JP3622374B2 - Method and apparatus for determining contamination state of object - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a method for determining an object's fouling state as configured in various types of automatic transaction machines that handle objects such as coins, and more specifically, an object's fouling state determination method for accurately determining the object's fouling state and its Relates to the device.
[0002]
[Prior art]
Hereinafter, a description will be given of a coin fouling state discriminating device as an example. By comparing this acquired amount of reflected light with a preset contamination determination level, the contamination state of the coin is locally detected.
[0003]
[Problems to be solved by the invention]
However, in this case, because the state of the coins is locally detected, the entire state of the coins cannot be detected accurately, and detection irregularities are likely to cause inaccurate determinations. It had a problem with poor reliability of detection accuracy.
[0004]
Therefore, the present invention provides an object contamination state determination method and apparatus capable of accurately detecting the object contamination state by detecting the entire object uniformly, not locally, when detecting the object contamination state. The purpose is to provide.
[0005]
[Means for Solving the Problems]
According to the present invention, the entire image data of the object is acquired by the image data acquisition means, and the area ratio obtained from the pixel number distribution in each gradation value of the acquired image data is a predetermined ratio in the whole. This is a method for determining the contamination state of an object by calculating a gradation value to be a value from a higher gradation and determining that there is contamination when the calculated gradation value is lower than a preset reference gradation value. It is characterized by that.
[0006]
As an aspect of the present invention, the object is a coin, the true / false identification means identifies the true / false and the denomination, and if it is identified as the true coin, based on the reference gradation value preset for the identified denomination It is possible to use a method for determining the contamination state of an object for which the determination is performed.
[0007]
Further, according to the present invention, the image data acquisition means for acquiring the overall image data of the object, and the image data acquired by the image data acquisition means, the area ratio obtained from the pixel number distribution in each gradation value is the whole. Calculated by means for calculating a gradation value that is a predetermined ratio value from a higher gradation, reference value setting means for setting a reference gradation value for determining contamination, and the above-mentioned calculating means gradation value is equal to or is an object of the fouling state detecting apparatus provided with a discriminating means for discriminating that there is contamination in the case lower than the reference grayscale value set in the reference value setting means.
[0008]
As an aspect of the present invention, the object is a coin, and includes a true / false identifying means for identifying whether the coin is true or false and denomination, and if the true / false identifying means identifies the coin as a positive coin, An object contamination state determination apparatus configured to execute the determination based on the set reference gradation value can be provided.
[0009]
[Action]
According to the present invention, when determining the contamination state of an object, first, the entire image data of the object is acquired by the image data acquisition means, and the pixel number distribution in each gradation value is obtained for the acquired image data. Then, the contamination state of the object is determined from the gradation value at which the area ratio obtained from the obtained pixel number distribution becomes a predetermined ratio value as a whole .
[0010]
Further, when determining the contamination state of the object, the entire image data of the object is acquired by the image data acquisition unit, the pixel number distribution in each gradation value is obtained for the acquired image data , and the obtained pixel number Comparing the gradation value whose area ratio calculated from the distribution is a predetermined ratio value of the whole with the reference gradation value stored according to the identified object type and the identified object type Determine the contamination status of the object.
[0011]
【The invention's effect】
As a result, since the area ratio obtained from the pixel number distribution in the gradation value of the image data capturing the entire object can determine the overall contamination state of the object from the gradation value that becomes the predetermined ratio value of the entire object, Detection unevenness is eliminated when determining the contamination of an object such as a coin, and uniform and accurate determination can be made. In particular, since the detection is not performed locally but is detected as a whole, and determination is made, it is possible to determine the contamination close to human sensitivity. Therefore, erroneous discrimination can be resolved naturally, and highly reliable stain discrimination can be performed.
[0012]
In addition, even when determining the state of fouling of coins and other objects with many types of handling, normal coins that are not fouled and fouled coins that are soiled or damaged can be determined by comparing with the reference value set for the money type. And can be accurately distinguished. In addition, when this highly reliable contamination state discriminating apparatus is incorporated in an automatic transaction machine, it is possible to accurately select the contamination coins and normal coins, restrict the distribution of the contamination coins, and reliably use only normal coins.
[0013]
【Example】
Embodiments of the present invention will be described in detail below with reference to the drawings.
[First embodiment]
FIG. 1 shows a coin detection structure of a coin fouling state discriminating apparatus 11, which is a coin that sandwiches and conveys a coin 15 in the horizontal direction by combining conveying members such as conveying belts 12, 13, feed rollers 14,. A conveyance path 16 is provided, and a coin detection sensor 17 is provided along the coin conveyance path 16 to determine the denomination and the fouling state of the coin 15 introduced here.
