JP7658211B2 - IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, AND IMAGE PROCESSING PROGRAM - Google Patents

Description

This disclosure relates to an image processing device, an image processing method, and an image processing program.

JP 2013-40895 A (Patent Document 1) discloses an inspection system that inspects the appearance of a barcode. The inspection system sets a defect detection area in a photographed image of the barcode, and identifies areas of smudges or chipping (defective areas) based on changes in density values in the defect detection area. The inspection system determines that the appearance of the barcode is defective if the defective area is equal to or larger than a specified area.

JP 2013-40895 A

Sometimes smudges or chipping occurs at the longitudinal tip of the bar. In the inspection system described above, to prevent erroneous detection of edges, the defect detection area is set to an area that is the barcode area reduced by a specified amount in the length direction of the bar. Therefore, the inspection system described above does not detect smudges or chipping that occurs in areas outside the defect detection area. Since smudges or chipping that occurs in areas outside the defect detection area can mar the appearance of the barcode, there is a need for technology that can inspect the appearance of the barcode regardless of where the smudges or chipping occurs.

The objective of this disclosure is to provide an image processing device, an image processing method, and an image processing program that can inspect the appearance of a barcode regardless of where blurring or chipping occurs.

An image processing device according to an aspect of the present disclosure includes a receiving unit that receives a captured image of a barcode including multiple bars, a specifying unit that specifies a bar region in the captured image that corresponds to the multiple bars, a determining unit that determines an inspection target region based on the bar region, an extracting unit that extracts at least one partial region composed of pixels having characteristics corresponding to the multiple bars from the inspection target region, a calculating unit that calculates the longitudinal length of each of the at least one extracted partial region, and a determining unit that determines that the appearance of the barcode is poor if the minimum value of the lengths is less than a threshold value.

This makes it possible to inspect the appearance of the barcode regardless of where the mark is smudged or missing.

In the above disclosure, the inspection target area is preferably an area obtained by expanding the bar area by a predetermined width in the up, down, left and right directions.

This allows the tip of the bar to be included in the area extracted as the subregion.

In the above disclosure, preferably, the image processing device further includes a first setting unit that sets the predetermined width based on an input operation by a user.

This allows the user to change the specified width.

In the above disclosure, preferably, the image processing device further includes a second setting unit that sets the threshold value based on an input operation by a user.

This allows the threshold to be changed by user operation.

In the above disclosure, preferably, the receiving unit further receives a correct image of the barcode. The image processing device further includes a second setting unit that sets a threshold value based on the minimum value of the longitudinal length of at least one partial region of the correct image.

This improves user convenience by eliminating the need for users to set threshold values.

In another aspect of the present disclosure, an image processing method executed by a computer includes receiving an image of a barcode including multiple bars, identifying a bar region in the captured image that corresponds to the multiple bars, determining an inspection target region based on the bar region, extracting at least one partial region from the inspection target region that is composed of pixels having characteristics corresponding to the multiple bars, calculating the longitudinal length of each of the at least one extracted partial region, and determining that the appearance of the barcode is poor if the minimum value of the lengths is less than a threshold value.

This makes it possible to inspect the appearance of the barcode regardless of where the mark is smudged or missing.

In another aspect of the present disclosure, an image processing program causes a computer to execute the image processing method described above.

This makes it possible to inspect the appearance of the barcode regardless of where the mark is smudged or missing.

The present disclosure provides an image processing device, an image processing method, and an image processing program that can inspect the appearance of a barcode regardless of where blurring or chipping occurs.

1 is a schematic diagram showing an overall configuration of an image processing system including an image processing device according to an embodiment of the present invention. 1 is a block diagram showing a main hardware configuration of an image processing device according to an embodiment of the present invention; FIG. 2 is a block diagram showing an example of functions realized by the image processing device according to the present embodiment. FIG. 13 is a diagram showing a method for specifying a bar region. FIG. FIG. 13 is a diagram showing an example of a binarization level setting screen. FIG. 13 is a diagram showing an example of a partial region and its vertical width. FIG. 13 is a diagram showing an example of a margin width setting screen. FIG. 13 is a diagram showing an example of a vertical width threshold setting screen. FIG. 2 is a diagram illustrating an example of processing executed by the image processing device according to the present embodiment. FIG. 11 is a diagram showing an example of an output form of the inspection result. 11A and 11B are diagrams illustrating an example of a process in which one image is used as a correct image of a barcode. 11A and 11B are diagrams illustrating an example of processing when a plurality of images are used as correct images of a barcode.

