JP2012185762A - Recording medium processor, control method of recording medium processor, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To enhance a recognition rate when recognizing magnetic ink characters.SOLUTION: A check reading device 1 comprises: a check conveyance mechanism 30; a magnetic head 54; and a controller 71. The check reading device 1 analyzes signal waveform data that are obtained by magnetically reading magnetic ink characters, recorded on a check 4 to be conveyed, by means of the magnetic head 54 and determines a character cutout starting position of one magnetic ink character based on a position of a first peak that is determined to be a first peak P1 in the signal waveform data and detected so as to cut out first character waveform data. Further, the check reading device 1 executes magnetic ink character recognition with respect to the first character waveform data. Furthermore, in a case where character types of the magnetic ink characters are determined to be incapable of being recognized, the check reading device 1 re-determines the position character cutout starting position based on a position of a second peak having been determined to be a peak adjacent to the first peak and cuts out second character waveform data so as to re-executes the magnetic ink character recognition with respect to the second character waveform data.

Description

  The present invention relates to a recording medium processing apparatus, a control method for the recording medium processing apparatus, and a program.

A recording medium processing device (check device reader) that includes a magnetic head for reading magnetic ink characters recorded on a recording medium such as a check, and that reads magnetic ink characters on a recording medium conveyed on a conveyance path and recognizes the magnetic ink characters ) Is known (see, for example, Patent Document 1).
In such a recording medium processing apparatus, character waveform data corresponding to one magnetic ink character is cut out from the signal waveform data obtained by reading the magnetic ink character, based on the position of the detected first peak, and the cut out character The magnetic ink character recognition is performed by comparing the waveform of the waveform data with the reference waveform of the character type determined by the standard to determine the character type of the magnetic ink character.

JP 2004-206362 A

  However, when extracting the character waveform data from the signal waveform data, if the first peak that is the reference for determining the character extraction start position is not accurately detected, the character waveform data is extracted at the wrong character extraction start position. There has been a problem that magnetic ink character recognition may not be possible from the extracted character waveform data.

  SUMMARY An advantage of some aspects of the invention is to solve at least a part of the problems described above, and the invention can be implemented as the following forms or application examples.

  Application Example 1 A recording medium processing apparatus according to this application example includes a conveyance unit that conveys a recording medium, a reading unit that magnetically reads magnetic ink characters recorded on the recording medium, the conveyance unit, and the reading unit A control unit that controls the recording unit, the control unit controlling the transport unit to transport the recording medium, and reading the magnetic ink characters of the transported recording medium by the reading unit. The first peak determined to be the first peak in the signal waveform data is detected, and the character cutout start position of one magnetic ink character is determined based on the position of the first peak. The first character waveform data is cut out from the signal waveform data in a range corresponding to the one magnetic ink character, and magnetic ink character recognition is performed on the cut out first character waveform data. , And when it is determined that the character type of the magnetic ink character cannot be recognized, a second peak determined to be adjacent to the first peak is detected, and the character is determined based on the position of the second peak. The cut-out start position is determined again, the second character waveform data is cut out from the signal waveform data in a range corresponding to the one magnetic ink character, and the magnetic ink character is extracted from the cut out second character waveform data. The recognition is performed again.

  According to this configuration, when magnetic ink character recognition is performed on the first character waveform data and the character type of the magnetic ink character cannot be recognized, character cutting is started based on the position of the second peak adjacent to the first peak. The position is determined again and the second character waveform data is cut out. If the character type cannot be recognized by magnetic ink character recognition, the first peak that becomes the reference for determining the character extraction start position due to disturbances in the signal waveform data due to variations in the print quality of magnetic ink characters, etc. It is considered that the first peak once determined as is detected in error, and the second peak adjacent to the first peak is the original first peak. In such a case, the second character waveform data can be cut out with higher accuracy by re-determining the character cutting start position based on the position of the second peak. Then, by performing magnetic ink character recognition again on the second character waveform data, it is possible to improve the recognition rate of the character type of the magnetic ink character.

  Application Example 2 In the recording medium processing apparatus according to the application example described above, the control unit is configured to perform predetermined processing from the position of the first peak with respect to the height of the waveform at the position of the first peak in the signal waveform data. When the ratio of the height of the waveform at a position separated by a width exceeds a predetermined ratio, it is preferable to determine a position that is separated from the first peak position by the predetermined width as the position of the second peak. .

  According to this configuration, when the waveform is separated from the first peak position by a predetermined width and the waveform height exceeds a predetermined ratio with respect to the waveform height at the first peak position, the position is The position of 2 peaks. In the character waveform data in which the first peak and the next peak are separated from each other by a predetermined width, if the first peak once determined is not the first peak, it is separated from the position of the first peak by a predetermined width, In addition, if there is a second peak at a position where the height of the waveform exceeds a predetermined ratio with respect to the height of the waveform at the position of the first peak, there is a high degree of certainty that the second peak is the original first peak. . Therefore, the second character waveform data can be more reliably cut out by re-determining the character cutout start position based on the position of the second peak.

  Application Example 3 A recording medium processing apparatus according to the application example described above, including a storage unit that stores reference waveforms of a plurality of character types defined by a standard, and the control unit includes a font of the magnetic ink character. A plurality of characters stored in the storage unit when the magnetic ink character recognition is performed on the first character waveform data and it is determined that the character type of the magnetic ink character cannot be recognized. Character type candidates of the magnetic ink characters are selected from the types, and when the candidate character type is “3” or “8”, the second character waveform data is cut out, and the second character waveform data is cut out. Preferably, magnetic ink character recognition is performed again on the waveform data.

  According to this configuration, when the character type of the magnetic ink character cannot be recognized and the candidate character type is “3” or “8” in the E-13B font, the second character waveform data is cut out. And magnetic ink character recognition is performed again. The character types “3” and “8” in the E-13B font are positioned so that the first peak and the next peak, which are the reference for the character extraction start position, are adjacent to each other at a narrower interval than other character types. Therefore, when the waveform is crushed at the position of the first peak due to disturbance of the signal waveform data, the next peak may be erroneously detected as the first peak. Therefore, in such a case, the character waveform data can be accurately cut out by cutting out the second character waveform data based on the position of the second peak.

  Application Example 4 In the recording medium processing apparatus according to the application example described above, the control unit cuts out the second character waveform data based on the position of the second peak for one magnetic ink character. It is preferable to carry out once.

  According to this configuration, the extraction of the second character waveform data based on the position of the second peak is performed only once for one magnetic ink character. When the first peak and the second peak are not the first peak, there is a high possibility that the first peak cannot be detected even if another peak is searched for. Therefore, by cutting out the second character waveform data based on the position of the second peak only once, it is possible to prevent the character waveform data from being cut out and the magnetic ink character recognition from being repeated wastefully.

  Application Example 5 A control method for a recording medium processing apparatus according to this application example includes a conveyance unit that conveys the recording medium, and a reading unit that magnetically reads magnetic ink characters recorded on the recording medium. A control method for a recording medium processing apparatus, wherein the recording medium is transported by the transport unit, and signal waveform data obtained by reading the magnetic ink characters of the transported recording medium by the reading unit is analyzed, A range corresponding to the one magnetic ink character from the signal waveform data by detecting a first peak in the signal waveform data, determining a character cutout start position of one magnetic ink character based on the position of the first peak. To cut out the first character waveform data, perform magnetic ink character recognition on the cut out first character waveform data, and recognize the character type of the magnetic ink character. If it is determined that it is not possible, the second peak determined to be a peak adjacent to the first peak is detected, the character cutout start position is determined again based on the position of the second peak, and the signal waveform data To the second character waveform data in a range corresponding to the one magnetic ink character, and magnetic ink character recognition is performed again on the extracted second character waveform data.

