Word recognition device
The device ensures character recognition reflects user intent by deleting unwanted image data before stabilizing, preventing recognition of unintended characters.
Patent Information
- Application Number
- JP2022141408
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2022-09-06
- Publication Date
- 2025-12-04
- Estimated Expiration
- 2042-09-06
AI Technical Summary
Character recognition devices that continuously output image data risk recognizing characters different from the user's intended characters due to image data captured before achieving a stationary state.
The device includes an operation unit, camera, measurement unit, deletion unit, and output control unit to delete image data stored before the device stabilizes, ensuring character recognition is performed only on intended data.
Prevents recognition of unintended characters by deleting unwanted image data and allowing character recognition to reflect the user's intended input effectively.
Smart Images

Figure 0007780090000001 
Figure 0007780090000002 
Figure 0007780090000003
Abstract
Description
[Technical Field]
[0001] This specification discloses a technique related to a character recognition device that performs character recognition on image data. [Background technology]
[0002] Patent Document 1 discloses a character recognition device that includes a character recognition unit that recognizes characters in captured image data and a still state detection unit that detects a still state. In the character recognition device, the detection of a still state is set as one of the conditions for starting character recognition. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2010-217997 Summary of the Invention [Problem to be solved by the invention]
[0004] For example, a camera that continuously outputs image data is considered. If this camera is used in the character recognition device of Patent Document 1, multiple pieces of image data are stored in the character recognition device. Therefore, there is a risk that character recognition will be performed on image data captured before the device was in a stationary state, among the multiple pieces of image data stored in the character recognition device. In this case, there is a risk that characters different from those intended by the user will be recognized. This specification provides a technology for preventing characters different from those intended by the user from being recognized in a configuration in which a camera continuously outputs image data. [Means for solving the problem]
[0005] The character recognition device disclosed in this specification may include an operation unit, a camera that starts operating in response to the operation unit receiving a predetermined first instruction from a user, a memory that stores image data continuously output from the camera while the camera is operating, a measurement unit that measures an attitude value that indicates a fluctuation in the attitude of the character recognition device, an output unit, a deletion unit that deletes a plurality of pieces of image data stored in the memory between a first timing when the operation unit receives the first instruction from the user and a second timing when the attitude value indicates that the fluctuation in the attitude has stopped, a character recognition execution unit that executes character recognition on at least one piece of image data stored in the memory after the second timing, and an output control unit that causes the output unit to output data that indicates a result of the character recognition.
[0006] Image data stored in memory before the shaking in the attitude of the character recognition device stops may be image data contrary to the user's intention. According to the above configuration, multiple pieces of image data that may be contrary to the user's intention between the first timing and the second timing are deleted from the memory. Character recognition is not performed on image data stored in memory before the shaking in the attitude of the character recognition device stops. In a configuration in which the camera continuously outputs image data, it is possible to prevent characters different from those intended by the user from being recognized.
[0007] In the character reading device described above, the operation unit may receive a predetermined second instruction after the first instruction, and in this case, the character recognition execution unit may execute the character recognition on the at least one image data stored in the memory after the operation unit receives the second instruction.
[0008] With this configuration, the user can activate the camera with a first instruction and execute character recognition with a second instruction, which allows the user's intention to be reflected in the character recognition target more effectively than in the comparative example where there is no second instruction.
[0009] In the character recognition device described above, the output control unit may output the data to the output unit when the posture value indicates that the posture fluctuation has stopped after the second instruction. In this case, the output control unit may not output the data to the output unit when the posture value does not indicate that the posture fluctuation has stopped.
[0010] If the posture of the character recognition device fluctuates after receiving the second instruction from the user, character recognition may be performed on a character contrary to the user's intention. By not outputting data to the output unit when the posture value does not indicate that the posture fluctuation has stopped, it is possible to prevent data for a character different from the character intended by the user from being output to the output unit.
[0011] The character recognition device may further include an image comparison unit that compares first image data stored in the memory from the second timing to a third timing at which the operation unit accepts the second instruction with second image data stored in the memory after the third timing. In this case, the character recognition execution unit may execute the character recognition on at least one of the first image data and the second image data when the first image data and the second image data are similar, or may execute the character recognition on the second image data when the first image data and the second image data are not similar.
