JP4403063B2 - Symbol information reading method and symbol information reading apparatus - Google Patents

Description

  The present invention relates to a symbol information reading method and a symbol information reading apparatus that optically read symbol information such as a bar code, and in particular, symbol information that can read symbol information while suppressing the influence of noise. The present invention relates to a reading method and a symbol information reading apparatus.

  2. Description of the Related Art Conventionally, barcodes have been widely used as means for assigning unique information to a medium such as paper or plastic and automatically recognizing the information. For example, a one-dimensional barcode is used for general consumer goods. In recent years, demands for the amount of information on barcodes have increased, and symbol information called two-dimensional barcodes that have a much larger capacity than one-dimensional barcodes have appeared. A reading apparatus corresponding to the two-dimensional bar code is gradually becoming widespread.

  Among these two-dimensional barcodes, there is a method of increasing the amount of information by stacking one-dimensional barcodes, which is called a stack barcode. A typical one is a stack type barcode called PDF417. This code system PDF417 is internationally standardized as ISO / IEC15438.

  As a reading device that reads a stack barcode, for example, there is a reading device described in Patent Document 1 or Patent Document 2. The barcode reader disclosed in Patent Document 1 captures a barcode with a two-dimensional imaging device, takes the image into a memory, and decodes barcode symbol information based on this data.

  However, in the barcode reader disclosed in Patent Document 1, there is a problem that the reading accuracy depends on the direction of the label of the stacked barcode, or the label is taken out of the field of view of the imaging device. There is a problem that it is not considered. As a means for improving such a problem, there is a symbol information reading apparatus disclosed in Patent Document 2. The symbol information reading device disclosed in Patent Document 2 captures a barcode with a two-dimensional imaging device and detects the position and inclination of the barcode, so that the stack barcode label is set in any orientation. The barcode symbol information can be read even if the captured image has a defect or is missing.

JP-A-2-268383 JP-A-5-324887 (paragraph [0013])

  However, the symbol information reading apparatus disclosed in Patent Document 2 has a problem that the reliability of decoding is lowered when the inclination of the label of the stack barcode is not zero.

  That is, the symbol information reading device disclosed in Patent Document 2 obtains a straight line as a cutting reference after obtaining the inclination of the label of the stack barcode, determines a scan line based on this, and determines the scan line. The address at the upper point is calculated, the pixel value at the corresponding point is extracted, and stored in the pixel value array.

  Therefore, in particular, when the label inclination of the stack barcode is not zero (when the label inclination is not horizontal or vertical), noise is generated in the obtained pixel array due to a quantization error generated during address calculation. As a result, there is a problem that the reliability of decoding is lowered.

  Further, since the symbol information reading device disclosed in Patent Document 2 basically obtains a pixel array by thinning scanning, it is vulnerable to local noise and only a part of the symbol image information is used for decoding. There are problems such as lack of reliability.

  The present invention has been made in view of these points, and an object of the present invention is to reduce the reliability of decoding by reducing noise due to quantization error, local contamination, and the like. An information reading method and a symbol information reading device are provided.

  In order to solve the above-described problems, the present invention provides a process for converting image data obtained by imaging symbol information such as a barcode into corrected image data having a zero inclination angle in a symbol information reading method. A step of smoothing the corrected image data, and a step of specifying a column delimiter of the symbol information by calculating a sum value in the column direction on the smoothed corrected image data. Features.

  More specifically, the present invention provides the following.

  (1) In a symbol information reading method for reading the symbol information by processing the image data obtained by imaging the symbol information recorded on the medium, the image data is converted into corrected image data having a zero inclination angle. A column of the symbol information by calculating an angle conversion step for conversion, a smoothing step for smoothing the corrected image data, and calculating a sum value in the column direction on the corrected image data smoothed by the smoothing step. And a column specifying step for specifying a delimiter of the symbol information reading method.