Below, an embodiment of the present invention will be described with reference to the drawings. In the following description, the same parts and components are given the same reference numerals. Their names and functions are also the same. Therefore, detailed descriptions thereof will not be repeated. Note that the embodiments and variations described below may be combined as appropriate.

[Application example]
An application example of the present invention will be described with reference to Fig. 1. In this application example, an image processing device that executes an image processing program for inspecting the appearance of a barcode will be described.

Generally, barcodes are printed on various media (such as labels attached to product packaging). As a result, printing defects can cause the barcode to become smudged or chipped. In such cases, in addition to the readability of the barcode (whether it can be read by a barcode reader), the appearance of the barcode becomes an issue.

This is because if the appearance of the barcode is poor, it will cause anxiety to the user. Even if there is no problem with the readability of the barcode, there are many cases where products with barcodes that have poor appearances are returned. Therefore, it is necessary to inspect the appearance of the barcode.

Figure 1 is a schematic diagram showing the overall configuration of an image processing system including an image processing device in this embodiment. The image processing system 1 includes an image processing device 100, an imaging device 500, an input device 600, and an output device 700. The imaging device 500, the input device 600, and the output device 700 are connected to the image processing device 100.

The imaging device 500 includes, as an example, an imaging element partitioned into multiple pixels, such as a CCD (Coupled Charged Device) or CMOS (Complementary Metal Oxide Semiconductor) sensor, in addition to an optical system such as a lens. The imaging device 500 captures an image of a barcode C including multiple bars B, and transmits image data acquired by the image capture (hereinafter also referred to as the "captured image") to the image processing device 100. In the example shown in FIG. 1, the barcode C is printed on a label L.

The image processing device 100 inspects the appearance of the barcode C by performing image processing on the captured image received from the imaging device 500. In detail, the image processing device 100 calculates the longitudinal length of each bar B (hereinafter also referred to as "vertical width" or "vertical width W") based on the captured image received from the imaging device 500. If a bar that should be a single bar is divided into multiple pieces due to smudges or chipping, the image processing device 100 calculates the vertical width W for each divided bar. If the minimum value of the calculated vertical width W is less than a threshold value, the image processing device 100 determines that the appearance of the barcode C is defective.

If the bar B is blurred or missing, the vertical width W of the bar B will be shorter than the original vertical width, regardless of where the blur or missing occurs. Therefore, the image processing device 100 makes it possible to inspect the appearance of the barcode, regardless of where the blur or missing occurs.

The input device 600 includes at least one of a mouse, a keyboard, and a touch panel, and accepts operations on the image processing device 100. The output device 700 includes a liquid crystal display, an organic EL (Electro Luminescence) display, etc., and displays various types of information. Note that the output device 700 may further include an indicator and a speaker in addition to the display.

The image processing system 1 may further include an illumination device that irradiates light onto the barcode C imaged by the imaging device 500.

(Hardware configuration of image processing device)
The hardware configuration of the image processing device 100 will be described with reference to Fig. 2. Fig. 2 is a block diagram showing the main hardware configuration of the image processing device in this embodiment. The image processing device 100 includes a processor 101, a main memory 102, a communication interface 103, a camera interface 104, an input interface 105, an output interface 106, a memory card interface 107, and a storage device 120. These components are connected to each other via an internal bus 119 so as to be able to communicate with each other.

The processor 101 is, for example, configured with at least one integrated circuit. The integrated circuit is, for example, configured with at least one CPU (Central Processing Unit), at least one ASIC (Application Specific Integrated Circuit), at least one FPGA (Field Programmable Gate Array), or a combination thereof.

The processor 101 realizes various processes according to the present embodiment by expanding the program 122 stored in the storage device 120 into the main memory 102 and executing it. The main memory 102 is composed of a volatile memory, and functions as a work memory required for the processor 101 to execute the program.

The communication interface 103 exchanges data and signals with external devices via the network.

The camera interface 104 corresponds to a "reception unit" that receives an image of a barcode including multiple bars from the imaging device 500, and mediates data transmission between the processor 101 and the imaging device 500. In detail, when the camera interface 104 receives an image from the imaging device 500, it outputs the image to the processor 101.

The input interface 105 mediates data transmission between the processor 101 and the input device 600. That is, the input interface 105 accepts operation commands given by the user operating the input device 600.