[0012] If the first image data and the second image data are not similar, it is assumed that the user intends to perform character recognition on the second image data rather than the first image data. With this configuration, by comparing the first image data and the second image data, it is possible to appropriately perform character recognition on the image data intended by the user, out of the first image data and the second image data.
[0013] In the character recognition device described above, the character recognition may include a first recognition process for extracting character image data from image data and a second recognition process for performing the character recognition on the extracted character image data. In this case, the character recognition device may further include an image comparison unit that compares first image data stored in the memory between the second timing and a third timing at which the operation unit accepts the second instruction with second image data stored in the memory after the third timing. The character recognition execution unit may perform the first recognition process on the first image data between the second timing and the third timing, and if the first image data and the second image data are similar, perform the second recognition process on the first image data on which the first recognition process has been performed. If the first image data and the second image data are not similar, perform both the first recognition process and the second recognition process on the second image data.
[0014] If the first image data and the second image data are similar, it is presumed that the user intends to perform character recognition on the first image data. With this configuration, if both image data are similar to each other, the second recognition process is performed on the first image data on which the first recognition process has already been performed, so that character recognition can be performed quickly on the first image data. On the other hand, if the both image data are not similar to each other, it is possible to appropriately perform character recognition on the second image data on which it is presumed that the user intends to perform character recognition.
[0015] In the character recognition device described above, the first instruction may be an action of pressing a predetermined button included in the operation unit, and the second instruction may be an action of releasing a finger from the button that was pressed by the first instruction.
[0016] According to this configuration, the user's operation can be simplified compared to the comparative example in which the button is pressed twice, for example.
[0017] The character recognition device described above may further include an operation execution unit that executes a predetermined notification operation when the posture value indicates that the posture fluctuation has stopped.
[0018] With this configuration, the user can recognize that the shaking of the character recognition device's posture has stopped by the predetermined notification action.
[0019] The character recognition device may further include a display unit that displays the at least one image data, and in this case, the notification action may include an action of displaying, on the display unit after the second timing, a highlight line that highlights a character included in the at least one image data.
[0020] With this configuration, the user can see the highlighted lines and recognize the characters that are the subject of character recognition.
[0021] The character recognition device may further include an irradiation unit that irradiates an indication marker to indicate a character to be recognized, and an irradiation control unit that causes the irradiation unit to irradiate the indication marker when the operation unit receives the first instruction as a trigger.
[0022] With this configuration, the user adjusts the posture of the character recognition device before the indicator marker points to the target character. While the posture is being adjusted, the posture of the character recognition device is likely to fluctuate. For this reason, in a character recognition device that irradiates an indicator marker, it is presumed that the image data stored in memory between the first timing and the second timing does not reflect the user's intention. The technology disclosed in this specification is particularly useful for a character recognition device having such a configuration.
[0023] In the above-mentioned character reading device, the illumination control unit may change the display mode of the indication marker from a first mode to a second mode different from the first mode when the posture value indicates that the posture fluctuation has stopped.
[0024] With this configuration, the user can see the indication marker changed to the second mode and recognize that the shaking of the attitude of the character recognition device has stopped.
[0025] The above-mentioned character recognition device may further include a character recognition stopping unit that stops the character recognition if the character recognition is not completed within a predetermined time, and a stop notification unit that notifies the user that the character recognition has been stopped.
[0026] With this configuration, it is possible to notify the user that character recognition has been stopped.