  According to the present invention, an image data obtained by imaging symbol information recorded on a medium such as paper or plastic is processed in software so that the symbol information reading method reads the symbol information. An angle conversion step for converting the data into corrected image data with a zero tilt angle, a smoothing step for smoothing the corrected image data, and a sum value in the column direction on the corrected image data smoothed by the smoothing step. Since the calculation includes a column specifying step that specifies a column break of the symbol information, the column specifying step has smoothed the corrected image data whose inclination angle has been zeroed by the angle conversion step. It will be done later.

  Accordingly, it is possible to reduce noise due to quantization error, local contamination, and the like, and to prevent deterioration in decoding reliability. In addition, since the column boundary can be specified by calculating the profile obtained by calculating the pixel for each column of symbol information, the influence of noise such as local contamination can be reduced by the projection averaging function. it can.

  Here, in the “angle conversion step”, the inclination of the image data itself obtained by imaging the symbol information is changed and converted into corrected image data having a zero inclination angle, and the optical coordinate system is rotated. Thus, any method may be used as long as it can generate corrected image data with a zero inclination angle as a result, for example, conversion into corrected image data with a substantially zero inclination angle.

  The “smoothing step” may be any method as long as it is an interpolation process or an averaging process for the purpose of smoothing. For example, the corrected image data is converted into a median filter, an edge preserving filter, an adaptive winner filter, a movement Examples include interpolation or averaging through various filters such as an average filter.

  (2) The symbol information reading method further sets a set of a plurality of continuous rows on the corrected image data smoothed by the smoothing step, and sets the set relative to the corrected image data. The symbol according to (1), further including a row specifying step of specifying a line delimiter of the symbol information by calculating a correlation value sequence for the row in which the set is set while moving the symbol. Information reading method.

  According to the present invention, the above-described symbol information reading method includes a set of a plurality of consecutive rows such as one row, two rows, and three rows on the corrected image data smoothed by smoothing affirmation. , And move the set relative to the corrected image data (that is, 2 rows, 3 rows and 4 rows, then 3 rows, 4 rows and 5 rows, etc.) By calculating the correlation value sequence for, the line identification process for identifying the line breaks of the symbol information is included, so the symbol information is reduced after reducing noise due to quantization errors and local contamination. Can be specified, and as a result, degradation in reliability of decoding can be prevented.

(3) The symbol information includes a start pattern indicating the start of the symbol information and a stop pattern indicating the end of the symbol information.
The symbol information reading method further includes calculating the similarity between a bar length and a run length data string of one column and a predetermined reference pattern in a row direction on the corrected image data. The symbol information reading method according to (1) or (2), further comprising a detection step of detecting a pattern or the stop pattern.

  According to the present invention, the symbol information described above includes a star and pattern indicating the start of the symbol information and a stop pattern indicating the end of the symbol information, and the symbol information reading method includes a correction. A detection step of detecting a start pattern or a stop pattern by calculating a similarity between a run length data string of bars and spaces for one column and a predetermined reference pattern in the row direction on the image data is included. Therefore, it is possible to detect a start pattern or a stop pattern after reducing noise due to quantization error, local contamination, and the like, and to prevent a reduction in decoding reliability.

  (4) The symbol information reading method further includes a determination step of determining whether or not the total number of bars and spaces for one column is equal to a preset number in the row direction on the corrected image data. The symbol information reading method according to any one of (1) to (3), comprising:

  According to the present invention, in the above-described symbol information reading method, it is determined whether or not the total number of bars and spaces for one column is equal to a preset number in the row direction on the corrected image data. Since the process is included, it is possible to appropriately determine whether or not there is an abnormality in the data column representing the desired data after reducing noise due to quantization error or local contamination, and in turn decoding. It is possible to prevent a decrease in reliability.

  (5) A symbol information reading apparatus comprising reading means for reading symbol information using the symbol information reading method according to any one of (1) to (4).

  According to the present invention, it is possible to provide a symbol information reading apparatus including a reading unit that reads symbol information using the above-described symbol information reading method, so that noise due to quantization error or local contamination is reduced. As a result, it is possible to prevent a decrease in reliability of decoding.

