JP4916230B2 - Two-dimensional code, program, information storage medium, and image recognition apparatus - Google Patents

Description

  The present invention relates to a two-dimensional code, a program, an information storage medium, and an image recognition apparatus.

Conventionally, a two-dimensional code in which modules indicating data are two-dimensionally arranged based on predetermined format information is known. With this two-dimensional code, a larger amount of data can be read in a narrower area than the one-dimensional code. As such a conventional technique, for example, there is one disclosed in Japanese Patent No. 2938338.
Japanese Patent No. 2938338

  When such a two-dimensional code is used for card identification or the like, it is printed on the front or back surface of the card with visible ink or invisible ink that absorbs infrared rays or the like.

  Here, as shown in FIG. 46, there is a problem that a rare card can be forged relatively easily when cut and pasted.

  For example, by introducing advanced technology on the card side, it is possible to take countermeasures against counterfeiting, but the manufacturing cost increases and the profit margin decreases.

  It is also possible to take measures against counterfeiting by printing fine patterns on the card, but a high-performance camera is required for reading, and it is difficult to use a low-cost camera for reading a large amount at once. .

  The present invention has been made in view of the above-described problems, and the object of the present invention is to enable manufacture and reading at low cost, making counterfeiting difficult, and enabling code generation and recognition at high speed. Providing a two-dimensional code.

(1) The present invention
Two-dimensional code in which given data is encoded as a two-dimensional image,
In accordance with a preset binary data string arrangement condition, a point arranged at a point arrangement reserved position in a two-dimensional area based on a binary data string uniquely associated with given data;
The image component includes a line that is connected in accordance with a predetermined connection condition for each point and a point to be connected,
This is a two-dimensional code that is formed into a two-dimensional image by giving a given width to a line connecting the points.

(2) The two-dimensional code of the present invention is
The line is
The other points satisfying the requirement that the straight line connecting each point and the other point does not cross the point arrangement reserved area including the point arrangement reserved position of the other points is set as the connection target point of each point, and the predetermined condition is satisfied. It is a line connecting between the connection target point and each point.

(3) The two-dimensional code of the present invention is
The point is
According to a binary data string arrangement condition set in advance, a point arranged at a point arrangement reserved position belonging to a main layer set in a two-dimensional area is included based on the binary data string.

(4) The present invention
Two-dimensional code in which given data is encoded as a two-dimensional image,
Based on a binary data string uniquely associated with given data, a point arranged at a point arrangement reserved position belonging to the main layer set in the two-dimensional area;
A dummy point arranged at a point arrangement reserved position belonging to other than the main layer of the two-dimensional area, and the image component,
This is a two-dimensional code that is formed into a two-dimensional image by giving a given pattern to the point.

(5) The two-dimensional code of the present invention is
The point is
A point arrangement reserved position belonging to a sublayer set other than the main layer of the two-dimensional region includes dummy points arranged according to preset dummy point arrangement conditions.

(6) The two-dimensional code of the present invention is
The point is
The point arrangement reserved position belonging to the parity layer set other than the main layer of the two-dimensional area includes a point arranged based on the parity information.

(7) The two-dimensional code of the present invention is
The binary data string is generated based on a standard Fibonacci representation of given data.

(8) The present invention
A program for recognizing a two-dimensional code,
Detects the reference point corresponding position of the recognition target image, calculates the target point corresponding position on the recognition image corresponding to the target point set in association with the reference point based on the reference point corresponding position, and corresponds the calculated target point position A point-of-interest pixel information detector that detects pixel information of the recognition target image based on the position;
A corresponding data calculation unit for calculating corresponding data associated with the two-dimensional code based on the detected pixel information;
It is characterized by functioning a computer.

  The present invention also relates to an image recognition apparatus including the above-described units. The present invention is also a computer-readable information storage medium, and relates to an information storage medium storing a program that causes a computer to function as each of the above-described units.

(9) A program, an information storage medium, and an image recognition device according to the present invention are:
The attention pixel information detecting unit
Using the planned point placement position belonging to the main layer as the point of interest, calculating the point placement planned position on the recognition image as the point of interest correspondence position, detecting the pixel information of the recognition target image based on the calculated point placement planned position,
The corresponding data calculation unit is
A binary data string is obtained based on the detected pixel information, and given data uniquely associated with the obtained binary data string is obtained as correspondence data.