[0014]
In this case, the coin detection sensor 17 irradiates the entire upper surface of the coin 15 conveyed in a horizontal state with the irradiation light 17b of the annularly arranged LED 17a, and the CCD camera 17d detects the reflected light 17c of the upper surface uneven pattern of the coin. Then, image data representing the surface pattern of the coin and its fouling state is acquired. This coin detection sensor 17 instantaneously reads a coin in the middle of conveyance led here, and the read coin is conveyed to the subsequent stage as it is.
[0015]
FIG. 2 is a circuit configuration diagram of the coin fouling state discriminating apparatus 11, which includes an image input unit 21, an A / D conversion unit 22, a density histogram creation unit 23, a binarization unit 24, and an identification unit 25. And a contamination level determination unit 26.
[0016]
The image input unit 21 acquires reflected light of the entire surface of the coin 15 as image data by the CCD camera 17d of the coin detection sensor 17, and the acquired image data is converted from analog to digital (multivalue) by the A / D conversion unit 22. Convert to
[0017]
The density distribution and the denomination are obtained from the image data obtained through the A / D conversion unit 22, and each density (gradation) is obtained from the image data A / D converted by one density histogram creation unit 23. The pixel number distribution for each (value) is calculated, and the image data A / D converted by the other binarization unit 24 is converted from multivalue to binary for denomination determination.
[0018]
The identification unit 25 stores a reference concentration distribution corresponding to the front and back of each denomination, and compares the reference concentration distribution with the binarized data to determine the denomination.
[0019]
The contamination level determination unit 26 stores a contamination determination level for each denomination that is set in advance to determine contamination. The contamination determination level and the distribution of the number of pixels for each density calculated by the density histogram creation unit 23. To determine the fouling state of the coin.
[0020]
FIG. 3 shows image data 31 of a beautiful normal coin suitable for circulation without fouling, and is represented by, for example, image data of 256 × 256 pixels (256 gradations / one pixel), and this normal coin is relatively clear. An uneven pattern of coins is acquired.
[0021]
FIG. 4 shows an example of a density histogram 41 obtained by calculating a pixel number distribution for each density (gradation value) from image data of normal coins. The density histogram 41 obtained from normal coins has a higher gradation value (darker). ), The density position (tone value = 105) where the area ratio becomes a certain ratio value (about 15%) is calculated, and this is compared with a preset contamination judgment level (reference tone value = 64). If the calculated gradation value is larger than the reference gradation value, it is determined that there is no contamination, and if it is smaller, it is determined that there is contamination. In the case of this normal coin, since it is sufficiently large (64 <105), it is determined that there is no fouling.
[0022]
FIG. 5 shows image data 51 of a fouled coin that is unsuitable for distribution. In the case of this fouled coin, the concave / convex pattern of the coin is acquired unclearly with low reflection, and the regular concave / convex pattern cannot be acquired sufficiently.
[0023]
FIG. 6 shows an example of a density histogram 61 in which the pixel number distribution for each density (tone value) is calculated from the image data of the soiled coin. In the case of the density histogram 61 obtained from this soiled coin, the tone value is high. The density position (gradation value = 1) where the area ratio is 15% of the whole is calculated from the one, and the presence / absence of contamination is determined by comparing this with a preset contamination determination level (reference gradation value = 64). To do. In the case of this fouling coin, it is determined that there is fouling because it is quite small (64> 1).
[0024]
The overall processing operation of the thus configured coin fouling state discriminating apparatus 11 will be described with reference to the flowchart of FIG.
Now, when the coin 15 is conveyed to the coin conveyance path 16 and guided to the position of the coin detection sensor 17, the reflected light irradiated on the coin 15 is received by the CCD camera, and the image data of the entire upper surface of the coin is imaged. Obtained by the input unit 21 (step n1).
[0025]
The acquired image data is converted from analog to digital (multivalue) by the A / D converter 22, and then output to both the density histogram generator 23 and the binarizer 24 (step n2).
The density histogram creation unit 23 creates a pixel number distribution for each density (gradation value) from the A / D converted image data (step n3).
On the other hand, the binarization unit 24 converts the A / D-converted image data from multivalue to binary for denomination determination, and based on the converted binarization data, the identification unit 25 determines whether the coin is true or false. The denomination is identified (steps n4 to n5).
[0026]
If it is identified as a regular coin based on the identification result, the contamination level determination unit 26 subsequently determines the contamination state of the coin to determine the appropriate / unsuitable validity as a circulation coin. On the other hand, if it is a fake coin, fake coin processing such as return or collection is performed (steps n6 to n7).
[0027]
Next, the fouling determination processing operation of the coin fouling state determination device 11 will be described with reference to the flowchart of FIG.