  Since the symbol information reading method and the symbol information reading apparatus according to the present invention smooth the corrected image data with zero tilt angle and specify the column separator of the symbol information as described above, the quantization error Noise and local contamination can be reduced, which in turn can prevent degradation in decoding reliability, and can also reduce the effects of noise such as local contamination due to projection averaging. it can.

  The best mode for carrying out the present invention will be described below with reference to the drawings.

[Symbol information reader]
FIG. 1 is a block diagram showing an electrical configuration of a symbol information reading apparatus 1 according to an embodiment of the present invention.

  In FIG. 1, the symbol information reading device 1 includes an imaging device 11 having a contact-type imaging device 11 a and a card transport mechanism 11 b, an image memory 12, and a data processing device 13. The data processing device 13 includes a position detection unit 13a, an inclination correction unit 13b, a structure analysis unit 13c, and a decoding unit 13d. A barcode symbol 21 of a two-dimensional barcode is printed on a record carrier 2 such as a card to which symbol information such as a barcode is given.

  The imaging device 11a of the imaging device 11 images the barcode symbol 21 printed on the record carrier 2 by photoelectric conversion. The image memory 12 stores image data of the barcode symbol 21 imaged by the image sensor 11a. The data processing device 13 captures the image data of the barcode symbol 21 from the image memory 12 and performs various processes on the captured image data.

  A symbol information reading method according to an embodiment of the present invention in the symbol information reading device 1 having such an electrical configuration will be described.

[Symbol information reading method]
FIG. 2 is a flowchart showing the flow of the symbol information reading method according to the embodiment of the present invention. The flow of the symbol information reading method according to the embodiment of the present invention will be outlined with reference to FIG.

  First, position detection is performed (step S21). More specifically, the imaging element 11a of the symbol information reading apparatus 1 images the barcode symbol 21 of the record carrier 2 that has moved to a predetermined position along the card transport mechanism 11b by photoelectric conversion. The captured image data of the barcode symbol 21 is stored in the image memory 12. The image memory 12 may be anything such as RAM, SDRAM, DDRSDRAM, RDRAM, etc. as long as it can store image data.

  Thereafter, the position detection unit 13a of the data processing device 13 reads the image data stored in the image memory 12, and detects the position of the barcode symbol 21 in the image data.

  Next, tilt correction is performed in the data processing device 13 (step S22). More specifically, the inclination correction unit 13b of the data processing device 13 reads the image data whose position has been detected in step S21, and converts the image data into corrected image data with a zero inclination angle.

  Next, structural analysis is performed in the data processing device 13 (step S23). More specifically, the structure analysis unit 13c of the data processing device 13 analyzes the structure of the barcode symbol 21 based on the corrected image data converted in step S22.

  Finally, decryption processing is performed in the decryption unit 13d of the data processing device 13 (step S24). More specifically, the decoding unit 13d of the data processing device 13 performs the decoding process of the barcode symbol 21 based on the structure of the barcode symbol 21 analyzed in step S23. If the decoding process fails, the process returns to step S21 again.

  FIG. 3 is a diagram illustrating an example of the image data of the barcode symbol 21 captured in step S21 described above. A bar code symbol 21 shown in FIG. 3 represents a bar code symbol having a label structure of PDF417, which is a kind of stack type bar code.

  In FIG. 3, the barcode symbol 21 has a vertical direction in the figure as a row direction and a horizontal direction as a column direction, and the column direction is largely divided into five (in FIG. 3, it is divided into five columns). A data column is arranged at the center, a left row indicator and a right row indicator are arranged on the left and right sides of the data column, and a start pattern and a stop pattern are arranged on the left and right sides thereof. On the other hand, the barcode symbol 21 shown in FIG. 3 is composed of six rows, and each row contains one data word. Therefore, the number of data of the barcode symbol 21 is 6 (1 (for one data column) × 6 rows).

  FIG. 4 is a diagram illustrating a state in which the barcode symbol 21 is imaged in an inclined state by the imaging element 11 a of the imaging device 11. When the barcode symbol 21 is scanned by the imaging device 11, the row direction is not necessarily positioned perpendicular to the card transport mechanism 11b. The image data read by the image sensor 11a may be tilted as shown in FIG. 4, for example. In such a case, in the conventional symbol information reading apparatus 1, the reliability of decoding has been impaired by noise due to quantization errors. However, according to the present invention, the influence of such noise can be reduced. Hereinafter, each process (step S21-step S24) of the flowchart shown in FIG. 2 will be described in detail.