(10) A program, an information storage medium, and an image recognition apparatus according to the present invention are:
Based on the binary data string calculated by the corresponding data calculation unit, the point is arranged at the point arrangement reserved position of the two-dimensional area according to the preset binary data string arrangement condition, and the point according to the preset connection condition A connection simulation processing means for performing a connection simulation process for connecting each point and a point to be connected;
A line error detection / correction processing unit that compares at least one of error detection and error correction by comparing the connection state of the sampled points detected from the recognition target image with the connection state of the sampled points obtained by the connection simulation process. Is further included.

(11) A program, an information storage medium, and an image recognition apparatus according to the present invention are:
A Fibonacci error detection / correction processing unit that performs at least one of error detection and error correction on the binary data sequence calculated by the corresponding data calculation unit based on the condition of the binary data sequence expressed in standard Fibonacci expression; Is further included.

(12) A program, an information storage medium, and an image recognition apparatus according to the present invention are:
A dummy point placement simulation processing unit for performing a simulation process for placing a dummy point in a preset dummy point placement condition at a point placement reserved position belonging to a sublayer set other than the main layer of the two-dimensional region;
A dummy point error detection / correction processing unit that compares at least one of error detection and error correction by comparing the position of the sampled dummy point detected from the recognition target image and the position of the dummy point obtained by the dummy point simulation process. Is further included.

(13) A program, an information storage medium, and an image recognition apparatus according to the present invention are:
Means for storing orientation determination information related to the relationship between the value of the binary data string and the orientation of the recognition target image;
The image processing apparatus further includes a direction determination unit that determines the direction of the recognition target image based on the binary data string calculated by the corresponding data calculation unit and the direction determination information.

(14) A program, an information storage medium, and an image recognition apparatus according to the present invention include:
A recognition target image extraction unit for extracting a recognition target image from the input image data;
The pixel information extraction unit
Extract pixel information based on the recognition target image extracted by the recognition target image extraction unit,
The recognition target image extraction unit includes:
A contour extraction unit that performs a contour extraction process for extracting a contour of a pixel group including continuous pixels having pixel information satisfying a predetermined pixel condition from the image data;
A contour determining unit that determines whether or not a contour locus extracted by the contour extracting unit satisfies a predetermined locus condition;
Pixel information other than the pixel information satisfying the predetermined pixel condition is set as the pixel information of each pixel constituting the outline extracted by the contour extraction unit when the contour determination unit determines that the predetermined locus condition is not satisfied. A pixel information changing unit to be changed to,
An extraction unit that extracts, as the recognition target image, image data corresponding to an inner region of the contour extracted by the contour extraction unit when the contour determination unit determines that a predetermined trajectory condition is satisfied;
It is characterized by including.

(15) A program, an information storage medium, and an image recognition apparatus according to the present invention are provided:
Causing a computer to function as a binarization processing unit that performs binarization processing on the image data;
The contour extraction unit
The contour is extracted from image data that has been binarized by the binarization processing unit.

(16) A program, an information storage medium, and an image recognition apparatus according to the present invention are:
A differential processing unit for performing differential processing on the image data;
A blur process for performing blur processing on the image data that has been subjected to differentiation processing by the differentiation processing unit, by averaging pixel information of the pixel of interest and surrounding pixels arranged in the vicinity thereof to obtain new pixel information of the pixel of interest. The computer as a part,
The binarization processing unit
A binarization process is performed on the image data subjected to the blur process by the blur processing unit.

(17) A program, an information storage medium, and an image recognition apparatus according to the present invention are:
A line width detection unit for detecting the width of the lines constituting the recognition target image extracted by the recognition target image extraction unit;
The blur processing unit
A program characterized by determining the number of blurring processes based on the detected line width and performing the blurring process for the determined number of times.

(18) A program, an information storage medium, and an image recognition apparatus according to the present invention are provided:
A line width detection unit for detecting the width of a line constituting the recognition target image extracted by the recognition target image extraction unit;
The binarization processing unit
The threshold value used for the binarization process is determined based on the detected line width, and the binarization process is performed using the determined threshold value.

