JP2013196470A - Two-dimensional code reader - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a two-dimensional code reader capable of suppressing failures in reading a dot code.SOLUTION: A connection component is extracted by labeling processing (S3), and a peripheral length of the connection component is statistically processed (S4, S5). In the case of a dot code, since almost all the connection components that can be extracted by the labeling processing are dots, a result of statistical processing becomes a value indicating that it is the dot. In cell shape determination (S6), whether or not an imaged two-dimensional code is a dot code is determined on the basis of the result of the statistical processing, and when determined that it is the dot code (S7:YES), reading processing exclusive for the dot code is performed (S8), and thus failures in reading the dot code are suppressed.

Description

  The present invention relates to a two-dimensional code, and more particularly to a technique for determining whether or not a two-dimensional code is printed with dots.

  Two-dimensional codes are used in various situations, and there is an opportunity for codes printed by direct part marking (DPM) to be printed directly on various materials and shapes for quality control and distribution management. It is increasing.

  In DPM, since printing is directly performed on a member such as a metal or a substrate, various methods such as laser engraving are used. Among them, a general method is a printing method using dot peening.

  In a two-dimensional code reading method, generally, subsequent processing such as positioning of each cell is performed by detecting a feature pattern included in the two-dimensional code.

JP 2000-222517 A

  In a two-dimensional code (hereinafter, dot code) printed by dot peening, a straight line is expressed by arranging circular dots in a straight line. That is, in the dot code, even though it is a straight line, each dot forming a straight line is not in contact with an adjacent dot and retains the shape as a dot.

  In the dot code, between adjacent dots in the straight line portion is a portion that is not peened, and a bright cell is also a portion that is not peened. Therefore, the dot code is characterized in that between the adjacent dots and bright cells exist as non-peened portions.

  Due to the above characteristics, if the same reading method as a normal code (a code having a square cell shape) is used for a dot code, there are problems such as a feature pattern not being detected or a mistake between a bright cell and a dot. May occur, making reading difficult. Therefore, the code is read using a dot code-dedicated reading algorithm.

  However, a use environment in which dot codes and normal codes are mixed is also conceivable. In this case, it is necessary to change the algorithm to be used depending on whether the dot code is used or not. If a normal code algorithm is used even though it is a dot code, there is a high possibility that reading will fail.

  The present invention has been made based on this situation, and an object of the present invention is to provide a two-dimensional code reader capable of suppressing a failure in reading a dot code.

  In order to achieve the object, the present invention provides a two-dimensional code reading device that captures an image including a two-dimensional code and reads information from the two-dimensional code of the captured image. The two-dimensional code is captured in the image. Extracting means for extracting a connected component by performing a labeling process from a region including a portion that has been processed, and a morphological feature value calculating means for calculating a morphological feature value representing a feature of the connected component extracted by the extracting means And determining means for determining whether or not the captured two-dimensional code is a dot code based on the morphological feature value calculated by the morphological characteristic value calculating means; and And a reading unit that executes a reading process dedicated to the dot code when the dot code is determined.

  As described above, the dot code is characterized in that each dot forming a straight line also retains its shape as a dot. Therefore, in the case of a dot code, most of the connected components that can be extracted by the labeling process are dots, and as a result, the form feature value calculated for the connected components is also a value indicating that it is a dot. Since the determination means determines whether or not the captured two-dimensional code is a dot code based on this form feature value, it can be accurately determined whether or not it is a dot code. Then, when the determination unit determines that the captured two-dimensional code is a dot code, the reading unit performs reading processing dedicated to the dot code, and thus can prevent the dot code reading from failing.

  Further, in the invention according to claim 2, the form feature value calculating unit extracts a single cell component from the connected component, calculates a circularity of the single cell component as the form feature value, and the determining unit includes: When the circularity is within a predetermined range indicating circularity, it is determined that the captured two-dimensional code is a dot code.

  Some of the dots may be combined with the adjacent dots due to imprint errors or poor imaging conditions, but the combination of dots is excluded from the single cell component. The circularity of the single cell component is not affected. Therefore, according to the present invention, it is possible to accurately determine whether a dot code is used, even in an image in which some of a plurality of dots are combined with adjacent dots.