The output interface 106 is connected to the output device 700, and outputs signals to the output device 700 to output various types of information in accordance with commands from the processor 101.

The memory card interface 107 mediates data transmission between the processor 101 and the memory card 107A. The memory card 107A includes general-purpose semiconductor storage devices such as SD (Secure Digital), magnetic recording media such as flexible disks, and optical recording media such as CD-ROMs (Compact Disk Read Only Memory).

The storage device 120 is, for example, a hard disk. As an example, the storage device 120 includes a program 122 for implementing various processes according to the present embodiment, and various setting information 124.

The program 122 is provided by being stored in a storage medium such as the memory card 107A. The program 122 is read from the memory card 107A by the memory card interface 107 and installed in the image processing device 100.

Program 122 may be provided not as a standalone program, but as part of an arbitrary program. In this case, the program 122 cooperates with the arbitrary program to realize the processing according to this embodiment. Even if the program does not include some of these modules, this does not deviate from the spirit of the image processing device 100 according to this embodiment. In addition, some or all of the functions provided by program 122 may be realized by dedicated hardware.

In addition, instead of installing the program 122 stored in the memory card 107A in the image processing device 100, a program downloaded from a distribution server or the like via the communication interface 103 may be installed in the image processing device 100.

The setting information 124 includes the margin width and the threshold value of the vertical width of the bar, which will be described later. In the following, the margin width, the threshold value of the vertical width of the bar, etc. being stored in the storage device 120 as the setting information 124 will be expressed as being "set."

(Functions of image processing device)
The functions realized by the image processing device 100 will be described with reference to Fig. 3. Fig. 3 is a block diagram showing an example of the functions realized by the image processing device in this embodiment. In this embodiment, the image processing device 100 realizes a reception unit 131, a specification unit 132, a determination unit 133, an extraction unit 134, a calculation unit 135, a determination unit 136, a first setting unit 137, and a second setting unit 138.

The reception unit 131 is realized by the camera interface 104 shown in FIG. 2. The reception unit 131 receives an image of a barcode including multiple bars from the imaging device 500.

The identification unit 132, the determination unit 133, the extraction unit 134, the calculation unit 135, the judgment unit 136, the first setting unit 137, and the second setting unit 138 are realized by the processor 101 executing the program 122.

The identification unit 132 identifies a bar area in the captured image received by the reception unit 131. A barcode may include numbers in addition to multiple bars. A bar area is an area that corresponds to multiple bars in a barcode.

Now, with reference to FIG. 4, a method for identifying a bar area will be described. FIG. 4 is a diagram showing a method for identifying a bar area. A screen G1 is displayed on the output device 700 (see FIG. 1). The screen G1 includes a field 41 in which a captured image I acquired by the imaging device 500 (see FIG. 1) is displayed, and an input field 42 for inputting the approximate position of the barcode in the captured image I. In the example shown in FIG. 4, the captured image I includes an image of a barcode C (see FIG. 1) and an image of a label L (see FIG. 1) on which the barcode C is printed.

The user inputs the approximate position of the barcode by dragging the four vertices K1 to K4 of the area AR using an input device 600 such as a mouse (see FIG. 1). The coordinates of vertex K1 and vertex K3 are displayed in the input field 42. The user may input the approximate position of the barcode by inputting a numerical value in the input field 42. The input device 600 is used for inputting into the input field 42. The identification unit 132 (see FIG. 3) identifies the bar area P by performing image processing on the area AR using a known technique. It is also possible that the approximate position of the barcode is not input. In that case, the identification unit 132 identifies the bar area P by performing image processing on the entire captured image I using a known technique.

Referring again to FIG. 3, the determination unit 133 determines the inspection target area based on the bar area identified by the identification unit 132. As an example, the determination unit 133 determines an area obtained by expanding the bar area by a predetermined width in the up, down, left, and right directions as the inspection target area. The predetermined width is stored in the storage device 120 as a margin width, which is one of the setting information 124. The predetermined width may be specified by the number of pixels (e.g., 10 pixels, etc.) or may be specified as a ratio to the bar area (e.g., 1.1 times, etc.).