[0027] Furthermore, the above-described control method for the character recognition device, the computer program for the character recognition device, and the storage medium for storing the computer program are also novel and useful. [Brief explanation of the drawings]
[0028] [Figure 1] 1 shows a perspective view of an information reading terminal according to a first embodiment. [Figure 2] 1 shows a configuration diagram of an information reading terminal according to a first embodiment. [Figure 3] 1 shows a flowchart of image recognition processing in a first embodiment. [Figure 4] FIG. 10 shows a flowchart of image recognition processing according to a second embodiment. DETAILED DESCRIPTION OF THE INVENTION
[0029] (First Example) (Configuration of information reading terminal 10; Figures 1 and 2) The information reading terminal 10 shown in FIG. 1 is a portable terminal device having multiple functions for reading information. The multiple functions include a function for reading information recorded in an information code, a function for reading information stored in a storage medium, and a character recognition function for recognizing characters displayed on a print medium such as paper. The information code may be, for example, a two-dimensional code or a barcode. The storage medium may be, for example, an IC chip or an RFID. The character recognition function is realized, for example, by OCR (Optical Character Recognition). A user holds the information reading terminal 10 and causes the information reading terminal 10 to read, for example, a character string S1 written on a label L1 attached to the top surface of a package 100. The "character recognition" performed by the information reading terminal 10 in this specification includes a process for determining whether an image corresponding to image data includes an image representing characters, and a process for recognizing the image representing characters as character data.
[0030] The information reading terminal 10 includes an operation unit 12, a display unit 14, a camera 16, a communication interface 18, an irradiation unit 20, an acceleration sensor 22, a notification unit 24, a control unit 30, and a housing 60. Hereinafter, in this specification, the interface will be referred to as "I / F."
[0031] The operation unit 12 includes a plurality of buttons provided on the front surface of the information reading terminal 10 (i.e., the surface on the positive side in the Z-axis direction, the surface on the upper side of the paper in FIG. 1) and a trigger button B1 provided on the side surface of the information reading terminal 10 (i.e., the surface on the negative side in the Y-axis direction, the surface on the left side of the paper in FIG. 1). A user can input various instructions to the information reading terminal 10 by operating the operation unit 12. In particular, the trigger button B1 is a button for starting the operation of the camera 16. The display unit 14 is a display that displays various information. The display unit 14 displays, for example, an image captured by the camera 16. The display unit 14 also displays data indicating the results of character recognition (e.g., character data). The display unit 14 may function as a touch panel (i.e., the operation unit 12) that can accept user operations.
[0032] The camera 16 is provided on the back surface of the information reading terminal 10 (i.e., the surface on the negative side in the Z-axis direction, the surface on the lower side of the paper in FIG. 1), and includes a light source such as an LED light and a CCD image sensor. The communication I / F 18 is an interface for executing communication with, for example, an external device (e.g., a server not shown).
[0033] The illuminating unit 20 is provided adjacent to the camera 16. The illuminating unit 20 is a laser light source that irradiates an indication marker M1 that indicates an object to be read (e.g., a two-dimensional code, characters). As shown in FIG. 1, the indication marker M1 has a cross shape. The illuminating unit 20 irradiates the indication marker M1 when a trigger button B1 is pressed by a user. This allows the user to move the imaging range of the camera 16 closer to the object to be read. The shape of the indication marker M1 may be other shapes, such as a dot shape, a polygon such as a triangle, a circle, an ellipse, or the like.
[0034] The acceleration sensor 22 is built into the information reading terminal 10. The acceleration sensor 22 is, for example, a piezoelectric sensor, a capacitance sensor, or a piezo-resistive sensor. The acceleration sensor 22 detects and outputs acceleration in each direction of the information reading terminal 10 (i.e., the X-axis direction, the Y-axis direction, and the Z-axis direction). The acceleration sensor 22 is triggered by the user pressing the trigger button B1, and continuously detects the acceleration of the information reading terminal 10. The output values of the acceleration sensor 22 in each direction change depending on the attitude of the information reading terminal 10. The acceleration sensor 22 outputs an output value that indicates the attitude of the information reading terminal 10. In a modified example, a gyro sensor may be used instead of the acceleration sensor 22.
[0035] The notification unit 24 is a device that notifies the user. The notification unit 24 is a speaker that can output various sounds (for example, various notification sounds, message voices, etc.). In a modified example, the notification unit 24 is not limited to a speaker, and may be a light that can emit light, a vibration device that can vibrate the information reading terminal 10, etc.