  According to this method, when magnetic ink character recognition is performed on the first character waveform data and the character type of the magnetic ink character cannot be recognized, character segmentation is started based on the position of the second peak adjacent to the first peak. The position is determined again and the second character waveform data is cut out. If the character type cannot be recognized by magnetic ink character recognition, the first peak that becomes the reference for determining the character extraction start position due to disturbances in the signal waveform data due to variations in the print quality of magnetic ink characters, etc. It is considered that the first peak once determined as is detected in error, and the second peak adjacent to the first peak is the original first peak. In such a case, the second character waveform data can be cut out with higher accuracy by re-determining the character cutting start position based on the position of the second peak. Then, by performing magnetic ink character recognition again on the second character waveform data, it is possible to improve the recognition rate of the character type of the magnetic ink character.

  Application Example 6 A program according to this application example includes a transport unit that transports a recording medium, and each unit of a recording medium processing apparatus that includes a reading unit that magnetically reads magnetic ink characters recorded on the recording medium. Is obtained by reading the magnetic ink characters of the recording medium being conveyed by the reading unit, the control unit being caused to convey the recording medium by the conveying unit. Analyzing the signal waveform data, detecting a first peak in the signal waveform data, determining a character cutout start position of one magnetic ink character based on the position of the first peak, and determining the 1 from the signal waveform data Cut out the first character waveform data in a range corresponding to one magnetic ink character, and perform magnetic ink character recognition on the cut out first character waveform data When it is determined that the character type of the magnetic ink character cannot be recognized, a second peak determined to be a peak adjacent to the first peak is detected, and the character cutout start position is determined based on the position of the second peak. The second character waveform data is cut out from the signal waveform data in a range corresponding to the one magnetic ink character, and magnetic ink character recognition is again performed on the cut out second character waveform data. It is made to function as a means to perform.

  According to this configuration, when magnetic ink character recognition is performed on the first character waveform data and the character type of the magnetic ink character cannot be recognized, character cutting is started based on the position of the second peak adjacent to the first peak. The position is determined again and the second character waveform data is cut out. If the character type cannot be recognized by magnetic ink character recognition, the first peak that becomes the reference for determining the character extraction start position due to disturbances in the signal waveform data due to variations in the print quality of magnetic ink characters, etc. It is considered that the first peak once determined as is detected in error, and the second peak adjacent to the first peak is the original first peak. In such a case, the second character waveform data can be cut out with higher accuracy by re-determining the character cutting start position based on the position of the second peak. Then, by performing magnetic ink character recognition again on the second character waveform data, it is possible to improve the recognition rate of the character type of the magnetic ink character.

1 is an external perspective view of a check reading apparatus according to the present embodiment. It is a figure which shows the internal structure of a check reading apparatus. It is a block diagram which shows the functional structure of a check reading apparatus. It is a flowchart which shows operation | movement of a character recognition part. It is a figure which shows an example of detection signal waveform data. It is a figure which shows an example of character waveform data. It is a figure for demonstrating a difference amount. (A) schematically shows the contents of the reference waveform data corresponding to the character type “3” in the E-13B font, and (B) shows the contents of the reference waveform data corresponding to the character type “8” in the E-13B font. FIG. It is a flowchart which shows operation | movement of the character recognition part at the time of execution of an optical recognition process.

  Hereinafter, a recording medium processing apparatus, a control method for the recording medium processing apparatus, and a program according to an embodiment of the present invention will be described with reference to the drawings. In each drawing referred to, in order to show the configuration in an easy-to-understand manner, the dimensional ratio, angle, and the like of each component may be different.

<Recording medium processing apparatus>
A recording medium processing apparatus according to this embodiment will be described. The recording medium processing apparatus according to this embodiment includes a check reading apparatus 1 and a host computer 70.

First, a schematic configuration of the check reading apparatus 1 according to the present embodiment will be described. FIG. 1 is an external perspective view of a check reading apparatus 1 according to this embodiment.
The check reading device 1 reads a magnetic ink character (MICR character) recorded on the check 4, reads images on both sides of the check 4, and endorses the check 4 with respect to the check 4 that is a sheet-like recording medium. It is an apparatus that performs processing such as recording of a predetermined image.

The check reading device 1 includes a main body case 2 and a lid case 3 placed on the upper side of the main body case 2, and each component is incorporated therein.
The cover case 3 is formed with a conveyance path 5 of a check 4 consisting of a narrow vertical groove having a U shape when viewed from above, and one end of the conveyance path 5 is a check consisting of a wide vertical groove. The other end of the conveyance path 5 branches right and left and is connected to a first check discharge portion 7 and a second check discharge portion 8 each having a wide vertical groove.

On the surface 4a of the check 4, a money amount, a payer, a number, a signature, and the like are written on the background on which a predetermined pattern is formed, and the lower end portion thereof has a long side direction as shown in FIG. An extended magnetic ink character string 4A is recorded. The magnetic ink character string 4A is formed by arranging a plurality of magnetic ink characters in the horizontal direction.
In addition, an endorsement column is formed on the back surface 4 b of the check 4. A predetermined image related to the endorsement is recorded in the endorsement column by a recording device 56 described later.

  The check 4 is aligned in the vertical direction so that the upper end 4e is positioned upward and the lower end 4f is positioned downward, and the front and back are aligned so that the surface 4a faces the outside of the U-shaped conveyance path 5 ( In the state shown in FIG. 1, it is inserted into the check supply unit 6. The check 4 inserted into the check supply unit 6 is sent out to the transport path 5 with the rear end 4d as the first.

  As the check 4 sent out from the check supply unit 6 is conveyed along the conveyance path 5, the front image that is the image of the front surface 4a and the back image that is the image of the back surface 4b are read, and further, the check 4 is transferred to the front surface 4a. The recorded magnetic ink character string 4A is magnetically read. The check 4 for which the magnetic ink character string 4 </ b> A has been successfully read is discharged to the first check discharge unit 7 after a predetermined image related to the endorsement is recorded.

  On the other hand, the check 4 that has failed to be read is discharged to the second check discharge unit 8 without recording a predetermined image related to the endorsement. The check 4 discharged to the second check discharge unit 8 is subjected to processing such as investigation of the cause of reading failure and re-reading.

FIG. 2 is an explanatory diagram showing the internal structure of the check reading device 1.
The check supply unit 6 is provided with a check delivery mechanism 10 for sending the check 4 to the transport path 5. The check delivery mechanism 10 includes a delivery roller 11, a delivery roller 12, a retard roller 13 pressed against the delivery roller 12, a delivery motor 14, and a check pressing hopper 15.

  When the feeding motor 14 is driven, the check 4 placed in the check supply unit 6 is pressed against the feeding roller 11 by the hopper 15, and in this state, the feeding roller 11 and the feeding roller 12 rotate synchronously.

  The check 4 is fed between the feed roller 12 and the retard roller 13 by the feed roller 11. The retard roller 13 is given a predetermined rotational load, and only one check 4 that is in direct contact with the delivery roller 12 is separated from the other checks 4 and delivered to the transport path 5.

  The conveyance path 5 has a U shape as described above, and is connected to the linear upstream conveyance path portion 21 connected to the check supply unit 6, the first check discharge unit 7, and the second check discharge unit 8. In addition, a downstream conveyance path portion 23 extending in a slightly bent state and a curved conveyance path portion 22 that connects the downstream conveyance path portion 22 are provided.

  A check conveyance mechanism 30 that conveys the check 4 sent from the check supply unit 6 to the conveyance path 5 along the conveyance path 5 is pressed by the first conveyance roller 31 to the sixth conveyance roller 36 and the rotation. The first pressing roller 41 to the sixth pressing roller 46 and a transport motor 37 for rotationally driving the first transport roller 31 to the sixth transport roller 36 are provided. The 1st conveyance roller 31-the 6th conveyance roller 36 rotate in synchronization. For example, a stepping motor is used as the transport motor 37. For this reason, the conveyance amount of the check 4 can be known from the number of steps for driving the stepping motor.

  The first conveyance roller 31 to the third conveyance roller 33 are respectively disposed at the upstream end of the upstream conveyance path portion 21, the middle position thereof, and the boundary position with the curved conveyance path portion 22. The fourth transport roller 34 is disposed at a downstream position in the curved transport path portion 22. The fifth transport roller 35 and the sixth transport roller 36 are respectively disposed at the middle position and the downstream end in the downstream transport path portion 23.