Now, when the fouling level determination unit 26 determines the fouling state of the coin 15, the fouling level determination unit 26 first acquires denomination data of the same coin recognized as a regular coin from the identification unit 25 (step n11). .
[0028]
Subsequently, a gradation value having an area ratio of 15% is calculated from the density histogram creating unit 23 (step n12).
The calculated gradation value is determined by comparing it with a contamination determination level preset for each denomination and front and back (step n13).
[0029]
At this time, if it is determined that there is no fouling, the coin is determined to be a coin suitable for distribution use (steps n14 to n15).
[0030]
On the other hand, if the coin is determined to be a dirty coin, the coin is dirty or damaged and is unsuitable for recycling, so that it is collected inside the device and regulated for distribution (step n16).
[0031]
[Second Embodiment]
FIG. 9 shows a coin detection structure of a coin fouling state discriminating device 91. This coin detection structure is a combination of transport members such as transport belts 92, 93, feed rollers 94, etc., and sandwiches and transports a coin 95 in the horizontal direction. A conveyance path 96 is provided, and a coin detection sensor 97 and a magnetic detection sensor 98 are arranged in this order along the coin conveyance path 96 to discriminate the fouling state and denomination of the coin 95 introduced here.
[0032]
In this case, the CCD camera 97b receives the reflected light emitted from the annularly arranged LED 97a of the coin detection sensor 97 to acquire image data representing the surface pattern of the coin 95 and its fouling state, and the subsequent magnetic detection sensor. At 98, the magnetic data of the coin for obtaining the outer diameter and material of the coin is acquired.
[0033]
FIG. 10 shows a circuit configuration diagram of a coin fouling state discriminating apparatus 91, which includes an image input unit 101, an image A / D conversion unit 102, a density histogram creation unit 103, a magnetic input unit 104, and a magnetic A / D. A D conversion unit 105, an identification unit 106, and a contamination level determination unit 107 are provided.
[0034]
The image input unit 101 acquires reflected light of the entire surface of the coin 95 as image data by the CCD camera 97b of the coin detection sensor 97, and the acquired image data is converted from analog to digital (multivalued) by the image A / D conversion unit 102. ).
[0035]
The density histogram creation unit 103 calculates a pixel number distribution for each density (gradation value) from the A / D converted image data.
[0036]
On the other hand, the magnetic input unit 104 acquires the magnetic data of the outer diameter and material of the coin 95 with the magnetic detection sensor 98, and the acquired magnetic data is converted from analog to digital (for analog denomination by the magnetic A / D conversion unit 105). Multivalue).
[0037]
The identification unit 106 stores reference magnetic data corresponding to the outer diameter and material for each denomination, and compares the reference magnetic data with the magnetic data detected by the magnetic detection sensor 98 to determine the denomination.
[0038]
The contamination level determination unit 107 stores a contamination determination level for each denomination set in advance to determine contamination, and the contamination determination level and the pixel number distribution for each density calculated by the density histogram creation unit 103. Are compared, and the fouling state of the coin 95 is determined. Thus, when the magnetic detection sensor 98 for determining the denomination of the coin is provided, the denomination determination can be further narrowed down based on the detection information of this sensor, and the identification accuracy of the denomination determination can be improved.
[0039]
The processing operation of the coin fouling state discriminating apparatus 91 configured as described above will be described with reference to the flowchart of FIG.
Now, when the coin 95 is conveyed to the coin conveyance path 96 and guided to the position of the coin detection sensor 97, the reflected light irradiated on the coin 95 is received by the CCD camera, and the image data of the entire upper surface of the coin is imaged. Obtained by the input unit 101 (step n21).
[0040]
The acquired image data is converted from analog to digital (multi-value) by the image A / D converter 102 and then output to the density histogram generator 103 (step n22).
A pixel number distribution for each density (gradation value) is created from the image data A / D converted by the density histogram creation unit 103 (step n23).
The created pixel number distribution is input to the contamination level determination unit 107 as a contamination state determination element (step n24).
[0041]
On the other hand, the magnetic input unit 104 that has acquired the magnetic data of the coin 95 via the magnetic detection sensor 98 converts the magnetic data from analog to digital (multi-value) by the magnetic A / D conversion unit 105 (steps n25 to n25). n26),
From the magnetic data, the identification unit 106 identifies the true / false of the coin and the denomination (step n27).
[0042]
If it is identified as a regular coin based on this identification result, the contamination level determination unit 107 subsequently determines the contamination state of the same coin to determine the appropriate / inappropriate validity as a distribution coin. On the other hand, if it is a fake coin, a fake coin process such as return or collection is performed (step n28).