  According to a third aspect of the present invention, the morphological feature value calculating means calculates a circumference of the connected component extracted by the extracting means, calculates a statistical feature value of the calculated circumference as the morphological feature value, and the determination The means determines whether or not the captured two-dimensional code is a dot code based on a comparison between the statistical feature value and a statistical threshold value preset for the statistical feature value.

  In the present invention, the circumference is a form, and a statistical characteristic value of the circumference is calculated as a feature value of the form. In the case of a dot code, since most of the connected components are dots, the circumference of a plurality of connected components should also be increased by a certain length assumed to be the circumference of one dot. Therefore, the determination means determines whether or not the captured two-dimensional code is a dot code based on a comparison between the statistical feature value of the circumference and a statistical threshold value preset for the statistical feature value. be able to.

  In addition, as a statistical feature value, when the perimeter is divided into predetermined classes (for example, for each pixel) and the perimeter of the connected components is classified by class, the number of connected components in the class that is the maximum number, There is dispersion of circumference.

  In the invention according to claim 4, in addition to the comparison between the statistical feature value and the statistical threshold value, the determination means also compares the number of the connected components with a component number threshold set in advance for the number of connected components. If the number of connected components is smaller than the component number threshold, it is determined that the captured two-dimensional code is not a dot code.

  The comparison between the statistical feature value and the statistical threshold value is not reliable when the number of statistics is too small. Therefore, in the present invention, the number of connected components is also compared with the component number threshold. When the number of connected components is smaller than the component number threshold value, the reliability of the statistical feature value is low. Therefore, even if it is determined that the dot code is based on this comparison, the determination reliability is low. Therefore, when the number of connected components is smaller than the component number threshold, it is determined that the captured two-dimensional code is not a dot code. Thereby, the fall of the reliability of the determination result that it is a dot code can be suppressed.

  In the invention of claim 5, the extraction means extracts a plurality of labeling regions having different sizes, performs the labeling process on each labeling region, and extracts a connected component for each of the plurality of labeling regions, The form feature value calculating unit calculates the statistical feature value for each of a plurality of labeling regions, and the determination unit satisfies a determination condition that the statistical feature value for at least one labeling region is a dot code In this case, it is determined that the captured two-dimensional code is a dot code.

  Since the cell size is also unknown at the stage before the determination means determines whether or not it is a dot code, if the labeling area is determined to be one size, the size of the labeling area will be smaller than the cell size. It may be too large or too small. If the labeling area is too small, the number of cells (dots) included in the labeling area is too small, and the reliability of the statistics is lacking. On the other hand, even if the labeling area is large, an unnecessary portion is included, and there is a possibility that the statistical feature value does not become a value indicating the feature of the dot code despite the dot code.

  Therefore, in the present invention, a plurality of labeling regions having different sizes are extracted, and a statistical feature value is calculated for each of the plurality of labeling regions. Then, when the determination condition that the statistical feature value for at least one labeling region is a dot code is satisfied, it is determined that the captured two-dimensional code is a dot code. As a result, when a dot code is imaged, there is a high probability that the statistical feature value in any size labeling area is a dot code, so whether or not it is a dot code with high accuracy. Can be determined.

It is a block diagram which shows the mechanical structure of the two-dimensional code reader 10 used as embodiment of this invention. It is a flowchart which shows the outline | summary of a code reading process. It is a figure which illustrates the connected component extracted by step S3 of FIG. 2, Comprising: It is an example of a dot code. It is a figure which illustrates the connected component extracted by step S3 of FIG. 2, Comprising: It is an example of a normal code. It is the graph which statistically processed the circumference calculated | required from the image of the dot code shown in FIG. 5 is a graph obtained by statistically processing the circumference obtained from the normal code image shown in FIG. 4. It is a figure explaining that the number of dark cells contained in this area | region becomes small when a labeling area | region is too small. It is a graph which shows distribution of the circumference in the area | region of FIG. It is a flowchart which shows the part which is different from 1st Embodiment in the code reading process in 2nd Embodiment.

(First embodiment)
Hereinafter, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram showing a mechanical configuration of a two-dimensional code reading apparatus 10 according to an embodiment of the present invention. The mechanical configuration is the same as that of a conventionally known two-dimensional code reader.

  The circuit unit 20 shown in FIG. 1 is accommodated in a housing (not shown). The circuit unit 20 mainly includes an optical system, a computer system, and a power supply system. The optical system includes a marker light projector 60, a light emitting diode 21, an area sensor 23, an imaging lens 27, and the like.