  Between the first transport roller 31 and the second transport roller 32 in the upstream transport path portion 21, the magnet 51 for magnetizing the magnetic ink characters, the front contact image sensor 52, and the back contact image from the upstream side. A sensor 53 is arranged. The front-side contact image sensor 52 faces the front surface 4a of the check 4 transported on the transport path 5, and reads a front surface image that is an image of the front surface 4a. The back side contact image sensor 53 faces the back side 4b of the check 4 conveyed on the conveyance path 5, and reads a back side image that is an image of the back side 4b.

Further, a magnetic head 54 as a reading unit for reading magnetic ink characters is disposed between the second transport roller 32 and the third transport roller 33, and the check 4 is pressed against the magnetic head 54. The pressing roller 55 faces each other.
Between the fifth transport roller 35 and the sixth transport roller 36 in the downstream transport path portion 23, a recording device 56 for recording a predetermined image related to the endorsement is disposed. The recording device 56 includes a print head, a stamp, and the like that can record a predetermined image in an appropriate direction at an appropriate position on the back surface 4b of the check 4 conveyed on the conveyance path 5.

  Various sensors for check conveyance control are arranged in the conveyance path 5. A paper length detector 61 for detecting the length of the check 4 to be sent out is disposed at a position on the front side of the magnet 51. Between the back side contact image sensor 53 and the second transport roller 32, a double feed detector 62 for detecting that the check 4 is transported in an overlapping state is disposed. A jam detector 63 is disposed at a position on the front side of the fourth transport roller 34. When the check 4 is continuously detected by the jam detector 63 over a predetermined time, the transport path 5 is detected. It can be seen that the check 4 is jammed.

  A print detector 64 for detecting the presence or absence of the check 4 endorsed by the recording device 56 is disposed at a position on the front side of the fifth transport roller 35. Furthermore, it is discharged into these positions on the downstream side of the sixth transport roller 36, that is, the position of the branch path 9 that branches from the transport path 5 to the first check discharge section 7 and the second check discharge section 8. A discharge detector 65 for detecting the check 4 is arranged.

  A switching plate 66 that is switched by a drive motor 67 (see FIG. 3) is disposed in the branch path 9. The switching plate 66 is a member for selectively switching the downstream end of the transport path 5 with respect to the first check discharge unit 7 and the second check discharge unit 8 and guiding the check 4 to the selected discharge unit.

FIG. 3 is a block diagram showing a functional configuration of the check reading apparatus 1.
The control unit 71 centrally controls each part of the check reading device 1 under the control of the host-side control unit 73 of the host computer 70 described later, and controls the CPU, ROM, RAM, and other peripheral circuits. I have.

  The control unit 71 drives the delivery motor 14 and the conveyance motor 37 under the control of the host-side control unit 73 to feed the checks 4 (see FIG. 1) one by one to the conveyance path 5, and the sent checks 4 is transported along the transport path 5. The conveyance control of the check 4 by the control unit 71 is based on detection signals from the paper length detector 61, the double feed detector 62, the jam detector 63, the print detector 64 and the discharge detector 65 arranged in the conveyance path 5. Based on.

As the check 4 is transported, the front-side contact image sensor 52 and the back-side contact image sensor 53 respectively read the image on the front surface and the back surface of the check 4 transported on the transport path 5, and read the read images. The image data shown is output to the control unit 71. The control unit 71 outputs these image data to the host side control unit 73.
Further, the magnetic head 54 detects an electromotive force generated by a change in the magnetic field formed by the passing magnetic ink character string 4A (see FIG. 1) under the control of the control unit 71, and the signal processing circuit 74 as a detection signal. Output to.

The signal processing circuit 74 includes an amplifier, a noise removal filter circuit, an A / D converter, and the like, amplifies the detection signal input from the magnetic head 54, shapes the waveform, and outputs the amplified signal to the control unit 71 as data. To do. The control unit 71 transmits data indicating the detection signal input from the signal processing circuit 74 to the host side control unit 73.
The operation unit 75 includes various switches such as a power switch and operation switches formed on the main body case 2 (see FIG. 1), detects user operations on these switches, and outputs them to the control unit 71.

A host computer 70 is connected to the check reading device 1 via a communication cable 72.
The host computer 70 includes a host-side control unit 73 that includes a CPU, ROM, RAM, and other peripheral circuits. The host-side control unit 73 includes a character recognition unit 80 described later.

The host-side control unit 73 includes a display 76 that can display various types of information, an operation unit 77 to which input devices such as a keyboard and a mouse are connected, and a storage unit that stores various types of rewritable data such as an EEPROM and a hard disk. 78 is connected.
The storage unit 78 stores the front image of the check 4 input from the check reading device 1, data indicating the back image, and data indicating the detection signal.

  In the present embodiment, the control unit 71 of the check reading device 1 controls each part of the check reading device 1 under the control of the host side control unit 73 of the host computer 70. Specifically, the host-side control unit 73 executes a program stored in the ROM by the CPU to generate control data for controlling the control unit 71, and uses the generated control data for the check reading device 1. By outputting to the control unit 71, each part of the check reading device 1 is controlled. That is, in this embodiment, the host computer 70 and the check reading device 1 cooperate to function as a recording medium processing device that executes various processes on the check 4 as a recording medium.

<Character recognition part>
Next, the character recognition unit 80 included in the host-side control unit 73 will be described.
The character recognition unit 80 performs character recognition for each of the magnetic ink characters constituting the magnetic ink character string 4A. The magnetic ink character is a character magnetically printed on the check 4 in accordance with a predetermined font (for example, E-13B font), and one magnetic ink character has a plurality of predetermined character types. Corresponds to any one character type. The recognition of the magnetic ink character is to determine the character type of each magnetic ink character for each of the read magnetic ink characters or to detect that the character type of the magnetic ink character cannot be determined.

  In the E-13B font, the shapes of magnetic ink characters are “0” to “9”, transit symbol (TRANSIT SYMBOL), amount symbol (AMOUNT SYMBOL), on-as symbol (ON-US SYMBOL), and Shapes corresponding to 14 character types of dash symbols (DASH SYMBOL) are prepared. The reference waveforms of the plurality of character types determined by the standard are stored in the storage unit 78.

  In addition, each magnetic ink character of the magnetic ink character string 4A may be printed on the check 4 by offset printing or may be printed by laser printing. The magnetic ink characters printed by offset printing and the magnetic ink characters printed by laser printing have different shapes. In this embodiment, as described later, The recognition of magnetic ink characters is executed.

In the present embodiment, if the character type of the magnetic ink character can be determined for all the magnetic ink characters included in the magnetic ink character string 4A, it is determined that the magnetic ink character string 4A has been successfully read. If one of the characters cannot determine the character type of the magnetic ink character, it is determined that the reading of the magnetic ink character string 4A has failed.
As described above, under the control of the host-side control unit 73, the control unit 71 conveys the check 4 to the first check discharge unit 7 for the check 4 for which the magnetic ink character string 4A has been successfully read. For the check 4 for which reading of the magnetic ink character string 4A has failed, the check 4 is conveyed to the second check discharge unit 8 after executing a predetermined process.

FIG. 4 is a flowchart showing the operation of the character recognition unit 80. The flow chart of FIG. 4 shows the operation of the character recognition unit 80 when executing recognition of a magnetic ink character string 4A recorded on a check 4 for a certain check 4. The magnetic ink character string 4A recorded on the check 4 is read by the magnetic head 54, and the signal processing circuit 74 performs various processing such as amplification processing, filtering processing, and waveform shaping processing. It is assumed that data indicating the detection signal (hereinafter referred to as “detection signal waveform data”) is generated and the detection signal waveform data is output to the host-side control unit 73 by the control unit 71.
Further, it is assumed that an image of the surface of the check 4 is read by the front-side contact image sensor 52 and output from the control unit 71 to the host-side control unit 73 as image data. The function of the character recognition unit 80 is realized by the cooperation of hardware and software, such as the CPU of the host-side control unit 73 executing a program stored in the ROM.