[0036] The control unit 30 is electrically connected to each of the above-mentioned units 12 to 24. The control unit 30 communicates with each of the units 12 to 24 and controls the operation of each of the units 12 to 24. The control unit 30 includes a CPU 32 and a memory 34. The CPU 32 executes various processes in accordance with a program 36 stored in the memory 34.
[0037] The memory 34 includes RAM, ROM, non-volatile memory, etc. The memory 34 also stores a threshold value Th in addition to the program 36. The threshold value Th is a threshold value for determining whether the attitude of the information reading terminal 10 is shaking based on a change in the output value of the acceleration sensor 22. The threshold value Th is a threshold value for the rate of change of the output value of the acceleration sensor 22 per unit time. Here, the unit time is, for example, 1 millisecond, which is a very short time. The control unit 30 detects that the attitude of the information reading terminal 10 is shaking when the output value of the acceleration sensor 22 changes by more than the threshold value Th. In this way, the output value of the acceleration sensor 22 is an attitude value that indicates the shaking of the attitude of the information reading terminal 10.
[0038] Furthermore, memory 34 stores image data continuously output from camera 16 while camera 16 is in operation.
[0039] (Image recognition processing; Figure 3) The image recognition process executed by the control unit 30 of the information reading terminal 10 of the first embodiment will be described with reference to Fig. 3. The image recognition process of this embodiment is triggered by the user pressing down the trigger button B1. When the user presses down the trigger button B1, the camera 16 starts operating and continuously outputs image data to the memory 34. As a result, multiple pieces of image data are stored in the memory 34. The process of storing the image data in the memory 34 is executed in parallel with the process of Fig. 3.
[0040] In S2, the control unit 30 causes the projection unit 20 to project the instruction marker M1. In S10, the control unit 30 acquires the latest image data from among the plurality of image data stored in the memory .
[0041] In S12, the control unit 30 determines whether the image corresponding to the image data acquired in S10 contains an image representing text. For example, if the image data contains an image that resembles text, the control unit 30 determines that the image corresponding to the image data contains an image representing text and crops the image. Here, a "text-like image" refers to an image that is presumed to contain text based on information such as the size and brightness per unit area of the image corresponding to the image data. Furthermore, for example, the control unit 30 may store text sample data in the memory 34. In this case, the control unit 30 may determine that the image contains an image representing text if the image contains an image that is similar to the text contained in the sample data in the memory 34 to a degree exceeding a predetermined ratio. If the control unit 30 determines that the image corresponding to the image data acquired in S10 contains an image representing text (YES in S12), the control unit 30 proceeds to S20. If the control unit 30 determines that the image corresponding to the image data acquired in S10 does not contain an image representing text (NO in S12), the control unit 30 proceeds to S18.
[0042] In S20, the control unit 30 determines whether the change in the output value of the acceleration sensor 22 is smaller than the threshold value Th. If the change in the output value is smaller than the threshold value Th (YES in S20), the control unit 30 determines that the attitude of the information reading terminal 10 is stationary, and proceeds to S22. If the change in the output value is larger than the threshold value Th (NO in S20), the control unit 30 determines that the attitude of the information reading terminal 10 is shaking, and proceeds to S18.
[0043] In S18, the control unit 30 deletes the multiple image data stored in the memory 34. As a result, image data corresponding to images that do not include text and image data captured before the shaking in the attitude of the information reading terminal 10 stopped are deleted from the memory 34. Thereafter, the control unit 30 returns to S10.
[0044] In S22, the control unit 30 causes the irradiation unit 20 to irradiate an indication marker M2. The indication marker M2 has a rectangular shape. When the shaking of the attitude of the information reading terminal 10 stops, the control unit 30 changes the shape of the indication marker from the cross-shaped indication marker M1 to the rectangular indication marker M2. The cross-shaped indication marker M1 indicates the range to be read, while the rectangular indication marker M2 surrounds the characters to be read. Seeing the change from the indication marker M1 to the indication marker M2, the user recognizes that the shaking of the attitude of the information reading terminal 10 has stopped and can know that the characters to be read have been confirmed.