  Hereinafter, this embodiment will be described. In addition, this embodiment demonstrated below does not unduly limit the content of this invention described in the claim. In addition, all the configurations described in the present embodiment are not necessarily essential configuration requirements of the present invention.

1.2 Dimensional Code FIGS. 16A to 16C are examples of the two-dimensional code of the present embodiment.

  16A shows a two-dimensional code corresponding to ID = 1234567890123456, FIG. 16B shows a two-dimensional code corresponding to ID = 1234567890123457, and FIG. 16C corresponds to ID = 1234567890123458. Is a two-dimensional code.

  FIGS. 17A and 17B are examples of the simplified two-dimensional code of the present embodiment. FIG. 2A shows a two-dimensional code corresponding to ID = 12345678, and FIG. 17B shows a two-dimensional code corresponding to ID = 123545679.

As shown in FIGS. 16A to 16C and FIGS. 2A and 2B, the two-dimensional code of the present embodiment is a two-dimensional image having a design that is difficult to cut and paste, such as a melon skin pattern. It is. In FIGS. 16A to ^16C , integer values of 0 to 2 ⁵⁵ and (3.6 × 10 ¹⁶ ) can be embedded, and in FIGS. 17A and 17B, 0 to 2 ²⁵ and (3.3) can be embedded. An integer value of × 10 ⁷ ) can be embedded.

  The two-dimensional code of the present embodiment is a two-dimensional code in which given data (corresponding to the IDs in FIGS. 16A to 16C and FIGS. 17A and 17B) is encoded as a two-dimensional image. A point arranged at a point arrangement reserved position in a two-dimensional area based on a binary data string uniquely associated with given data in accordance with a preset binary data string arrangement condition; A two-dimensional code that includes a line in which each point and a point to be connected in accordance with a preset connection condition are included in an image component, and a given width is given to the line connecting the points to form a two-dimensional image It is.

  The constituent points and lines will be described in detail in “2.2 Dimensional Code Generation”.

  The corresponding data (ID) can be obtained by recognizing the information of the points and lines as the constituent elements from the two-dimensional codes shown in FIGS. 16 (A) to 16 (C) and FIGS. 17 (A) and 17 (B). it can. A method of recognizing information about points and lines as constituent elements from the two-dimensional code will be described in detail in “4-4. Recognition processing of image to be recognized and error correction processing”.

  In addition, the two-dimensional code of the present embodiment has other points that satisfy the requirement that the straight line connecting each point and another point does not cross the point arrangement reservation area including the point arrangement reservation positions of other points. May be a connection line between each point and a connection target point that satisfies a predetermined condition.

  The connection target points that satisfy the predetermined condition will be described in detail in “2-2. Bridge Construction Process (Connection Process)”.

  Further, the two-dimensional code of the present embodiment is such that the point is a point arrangement reserved position belonging to a main layer set in a two-dimensional area based on the binary data string in accordance with a preset binary data string arrangement condition. The structure including the points arranged in the above may be used. The preset binary data string arrangement condition and the main layer set in the two-dimensional area will be described in detail in “2-3.2 Two-dimensional area” and “2-4. Data arrangement in main layer”.

  The two-dimensional code of the present embodiment is a two-dimensional code in which given data is coded as a two-dimensional image, and is based on a binary data string uniquely associated with the given data. The image component includes a point arranged at a point arrangement reserved position belonging to the main layer set in the two-dimensional area and a dummy point arranged at a point arrangement reserved position belonging to other than the main layer of the two-dimensional area, This is a two-dimensional code that is formed into a two-dimensional image by giving a given pattern to the point.

  Further, the two-dimensional code of the present embodiment is a dummy code in which the point is arranged at a point arrangement reserved position belonging to a sublayer set other than the main layer of the two-dimensional area according to a preset dummy point arrangement condition. The structure containing a point may be sufficient. A method for arranging dummy points in the sublayer will be described in detail in “2-6. Arrangement of dummy data in the sublayer”.

  Further, the two-dimensional code of the present embodiment may include a point arranged based on parity information at a point arrangement reserved position belonging to a parity layer set other than the main layer of the two-dimensional area. The method of arranging parity information at the point arrangement reserved position belonging to the parity layer will be described in detail in “2-5. Setting of parity information”.