Now, the inspection target area will be described with reference to FIG. 5. FIG. 5 is a diagram showing the inspection target area. Bar area P is indicated by the coordinates of four vertices E1 to E4. Inspection target area Q is indicated by the coordinates of four vertices F1 to F4. Inspection target area Q is an area obtained by expanding bar area P by a predetermined width TH in the up, down, left, and right directions. In the following description, the arrangement direction of the multiple bars is defined as the X direction, and the direction perpendicular to the arrangement direction of the multiple bars in the captured image I is defined as the Y direction.

As an example, assume that 10 pixels are set as the predetermined width. In that case, the determination unit 133 (see FIG. 3) sets the X coordinate value of vertex F1 to the value obtained by subtracting 10 pixels from the X coordinate value of vertex E1, and sets the Y coordinate value of vertex F1 to the value obtained by adding 10 pixels to the Y coordinate value of vertex E1. The determination unit 133 also sets the X coordinate value of vertex F2 to the value obtained by subtracting 10 pixels from the X coordinate value of vertex E2, and sets the Y coordinate value of vertex F2 to the value obtained by subtracting 10 pixels from the Y coordinate value of vertex E2. The determination unit 133 also sets the X coordinate value of vertex F3 to the value obtained by adding 10 pixels to the X coordinate value of vertex E3, and sets the Y coordinate value of vertex F3 to the value obtained by subtracting 10 pixels from the Y coordinate value of vertex E3. In addition, the determination unit 133 sets the X coordinate value of vertex F4 to the X coordinate value of vertex E4 plus 10 pixels, and sets the Y coordinate value of vertex F4 to the Y coordinate value of vertex E4 plus 10 pixels.

When the specified width TH is specified by the number of pixels, the specified width TH1 in the upward direction, the specified width TH3 in the downward direction, the specified width TH2 in the leftward direction, and the specified width TH4 in the rightward direction may be equal to each other, or at least one of them may be a different value.

Referring again to FIG. 3, the extraction unit 134 extracts at least one partial region consisting of pixels having characteristics corresponding to the multiple bars from the inspection target region. The characteristics corresponding to the multiple bars are the characteristics of the reflected light of the multiple bars, and more specifically, the color, density (brightness), etc. As an example, the extraction unit 134 extracts at least one partial region consisting of pixels having colors corresponding to the multiple bars from the inspection target region. As another example, the extraction unit 134 extracts at least one partial region consisting of pixels having densities corresponding to the multiple bars from the inspection target region. The processing by the extraction unit 134 corresponds to a labeling process in so-called image processing. The extraction unit 134 binarizes the inspection target region at a predetermined binarization level, and then extracts the partial region based on the density value. In detail, the extraction unit 134 binarizes the inspection target region at a predetermined binarization level, thereby extracting a group of pixels classified as black as one partial region. The binarization level indicates the range of density values of pixels classified as black. The binarization level is set so that the pixels that make up the bar image, i.e., pixels that have a color that corresponds to multiple bars or pixels that have a density that corresponds to multiple bars, are classified as black.

As a result, the area corresponding to each bar is extracted as a partial area by the extraction unit 134. Note that if a bar that should be a single bar is divided into multiple parts due to smudges or chipping, each divided part is extracted as a single partial area.

Now, with reference to FIG. 6, the setting of the binarization level will be described. FIG. 6 is a diagram showing an example of a binarization level setting screen. Screen G2 is an example of a binarization level setting screen. Screen G2 is displayed on the output device 700 (see FIG. 1). Screen G2 includes an input field 61 for inputting the binarization level, and a button 62. In the input field 61, a range of density values of pixels classified as black is input as the binarization level. When the user inputs a numerical value in the input field 61 and presses the button 62, the processor 101 (see FIG. 2) sets the numerical value input in the input field 61 as the binarization level. When the values shown in FIG. 6 are set as the binarization level, the extraction unit 134 (see FIG. 3) classifies pixels with density values of 0 to 159 as black.

Generally, the color of the bar is black, but the darkness of the black varies depending on the color of the label on which the barcode is printed. Therefore, by adjusting the value entered in input field 61, it is possible to set the pixels that make up the image of the bar to be classified as black.

Referring again to FIG. 3, the calculation unit 135 calculates the longitudinal length (vertical width) of each of at least one partial region extracted by the extraction unit 134. This calculates the vertical width of the bar. If a bar that should be a single piece is divided into multiple pieces due to smudges or chipping, the vertical width of each of the divided pieces is calculated.