<Cutting out magnetic ink characters>
As shown in FIG. 4, first, the host-side control unit 73 analyzes the detection signal waveform data input from the control unit 71 and selects one magnetic ink character from among the magnetic ink characters included in the magnetic ink character string 4A. First peak P1 (see FIG. 6) and its position (X-axis value) are detected (step SA21).

  The peak detected by determining that it is the first peak P1 in step SA21 is referred to as a first peak. Then, for one magnetic ink character among the magnetic ink characters included in the magnetic ink character string 4A, the character clipping start position of the magnetic ink character is determined based on the detected position of the first peak, and the detection signal waveform data The character is cut out from (step SA1). Character segmentation refers to generating character waveform data indicating the waveform of a magnetic ink character for one magnetic ink character included in the magnetic ink character string 4A based on the detection signal waveform data. is there.

  The processes of step SA21 and step SA1 are executed as follows, for example. FIG. 5 is a diagram schematically showing an example of the contents of the detection signal waveform data (part), and FIG. 6 is a schematic example of the contents of the character waveform data generated by the processing in step SA21 and step SA1. FIG.

  As described above, in the present embodiment, the magnetic ink character string 4 </ b> A recorded on the check 4 is read by the magnetic head 54 while the check 4 is being conveyed in the conveyance path 5. The magnetic ink character string 4A of the check 4 being conveyed is read at a predetermined sampling period from the rear end 4d side to the front end 4g side, thereby reading the magnetic ink character string 4A. In the following description, the interval of the minimum unit of the sampling period is assumed to be one sampling unit.

  In FIG. 5, the X axis (horizontal axis) defines the passage of time (sampling period) (showing that one sampling unit has passed sequentially from the origin toward the right of the X axis), and the Y axis ( The vertical axis) defines the relative value of the amount of change in magnetic charge with time. In FIG. 5, in the magnetic ink character string 4A, how the relative value of the change amount of the magnetic charge changes every predetermined sampling period from the rear end 4d side of the check 4 to the front end 4g side. The value in the Y-axis direction rises and falls according to the amount of change in magnetic charge of each magnetic ink character included in the magnetic ink character string 4A, and the amount of change in magnetic charge is positive or negative. Depending on whether the value is positive or negative in the Y-axis direction.

  Here, as shown in the example of FIG. 6, the range occupied by the waveform corresponding to one magnetic ink character in the X-axis direction of the detection signal waveform data is defined as a predetermined sampling unit S0, which conforms to this rule. As described above, various conveyance controls are executed, and the length of one sampling unit is defined. In the waveform corresponding to one magnetic ink character, it is defined that the first peak P1 is located at a predetermined sampling unit S1 from the character cutout start position. In the present embodiment, the predetermined sampling unit S0 is, for example, 70 sampling units, and the predetermined sampling unit S1 is, for example, the 11th sampling unit.

  Based on this, in step SA21, the character recognition unit 80 analyzes the detection signal waveform data, and the first detected from the peaks of the waveform toward the rear end side (right side of the X axis) of the waveform. It is determined that one peak is the first peak P1. Here, the peak is a portion corresponding to the maximum value and the minimum value in the detection signal waveform data, and these peaks are defined to appear in a predetermined cycle in the X-axis direction. The value on the X axis corresponding to each peak is called the peak position.

Subsequently, in step SA1, the character recognition unit 80 determines a character cutout start position for each of the magnetic ink characters included in the magnetic ink character string 4A based on the detected position of the first peak. Then, the waveform indicated by the detection signal waveform data is cut out from the determined character cutting start position in a predetermined sampling unit S0 (70 sampling units) that is a range corresponding to the width of one magnetic ink character.
At this time, as shown in the example of FIG. 6, the character recognition unit 80 determines that the position of the first peak detected as the first peak P1 in the cut out waveform is the predetermined sampling unit S1 on the X axis (the 11th sampling unit). ) Is determined so that the waveform of the detection signal waveform data is cut out.

  By cutting out characters in step SA1, for one magnetic ink character included in the magnetic ink character string 4A, character waveform data as shown in FIG. 6 is generated from detection signal waveform data of the magnetic ink character. The character waveform data cut out based on the position of the first peak is referred to as first character waveform data.

The character cut-out in step SA1 is performed for each magnetic ink character included in the magnetic ink character string 4A from the magnetic ink character arranged on the rear end 4d side of the check 4 to the magnetic ink character arranged on the front end 4g side. Steps SA <b> 2 and subsequent processing relating to character recognition are executed for each magnetic ink character cut out in order.
Hereinafter, one magnetic ink character cut out in step SA1 is referred to as a “processing target character”.

After the character segmentation, the character recognition unit 80 determines that the amplitude level in the Y-axis direction of the waveform indicated by each data is the Y-axis of the reference waveform data for pattern matching for the generated first character waveform data of the processing target character. Data normalization is performed so as to be equivalent to the amplitude level in the direction (step SA2).
The reference waveform data for pattern matching is data indicating an ideal waveform of a detection signal when a magnetic ink character corresponding to one of the 14 character types described above is read by the magnetic head 54. This is data corresponding to template data provided in pattern matching processing in so-called magnetic ink character recognition.

<Magnetic ink character recognition processing>
The predetermined processing after step SA3 is processing related to so-called magnetic ink character recognition, which is sequentially executed on the magnetic ink characters (processing target characters) cut out in step SA1, and thereby the magnetic ink character string 4A. Is executed once for each of the magnetic ink characters included in the.

  As shown in FIG. 4, four recognition phases of the first recognition phase (step SA3) to the fourth recognition phase (step SA11) are included after step SA3. These four recognition phases are phases in which magnetic ink character recognition of the character to be processed is performed by different methods, and the character type of the character to be processed is determined or it is detected that it cannot be determined.

If the character type of the character to be processed is confirmed in any of the first to third recognition phases, the next magnetic ink character of the character to be processed is processed without executing the next phase. After selecting the target character, magnetic ink character recognition is executed for the new processing target character.
In the following description of each recognition phase, the first character waveform data and the second character waveform data are not distinguished from each other and are simply referred to as character waveform data.

  In the first recognition phase (step SA3), the character recognition unit 80 detects a difference amount between each of the character waveform data of the character to be processed and each of the reference waveform data corresponding to the 14 character types.

The detection of the difference between the character waveform data of the character to be processed and the reference waveform data will be described. FIG. 7 is a diagram illustrating the difference amount detected in step SA3. In FIG. 7, the waveform indicated by the character waveform data is indicated by a thin line, and the waveform indicated by the reference waveform data is indicated by a thick line.
The difference amount is the size of the hatched area in FIG. 7, and more specifically, in the Y-axis direction of the waveform indicated by the character waveform data in each sampling unit defined on the X-axis. This is the sum of absolute values of the difference between the value and the value in the Y-axis direction of the waveform indicated by the reference waveform data. The smaller the difference between the waveform indicated by one character waveform data and the waveform indicated by one reference waveform data, the smaller the waveform indicated by the one character waveform data and the waveform indicated by the one reference waveform data. And the character type of the magnetic ink character corresponding to the one character waveform data is highly likely to be the character type corresponding to the one reference waveform data.

  The detection of the difference amount of the waveform data in the first recognition phase is performed, for example, when the waveform indicated by the character waveform data of the character to be processed is simply compared with the waveform of the reference waveform data corresponding to the type of character to be compared, This is performed when the waveform indicated by the character waveform data of the character and the waveform of the reference waveform data corresponding to the character type to be compared are slid by a predetermined distance within a predetermined range and compared.