[0045] In S30, the control unit 30 performs character data recognition on the latest image data acquired in S10. Specifically, the control unit 30 recognizes, as character data, an image representing a character determined to be included in the latest image data in S12.
[0046] In S32, the control unit 30 determines whether or not the character data recognition in S30 was successful. If the character data recognition in S30 was successful (YES in S32), the control unit 30 proceeds to S34.
[0047] In S34, the control unit 30 displays the result of the character data recognition on the display unit 14. Specifically, the control unit 30 causes the display unit 14 to display the character data recognized by the character data recognition. Thereafter, the control unit 30 ends the processing of Fig. 3. In a modified example, the control unit 30 may transmit data indicating the result of the character data recognition to an external device (e.g., a server) via the communication I / F 18.
[0048] Furthermore, if the character data recognition in S30 is not successful and a predetermined time has elapsed since the start of the process in S30 (YES in S40), the control unit 30 proceeds to S42.
[0049] In S42, the control unit 30 stops the character data recognition performed in S30 midway through, thereby preventing the character data recognition from being unnecessarily continued when, for example, the image corresponding to the image data acquired in S10 is unclear.
[0050] In S44, the control unit 30 causes the notification unit 24 to output an alarm sound indicating that the character data recognition in S30 has been stopped midway, and ends the processing in Fig. 3. This allows the user of the information reading terminal 10 to know that the character data recognition has been stopped midway. In a modified example, the control unit 30 may cause the display unit 14 to display a message indicating that the character data recognition has been stopped midway.
[0051] (Effects of this embodiment) The information reading terminal 10 uses the indicator marker M1 to indicate the character to be recognized. Therefore, the user adjusts the orientation of the information reading terminal 10 to align the indicator marker M1 with the character. While the orientation is being adjusted, the orientation of the information reading terminal 10 tends to fluctuate. It is assumed that the image data captured by the camera 16 during the orientation adjustment does not reflect the user's intention. In this embodiment, the information reading terminal 10 deletes multiple pieces of image data stored in the memory 34 between the time the user presses the trigger button B1 and the time the change in the output value of the acceleration sensor 22 becomes smaller than the threshold value Th (YES in S20) (S18). Character data recognition is not performed on the multiple pieces of image data stored in the memory 34 before the change in the output value of the acceleration sensor 22 becomes smaller than the threshold value Th. In a configuration in which the camera 16 continuously outputs image data, it is possible to prevent the user from recognizing characters different from the characters intended by the user.
[0052] (Correspondence) The information reading terminal 10 is an example of a "character recognition device." Pressing the trigger button B1 is an example of a "first instruction." The acceleration sensor 22 and the display unit 14 are examples of a "measurement unit" and an "output unit," respectively. The timing when the user presses the trigger button B1 and the timing when the change in the output value of the acceleration sensor 22 becomes smaller than the threshold value Th are examples of a "first timing" and a "second timing," respectively. The instruction marker M1 and the instruction marker M2 are examples of a "first aspect" and a "second aspect," respectively.
[0053] S18 is an example of a process executed by a "deletion unit." S30 is an example of a process executed by a "character recognition execution unit." S36 is an example of a process executed by an "output control unit." S42 and S44 are examples of processes executed by a "character recognition stop unit" and a "stop notification unit," respectively.
[0054] (Second Example) (Image recognition processing; Figure 4) The image recognition process executed by the control unit 30 of the information reading terminal 10 of the second embodiment will be described with reference to Fig. 4. The information reading terminal 10 of the second embodiment has the same configuration as the information reading terminal 10 of the first embodiment. The control unit 30 of the information reading terminal 10 of the second embodiment keeps the camera 16 operating and continuously outputs image data to the memory 34 while the trigger button B1 is pressed. The camera 16 continuously outputs image data to the memory 34 until the process of Fig. 4 is completed.
[0055] In S102, the control unit 30 causes the projection unit 20 to project the instruction marker M1, and instead causes the display unit 14 to display an image captured by the camera 16. In S110 to S120, the control unit 30 executes the same processes as S10 to S20 in FIG.