  The light emitting diode 21 is configured to be able to irradiate the illumination light Lf toward the reading surface R through a reading port (not shown) of the housing body. A two-dimensional code or the like is recorded on the reading surface R. The recording form includes printing, engraving, and the like.

  The area sensor 23 is configured to be able to receive the reflected light Lr irradiated and reflected on the reading surface R. For example, the area sensor 23 includes a light receiving element that is a solid-state image pickup element such as a C-MOS or a CCD. It is arranged in two dimensions of m rows and n columns in the order of 10,000. The light receiving element converts the received light into an electrical signal and outputs it.

  The light receiving surface 23a of the area sensor 23 is positioned so as to be visible from the outside of the housing main body through the above-described reading port, and the area sensor 23 receives incident light incident through the imaging lens 27 as the light receiving surface 23a. It is arranged so that it can receive light.

  The imaging lens 27 functions as an imaging optical system capable of condensing incident light incident from the outside via a reading port and forming an image on the light receiving surface 23a of the area sensor 23. And a plurality of condensing lenses housed in the lens barrel. The reflected light Lr that is reflected from the two-dimensional code by the illumination light Lf emitted from the light emitting diode 21 and is incident on the reading port is condensed by the imaging lens 27, and thereby the code image is formed on the light receiving surface 23 a of the area sensor 23. Forms an image. The marker light projector 60 projects the marker light M indicating the reading range of the two-dimensional code onto the reading surface R.

  Next, a configuration outline of the computer system will be described. The computer system includes an amplification circuit 31, an A / D conversion circuit 33, a memory 35, an address generation circuit 36, a synchronization signal generation circuit 38, a control circuit 40, an operation switch 42, an LED 43, a buzzer 44, a liquid crystal display 46, and a communication interface 48. Etc. This computer system can process the image signal of the code image captured by the optical system described above in hardware and software. The control circuit 40 also performs control related to the entire system of the two-dimensional code reader 10.

  The image signal (analog signal) output from the area sensor 23 of the optical system is amplified by a predetermined gain by being input to the amplifier circuit 31, and then input from the analog signal when input to the A / D conversion circuit 33. Converted into a digital signal. The digitized image signal, that is, image data (image information) is input to the memory 35 and stored. The synchronization signal generation circuit 38 is configured to generate a synchronization signal for the area sensor 23 and the address generation circuit 36. The address generation circuit 36 is based on the synchronization signal supplied from the synchronization signal generation circuit 38. Thus, the storage address of the image data stored in the memory 35 can be generated.

  The memory 35 is a semiconductor memory device, and corresponds to, for example, a RAM (DRAM, SRAM, etc.) or a ROM (EPROM, EEPROM, etc.). In addition to the image processing program, the ROM stores in advance a system program that can control each hardware such as the marker light projector 60, the light emitting diode 21, and the area sensor 23.

  The control circuit 40 is a computer that can control the entire two-dimensional code reader 10 and includes a CPU, a system bus, an input / output interface, and the like. The control circuit 40 is configured to be connectable to various input / output devices (peripheral devices) via a built-in input / output interface, and includes a power switch 41, an operation switch 42, an LED 43, a buzzer 44, and a liquid crystal display 46. The communication interface 48, the marker light projector 60, and the like are connected.

  Accordingly, for example, code reading processing, monitoring and management of the power switch 41 and the operation switch 42, turning on / off the LED 43 functioning as an indicator, turning on / off the buzzer 44 capable of generating a beep sound and an alarm sound, Is a screen control of the liquid crystal display 46 capable of displaying the code contents of the read two-dimensional code, communication control of the communication interface 48 enabling communication with an external device, and projection of the marker light M from the marker light projector 60. Control is possible.

  The power supply system includes a power switch 41, a battery 49, and the like. When the power switch 41 managed by the control circuit 40 is turned on and off, the conduction of the drive voltage supplied from the battery 49 to each device and each circuit described above is established. Or shut off is controlled.

  Next, the reading process of the control circuit 40 will be described. The reading process is a process of reading a character code from the captured code image. In the reading process of this embodiment, it is determined whether or not the two-dimensional code is a dot code, and the algorithm used thereafter is changed according to the determination result.