Based on the detection result of the difference amount, the character recognition unit 80 sets the character type corresponding to the reference waveform data having the smallest difference amount as the first candidate, and then the character type corresponding to the reference waveform data having the smallest difference amount. Is the second candidate.
Then, the character recognizing unit 80 compares the difference amount between the reference waveform data corresponding to the character types determined as the first candidate and the second candidate and the character waveform data of the character to be processed with a predetermined threshold value. As a result, the amount of difference between the reference waveform data corresponding to the first candidate and the character waveform data of the character to be processed is equal to or less than the threshold, and the reference waveform data corresponding to the second candidate and the character waveform data of the character to be processed are When the difference amount exceeds the threshold value, the character type set as the first candidate is determined as the character type of the processing target character. If the difference from the first candidate exceeds the threshold, the first recognition phase is terminated without determining the character type of the processing target character.

  On the other hand, the reference waveform data corresponding to the character type determined as the second candidate and the difference amount between the reference waveform data corresponding to the character type determined as the first candidate and the character waveform data of the character to be processed is equal to or smaller than the threshold. If the difference between the character waveform data of the character to be processed and the character waveform data to be processed is equal to or smaller than the threshold, the character recognition unit 80 does not determine the character type of the character to be processed.

  Here, the above threshold value is such that only the amount of difference between the character waveform data of the character to be processed and the reference waveform data corresponding to the correct character type of the character to be processed is equal to or less than the threshold, and The amount of difference from the reference waveform data corresponding to the character type is appropriately set so as to exceed the threshold value. By setting the threshold value in this manner, if the check 4 is conveyed normally and the magnetic head character string 4A is normally read by the magnetic head 54, the number of character types related to the difference amount that is equal to or less than the threshold value is limited to one.

  On the other hand, when there are a plurality of character types related to the difference amount that are less than or equal to the threshold, the situation appears due to a reading error by the magnetic head 54, a conveyance error of the check 4, or some other cause. there is a possibility. Therefore, if the character type of the character to be processed is determined in such a situation, there is a risk of erroneous recognition.

  As described above, in the present embodiment, the shape of the magnetic ink character printed by offset printing is different from the shape of the magnetic ink character printed by laser printing. Two types of data, reference waveform data for offset printing and reference waveform data for laser printing, are prepared corresponding to one character type. In the first recognition phase, various processes are executed using the reference waveform data for offset printing out of the two types of reference waveform data. In the third recognition phase (step SA9), various processes are executed using the reference waveform data for laser printing.

After execution of the first recognition phase (step SA3), the character recognition unit 80 determines whether or not the character type of the processing target character has been confirmed in the first recognition phase (step SA4).
If the character type of the character to be processed can be confirmed (step SA4: YES), the character recognition unit 80 proceeds to step SA5 without performing the second recognition phase.

  In step SA5, it is determined whether or not all magnetic ink characters included in the magnetic ink character string 4A are characters to be processed. In other words, for all the magnetic ink characters included in the magnetic ink character string 4A, the characters for step SA1. Is cut out, and it is determined whether or not processing relating to character recognition has been executed.

  When all the magnetic ink characters included in the magnetic ink character string 4A are not the characters to be processed (step SA5: NO), the character recognition unit 80 returns the processing procedure to step SA21 to perform the next magnetic ink character. When the first peak P1 is detected and the characters are cut out, on the other hand, when all the magnetic ink characters included in the magnetic ink character string 4A have been processed (step SA5: YES), the processing procedure goes to step SA6. Transition.

  Next, when it is determined in step SA4 that the character type of the processing target character cannot be determined in the first recognition phase (step SA4: NO), the character recognition unit 80 selects the first candidate selected in the first recognition phase. It is confirmed whether the character type set is “3” or “8” of the E-13B font (step SA22).

When the character type set as the first candidate is neither “3” nor “8” (step SA22: NO), the character recognition unit 80 executes the second recognition phase (step SA7).
When the character type set as the first candidate is either “3” or “8” (step SA22: YES), the character recognition unit 80 updates the position of the first peak P1 (step to be described later). It is confirmed whether SA25) has already been performed (step SA23).

When the process of updating the position of the first peak P1 has already been performed (step SA23: YES), the character recognition unit 80 executes the second recognition phase (step SA7).
On the other hand, when the process of updating the position of the first peak P1 has not been performed yet (step SA23: NO), the character recognition unit 80 is on the front side by a predetermined width from the position of the first peak that is the first peak P1. It is determined whether the ratio of the height (value) of the waveform at a position away from (to the left of the X axis shown in FIG. 5) to the height (value) of the waveform at the position of the first peak exceeds a predetermined ratio. (Step SA24).

  When the ratio of the height (value) of the waveform at a position separated by a predetermined width from the position of the first peak to the height (value) of the waveform at the position of the first peak is equal to or less than a predetermined ratio ( Step SA24: NO), the character recognizing unit 80 executes the second recognition phase (Step SA7).

  On the other hand, when the ratio of the height (value) of the waveform at a position separated by a predetermined width from the position of the first peak to the height (value) of the waveform at the position of the first peak exceeds a predetermined ratio ( Step SA24: YES), it is determined that there is a second peak adjacent to the first peak at a position that is a predetermined width away from the position of the first peak, and that the second peak is the first peak P1. (Step SA25). That is, the position of the first peak P1 is not the position of the first peak but the position of the second peak. The process in step SA25 is referred to as a process for updating the position of the first peak P1.

  Next, the character recognition unit 80 returns the processing procedure for this magnetic ink character to step SA1, cuts out character waveform data (hereinafter referred to as second character waveform data) based on the position of the second peak, The first recognition phase of step SA3 is executed again on the character waveform data.

  Here, the processing of step SA22 to step SA25 will be described in detail with reference to FIGS. 8 (A) and 8 (B). FIG. 8A schematically shows the content of the reference waveform data corresponding to the character type “3” in the E-13B font, and FIG. 8B shows the reference corresponding to the character type “8” in the E-13B font. It is a figure which shows the content of waveform data typically.

If the character type of the character to be processed has not been determined in step SA4 and the character type determined as the first candidate in step SA22 is either “3” or “8”, the first peak P1 is detected. It is possible that there was an error. This is due to the following reason.
That is, as shown in FIGS. 8A and 8B, in the character types “3” and “8” in the E-13B font, the first peak P1 and the next peak P2 that serve as the reference for the character extraction start position are used. Are positioned with a predetermined width (predetermined sampling unit S2) so as to be adjacent to each other in the X-axis direction, and compared with other character types, the position of the first peak P1 and the position of the next peak P2 The interval between and is narrower. In the present embodiment, the predetermined sampling unit S2 is 7 sampling units, and therefore the position of the first peak P1 and the position of the next peak P2 in the character types “3” and “8” are separated by 7 sampling units. .

  For example, the waveform of the first peak P1 is crushed as shown by the broken line in FIG. 8A due to disturbance in the signal waveform data due to variations in print quality of magnetic ink characters. To do. In such a case, when the first peak P1 is detected in step SA21, the first peak P1 cannot be detected due to the collapse of the waveform, and the next adjacent peak P2 is erroneously detected as the first peak P1. There can be. When the first peak P1 is erroneously detected and the character is cut out, it is difficult to recognize the character type of the magnetic ink character even if the subsequent recognition phases of the first recognition phase to the fourth recognition phase are executed. It becomes.

  Therefore, the character recognition start position of the magnetic ink character is determined based on the position of the first peak detected as the first peak P1, and the first recognition phase is executed on the extracted first character waveform data. If the type cannot be determined and the character type set as the first candidate is “3” or “8”, the first peak detected in step SA21 is not the original first peak P1, but the next peak. It may be peak P2. In this case, the original first peak P1 is considered to be at a position separated from the first peak (next peak P2) to the front side (left side of the X axis) by 7 sampling units.

  Therefore, in step SA24, the ratio of the height (value) of the waveform at a position separated by 7 sampling units from the first peak position to the front side with respect to the height (value) of the waveform at the first peak position is a predetermined ratio. In the case where the second peak is exceeded, there is a second peak at this position, and this second peak is likely to be the first peak P1. If the printed magnetic ink characters are stretched or shrunk, the detection signal waveform data may be stretched or shrunk. In such a case, a position that is 6 sampling units away from the position of the first peak or a position that is 8 sampling units away may be used as the second peak position.