[0056] If the change in the output value of the acceleration sensor 22 is smaller than the threshold value Th (NO in S120), in S122 the control unit 30 causes the display unit 14 to display a character frame F1. The character frame F1 has a rectangular shape that surrounds the character to be read. In other words, the character frame F1 is a highlighting line that emphasizes the character to be read. When the shaking of the information reading terminal 10 stops, the control unit 30 causes the display unit 14 to display the character frame F1. This allows the user to see the character frame F1 and recognize that the shaking of the information reading terminal 10 has stopped, as well as to know that the character to be read has been confirmed. In a modified example, the character frame F1 may be another shape, such as a circle or an oval.
[0057] In S200, the control unit 30 monitors whether the user has stopped pressing the trigger button B1. If the user continues to press the trigger button B1 (NO in S200), the control unit 30 returns to S110. If the user stops pressing the trigger button B1 (YES in S200), the control unit 30 proceeds to S210. In the information reading terminal 10 of this embodiment, when the user stops pressing the trigger button B1, the control unit 30 proceeds to the processing from S210 onwards and executes character data recognition. This allows the information reading terminal 10 of this embodiment to reflect the user's intention in the target of character data recognition more effectively than the comparative example, which executes character data recognition without the user stopping pressing the trigger button B1. Furthermore, in this embodiment, the user simply releases his or her finger from the trigger button B1 to stop pressing the trigger button B1. This simplifies the user's operation compared to the comparative example, in which the user presses the trigger button B1 twice. Furthermore, in the information reading terminal 10 of this embodiment, the number of times the trigger button B1 is operated is less than in the comparative example in which the trigger button B1 is pressed down twice, which can prevent the posture of the information reading terminal 10 from shaking. Note that the above comparative example may be adopted in the modified example.
[0058] In S210, the control unit 30 acquires the latest image data from among the multiple pieces of image data stored in the memory 34. The image data acquired in S210 is image data captured later than the image data acquired in S110.
[0059] In S220, the control unit 30 determines whether the image data acquired in S110 (hereinafter referred to as first image data) and the image data acquired in S210 (hereinafter referred to as second image data) are similar to each other. For example, if the image corresponding to the first image data matches the image corresponding to the second image data by more than a predetermined percentage (YES in S220), the control unit 30 determines that the two pieces of image data are similar to each other and proceeds to S222. If the image corresponding to the first image data does not match the image corresponding to the second image data by more than a predetermined percentage (NO in S220), the control unit 30 determines that the two pieces of image data are not similar to each other and proceeds to S224.
[0060] In S222, the control unit 30 executes character data recognition on the first image data.
[0061] In S224, the control unit 30 performs the same process as in S112 on the second image data. If the control unit 30 determines that the image corresponding to the second image data includes an image representing text (YES in S224), the process proceeds to S226. In S226, the control unit 30 performs character data recognition on the second image data. If the control unit 30 determines that the image corresponding to the second image data does not include an image representing text (NO in S224), the process proceeds to S118.
[0062] In the information reading terminal 10 of this embodiment, the first image data and the second image data are compared in S220. If the two image data are similar to each other (YES in S220), character data recognition is performed on the first image data (S222). The first image data has already been determined in S112 as to whether the corresponding image contains an image representing text. Therefore, if the two image data are similar to each other, character data recognition can be quickly performed on the first image data. On the other hand, if the two image data are not similar to each other (NO in S220), it is presumed that the user intends to perform character data recognition on the second image data rather than the first image data. In this embodiment, if the two image data are not similar to each other, a determination is made as to whether the image corresponding to the second image data contains an image representing text (S224), and character data recognition is performed on the image representing text (S226). Therefore, the information reading terminal 10 can appropriately perform character data recognition on the image data intended by the user, between the first image data and the second image data.