  In the two-dimensional code of the present embodiment, the binary data string may be generated based on a standard Fibonacci expression of given data. A method for generating a binary data string from given data will be described in detail in “2-2. Standard Fibonacci Expression and Binary Data String”.

  The two-dimensional code of the present embodiment has a one-to-one correspondence between the integer value and the pattern, and even if partly different, an error occurs, so that it is difficult to cut and paste.

  Note that when printing is actually performed, the ink may be printed with an invisible ink (for example, an ink that reacts only to infrared rays) and may not be seen with the naked eye, or may be printed with visible ink.

  A two-dimensional code such as a QR code (trademark) can be considered to have a large number of tiles laid out on a two-dimensional plane basically having black and white binary or several colors, and represented by a combination thereof. Therefore, in principle, it can be rearranged in one dimension (linear), and the information amount is the same as in the case of one dimension.

  On the other hand, since the two-dimensional code of the present embodiment makes full use of the two-dimensional area and embeds “significant information” including connection information in the two-dimensional spread, the two-dimensional plane It can only be expressed above. In other words, it cannot be rearranged in a one-dimensional (linear) manner, and includes a larger amount of information by utilizing the fact that it is two-dimensional.

2.2-Dimensional Code Generation 2-1.2 Dimensional Code Generation Process Flow FIG. 18 is a flowchart showing the flow of a two-dimensional code generation process.

  First, a numerical value to be converted into a two-dimensional code is input (step S10). Hereinafter, the case where the substantial information amount is 55 bits (excluding parity and the like) will be described as a sample.

  Next, rearrangement in units of bits is performed based on a given rule (step S20).

  Next, it is divided into a plurality of blocks (step S30). Here, a case where one block is 5 bits and 5 bits × 11 blocks will be described as an example.

  Next, encryption is performed for each block (step S40). The encryption method is arbitrary.

  Next, each ciphertext block is converted into a standard Fibonacci expression (step S50).

  Specifically, it will be described in “2-2. Standard Fibonacci Expression and Binary Data String”.

  Next, the data after conversion into the standard Fibonacci expression is arranged (developed on a two-dimensional plane) at a predetermined position of the main layer (step S60).

  Specifically, it will be described in the section “2-4. Data Arrangement on Main Layer”.

  Next, the arrangement of “stones” (corresponding to points) arranged in the main layer is seen, and according to the rule, the “stones” (corresponding to points) are arranged also in the parity layer (step S70).

  Specifically, it will be described in the section “2-5. Setting of parity information”.

  Next, the arrangement of the “stones” arranged in the main layer and the parity layer is seen, and the “stones” are arranged also in the sub-layer according to the rule (step S80).

  Specifically, it will be described in the section “2-6. Arrangement of Dummy Data in Sublayer”.

  Next, a “bridge” is built between “stones” placed on the three layers according to a given rule (step S90).

  Specifically, it will be described in the section “2-7.

  Next, a “bridge” is built from the point placed on the outermost periphery to the surrounding “frame” (step S100).

2-2. Standard Fibonacci Expression A given data may be converted into a standard Fibonacci expression to generate a binary data string uniquely associated with the given data.

  The standard Fibonacci expression refers specifically to the standard expression / minimum expression among the Fibonacci expressions, and the one with the smallest number of 1 is called the standard Fibonacci expression. In the standard Fibonacci representation, bit strings can be configured so that 1s are not adjacent. Because all the natural numbers can be expressed by the sum of Fibonacci numbers that do not match, by using this property, a given decimal number can be converted into a Fibonacci expression in which no bits are continuously set.

  In the present embodiment, a converted decimal number (ID) into a standard Fibonacci representation is used as a binary data string.

  For example, 1 block = 5 bits (32 ways) is expressed in standard Fibonacci (Here, "Fibonacci bit" = "fit" for short) assuming that the sequence of "1" and "0" is a binary bit) 7fit (34 ways) is required to express the above, and this conversion work is performed on all blocks. Since 7fit is 2 more than 5bit, we decided to substitute "33" (1010101) instead of using "0" (0000000) among the combinations expressed in 7fit. By doing this, the two-dimensional code that is finally generated changes and becomes interesting.