[Position detection]
FIG. 5 is a flowchart showing a flow of position detection in the flowchart shown in FIG. FIG. 6 is an enlarged view in which the big bar portion and its periphery in the start pattern of the barcode symbol 21 are enlarged.

  In FIG. 5, first, the variable i is initialized by substituting 0 (step S51).

  Next, on the horizontal line L (i) at Y = i, image data is read in the X direction, and a point where the image changes from light to dark (referred to as point P (i)) is searched. In addition, a point where the image changes from dark to light (referred to as point Q (i)) is searched for on the same line (step S52).

  Next, it is determined whether i = n−1 (n: the number of pixels in the Y direction in FIG. 6) is satisfied (step S53). If it is determined that i is not satisfied, i is incremented by one. Then (step S54), the process of step S52 is performed again. On the other hand, when it determines with satisfy | filling, a process is moved to following step S55. At this stage, a set of n points (P (i), Q (i)) (I = 0, 1,..., N−2, n−1) is obtained.

  Next, the coordinates of point A and point C in FIG. 6 are obtained (step S55). More specifically, D (i) = | P (i) −Q (i) | is calculated, and the minimum value min (D (i)) of D (i) is obtained. This min (D (i)) corresponds to two points of the big bar point A and point C where the distance between the PQs is the shortest (see FIG. 6). Thereby, the Y coordinate of the point A and the point C becomes Ay = min (i) and Cy = max (i), respectively. Further, since the X coordinates of the point A and the point C are the X coordinates of the point P with respect to each i, the X coordinate of Ax = P (i = Ay) and the X coordinate of Cx = P (i = Cy), respectively. Become.

  Next, the coordinates of point B and point C in FIG. 6 are obtained (step S56). More specifically, the range of i in which D (i) is constant is specified. The Y coordinates of the points B and D of the big bar are max (i) and min (i) in the range. Since the X coordinates of the points B and D are the X coordinates of the points P and Q with respect to each i, the X coordinates of Bx = P (i = By) and Dx = Q (i = Dy) respectively. X coordinate.

  In this way, since the coordinates of the four corners of the big bar are determined through the processing of step S51 to step S56, the inclination angle can be calculated by atan ((Ay−Dy) / (Ax−Dx)). .

  In order to increase the accuracy of tilt detection, the same operation is performed by exchanging the roles of X and Y in FIG. 6 to obtain the coordinates A ′, B ′, C ′, D ′ of the four corners of the big bar. The average of the coordinate values A, B, C, and D may be taken as final coordinate values.

  In FIG. 5, the coordinates of the points A and C are obtained (step S55), and the coordinates of the points B and D are also obtained (step S56). However, the present invention is not limited to this. The inclination may be detected by obtaining only the coordinates of A and point C.

[Tilt correction]
FIG. 7 shows a state in which the image data of the barcode symbol 21 inclined at the above-described angle (= atan ((Ay−Dy) / (Ax−Dx))) is converted into corrected image data having a zero inclination angle. FIG.

  In FIG. 7, conversion to corrected image data with a tilt angle of zero is performed using the tilt angle of the barcode symbol 21. For example, it can be performed by a method such as affine transformation. In the symbol information reading method according to the embodiment of the present invention, an interpolation process or an averaging process is performed on the image after the coordinate conversion for the purpose of smoothing in order to reduce the influence of the quantization error accompanying the coordinate conversion. I do. For example, the correction image data is applied to various filters such as a median filter, an edge preserving filter, an adaptive winner filter, and a moving average filter.

[Structural analysis]
FIG. 8 is a flowchart showing the flow of structural analysis in the flowchart shown in FIG.

  In FIG. 8, first, a horizontal projection process is performed (step S81), and then a start pattern and a stop pattern are analyzed using the difference in projection (step S82). Unlike the other code words, the start pattern and the stop pattern are invariant patterns common to all the rows. Therefore, by taking a projection, the patterns are averaged and stable detection is possible.