[0063] In S230, the control unit 30 executes the same process as in S120. If the change in the output value is smaller than the threshold value Th (YES in S230), the control unit 30 determines that the information reading terminal 10 is not shaking, and proceeds to S234. If the change in the output value is greater than the threshold value Th (NO in S230), the control unit 30 determines that the information reading terminal 10 is shaking, and proceeds to S118. If the information reading terminal 10 starts shaking after the user stops pressing the trigger button B1 (YES in S200), character data recognition may be performed on characters contrary to the user's intention. In this embodiment, if it is determined that the information reading terminal 10 is shaking (NO in S230), the result of the character data recognition is not output, and the image in the memory is deleted in S118. This allows the information reading terminal 10 to prevent data on characters different from the characters intended by the user from being output to the output unit.
[0064] In S234, the control unit 30 executes the same process as S34 in Fig. 3. When the process of S234 ends, the control unit 30 ends the process of Fig. 4.
[0065] (Correspondence) Stopping the pressing of trigger button B1 and the timing at which the pressing of trigger button B1 is stopped are examples of a "second instruction" and a "third timing", respectively. The character box F1 is an example of a "highlighted line". The processes of S112 and S224 are each an example of a "first recognition process". The processes of S222 and S226 are each an example of a "second recognition process". S122 and S220 are examples of processes executed by an "action execution unit" and an "image comparison unit", respectively.
[0066] Although specific examples of the technology disclosed in this specification have been described above, these are merely examples and do not limit the scope of the claims. The technology described in the claims includes various modifications and variations of the specific examples exemplified above. For example, the following modifications may be adopted.
[0067] (Variation 1) In the above-described embodiment, the control unit 30 determines that the shaking of the attitude of the information reading terminal 10 has stopped by comparing the change in the output of the acceleration sensor 22 with the threshold value Th. In this variation, the control unit 30 may determine that the shaking of the attitude of the information reading terminal 10 has stopped by comparing the rate of change per unit time of the brightness of the image corresponding to the image data with the threshold value. In this variation, the control unit 30 that measures the brightness is an example of a "measurement unit," and the brightness of the image corresponding to the image data is an example of an "attitude value" that indicates the shaking of the attitude of the information reading terminal 10.
[0068] (Modification 2) The control unit 30 of the information reading terminal 10 of the second embodiment does not need to execute the process of S230.
[0069] (Modification 3) The control unit 30 of the information reading terminal 10 in the first embodiment does not need to execute the process of S12.
[0070] (Variation 4) In S122, the control unit 30 of the information reading terminal 10 of the second embodiment may, instead of displaying the character frame F1 on the display unit 14, for example, cause the notification unit 24 to issue a sound indicating that the character to be read has been confirmed. In this variation, outputting the sound is an example of a "predetermined notification action." In a further variation, the "predetermined notification action" may be vibrating the information reading terminal 10 or outputting light on the display unit 14.
[0071] (Variation 5) In 122, the control unit 30 of the information reading terminal 10 of the second embodiment may, instead of displaying the character frame F1 on the display unit 14, display, for example, a straight line positioned below the character to be recognized on the display unit 14. In this variation, the straight line is an example of an "emphasis line." In a further variation, the "emphasis line" may be a straight line positioned above the character to be recognized, or a curved line that surrounds the character to be recognized in a circular shape.
[0072] (Variation 6) In S102, the control unit 30 of the information reading terminal 10 of the second embodiment may cause the irradiation unit 20 to irradiate the instruction marker M1 and cause the image of the camera 16 to be displayed on the display unit 14. In this case, in S122, the control unit 30 may change the instruction marker from M1 to M2 and cause the display unit 14 to display a character frame F1.
[0073] (Variation 7) The control unit 30 of the information reading terminal 10 in the first embodiment does not have to change the display mode of the indication marker from M1 to M2 in S22. In this variation, the "second mode" can be omitted.
[0074] (Variation 8) The control unit 30 of the information reading terminal 10 of the first embodiment does not have to execute the processes of S40 to S44. Generally speaking, the "character recognition stopping unit" and the "stop notification unit" can be omitted.