  In step SA25, the position of the first peak P1 is updated, and the position of the second peak is set as the position of the first peak P1. Based on the position of the second peak, the character waveform data can be extracted more accurately by re-determining the character extraction start position in step SA1 and extracting the second character waveform data. And the recognition rate of the character type of a magnetic ink character can be improved by performing magnetic ink character recognition with respect to 2nd character waveform data by step SA3. In step SA25, when the process of updating the position of the first peak P1 is performed, the flag indicating the updated state of the position of the first peak P1 is rewritten.

  In the present embodiment, the predetermined ratio of the difference for comparing the heights (values) of the waveforms in step SA24 is appropriately set depending on the degree of waveform collapse, and is, for example, 1/3. If the predetermined ratio is set high, there is a high possibility that the first peak P1 cannot be detected when the degree of waveform collapse is large. On the other hand, if the predetermined ratio is set low, there is noise or waveform disturbance. In this case, there is a high possibility that these are erroneously detected as the first peak P1. Therefore, it is desirable to set the predetermined ratio so that the signal and the noise can be distinguished well.

In the present embodiment, if the flag indicating the updated state of the position of the first peak P1 is rewritten in step SA23 and the process of updating the position of the first peak P1 has not yet been performed. Only by proceeding to step SA24, the second character waveform data based on the position of the second peak is cut out only once for one magnetic ink character, and is not repeatedly performed.
This is because if the character type cannot be determined even if magnetic ink character recognition is performed on the second character waveform data, it is considered that not only the first peak but also the second peak is not the first peak P1. . In this case, there is a high possibility that the first peak P1 cannot be detected even if another peak is searched for under the above-described conditions. Therefore, by cutting out the second character waveform data based on the position of the second peak only once, the processing of cutting out the character waveform data and magnetic ink character recognition is prevented from being wasted.

  Now, with reference to FIG. 4, the processing after step SA7 will be described. When the position of the first peak P1 is updated in step SA25 and the second character waveform data is cut out based on the position of the second peak, the second recognition phase (step SA7) to the fourth recognition phase ( Also in the three recognition phases of step SA11), magnetic ink character recognition is performed on the second character waveform data.

  In the second recognition phase (step SA7), the expansion or contraction of the magnetic ink character is detected based on the character spacing of the processing target character in the detection signal waveform data, and the detected character type is reflected by reflecting the detected expansion or contraction. For example, the waveform of the reference waveform data corresponding to is corrected by expanding and contracting to both sides or one side of the character interval. Then, a difference amount between each of the corrected reference waveform data (corrected waveform data) and the waveform of the character waveform data corresponding to the character to be processed is detected.

  Here, due to the magnetic ink characters being printed out of the center value of the printing standard, the magnetic ink characters are contracted in the horizontal direction (direction corresponding to the X axis) or in the expanded state. May be printed. In this case, the waveform of the character waveform data generated based on the detection signal waveform data may extend or contract in the X-axis direction. In addition, depending on the state of conveyance of the check 4, the waveform of the character waveform data may extend or contract in the X-axis direction. Based on this, by sliding the waveform of the reference waveform data within a predetermined range from a predetermined position, the amount of difference from the waveform of the character waveform data of the character to be processed is detected. Thus, the difference amount can be appropriately calculated.

  In the second recognition phase, the character recognition unit 80 sets the character type corresponding to the corrected waveform data having the smallest detected difference amount as the first candidate, and then the character type corresponding to the corrected waveform data having the smallest difference amount. Is the second candidate. Then, a difference amount between the corrected waveform data corresponding to the character types determined as the first candidate and the second candidate and the character waveform data of the character to be processed is compared with a predetermined threshold, and the reference waveform data corresponding to the first candidate When the amount of difference between the character waveform data of the character to be processed is equal to or less than the threshold and the amount of difference between the reference waveform data corresponding to the second candidate and the character waveform data of the character to be processed exceeds the threshold, The determined character type is determined as the character type of the processing target character.

  Further, the reference waveform data corresponding to the character type determined as the second candidate and the difference amount between the reference waveform data corresponding to the character type determined as the first candidate and the character waveform data of the character to be processed is equal to or less than a threshold value. Even if the difference between the character waveform data of the character to be processed and the character to be processed is equal to or less than the threshold, if the difference is greater than or equal to the difference between the first candidate and a predetermined coefficient, the first candidate The selected character type is determined as the character type of the processing target character. In other cases, the character type of the character to be processed is not fixed.

  In the second recognition phase, as described above, the first candidate and the second candidate character type are selected after reflecting the expansion and contraction of the waveform of the character waveform data. Therefore, it can be said that the first candidate and the second candidate selected in the second recognition phase have the highest reliability compared to the first candidate and the second candidate selected in the other recognition phases in the present embodiment.

After execution of the second recognition phase (step SA7), the character recognition unit 80 determines whether or not the character type of the character to be processed has been confirmed in the second recognition phase (step SA8). (SA8: YES), the process proceeds to step SA5, and if it cannot be determined (step SA8: NO), the third recognition phase is executed (step SA9).
In the third recognition phase (step SA9), the reference waveform data for laser printing is used, and various processes similar to those in the first recognition phase are executed.

  After execution of the third recognition phase, the character recognition unit 80 determines whether or not the character type of the processing target character has been confirmed in the third recognition phase (step SA10), and if it can be confirmed (step SA10: YES). Then, the process procedure proceeds to step SA5, and if it cannot be determined (step SA10: NO), the fourth recognition phase is executed (step SA11).

  In the fourth recognition phase (step SA11), not all sampling units but the peak position of the reference waveform data and the waveform of the reference waveform data in the sampling unit before and after that are compared with the waveform of the character waveform data of the character to be processed. To do. As a result, in the waveform of the character waveform data of the character to be processed, the influence is removed when there is any disturbance, and when partial expansion, shrinkage, or deviation occurs, these are reflected and processed appropriately. Perform character recognition of the target character.

  In the fourth recognition phase, the character type of the processing target character is not finalized, and the character type of the processing target character is determined only when a predetermined condition described later is satisfied. Based on this, the determination of the character type of the character to be processed in the fourth recognition phase is expressed as “provisional determination” and is distinguished from the determination of the character type in the other recognition phases.

After the end of the fourth recognition phase, the character recognition unit 80 determines whether or not the character type of the character to be processed has been provisionally determined in the fourth recognition phase (step SA12).
If the character type of the processing target character cannot be temporarily determined in the fourth recognition phase (step SA12: NO), in other words, the character type of the processing target character is determined in any of the first recognition phase to the fourth recognition phase. If not, the character recognition unit 80 determines that the character type of the character to be processed cannot be determined by magnetic ink character recognition (step SA13), and the process proceeds to step SA5.

  When the character type of the processing target character can be provisionally confirmed in the fourth recognition phase (step SA12: YES), the character recognition unit 80 determines the character type provisionally confirmed in the fourth recognition phase and the first candidate in the second recognition phase. It is determined whether or not the character type determined and the character type determined as the second candidate match (step SA14).

If they do not match (step SA14: NO), the character recognition unit 80 determines that the character type of the character to be processed cannot be determined by magnetic ink character recognition (step SA13), and moves the processing procedure to step SA5.
On the other hand, if they match (step SA14: YES), the character recognition unit 80 determines the character temporarily determined in the fourth recognition phase as the character type of the processing target character (step SA15), and the processing procedure proceeds to step SA5. To do.

As described above, in the present embodiment, the character type temporarily determined as the character type of the processing target character in the fourth recognition phase is the character type that is the first candidate in the second recognition phase and the second candidate. Only when it matches one of the character types, the temporarily determined character type is determined as the character type of the processing target character. This is due to the following reason.
That is, in the second recognition phase, magnetic ink characters are recognized using a difference amount between the waveform of the character waveform data of the character to be processed and the waveform of the reference waveform data in all sampling units. On the other hand, in the fourth recognition phase, magnetic ink characters are recognized using a comparison value obtained by comparing the waveform of the reference waveform data and the waveform of the character waveform data in a specific sampling unit.