  FIG. 9 is a diagram obtained by performing predetermined processing on the averaged corrected image data (see FIG. 7). More specifically, FIG. 9A shows a calculation of a projection in the horizontal direction (in the row direction in FIG. 3) for the averaged corrected image data (see FIG. 7). FIG. 9B shows the difference calculated for the graph of FIG.

  The detection of the start pattern is performed by counting the interval (run length) of the points where the pattern changes by the number of pixels using the graph shown in FIG. 9A or 9B. For example, in FIG. 9B, the sense of the point where the pattern changes is obtained as StartWork = [47, 6, 5, 6, 7, 6, 6, 18]. On the other hand, the ratio between the length of the start pattern bar and the space is StartMark = [8, 1, 1, 1, 1, 1, 1, 3] according to the PDF417 standard. Here, for example, a normalized correlation R can be used as an index for examining the similarity between the two. In FIG. 9B, when considering the normalized correlation R, R = corrcoef (StartWork, StartMark) = 0.993, and R is sufficiently close to 1. Therefore, in this case, it is determined that the start pattern is appropriately detected.

  Thus, after it is determined whether or not the start / stop pattern is properly detected (step S83), if it is determined that the start / stop pattern is properly detected, the process proceeds to step S85. . On the other hand, when it is determined that the start / stop pattern is not properly detected, the process is terminated as being undecodable (step S84).

  In this embodiment, the normalized correlation R is used as a measure of similarity. However, the present invention is not limited to this, and for example, sum of absolute differences, sum of products, etc. can be used as appropriate.

  Next, peak detection is performed on the graph of FIG. 9B (step S85). More specifically, since a transition from space to bar occurs in all rows at the codeword boundary, a large difference value appears in this portion on the projected difference waveform (upward arrow in FIG. 9B). . Then, in order to obtain the difference value (peak value) indicated by the upward arrow in FIG. 9B, an appropriate threshold value is prepared, and the presence or absence of a peak can be determined based on whether or not the threshold value is exceeded. . Note that this peak position is stored for use in the next processing.

  Next, column boundary detection is performed (step S86). More specifically, the column boundary is detected based on the peak position stored in step S85. The interval between adjacent peaks represents the column width and is stored in the same manner. Here, if there is a stain near this boundary in a specific row, the codeword change point may not be detected correctly during the scan of the row, but by using projection as in the present embodiment, this The influence of the contamination is reduced by the averaging operation, and the adverse effect on the detection of the codeword boundary can be suppressed.

  Next, a row boundary is detected (step S87). More specifically, a description will be given with reference to FIGS. FIG. 10 is a waveform diagram showing pixel values of each line in the horizontal direction of the averaged corrected image data. FIG. 11 is an explanatory diagram for explaining a state in which a line break of the barcode symbol 21 is specified.

  In FIG. 10A, for detection of a row boundary, first, a set of a plurality of continuous rows is set on the averaged corrected image data. For example, a set (line set S1) composed of three consecutive horizontal lines L (1), L (2) and L (3) (hereinafter abbreviated as “L1, L2 and L3”) is set.

  Then, when these self-normalized correlations and cross-normalized correlations are obtained, a total of nine correlation values (values obtained by calculating self-normalized correlations for L1 and L1, L2 and L2, L3 and L3 (three) and , L1 and L2, L1 and L3, L2 and L1, L2 and L3, L3 and L1, and L3 and L2 are calculated as a correlation value string consisting of nine correlation values (6). ) Is obtained. If the smallest value among the nine correlation values is larger than a predetermined threshold value r0, 1 is given to this line set S1, and if it is smaller than the predetermined threshold value r0, this line set S1 is assigned to this line set S1. 0 is given.

  Here, for the set of horizontal lines L1, L2, and L3, since the horizontal lines L1, L2, and L3 are all included in row 1 (the uppermost row), the highest of the nine correlation values. The smaller value is larger than the threshold value r0 and 1 is given (in FIG. 11, the determination value of the line set S1 is 1).