[0075] The technical elements described in this specification or drawings exhibit technical utility either alone or in various combinations, and are not limited to the combinations described in the claims at the time of filing. Furthermore, the technologies illustrated in this specification or drawings simultaneously achieve multiple objectives, and achieving one of those objectives is itself technically useful. [Explanation of symbols]
[0076] 10: Information reading terminal 12:Operation unit 14:Display section 16: Camera 18: Communication interface 20: Irradiation unit 22: Acceleration sensor 24: Information Department 30: Control section 32 :CPU 34: Memory 36: Program 60: Housing 100: Luggage B1: Trigger button F1: Text frame L1: Label M1, M2: indicator markers S1: String Th: Threshold
Claims
1. A character recognition device, An operation unit; a camera that starts operating in response to the operation unit receiving a predetermined first instruction from a user; a memory for storing image data continuously output from the camera during operation of the camera; a measurement unit that measures a posture value that indicates a posture fluctuation of the character recognition device; an output unit; a deletion unit that deletes the plurality of pieces of image data stored in the memory during a period from a first timing when the operation unit receives the first instruction from the user to a second timing when the posture value indicates that the posture fluctuation has stopped; a character recognition execution unit that executes character recognition on at least one of the image data stored in the memory after the second timing; an output control unit that causes the output unit to output data indicating the result of the character recognition; A character recognition device comprising:
2. the operation unit receives a predetermined second instruction after the first instruction; The character recognition device according to claim 1 , wherein the character recognition execution unit executes the character recognition on the at least one image data stored in the memory after the operation unit accepts the second instruction.
3. The output control unit after the second instruction, when the attitude value indicates that the shaking of the attitude has stopped, causing the output unit to output the data; When the attitude value does not indicate that the shaking of the attitude has stopped, the data is not output to the output unit.
3. The character recognition device according to claim 2.
4. the character recognition device further includes an image comparison unit that compares first image data stored in the memory between the second timing and a third timing at which the operation unit accepts the second instruction with second image data stored in the memory after the third timing, The character recognition execution unit If the first image data and the second image data are similar, the character recognition is performed on at least one of the first image data and the second image data; If the first image data and the second image data are not similar, performing the character recognition on the second image data.
3. The character recognition device according to claim 2.
5. The character recognition a first recognition process for extracting character image data from the image data; a second recognition process for recognizing characters included in the extracted character image data as character data, the character recognition device further includes an image comparison unit that compares first image data stored in the memory between the second timing and a third timing at which the operation unit accepts the second instruction with second image data stored in the memory after the third timing, The character recognition execution unit executing the first recognition process on the first image data between the second timing and the third timing; If the first image data and the second image data are similar, the second recognition process is performed on the character image data extracted from the first image data by the first recognition process; If the first image data and the second image data are not similar, both the first recognition process and the second recognition process are performed on the second image data.
3. The character recognition device according to claim 2.
6. the first instruction is an action of pressing a predetermined button included in the operation unit, the second instruction is an action of releasing a finger from the button that has been pressed in response to the first instruction; 3. The character recognition device according to claim 2.
7. The character recognition device according to claim 1 , further comprising an operation execution unit that executes a predetermined notification operation when the posture value indicates that the posture fluctuation has stopped.
8. the character recognition device further includes a display unit that displays the at least one image data; the notification action includes an action of displaying, on the display unit after the second timing, a highlight line that highlights characters included in the at least one image data.
8. The character recognition device according to claim 7.
9. The character recognition device further comprises: an illumination unit that illuminates an indication marker to indicate the character to be recognized; an irradiation control unit that causes the irradiation unit to irradiate the indication marker when the operation unit receives the first instruction; Equipped with The character recognition device according to any one of claims 1 to 6.
10. 10. The character recognition device according to claim 9, wherein the illumination control unit changes the display mode of the indication marker from a first mode to a second mode different from the first mode when the posture value indicates that the posture fluctuation has stopped.
11. The character recognition device further comprises: a character recognition stopping unit that stops the character recognition if the character recognition is not completed within a predetermined time; a stop notification unit that notifies the user that the character recognition has stopped; Equipped with The character recognition device according to any one of claims 1 to 6.
Citation Information
Patent Citations
Optical character reader
JP1988305484A
Digital still camera
JP2003134389A
Digital equipment
JP2004215067A
Digital camera and program
JP2005260663A
Program for portable terminal device and portable terminal device
JP2013008389A