[0043]
As described above, since the contamination state of the entire coin can be determined from the density distribution of the image data that captures the entire coin, there is no detection unevenness when detecting the coin, and uniform and accurate contamination determination can be performed. In particular, since it is determined not by local determination but by overall detection, it is possible to perform contamination determination close to human sensitivity. Therefore, it is possible to reliably eliminate erroneous determination and to perform highly reliable contamination determination. Also, when discriminating the fouling status of coins with many types of handling, it is possible to accurately distinguish normal coins that are not fouled from fouling coins that are dirty or damaged by comparing them with the standard gradation value set for the money type. be able to. In addition, when this highly reliable pollution status determination device is incorporated into an automatic transaction machine, the dirty coins and normal coins should be accurately selected to restrict the circulation of the contaminated coins, and only normal coins should be recycled accurately. Can do.
[0044]
In correspondence between the present invention and the configuration of the above-described embodiment,
The object contamination state determination device of the present invention corresponds to the coin contamination state determination device 11, 91 of the embodiment,
Similarly,
The object corresponds to coins 15, 95,
The image data acquisition means corresponds to the coin detection sensors 17, 97 and the image input units 21, 101,
Means for calculating a gradation value from the higher gradation, in which the area ratio obtained from the distribution of the number of pixels in each gradation value becomes a predetermined ratio value as a whole, is a density histogram creation unit 23 , 103 , and Corresponding to the contamination level determination unit 26 , 107 ,
The reference value setting means and the authenticity identification means correspond to the identification units 25 and 106,
Discriminating means also corresponds to the damage level determining section 26,107, the invention is not limited only to the above-mentioned arrangement of the embodiment.
[Brief description of the drawings]
FIG. 1 is a side view showing a coin detection structure of a coin fouling state discriminating apparatus according to a first embodiment of the present invention.
FIG. 2 is a circuit configuration diagram of the coin fouling state discriminating apparatus according to the first embodiment of the present invention;
FIG. 3 is an image data diagram of normal coins without fouling according to the first embodiment of the present invention.
FIG. 4 is a table showing an example of a normal coin density histogram according to the first embodiment of the present invention;
FIG. 5 is an image data diagram of a soiled coin according to the first embodiment of the present invention.
FIG. 6 is a chart showing an example of a density coin density histogram according to the first embodiment of the present invention;
FIG. 7 is a flowchart showing an overall processing operation of the coin fouling state determination apparatus according to the first embodiment of the present invention;
FIG. 8 is a flowchart showing a fouling determination processing operation of the coin fouling state determination device according to the first embodiment of the present invention;
FIG. 9 is a side view showing a coin detection structure of a coin fouling state discriminating apparatus according to a second embodiment of the present invention.
FIG. 10 is a circuit configuration diagram of a coin fouling state discriminating apparatus according to a second embodiment of the present invention.
FIG. 11 is a flowchart showing the processing operation of the coin fouling state discriminating apparatus according to the second embodiment of the present invention;
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 11,91 ... Coin fouling state discrimination | determination apparatus 15,95 ... Coin 17,97 ... Coin detection sensor 21,101 ... Image input part 23,103 ... Density histogram preparation part 25,106 ... Identification part 26,107 ... Fouling level Determining unit 31 ... Normal coin image data 41 ... Normal coin density histogram 51 ... Fouling coin image data 61 ... Fouling coin density histogram 98 ... Magnetic detection sensor 104 ... Magnetic input unit

Claims (4)

The overall image data of the object is acquired by the image data acquisition means,
About this acquired image data ,
Calculate the gradation value from the higher gradation, in which the area ratio obtained from the distribution of the number of pixels in each gradation value becomes a certain ratio value as a whole,
Fouling state determination method of an object gradation value thus calculated is determined that there is contamination in the case lower than the reference grayscale value set in advance. Targeting a coin as the object,
Authenticating false and denomination by means of authenticity identification,
If it is identified as a positive coin, the determination is executed based on a reference gradation value preset for the identified denomination.
The method for determining a contamination state of an object according to claim 1 . Image data acquisition means for acquiring overall image data of the object;
With respect to the image data acquired by the image data acquisition means , a gradation value is calculated from the higher gradation level so that the area ratio obtained from the pixel number distribution in each gradation value becomes a predetermined ratio value as a whole. Means,
A reference value setting means for setting a reference gradation value in order to determine fouling;
Object fouling state detecting apparatus provided with a judging means for gradation value calculated by a means for calculating said it is determined that there is contamination in the case lower than the reference grayscale value set in the reference value setting means. Targeting a coin as the object,
A correct / false identification means for identifying the correctness and denomination of the coin,
It is set to execute the determination based on a reference gradation value set in advance for the identified denomination if it is identified as a genuine coin by the authenticity identification means.
The object contamination state determination apparatus according to claim 3 .

Images