  FIG. 2 is a flowchart showing an outline of the code reading process. The code reading process will be described in more detail with reference to FIG. The process of FIG. 2 starts when an image including a code is captured by a user operation.

  First, in step S1, imaging data is acquired from the memory 35, and a code area is extracted from the captured image by a conventionally known method. The area extracted in step S1 is for the purpose of determining whether it is a dot code or a normal code, and it is not necessary to extract the exact boundary of the code. For example, in step S1, the image is divided into a plurality of preset areas, and the black and white density is determined for each divided area. The black and white density is represented by an average luminance value. A divided area in which the black and white density is within a predetermined range indicating that there is much black is extracted as a code area.

  In subsequent step S2, a laven ring region is further extracted from the code region extracted in step S1. This labeling area is an area where labeling processing is performed in the next step S3. In the present embodiment, a plurality of labeling regions having different sizes are extracted. When there are a plurality of candidate areas to be extracted for a labeling area of a certain size, the area is assumed to have many dark cells. The determination that there are many dark cells is made based on the average luminance value of the area. Further, the size of the labeling area is set in advance. For example, a square having a predetermined number of pixels on one side is defined as one block, and 4 blocks, 9 blocks, and 25 blocks are extracted as labeling regions having different sizes.

  The reason for extracting a plurality of labeling regions having different sizes is as follows. At the time of executing step S2, information on the code version and cell size has not been obtained, and the proportion of cells in the area is unknown. There is a bright cell portion in the code, and when the labeling area to be extracted is small with respect to the code, the number of dark cells included in the labeling area may be reduced. In that case, the reliability of subsequent processing is lacking. Therefore, in order to cope with the size of the cell size (dot size), a plurality of different sizes of the labeling region are extracted. The large labeling area corresponds to a large cell size and does not require detailed information. Therefore, steps S3 to S5 are performed on the predetermined labeling area having a large size using the data subjected to the thinning process. Thereby, processing time can be shortened.

  Steps S <b> 3 to S <b> 5 are performed on each ravenling region extracted in step S <b> 2. First, in step S3 corresponding to the extracting means in the claims, a known labeling process is performed to extract connected components. Since the labeling process is known, a detailed description is omitted, and only an outline is described. The labeling process is a process of assigning the same number to pixels in which white portions (or black portions) are continuous in a binarized image.

  3 and 4 are diagrams illustrating the connected components extracted in step S3. FIG. 3 is an example of a dot code, and FIG. 4 is an example of a normal code.

  As shown in FIG. 3, in the case of a dot code, since each cell (dot) is separated, each cell (dot) becomes one connected component. On the other hand, normal cells are rectangular and adjacent dark cells are in contact with each other. Therefore, as shown in (1), (4), and (5) of FIG. May be a connected component.

  In subsequent step S4, contour tracing is performed on each connected component extracted in step S3 to obtain a circumference. In subsequent step S5, statistical processing of the circumference obtained in step S4 is performed. In the present embodiment, these steps S4 and S5 correspond to the form feature value calculation means in the claims.

  In step S6, it is determined whether or not the cell shape is a dot using the circumference statistical processing result in step S5. 5 is a graph obtained by statistically processing the circumference obtained from the dot code image shown in FIG. 3, and FIG. 6 is a graph obtained by statistically processing the circumference obtained from the normal code image shown in FIG. 5 and 6, the unit of the circumference on the horizontal axis is a pixel, and one scale is 1. That is, the circumference is obtained with 1 pixel as the minimum unit. In other words, the circumference is divided with one pixel as one class.

  In the case of a dot code, as shown in FIG. 5, the circumference tends to concentrate on a certain length, which is assumed to be the circumference of one dot. On the other hand, in the case of a normal code, as shown in FIG. 6, the circumference is dispersed in various lengths.

  Therefore, in step S6, when the tendency as shown in FIG. 5 is observed, it is determined that the dot code is used. Specifically, the determination is made based on the number of connected components in the peak or the variance. However, when the labeling area is too small, the number of dark cells included in the labeling area is reduced as shown in FIG. When the number of cells included in the labeling area is small, the influence of dots that have been partially cut off by the boundary of the labeling area, such as the dots shown in the upper side of FIG. 7, increases.

  FIG. 8 is a graph showing the distribution of the perimeter obtained for each connected component in the labeling region shown in FIG. If the number of connected components is too small, as shown in FIG. 8, even a dot code does not concentrate on a certain length. Therefore, the cell shape determination condition includes the number of connected components.