The determination unit 136 determines that the appearance of the barcode is defective if the minimum vertical width calculated by the calculation unit 135 is less than a threshold value. The threshold value is stored in the storage device 120 as the setting information 124.

Now, with reference to FIG. 7, the determination method used by the determination unit 136 will be described. FIG. 7 is a diagram showing an example of partial regions and their vertical widths. For ease of illustration, FIG. 7 shows only partial regions R1 to R4 that correspond to bars B1 to B4 out of the multiple partial regions R, but in reality, the regions corresponding to each of the bars B are extracted as partial regions R through processing by the extraction unit 134 (see FIG. 3).

Bars B1 and B2 are examples of a bar that should be a single bar but has been split into multiple pieces due to smudges or chipping. Partial region R2 corresponding to bar B2 is an example of a partial region having the shortest vertical width W among the partial regions R extracted by extraction unit 134. In this example, the vertical width W of partial region R1 calculated by calculation unit 135 (see FIG. 3) is 60 pixels, and the vertical width W of partial region R2 calculated by calculation unit 135 is 20 pixels.

Bar B3 is an example of a bar with a missing tip. In this example, the vertical width W of partial region R3 calculated by calculation unit 135 is 89 pixels.

Bar B4 is an example of a case where no blurring or chipping occurs. In this example, the vertical width W calculated by the calculation unit 135 for each of the multiple partial regions R, excluding partial region R1, partial region R2, and partial region R3, is 100 pixels.

In this example, the smallest value of the vertical width W for each partial region R calculated by the calculation unit 135 is the vertical width W of partial region R2, which is 20 pixels. If the threshold value for the vertical width W is set to 90 pixels, the minimum value of the vertical width W calculated by the calculation unit 135 (20 pixels) is less than the threshold value for the vertical width W (90 pixels), and therefore the determination unit 136 (see FIG. 3) determines that the appearance of the barcode is defective.

Referring again to FIG. 3, the first setting unit 137 sets the predetermined width based on an input operation by the user. In detail, the first setting unit 137 stores the value (predetermined width) input from the input device 600 in the storage device 120 as the margin width. Note that the image processing device 100 does not need to include the first setting unit 137, in which case it is assumed that a value (predetermined width) previously determined as the margin width is stored in the storage device 120.

Now, with reference to FIG. 8, a method for setting the margin width will be described. FIG. 8 is a diagram showing an example of a margin width setting screen. Screen G3 is an example of a margin width setting screen. Screen G3 is displayed on the output device 700 (see FIG. 1). Screen G3 includes an input field 81 for inputting a value (predetermined width), and a button 82. When the user inputs a value in the input field 81 and presses the button 82, the processor 101 (see FIG. 2) saves the value input in the input field 81 as the margin width in the storage device 120 (see FIG. 3).

Referring again to FIG. 3, the second setting unit 138 sets the vertical width threshold based on an input operation by the user. As an example, the second setting unit 138 stores the value input from the input device 600 in the storage device 120 as the vertical width threshold.

Now, with reference to FIG. 9, a method for setting the vertical width threshold will be described. FIG. 9 is a diagram showing an example of a vertical width threshold setting screen. Screen G4 is an example of a vertical width threshold setting screen. Screen G4 is displayed on the output device 700 (see FIG. 1). Screen G4 includes an input field 91 for inputting a value, and a button 92. When the user inputs a value in the input field 91 and presses the button 92, the processor 101 (see FIG. 2) saves the value input in the input field 91 as the vertical width threshold in the storage device 120 (see FIG. 3).

Referring again to FIG. 3, as another example, the second setting unit 138 may set the threshold value for the vertical width based on the correct image of the barcode. The correct image of the barcode is acquired by the imaging device 500 capturing an image of a correctly printed barcode, and is accepted by the acceptance unit 131. Details will be described later.

The image processing device 100 may not include the second setting unit 138. In that case, a predetermined value is stored in the storage device 120 as the vertical width threshold value.

(Processing Executed by Image Processing Device)
The process executed by the image processing device 100 will be described with reference to Fig. 10. Fig. 10 is a diagram showing an example of the process executed by the image processing device in this embodiment. The process shown in Fig. 10 is realized by the processor 101 shown in Fig. 2 executing the program 122 (see Fig. 2).

In step S1, the processor 101 receives an image of a barcode including multiple bars from the imaging device 500 (see FIG. 2) via the camera interface 104 (see FIG. 2).