  Next, the above-described set is moved relative to the corrected image data (for example, considering the line set S2 including L2, L3, and L4), a correlation value sequence is calculated, and the calculated correlation value sequence By determining whether or not the minimum value is greater than the threshold value, a determination value of 0 or 1 is given to the line set.

  Similarly, when the above-described processing (processing for giving a judgment value) is repeated up to the horizontal lines Ln-2, Ln-1, Ln (line set Sn-2), a total of n-2 1s and 0s are obtained. Is obtained (right column in FIG. 11).

  Here, when three horizontal lines are selected from the same row, the line set consisting of these three horizontal lines has a value close to 1, and the three horizontal lines are selected across the rows. In this case, the line set made up of these three horizontal lines has a relatively small value. More specifically, in FIG. 10B, the horizontal line above the horizontal line L18 belongs to row 1, the horizontal line below the horizontal line L18 belongs to row 2, and this horizontal line L18 is It is a horizontal line located at the boundary of row 2.

  Accordingly, in the line set including the horizontal line L18, the determination value is almost 0, and in other cases, the determination value is 1 (see FIG. 11). A line set whose judgment value is close to 0 represents a change of row. Therefore, by scanning a series of determination values and identifying a place where the determination value is close to 0, it is possible to know the change position of a row. it can. In this embodiment, since the similarity between horizontal lines is evaluated by a correlation function, a range excluding common patterns such as a start pattern and a stop pattern is evaluated as shown in FIG. By setting the range, useless calculation (calculation cost) can be omitted.

  As described above, step S87 is performed according to the flow of setting a line group, calculating a correlation value sequence, comparing the minimum value of the correlation value sequence with a threshold value, providing a determination value of 0 or 1, and scanning a sequence of determination values. The row boundary is detected.

  Note that if it is possible to determine which row each horizontal line of the corrected image data belongs to by detecting the row boundary, the process is terminated as being decodable (step S88). Moreover, the local noise of a horizontal line can be reduced by calculating the average of the horizontal lines included in each row. Further, the horizontal line after the averaging can be used as a pixel pattern of the row for a decoding process described later. Thereby, decoding accuracy can be improved.

[Decryption process]
FIG. 12 is a flowchart showing the flow of decoding in the flowchart shown in FIG.

  In FIG. 12, first, line width measurement is performed (step S121). More specifically, the line width measurement is a process of scanning the pixel pattern of each row to obtain the length of the bar and space, that is, the line width. This line width measurement will be described in detail with reference to FIG.

  FIG. 13 is a waveform diagram showing a part of a row pixel pattern. The bar width and the space width are obtained by counting the number of pixels between the change points of the pattern. Since one column is composed of four bars and four spaces, when there is no damage to the pixel pattern, a total of eight width data is obtained as shown in FIG.

  On the other hand, when there is an abnormality in the pixel pattern, a total of 8 or more (9) width data is obtained as shown in FIG. In such a case, it is found that the column is damaged, and a flag indicating that the reliability of this column is low is set. When this operation is executed up to the end of the pixel pattern, the same processing is executed in the next row. When the line width data is obtained for all the rows, the processing in step S121 (see FIG. 12) is terminated.

  Next, line width normalization processing is performed (step 122). The line width normalization process refers to a process of converting line width data expressed by the number of pixels into a module number expression. One module corresponds to the minimum width of the bar or space. One column is composed of 17 modules. If the line width data in one column is W1, W2, W3, W4, W5, W6, W7, W8, and Wc = W1 + W2 + W3 + W4 + W5 + W6 + W7 + W8, the normalized line width data is Xi = Wi * 17 / Wc (i = 1 , 2,..., 7, 8). For example, the X sequence of the left column shown in FIG. 13A is [5, 1, 1, 1, 1, 1, 5, 2].

  Further, the X sequence is converted into a t sequence. This is a sum of two adjacent Xi and Xi + 1. When the X sequence in the left column shown in FIG. 13A is converted into a t sequence, [6, 2, 2, 2, 2, 6 , 7].