Therefore, the cell shape determination conditions can be, for example, the following conditions (1) and (2). Either one of the following (1) and (2) may be set as the determination condition, or both may be set as the determination condition.
Determination condition (1) The number of connected components is greater than or equal to the component number threshold, and the number of connected components at the maximum peak of the circumference distribution graph is greater than or equal to a predetermined threshold. Determination condition (2) The number of connected components is greater than or equal to the component number threshold and the circumference If the dispersion condition of the length V is equal to or less than a predetermined threshold value, the cell shape is determined to be a dot. In addition, when two determination conditions are set as in (1) and (2) above, it is determined that the cell shape is a dot when either one is satisfied. Steps S3 to S5 are performed for each labeling region, and the determination in step S6 is also performed for each labeling region.

  A determination is made for each labeling region, and if the determination condition is not satisfied for all the labeling regions, it is determined that the cell is a normal cell.

  In step S7, it is determined whether or not the cell shape is determined to be a dot in step S6. If it is determined to be a dot (S7: YES), the process proceeds to step S8, and a dot reading process for executing a dot reading algorithm is performed. On the other hand, if it is determined that the cell is a normal cell (S7: NO), the process proceeds to step S9 to perform a normal cell reading process.

  As described above, according to the present embodiment described above, the dot code is determined based on the feature that each dot forming a straight line also retains the shape as a dot. Yes.

  Specifically, in this embodiment, connected components are extracted by a labeling process (S3), the circumference of this connected component is statistically processed, the number of connected components at the maximum peak of the circumference distribution graph, Circumference variance V is calculated (S4, S5). In the case of a dot code, since most of the connected components that can be extracted by the labeling process are dots, the number of connected components at the maximum peak and the dispersion V of the circumference are also values indicating dots.

  In the cell shape determination (S6), since it is determined whether or not the captured two-dimensional code is a dot code based on the number of connected components at the maximum peak and the dispersion V of the circumference, whether the dot code is accurate. A determination of whether or not can be made. If it is determined that the imaged two-dimensional code is a dot code (S7: YES), the dot code reading process is performed (S8), so that it is possible to suppress the dot code reading failure.

  In this embodiment, the determination conditions (1) and (2) also include a condition that “the number of connected components is equal to or greater than a component number threshold”. If this condition is not satisfied, the captured two-dimensional code is recorded. Is determined not to be a dot code (S6). Thereby, the fall of the reliability of the determination result that it is a dot code can be suppressed.

  In addition, a plurality of labeling regions having different sizes are extracted (S2), and a circumference statistical process is performed for each of the plurality of labeling regions (S4, S5). When the determination condition is satisfied for at least one of the labeling regions, it is determined that the captured two-dimensional code is a dot code (S6). As a result, when a dot code is imaged, it is highly possible that the statistical processing result for a labeling area of any size satisfies the determination condition that it is a dot code. Can be determined.

(Second Embodiment)
Next, a second embodiment will be described. The mechanical structure of the second embodiment is the same as that of the first embodiment, and the code reading process is different from that of the first embodiment. However, the code reading process is also similar to that of the first embodiment.

  FIG. 9 is a flowchart showing a portion different from the first embodiment in the code reading process in the second embodiment. The second embodiment is different from the first embodiment in that step S5-1 is executed following step S5, and step S6-1 is executed instead of step S6. Hereinafter, only portions different from the first embodiment will be described.

  In step S5-1, the circularity of the connected component is calculated. In step S5-1, a plurality of connected components are extracted. In step S5-1, among the plurality of extracted connected components, the circularity is measured for the minimum peak of the result of the statistical processing of the circumference in step S5. calculate. In addition, the minimum peak is determined without setting the number of connected components to 1 as a peak. The minimum peak determined by excluding the number of connected components of 1 can be considered as a single cell component.

  For the connected component included in the minimum peak, the circularity is calculated using the well-known circularity formula shown in the following formula 1. In the second embodiment, steps S5 and S5-1 correspond to the form feature value calculation means in the claims.

(Formula 1) Circularity = (4π × area) / (perimeter × perimeter)
In step S6-1, the cell shape is determined based on the circularity determined in step S5-1. Specifically, the cell shape is determined based on whether or not the circularity calculated in step S5-1 is within a circular determination range set in advance as a range that can be regarded as a circular shape. Note that the circular determination range is a range including 1 and is set in advance based on experiments.