In step S2, the processor 101 identifies a bar region in the captured image. The process of step S2 is executed by the identification unit 132 (see FIG. 3).

In step S3, the processor 101 determines the inspection target area based on the bar area. The process of step S3 is executed by the determination unit 133 (see FIG. 3).

In step S4, the processor 101 extracts at least one partial region from the inspection target region, the partial region being composed of pixels having characteristics corresponding to a plurality of bars. The process of step S4 is a so-called labeling process in image processing. The process of step S4 is executed by the extraction unit 134 (see FIG. 3).

In step S5, the processor 101 calculates the vertical width of each of the partial regions extracted in step S4. The process of step S5 is executed by the calculation unit 135 (see FIG. 3).

In step S6, the processor 101 determines whether the minimum vertical width calculated in step S5 is less than the threshold value. If the minimum vertical width calculated in step S5 is less than the threshold value (YES in step S6), the processor 101 transitions the process to step S7. On the other hand, if the minimum vertical width calculated in step S5 is equal to or greater than the threshold value (NO in step S6), the processor 101 transitions the process to step S8.

In step S7, the processor 101 determines that the appearance of the barcode is defective.

In step S8, the processor 101 determines that the appearance of the barcode is good. The processes in steps S6 to S8 are executed by the determination unit 136 (see FIG. 3).

After step S7 or step S8, the processor 101 ends the series of processes shown in FIG. 10.

(Test result output format)
Fig. 11 is a diagram showing an example of an output form of the inspection result. Screen G5 is an example of a screen showing the inspection result. Screen G5 is displayed on output device 700 (see Fig. 1). Screen G5 includes a field 11 in which the result of the visual inspection of the barcode is displayed, and a field 12 in which the minimum value of the vertical width calculated in step S5 (see Fig. 10) is displayed. Screen G5 further includes a field 13 in which an image of the barcode (captured image I) acquired by imaging device 500 (see Fig. 1) is displayed.

The user can view the results of the visual inspection of the barcode on screen G5. The user can also view the minimum vertical width calculated in step S5 (see FIG. 10) on screen G5. By comparing the value displayed in column 12 with the vertical width threshold value that was set, the user can see if there are any smudges or chips in the bar.

It is sufficient that screen G5 includes at least field 11. Furthermore, in addition to field 11, screen G5 may include a field that displays a value set as a threshold for the vertical width of the bar.

In addition, information indicating bars whose vertical width is less than a threshold value may be further displayed in column 13. This allows the user to know which bars have smudges or chips.In addition, information indicating bars whose vertical width is less than a threshold value and the vertical width of the bars may be further displayed in column 13. This allows the user to know which bars have smudges or chips and the vertical width of the bars.

The test results may also be output as audio. The test results may also be notified by lighting an indicator.

(Method of setting the vertical threshold based on the correct barcode image)
Among the threshold setting methods, a method of setting a threshold for the vertical width based on a correct image of a barcode will be described with reference to Figures 12 and 13. The method of setting a threshold for the vertical width based on a correct image of a barcode is a method of setting a threshold for the vertical width based on the minimum value of the vertical width of a bar calculated based on the correct image of a barcode. The method will be described separately for a case where one image is used as the correct image of a barcode and a case where multiple images are used.

Figure 12 is a diagram showing an example of processing when one image is used as the correct image of a barcode. The processing shown in Figure 12 is realized by the processor 101 shown in Figure 2 executing the program 122 (see Figure 2).

In step S21, the processor 101 receives one correct image of the barcode from the imaging device 500 (see FIG. 2) via the camera interface 104 (see FIG. 2). The correct image of the barcode is obtained by the imaging device 500 capturing an image of a correctly printed barcode.

In step S22, the processor 101 identifies a bar region in the correct image. The process of step S22 is executed by the identification unit 132 (see FIG. 3).

In step S23, the processor 101 determines the inspection target area based on the bar area. The process of step S23 is executed by the determination unit 133 (see FIG. 3).

In step S24, the processor 101 extracts at least one partial region from the inspection target region, the partial region being composed of pixels having characteristics corresponding to a plurality of bars. The process of step S24 is a so-called labeling process in image processing. The process of step S24 is executed by the extraction unit 134 (see FIG. 3).

In step S25, the processor 101 calculates the vertical width of each of the partial regions extracted in step S24. The process of step S25 is executed by the calculation unit 135 (see FIG. 3).