  Next, code word conversion is performed (step S123). More specifically, a code word corresponding to the t sequence obtained in step S122 is acquired from a predetermined reference table. When codeword conversion is completed, general high-level decoding is performed (step S124), and the decoding process is completed. Further, the data for which the decoding process has been completed is output to the upper control apparatus together with the symbol image and the like.

  As described above, according to the symbol information reading method performed in the flow shown in FIG. 2, noise due to quantization error, local contamination, and the like can be reduced by appropriate interpolation processing and averaging processing. As a result, the reliability of decoding can be prevented from being lowered.

  In the present embodiment, the present invention is applied to a combination of a one-dimensional imaging device and a linear transport mechanism. However, the present invention is not limited to this, and examples thereof include a two-dimensional CCD and a CMOS imager. The present invention may be applied to a combination of an area sensor and a subject support mechanism.

  Furthermore, in the present embodiment, the PDF417 format is used for the bar code label. However, the present invention is not limited to this. For example, the bar code label is a one-dimensional code such as Code 49 or other stack type bar code or JAN. A bar code may be used.

  INDUSTRIAL APPLICABILITY The symbol information reading method and symbol information reading apparatus according to the present invention are useful as those capable of preventing deterioration in decoding reliability by reducing noise due to quantization error and local contamination.

It is a block diagram which shows the electrical constitution of the symbol information reader which concerns on embodiment of this invention. It is a flowchart which shows the flow of the symbol information reading method which concerns on embodiment of this invention. It is a figure which shows an example of the image data of the barcode symbol imaged in step S21 mentioned above. It is a figure which shows a mode that the barcode symbol was imaged in the state inclined by the image pick-up element of the imaging device. It is a flowchart which shows the flow of the position detection in the flowchart shown in FIG. It is the enlarged view which expanded the part of the big bar in a start pattern, and its periphery among barcode symbols. It is a figure which shows a mode when the image data of the barcode symbol inclined by the predetermined angle is converted into the correction image data of zero inclination angle. It is a flowchart which shows the flow of the structural analysis in the flowchart shown in FIG. It is the figure calculated by giving a predetermined process to the averaged correction image data (refer FIG. 7). It is a wave form diagram which shows the pixel value of each line in the horizontal direction of the averaged correction | amendment image data. It is explanatory drawing for demonstrating a mode that the division | segmentation of the line | wire of a barcode symbol is specified. 3 is a flowchart showing a decoding flow in the flowchart shown in FIG. 2. It is a waveform diagram showing a part of a row pixel pattern.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Symbol information reader 2 Record carrier 11 Imaging device 11a Imaging element 12 Image memory 13 Data processing device 13a Position detection part 13b Inclination correction part 13c Structure analysis part 13d Decoding part

Claims (5)

In a symbol information reading method for reading symbol information by processing image data obtained by imaging symbol information recorded on a medium,
An angle conversion step of converting the image data into corrected image data having a tilt angle of zero;
A smoothing step of smoothing the corrected image data;
A column specifying step of specifying a column delimiter of the symbol information by calculating a sum value in the column direction on the corrected image data smoothed by the smoothing step. Method. The symbol information reading method further includes:
A set consisting of a plurality of continuous rows is set on the corrected image data smoothed by the smoothing step, and the set is set while moving the set relative to the corrected image data. 2. The symbol information reading method according to claim 1, further comprising a row specifying step of specifying a line break of the symbol information by calculating a correlation value sequence for the row. The symbol information includes a start pattern indicating the start of the symbol information and a stop pattern indicating the end of the symbol information.
The symbol information reading method further includes calculating the similarity between a bar length and a run length data string of one column and a predetermined reference pattern in a row direction on the corrected image data. 3. The symbol information reading method according to claim 1, further comprising a detection step of detecting a pattern or the stop pattern.   The symbol information reading method further includes a determination step of determining whether the total number of bars and spaces for one column is equal to a preset number in the row direction on the corrected image data. 4. A symbol information reading method according to claim 1, wherein 5. A symbol information reading apparatus comprising reading means for reading symbol information using the symbol information reading method according to claim 1.

Images