  In the case of the example shown in FIG. 3, the circularity is 1.05, which is close to 1. Therefore, it is determined that the cell shape is a dot. On the other hand, in the example shown in FIG. 4, the circularity is 0.78. In the case of 0.78, it cannot be said that it is close to a circle, and is out of the circle determination range. Therefore, the cell shape is determined as a normal cell. After executing step S6-1, the process proceeds to step S7, which is the same as in the first embodiment.

  Depending on the code, even if the cell shape is a dot, some of the cells may be joined due to misprinting or imaging state. When a part of cells is combined, the perimeter becomes longer. Therefore, the perimeter statistical processing (step S5 in the first embodiment) is affected by the fact that part of the cells are combined. As a result, the “number of connected components at the maximum peak” and “circumference variance V”, which are variables in the latter half of the above-described determination conditions (1) and (2), are also affected by this.

  In contrast, the circularity in the second embodiment is calculated for a single cell component extracted from the single cell component. In other words, cells that are originally merged are excluded. For this reason, even if some of the dot-shaped cells are coupled to each other, the second embodiment is not affected. Therefore, the method of the second embodiment can accurately determine whether the cell shape is a dot even if some of the dot-shaped cells are coupled to each other.

  As mentioned above, although embodiment of this invention was described, this invention is not limited to the above-mentioned embodiment, The following embodiment is also contained in the technical scope of this invention, and also the summary other than the following is also included. Various modifications can be made without departing from the scope.

  For example, in the above-described embodiment, a plurality of regions having different sizes are extracted as the labeling region, but there may be one labeling region. The size of the labeling area may be the entire code area extracted in step S1 or a part of the code area.

10: Two-dimensional code reading device, 20: Circuit section, 21: Light emitting diode, 23: Area sensor, 27: Imaging lens, 31: Amplification circuit, 33: A / D conversion circuit, 35: Memory, 36: Address generation Circuit 38: synchronization signal generation circuit 40: control circuit 41: power switch 42: operation switch 43: LED 44: buzzer 46: liquid crystal display 48: communication interface 49: battery 60: marker Optical projector S3: extraction means, S4, S5: morphological feature value calculation means, S5, S5-1: morphological feature value calculation means, S6: determination means, S7 to S9: reading means

Claims (5)

A two-dimensional code reader that captures an image including a two-dimensional code and reads information from the two-dimensional code of the captured image,
Extraction means for extracting a connected component by performing a labeling process from a region including a portion where the two-dimensional code is imaged in the image;
Morphological feature value calculating means for calculating a morphological feature value representing the characteristics of the form of the connected component extracted by the extracting means;
Determining means for determining whether or not the captured two-dimensional code is a dot code based on the form feature value calculated by the form feature value calculating means;
When the determination unit determines that the captured two-dimensional code is a dot code, a reading unit that executes a reading process dedicated to the dot code;
A two-dimensional code reading device comprising: In claim 1,
The form feature value calculating means extracts a single cell component from the connected component, calculates a circularity of the single cell component as the form feature value,
The determination unit determines that the captured two-dimensional code is a dot code when the circularity is within a predetermined range indicating that the circularity is circular. In claim 1,
The form feature value calculation means calculates a circumference of the connected component extracted by the extraction means, calculates a statistical feature value of the calculated circumference as the form feature value,
The determination unit determines whether the captured two-dimensional code is a dot code based on a comparison between the statistical feature value and a statistical threshold value preset for the statistical feature value. A two-dimensional code reader. In claim 3,
In addition to comparing the statistical feature value and the statistical threshold value, the determination unit also compares the number of connected components and a component number threshold set in advance with respect to the number of connected components. A two-dimensional code reading device, wherein when the number is smaller than a threshold value, it is determined that the captured two-dimensional code is not a dot code. In claim 3 or 4,
The extraction means extracts a plurality of labeling regions having different sizes, performs the labeling process on each labeling region, extracts a connected component for each of the plurality of labeling regions,
The form feature value calculating means calculates the statistical feature value for each of a plurality of labeling regions,
The determination unit determines that the captured two-dimensional code is a dot code when a determination condition that a statistical feature value for at least one labeling region is a dot code is satisfied. Code reader.

Images