In step S26, the processor 101 determines the minimum vertical width value calculated in step S25 as the vertical width threshold value.

In step S27, the processor 101 stores the value determined in step S26 in the storage device 120 (see FIG. 3) as the vertical width threshold. This completes the setting of the vertical width threshold. The processes in steps S26 and S27 are executed by the second setting unit 138 (see FIG. 3).

After step S27, the processor 101 ends the series of processes shown in FIG. 12.

Figure 13 is a diagram showing an example of processing when multiple images are used as correct images of a barcode. The processing shown in Figure 13 is realized by the processor 101 shown in Figure 2 executing the program 122 (see Figure 2).

In step S31, the processor 101 receives N (N≧2) correct images of the barcode from the imaging device 500 (see FIG. 2) via the camera interface 104 (see FIG. 2). The correct images of the barcode are obtained by the imaging device 500 capturing an image of a correctly printed barcode.

In step S32, the processor 101 sets the variable n (n≧1) to 1.

In step S33, the processor 101 identifies a bar region in the nth correct image. The process of step S33 is executed by the identification unit 132 (see FIG. 3).

In step S34, the processor 101 determines the inspection target area based on the bar area. The process of step S34 is executed by the determination unit 133 (see FIG. 3).

In step S35, the processor 101 extracts at least one partial region from the inspection target region, the partial region being composed of pixels having characteristics corresponding to a plurality of bars. The process of step S35 is a so-called labeling process in image processing. The process of step S35 is executed by the extraction unit 134 (see FIG. 3).

In step S36, the processor 101 calculates the vertical width of each of the partial regions extracted in step S35. The process of step S36 is executed by the calculation unit 135 (see FIG. 3).

In step S37, the processor 101 stores the minimum vertical width calculated in step S36 in the storage device 120 (see FIG. 2) or the main memory 102 (see FIG. 2).

In step S38, the processor 101 determines whether n is equal to or greater than N. If n is equal to or greater than N (YES in step S38), the processor 101 transitions the process to step S40. On the other hand, if n is less than N (NO in step S38), the processor 101 transitions the process to step S39.

In step S39, the processor 101 increments n by 1 and returns the process to step S33.

In step S40, the processor 101 determines the threshold height based on the minimum height of each correct image saved in step S37. As one example, the processor 101 determines the average of the minimum heights of each correct image saved in step S37 as the threshold height. As another example, the processor 101 determines the smallest value among the minimum heights of each correct image saved in step S37 as the threshold height. As another example, the processor 101 determines the largest value among the minimum heights of each correct image saved in step S37 as the threshold height.

In step S41, the processor 101 stores the value determined in step S40 in the storage device 120 (see FIG. 3) as the vertical width threshold. This completes the setting of the vertical width threshold. The processes in steps S37 to S41 are executed by the second setting unit 138 (see FIG. 3).

After step S41, the processor 101 ends the series of processes shown in FIG. 13.

Thus, according to this embodiment, the vertical width of each bar is calculated based on an image of a barcode containing multiple bars, and the appearance of the barcode is determined based on the minimum value of the calculated vertical widths. If the bars are smudged or chipped, the vertical width of the bar will be shorter than the original vertical width regardless of where the smudge or chipping occurs. Therefore, according to this embodiment, it is possible to inspect the appearance of the barcode regardless of where the smudge or chipping occurs.

The inspection area is also determined based on the bar area. This ensures inspection accuracy even if the barcode is misaligned from the originally intended printing position.

In the above embodiment, the area to be inspected is an area obtained by expanding the bar area by a certain width in the up, down, left, and right directions, but the bar area may be the area to be inspected.

In addition, in the above embodiment, the determination unit 136 determines that the appearance of the barcode is poor if the minimum value of the vertical width calculated by the calculation unit 135 is less than a threshold value, but the determination unit 136 may determine that the appearance of the barcode is poor if the minimum value of the vertical width calculated by the calculation unit 135 is equal to or less than a threshold value.

[Additional Notes]
The above-described embodiment includes the following technical ideas.

[Configuration 1]
a reception unit (131) for receiving a captured image (I) of a barcode (C) including a plurality of bars (B);
An identification unit (132) that identifies a bar region (P) corresponding to the plurality of bars (B) in the captured image (I);
A determination unit (133) that determines an inspection target area (Q) based on the bar area (P);
an extraction unit (134) for extracting at least one partial region (R) composed of pixels having characteristics corresponding to the plurality of bars (B) from the inspection target region (Q);
A calculation unit (135) that calculates the length of each of the at least one extracted partial region (R) in the longitudinal direction;
and a determination unit (136) that determines that the appearance of the barcode (C) is defective if the minimum length value is less than a threshold value.

