / output path A1 having a high priority is always selected even if there is a voice input from the customer at the same time. On the other hand, when there is no voice input from the operator and the customer talks to the robot 1, the voice input / output path with the highest priority at that time is selected from the voice input / output paths A2 to A4. Become. In this example, as an initial setting, the priority of the voice input / output path A2> the priority of the path A3> the priority of the path A4.

  Next, a priority update method will be described. First, as a first priority update method, there is a method of lowering the priority when the audio signal-to-noise ratio (S / N ratio) is less than a predetermined value. This is because if the S / N ratio is small, the probability of correctly recognizing the voice is low and there is a possibility that an accurate voice instruction cannot be performed. Therefore, the S / N ratio determination unit 211 of the voice recognition module 12 determines whether or not the S / N ratio of the input voice signal is less than a predetermined threshold, and notifies the priority update unit 201 of the result. To do. The priority update unit 201 resets the priority based on the determination result.

  Further, as a second priority update method, there is a method of lowering the priority when the recognition rate of voice recognition is equal to or lower than a predetermined threshold. As a speech recognition method, a known method such as a method using DP (Dynamic Programming) matching or a method using HMM (Hidden Markov Model) can be used. As the speech recognition rate, the likelihood calculated as a result of these probability models can be used. In this case, the speech recognition rate determination unit 212 of the speech recognition module 12 determines whether or not the speech recognition rate is less than a predetermined threshold, and notifies the priority update unit 201 of the result. The priority update unit 201 resets the priority based on the determination result.

  In the present embodiment, it is assumed that the voice signal switching unit 11 includes the priority update unit 201 and the voice recognition module 12 includes the S / N ratio determination unit 211 and the voice recognition rate determination unit 212. However, it goes without saying that a priority update unit, an S / N ratio determination unit, and a speech recognition rate determination unit may be provided separately.

  Next, the priority update method of the audio signal switch 11 will be described in detail with reference to FIG. FIG. 5 is a flowchart showing the priority update method according to the present embodiment. First, the initial priority of the voice input / output paths A1 to A4 is set in the voice signal switch 11 (step S1). At this time, as described above, the priority is set so that the voice input / output path A1 is preferentially selected when voices are input simultaneously. In this embodiment, since there are a plurality of voice input / output paths using the built-in microphone, the priority of these voice input / output paths is individually set.

  If there is a voice input (step S2: Yes), the voice input with the highest priority at this time is connected to the voice recognition module 12 (step S3). In the present embodiment, the priority of the voice input / output path A1 via the wireless LAN 31 is always highest, and the priority of the voice input / output paths A2 to A4 via the built-in microphone is the priority of the voice input / output path A1. It is updated within the range not exceeding. Therefore, when there is a voice input via the wireless LAN 31, even if the built-in microphone 21 or the like has a voice input, the input from the voice input / output path A1 by the wireless LAN 31 is supplied to the voice recognition module 12. That is, even when the robot 1 and the customer are interacting, the operator can intervene at any time. For example, during a dialogue between the robot 1 and the customer, if the robot 1 starts a dangerous operation by erroneously recognizing the customer's instruction, the operator can instruct the robot to stop the operation with a voice command. Further, when the background noise of the interaction environment between the robot and the customer is large and voice recognition fails, the operator can give an instruction on behalf of the customer.

  When there is a voice input, the S / N ratio determination unit 211 next determines whether or not the S / N ratio of the input voice information is equal to or greater than a predetermined threshold value. At this time, for example, when the S / N ratio is less than a predetermined threshold value, the input speech recognition may be stopped, and the speech utterance module 13 may utter the voice so as to be commanded again.

  When the S / N ratio is equal to or higher than the predetermined threshold (step S4: Yes), the voice recognition rate determination unit 212 determines whether or not the voice recognition rate is equal to or higher than the predetermined threshold. When the speech recognition rate, for example, the likelihood calculated as a result of the probability model is equal to or greater than a predetermined threshold, the speech utterance module 13 utters or otherwise shakes the hand based on the speech recognition result (Step S6).