Therefore, the strength of the correlation in the degree of approximation between the waveform of the reference waveform data and the waveform of the character waveform data in the fourth recognition phase using this comparison value is higher than that in the second recognition phase using the difference amount between the waveforms. Inferior. If the character type is determined based only on the result of recognition in the fourth recognition phase, there is a possibility of erroneous recognition.
Therefore, the character type temporarily determined in the fourth recognition phase matches either the character type related to the first candidate or the second candidate selected in the second recognition phase with higher reliability than the other recognition phases. Only in this case, the temporarily determined character type is determined as the character type of the character to be processed, thereby suppressing erroneous recognition.

  Next, when it is determined in step SA5 that all magnetic ink characters included in the magnetic ink character string 4A have been processed (step SA5: YES), the character recognition unit 80 is included in the magnetic ink character string 4A. The number of magnetic ink characters to be detected is detected (step SA6).

  Next, the character recognition unit 80 determines whether or not the character type has been determined for all the magnetic ink characters included in the magnetic ink character string 4A (step SA16).

  When the character type is determined for all the magnetic ink characters (step SA16: YES), the host-side control unit 73 assumes that the magnetic ink character string 4A has been successfully read, and that the magnetic ink character string 4A has been successfully read. The process to be performed is performed (step SA17). The processing to be performed when the reading of the magnetic ink character string 4A is successful includes, for example, storing the information indicated by the magnetic ink character string 4A in the storage unit 78, and causing the control unit 71 to control the recording device 56, A predetermined image related to the endorsement is recorded on the back surface of the check 4, and the first check discharge unit 7 discharges the check 4.

  On the other hand, when at least one of the magnetic ink characters included in the magnetic ink character string 4A has not been determined (step SA16: NO), the character recognition unit 80 has not determined the character type. An optical recognition process (step SA18) for performing optical character recognition on the magnetic ink character is executed.

  Next, the character recognition unit 80 determines whether or not the character type has been determined for all the magnetic ink characters whose character type has not been determined by the optical recognition process (step SA19), and for all the magnetic ink characters. If the character type is determined (step SA19: YES), processing to be performed when the magnetic ink character string 4A is successfully read is performed (step SA17).

On the other hand, if there is at least one magnetic ink character whose character type has not been determined (step SA19: NO), the host-side control unit 73 performs processing to be performed when reading of the magnetic ink character string 4A fails. (Step SA20).
As a process to be performed when reading of the magnetic ink character string 4A fails, the host-side control unit 73 controls the control unit 71 to perform the second check discharge unit without printing an image related to the endorsement. The process of conveying the check 4 to 8 is performed. The check 4 discharged to the second check discharge unit 8 is subjected to processing such as investigation of the cause of reading failure and re-reading.

<Optical recognition processing>
Next, the operation of the optical recognition process of the character recognition unit 80 will be described. FIG. 9 is a flowchart showing the operation of the character recognition unit 80 during the execution of the optical recognition process in step SA18.
In the optical recognition process, first, the character recognition unit 80 is included in the magnetic ink character string 4A based on data indicating the image of the surface of the check 4 generated based on the reading result of the front-side contact image sensor 52. Optical character recognition of magnetic ink characters is executed (step SK1).

  In step SK1, for example, the character recognition unit 80 specifies the range of data corresponding to the image of the magnetic ink character string 4A in the image data indicating the surface of the check 4, and uses the magnetic ink character for the specified range of data. The image data is cut out every time.

  Next, the character recognition unit 80 tentatively determines each character type of the magnetic ink character by comparing the bitmap pattern corresponding to each of the 14 character types with the image data of the cut out magnetic ink character. . Note that the character type determined in step SK1 is not final character type determination, and is therefore expressed as “provisional determination”.

  Next, the character recognition unit 80 detects the number of magnetic ink characters included in the magnetic ink character string 4A based on the result of optical character recognition in step SK1 (step SK2).

  Next, the character recognition unit 80 matches the number of characters detected in step SA6 in FIG. 4, that is, the number of characters detected based on the detection signal waveform data read by the magnetic head 54, and the number of characters detected in step SK2. It is determined whether or not to perform (step SK3).

If the number of characters does not match (step SK3: NO), the character recognition unit 80 determines that reading of the magnetic ink character string 4A has failed (step SK4), and ends the optical recognition process. This is due to the following reason.
That is, the processing after step SK5 is processing for trying to determine the character type for magnetic ink characters whose character type has not been determined using the result of the optical character recognition processing in step SK1, and the number of characters is different. If it is, at least one of the magnetic reading and the optical reading may have failed. Therefore, certainty cannot be ensured for the correspondence between each magnetic ink character cut out based on the detection signal waveform data by magnetic ink character recognition and each magnetic ink character cut out by optical character recognition, and the optical in step SK1. This is because the character type cannot be determined using the result of the character recognition process.

  When the number of characters matches (step SK3: YES), the character recognition unit 80 processes one magnetic ink character from the magnetic ink characters determined in step SA13 in FIG. (Step SK5).

The processes after step SK5 are sequentially performed for each magnetic ink character whose character type cannot be determined by magnetic ink character recognition. Hereinafter, the magnetic ink character specified in step SK5 is referred to as a “processing target character”.
Next, the character recognition unit 80 acquires the character type temporarily determined in step SK1 for the processing target character (step SK6).

Next, the character recognition unit 80 determines the character type temporarily determined in step SK1, the character type determined as the first candidate in the above-described second recognition phase, and the character type determined as the second candidate for the processing target character. It is determined whether or not any of the above matches (step SK7).
If they match (step SK7: YES), the character recognizing unit 80 determines the temporarily determined character as the character type of the processing target character (step SK8), and shifts the processing procedure to step SK9.
On the other hand, if they do not match (step SK7: NO), the character recognition unit 80 determines that the character type of the processing target character cannot be determined even by character recognition using optical character recognition (step SK10), and the processing procedure is stepped. Move to SK9.

  In step SK9, the character recognizing unit 80 determines whether or not all the magnetic ink characters determined to be unable to determine the character type in step SA13 in FIG. 4 have been processed. If not all magnetic ink characters are characters to be processed (step SK9: NO), the character recognition unit 80 returns the processing procedure to step SK5.

  On the other hand, when all the magnetic ink characters have been processed (step SK9: YES), the character recognition unit 80 determines whether there is even one magnetic ink character whose character type cannot be determined, that is, in step SK10. Then, it is determined whether or not there is even one magnetic ink character determined that the character type cannot be determined (step SK11).

If there is no character type that cannot be determined (step SK11: NO), the character recognition unit 80 determines that the magnetic ink character string 4A has been successfully read (step SK12), and ends the optical recognition process. To do.
On the other hand, if there is even one character type that cannot be determined (step SK11: YES), the character recognition unit 80 determines that reading of the magnetic ink character string 4A has failed (step SK4), and optical recognition is performed. The process ends.

As described above, in the present embodiment, the character type of the processing target character is provisionally determined in the optical character recognition process in step SK1, and the character type that has been provisionally confirmed is the character type that is the first candidate in the second recognition phase. And only when it matches with one of the character types made into the 2nd candidate, the said character type decided temporarily is decided as a character type of a character for processing. This is due to the following reason.
That is, in the optical character recognition process in step SK1, the character type of the magnetic ink character is provisionally determined by optical character recognition based on the image data indicating the surface of the check 4. Here, as described above, a sign or dirt written on the surface of the check 4 with a pen or the like may cause erroneous recognition of the magnetic ink character string 4A. Based on this, for the magnetic ink characters for which the character type cannot be determined by magnetic processing, the character type is not simply determined by optical character recognition. In the present embodiment, the character type temporarily determined by optical character recognition is the character type related to the first candidate that has the highest probability of being the correct character type in the second recognition phase, and the probability that it is the correct character type. Only when it matches one of the character types related to the second candidate that is the second highest, the temporarily determined character type is determined as the character type of the processing target character. As a result, erroneous recognition is effectively suppressed.