[Configuration 2]
2. The image processing apparatus according to configuration 1, wherein the inspection target area (Q) is an area obtained by expanding the bar area (P) by a predetermined width (TH) in all directions.

[Configuration 3]
The image processing device according to configuration 2, further comprising a first setting unit (137) that sets the predetermined width (TH) based on an input operation by a user.

[Configuration 4]
The image processing device (100) according to any one of configurations 1 to 3, further comprising a second setting unit (138) that sets the threshold value based on an input operation by a user.

[Configuration 5]
The reception unit (131) further receives a correct image of the barcode (C),
The image processing device (100) is further provided with a second setting unit (138) that sets the threshold value based on the minimum value of the length of at least one partial region (R) of the correct image. The image processing device described in any one of configurations 1 to 3.

[Configuration 6]
1. A computer-implemented image processing method, comprising:
Receiving a captured image (I) of a barcode (C) including a plurality of bars (B);
Identifying a bar region (P) corresponding to the plurality of bars (B) in the captured image (I);
determining an inspection area (Q) based on the bar area (P);
Extracting at least one partial region (R) composed of pixels having characteristics corresponding to the plurality of bars (B) from the inspection target region (Q);
Calculating the length of each of the at least one extracted partial region (R) in the longitudinal direction;
and determining that the appearance of the barcode (C) is defective if the minimum length value is less than a threshold value.

[Configuration 7]
7. An image processing program for causing a computer to execute the image processing method according to claim 6.

The embodiments disclosed herein should be considered to be illustrative and not restrictive in all respects. The scope of the present invention is indicated by the claims, not by the above description, and is intended to include all modifications within the meaning and scope of the claims.

1 Image processing system, 100 Image processing device, 101 Processor, 102 Main memory, 103 Communication interface, 104 Camera interface, 105 Input interface, 106 Output interface, 107 Memory card interface, 107A Memory card, 119 Internal bus, 120 Storage device, 122 Program, 124 Setting information, 131 Reception unit, 132 Identification unit, 133 Decision unit, 134 Extraction unit, 135 Calculation unit, 136 Judgment unit, 137 First setting unit, 138 Second setting unit, 500 Imaging device, 600 Input device, 700 Output device, B, B1, B4 Bar, C Bar code, G1, G2, G3, G4, G5 Screen, I Captured image, L Label, P Bar area, Q Inspection target area, R, R1, R2, R3, R4 Partial area, TH, TH1, TH2, TH3, TH4 predetermined width, W vertical width.

Claims (7)

a reception unit that receives an image of a barcode including a plurality of bars;
an identification unit that identifies a bar region corresponding to the plurality of bars in the captured image;
A determination unit that determines an inspection target area based on the bar area;
an extraction unit that extracts at least one partial area configured with pixels having characteristics corresponding to the plurality of bars from the inspection target area;
A calculation unit that calculates a length in a longitudinal direction of each of the at least one extracted partial region;
and a determination unit that determines that an appearance of the barcode is defective if the minimum length value is less than a threshold value. The image processing device according to claim 1, wherein the inspection target area is an area obtained by expanding the bar area by a predetermined width in the up, down, left and right directions. The image processing device according to claim 2, further comprising a first setting unit that sets the predetermined width based on an input operation by a user. The image processing device according to any one of claims 1 to 3, further comprising a second setting unit that sets the threshold value based on an input operation by a user. The reception unit further receives a correct image of the barcode,
The image processing device according to any one of claims 1 to 3, further comprising a second setting unit configured to set the threshold value based on a minimum value of the length of the at least one partial region of the correct image. 1. A computer-implemented image processing method, comprising:
receiving an image of a barcode including a plurality of bars;
Identifying a bar region corresponding to the plurality of bars in the captured image;
determining an inspection target area based on the bar area;
extracting at least one partial region from the inspection area, the partial region being composed of pixels having characteristics corresponding to the plurality of bars;
Calculating a length in a longitudinal direction of each of the at least one extracted partial region;
determining that the appearance of the barcode is defective if the minimum length is less than a threshold. An image processing program for causing a computer to execute the image processing method according to claim 6.

Images