  On the other hand, if there is no voice input (step S2: No), but a reset signal is input (step S7: Yes), the voice signal switch 11 sets the priority of the voice input / output paths A1 to A4 to the initial values. Reset it. Also, when there is a voice input, when the S / N ratio is less than a predetermined threshold (step S: No) and when the recognition rate is less than a predetermined threshold (step S5: No) If the priority of the voice input / output path is variable (step S9: Yes), the priority is lowered. If the priority is fixed, the process returns to step S2. By making the priority of the voice input / output paths A2 to A4 of the built-in speaker variable, the input / output path of the built-in microphone closest to the customer whose S / N ratio is good is automatically selected. Also, when the robot 1 is surrounded by the customers and asks the robot 1 with a good S / N ratio, the input / output path of the built-in microphone on the customer side having a high probability of the probability model, that is, the pronunciation that is easy to recognize Will be automatically selected.

  As described above, the priority update unit 201 of the audio signal switching unit 11 is likely to be erroneously recognized by lowering the priority of the input line when the S / N ratio of the input voice is small or the recognition rate is bad. , You can avoid selecting low quality voice input. Note that the updated priority is returned to the initial value by the input of the reset signal, but it is also possible to control the priority to the initial value when there is no voice input for a predetermined time.

  Next, a modification of the embodiment of the present invention will be described. In the robot 1 shown in FIG. 3, it has been described that the operator sends a voice instruction using a wireless LAN, but it is also possible to send a voice instruction using a mobile phone.

  FIG. 6 is a block diagram showing a main part related to the voice recognition of the robot according to the modification of the present embodiment. As shown in FIG. 6, the robot 1 includes a telephone 61 as communication means. Other configurations are the same as those of the first embodiment, and the same components are denoted by the same reference numerals and detailed description thereof is omitted.

  The operator can input a voice signal to the robot 1 via the mobile phone 81. As in the first embodiment, the audio signal switching unit 11 has an audio input path from the operator via the telephone 61 as the audio input / output path A1 having a fixed priority. Similarly to the above, the voice input / output paths A2 to A4 are provided by the built-in microphone and the speaker with variable priority, and the voice signal switch 11 switches the connection with the voice recognition module 12 according to the priority. Also in this modification, when there is an input from the telephone 61, the priority is set so as to preferentially select it. And the audio | voice signal switch 11 updates the priority of audio | voice input / output path | route A2-A4 based on the magnitude | size of an S / N ratio, and an audio | voice recognition rate.

  In the present embodiment, the priority of voice input by wireless communication is fixed and highest, and the voice input of a plurality of built-in microphones is appropriately selected according to the priority. In the case of erroneous recognition and malfunction, the operation can be immediately stopped or corrected by voice input through wireless communication. Further, among the plurality of built-in microphones, those having a good S / N ratio and those showing a good recognition rate are automatically selected according to the priority, so that the recognition rate can be improved.

  It should be noted that the present invention is not limited to the above-described embodiments, and various modifications can be made without departing from the scope of the present invention. For example, although the present embodiment has been described as having a speaker corresponding to each built-in microphone, the number of speakers may be one. Further, a plurality of front built-in microphones, right built-in microphones, and left built-in microphones may be provided, and priority may be set and updated for a plurality of front built-in microphones, right built-in microphones, and left built-in microphones. Furthermore, in this embodiment, the priority of the input / output path of the audio signal input via wireless communication is fixed, but may be variable.

1 is a perspective view showing a biped walking type robot according to an embodiment of the present invention. It is a block diagram which shows the robot concerning embodiment of this invention. FIG. 3 is a block diagram showing only a portion related to voice recognition in the robot according to the embodiment of the present invention. It is a block diagram which shows the detail of the audio | voice signal switcher and speech recognition module in the robot apparatus concerning embodiment of this invention. It is a flowchart which shows the priority update method concerning embodiment of this invention. It is a block diagram which extracts and shows the principal part in connection with the speech recognition of the robot concerning the modification of embodiment of this invention.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Robot 1a Head unit 1b Arm unit 1c Trunk unit 1d Leg unit 11 Voice signal switcher 12 Voice recognition module 13 Voice utterance module 14 Image recognition module 15 Action determination module 21, 41, 51 Built-in microphones 22, 42, 52, 75 Speaker 61 Telephone 74 Microphone 81 Mobile phone 101 Control unit 102 Input / output unit 103 Drive unit 104 Power supply unit 105 External storage unit 121 Camera 122 Built-in microphone 125 Sensor unit 131 Motor 132 Driver 141 Battery 142 Battery control unit 201 Priority update Unit 211 ratio determination unit 212 speech recognition rate determination unit