  As described above, according to the recording medium processing apparatus, the control method for the recording medium processing apparatus, and the program according to the present embodiment, the following effects can be obtained.

  In the present embodiment, magnetic ink character recognition is performed on the first character waveform data cut out based on the position of the first peak, and the character type of the magnetic ink character cannot be recognized. In the case of “3” or “8” in the −13B font, the height (value) of the waveform at a position away from the position of the first peak by a predetermined width is the height of the waveform at the position of the first peak ( If a predetermined ratio is exceeded with respect to (value), it is assumed that there is a second peak at that position. Then, based on the position of the second peak, the character cutout start position of the magnetic ink character is determined again, the second character waveform data is cut out, and magnetic ink character recognition is executed again.

  According to this, in the “13” and “8” of the E-13B font, the first peak P1 cannot be detected due to waveform disturbance or the like, and the next peak P2 adjacent to the first peak P1 in the X-axis direction is detected. It may be detected as the first peak by mistake. Therefore, the character type cannot be recognized by the first character waveform data cut out based on the position of the first peak, the character type set as the candidate is “3” or “8” of the E-13B font, and the first If there is a second peak at a position away from the position of one peak by a predetermined width, the second peak is considered to be the first peak P1. Therefore, by cutting out the second character waveform data based on the position of the second peak, it is possible to determine the character cutting start position with higher accuracy, cut out the character waveform data, and perform magnetic ink character recognition. Thereby, the recognition rate of magnetic ink characters can be improved.

  Further, since the second character waveform data based on the position of the second peak is cut out only once for one magnetic ink character, the character waveform is obtained when the first peak and the second peak are not the first peak P1. It is possible to prevent data cutout and magnetic ink character recognition from being repeated in vain.

  Further, in the present embodiment, the character type indicated by the magnetic ink character can be recognized in a multifaceted manner based on the results of magnetic ink character recognition in a plurality of recognition phases for recognizing the magnetic ink character by different methods. It becomes possible to suppress erroneous recognition of characters. Furthermore, even if recognition by magnetic ink character recognition is not possible, since recognition by optical character recognition is attempted, the recognition rate of magnetic ink characters is improved, and magnetic ink character recognition and optical character recognition are improved. Since both results can be used, erroneous recognition can be effectively suppressed.

  The above-described embodiment is merely an aspect of the present invention, and can be arbitrarily modified and applied within the scope of the present invention. A modification will be described below. In addition, about the structure same as embodiment mentioned above, the same code | symbol is used and the overlapping description is abbreviate | omitted.

(Modification)
For example, in the above-described embodiment, when the character type of the magnetic ink character cannot be recognized by the magnetic ink character recognition, the optical character is detected if the number of characters detected by the magnetic ink character recognition matches the number of characters detected by the optical character recognition. Although it is the structure which performs recognition, it is not limited to such a structure.
For each of the magnetic ink characters included in the magnetic ink character string 4A, the character type is determined by magnetic ink character recognition and the character type is determined by optical character recognition, and the character is determined by magnetic ink character recognition and optical character recognition. When the types match, the final character type of the magnetic ink character may be determined. In this way, the certainty of magnetic ink character recognition can be further increased.

  In the above-described embodiment, the host computer 70 includes the character recognition unit 80 and recognizes magnetic ink characters. However, the check reader 1 has the function of the character recognition unit 80. In addition, the check reading device 1 may be configured to execute various processes related to the recognition of the magnetic ink characters alone. In this case, the check reading device 1 functions as a recording medium processing device.

  DESCRIPTION OF SYMBOLS 1 ... Check reading apparatus (recording medium processing apparatus), 4 ... Check (recording medium), 4A ... Magnetic ink character string, 30 ... Check conveyance mechanism (conveyance part), 54 ... Magnetic head (reading part), 70 ... Host computer (Recording medium processing device) 71... Control unit 73.

Claims (6)

A transport unit for transporting the recording medium;
A reading unit that magnetically reads magnetic ink characters recorded on the recording medium;
A controller that controls the transport unit and the reading unit;
The controller is
Controlling the transport unit to transport the recording medium,
Signal waveform data obtained by reading the magnetic ink characters of the recording medium being conveyed by the reading unit is analyzed, a first peak determined to be the first peak in the signal waveform data is detected, and the first peak is detected. A character cutout start position of one magnetic ink character is determined based on a peak position, and first character waveform data is cut out from the signal waveform data in a range corresponding to the one magnetic ink character,
When magnetic ink character recognition is performed on the cut out first character waveform data and it is determined that the character type of the magnetic ink character cannot be recognized, it is determined that the second peak is adjacent to the first peak. A peak is detected, the character cutout start position is determined again based on the position of the second peak, and the second character waveform data is cut out from the signal waveform data in a range corresponding to the one magnetic ink character. A recording medium processing apparatus for performing magnetic ink character recognition again on the cut-out second character waveform data. The controller is
In the signal waveform data, when the ratio of the height of the waveform at a position separated by a predetermined width from the position of the first peak to the height of the waveform at the position of the first peak exceeds a predetermined ratio, 2. The recording medium processing apparatus according to claim 1, wherein a position separated from the position of one peak by the predetermined width is determined as the position of the second peak. A storage unit that stores a reference waveform of a plurality of character types defined in the standard,
The controller is
The magnetic ink character font is an E-13B font,
When magnetic ink character recognition is performed on the first character waveform data and it is determined that the character type of the magnetic ink character cannot be recognized, the magnetic ink character of the magnetic ink character is determined from the plurality of character types stored in the storage unit. Select character type candidates,
When the candidate character type is “3” or “8”, the second character waveform data is cut out and magnetic ink character recognition is performed again on the second character waveform data. The recording medium processing apparatus according to claim 2, wherein the recording medium processing apparatus is a recording medium processing apparatus. The controller is
The recording medium processing apparatus according to claim 3, wherein the second character waveform data is cut out once for each of the magnetic ink characters based on the position of the second peak. A control method for a recording medium processing apparatus comprising: a conveying unit that conveys a recording medium; and a reading unit that magnetically reads magnetic ink characters recorded on the recording medium,
Analyzing the signal waveform data obtained by transporting the recording medium by the transport unit, reading the magnetic ink characters of the transported recording medium by the reading unit, and detecting a first peak in the signal waveform data; Determining a character cutout start position of one magnetic ink character based on the position of the first peak, and cutting out the first character waveform data in a range corresponding to the one magnetic ink character from the signal waveform data;
When magnetic ink character recognition is performed on the cut out first character waveform data and it is determined that the character type of the magnetic ink character cannot be recognized, it is determined that the second peak is adjacent to the first peak. A peak is detected, the character cutout start position is determined again based on the position of the second peak, and the second character waveform data is cut out from the signal waveform data in a range corresponding to the one magnetic ink character. A method of controlling a recording medium processing apparatus, wherein magnetic ink character recognition is performed again on the cut-out second character waveform data. A program that is executed by a control unit that controls each unit of a recording medium processing apparatus that includes a conveyance unit that conveys a recording medium, and a reading unit that magnetically reads magnetic ink characters recorded on the recording medium. ,
The control unit
Analyzing the signal waveform data obtained by transporting the recording medium by the transport unit, reading the magnetic ink characters of the transported recording medium by the reading unit, and detecting a first peak in the signal waveform data; Determining a character cutout start position of one magnetic ink character based on the position of the first peak, and cutting out the first character waveform data in a range corresponding to the one magnetic ink character from the signal waveform data;
When magnetic ink character recognition is performed on the cut out first character waveform data and it is determined that the character type of the magnetic ink character cannot be recognized, it is determined that the second peak is adjacent to the first peak. A peak is detected, the character cutout start position is determined again based on the position of the second peak, and the second character waveform data is cut out from the signal waveform data in a range corresponding to the one magnetic ink character. A program for causing magnetic ink character recognition to be performed again on the cut-out second character waveform data.

Images