Claims (8)

A robot device that operates autonomously based on a voice recognition result,
First and second voice input means set with priority;
Voice signal switching means for switching and selecting input from the first or second voice input means based on the priority;
Voice recognition means for recognizing the voice input from the first or second voice input means selected by the voice signal switching means;
Action selection means for selecting an action based on the voice recognition result of the voice recognition means,
The voice signal switching means is configured to determine whether the signal-to-noise ratio of the voice from the voice input means is equal to or higher than a predetermined threshold value, and the first voice input means and / or the second voice input means. Robot device that updates the priority of the. A robot device that moves autonomously based on a voice recognition result,
First and second voice input means set with priority;
Voice signal switching means for switching and selecting input from the first or second voice input means based on the priority;
Voice recognition means for recognizing the voice input from the first or second voice input means selected by the voice signal switching means;
Action selection means for selecting an action based on the voice recognition result of the voice recognition means,
The voice signal switching means is configured to determine whether the voice recognition rate of the voice from the voice input means is greater than or equal to a predetermined threshold value based on a determination result of the first voice input means and / or the second voice input means. Robot device that updates priority. A robot device that moves autonomously based on a voice recognition result,
First and second voice input means set with priority;
Voice signal switching means for switching and selecting input from the first or second voice input means based on the priority;
Voice recognition means for recognizing the voice input from the first or second voice input means selected by the voice signal switching means;
An action selection means for selecting an action based on a voice recognition result of the voice recognition means;
S / N ratio determination means for determining whether or not the signal-to-noise ratio of the voice from the voice input means is equal to or greater than a predetermined threshold;
A recognition rate determination unit that determines whether or not a voice recognition rate of the voice from the voice input unit is equal to or greater than a predetermined threshold;
A robot apparatus comprising: a priority update unit that updates the priority of the first voice input unit and / or the second voice input unit based on determination results of the S / N ratio determination unit and the recognition rate determination unit. The priority update unit updates the priority when the S / N ratio is less than a predetermined threshold and when the speech recognition rate is less than a predetermined threshold. The robot apparatus described. The first voice input means is a voice reception means for receiving a radio signal, and the second voice input means is one or a plurality of microphones,
5. The robot according to claim 1, wherein an initial value of priority of the first voice input unit is set higher than an initial value of priority of the second voice input unit. apparatus. The priority set in the voice receiving means is a fixed value,
The priority update means is a range in which the priority set for the plurality of microphones does not exceed the fixed value based on the signal-to-noise ratio and / or the speech recognition rate of the audio signals input from the plurality of microphones. The robot apparatus according to claim 5, wherein the robot apparatus is updated by. The robot apparatus according to claim 5 or 6, wherein the priority set in the voice input unit is reset to the initial value when a reset signal is input or at a predetermined timing. A method for controlling a robot device that moves autonomously based on a speech recognition result,
A voice input selection step of switching and selecting the input from the first or second voice input means based on the priority set in the first and second voice input means;
A voice recognition step for recognizing a voice inputted from the first or second voice input means selected for switching;
An action selection step of selecting an action based on the voice recognition result in the voice recognition step,
The voice input selection step includes
S / N ratio determination step for determining whether or not the signal-to-noise ratio of the voice from the voice input means is equal to or greater than a predetermined threshold, and / or the voice recognition rate of the voice from the voice input means is a predetermined threshold A recognition rate determination step of determining whether or not
A priority update step of updating the priority of the first voice input means and / or the second voice input means based on the determination result of the S / N ratio determination step and / or the recognition rate determination step. Control method.

Images