  FIG. 19 is a correspondence table of decimal numbers, binary numbers, and standard Fibonacci expressions. Decimal numbers 1, 2, 3, 5, 8, 13, 21, and 34 are Fibonacci numbers. This sequence of numbers follows the rule that the sum of two successive numbers becomes the next number, such as 2 = 1 + 1,3 = 1 + 2,5 = 2 + 3. Such numbers are called Fibonacci numbers.

2-3. Two-dimensional area In the present embodiment, a binary data string uniquely associated with given data is generated based on given data, and a point may be placed in the two-dimensional area. A point arrangement reserved position with a certain value is set, a point is arranged at a point arrangement reserved position in a two-dimensional area according to a binary data string arrangement condition set in advance based on the binary data string, and two-dimensional according to a preset connection condition A connection process for connecting points arranged in the region with a line is performed, and an image of a two-dimensional code is generated based on the line. Here, generating a two-dimensional code image based on a line refers to a configuration in which a width is given to the line connecting the points to generate a two-dimensional code image.

  Here, the given data may be actual data associated with the two-dimensional code, or data after encryption of the actual data.

  The point arrangement reserved position is position information for specifying a point or an area, and may be set as a relative position with respect to a predetermined reference point.

  In the present embodiment, a matrix is set based on the binary data string, the point arrangement reservation position is associated with each element of the matrix, and the value of each element of the matrix is set to the associated point arrangement reservation position. You may make it arrange | position a point based on.

  In the present embodiment, the two-dimensional region may be divided into a plurality of cells arranged in a grid, and a grid point or a representative point of each cell may be used as the point arrangement reserved position.

  The representative point of each cell may be, for example, the center point of each cell.

  The point arrangement reserved positions may be arranged so as to be distributed so as not to be extremely dense and dense in the two-dimensional area.

  20 and 21 are diagrams for explaining an example of the two-dimensional region of the present embodiment.

  Reference numeral 200 denotes a two-dimensional area of the present embodiment, and a two-dimensional code image is generated in the two-dimensional area.

  In the present embodiment, a plurality of cells S (x, y) (x = 0, 1, 2,..., 16, y = 0, 1, 2,..., 24 in which the two-dimensional region 200 is arranged in a grid pattern. ), The values of each bit of the binary data string (bit string) are associated with each cell according to a predetermined rule, and the bit corresponding to each cell is a first value (for example, 1). In this case, a point placement process is performed in which a point is placed in the cell and a point corresponding to the binary data string is placed in a two-dimensional area.

  The main layer ML may be set in the two-dimensional area 200, and points may be arranged based on the binary data string at point arrangement reserved positions (for example, cells or representative points of the cells) belonging to the main layer ML.

  The point arrangement reserved position belonging to the main layer refers to the case where the lattice point belongs to the main layer when the lattice point when the two-dimensional area is divided into a plurality of cells in a lattice shape is the point arrangement reserved position, When the representative point (center point) of each cell is the point arrangement reserved position, the cell or the representative point belongs to the main layer.

  When a given point arrangement reserved position belongs to the main layer ML, the main layer is set so that the point arrangement reserved position ML within the predetermined range around the point arrangement reserved position does not become the main layer. May be.

  The predetermined range around the point arrangement reserved position may be set so as to include, for example, point arrangement reserved positions adjacent to the point arrangement reserved position obliquely before, after, left, and right.

  For example, the cell (2, 2) of the main layer ML is the cells S (1, 1), S (1, 2), S (1, 3), S (2, 1), S (2) that are diagonally adjacent to each other. , 3), S (3, 1), S (3, 2), S (3, 3) are set so as not to become the main layer ML.

  A two-dimensional area may be divided like a grid (divided in a lattice pattern), and each cell may be a cell, and an odd row and odd column cell or an even row and even column cell may be a main layer ML.

  Alternatively, the main layer may be set according to a predetermined rule set so that cells adjacent to the main layer cell via sides or vertices do not become the main layer.

  For example, if binary data is divided into 11 blocks and each block is 7 fit, cells with y = 2 and x = 2, 4, 6, 8, 10, 12, 14 correspond to each fit of one block. . That is, for example, the first fit of the first block corresponds to the cell S (2, 2), the second fit of the first block corresponds to the cell S (4, 2), and the third fit of the first block corresponds to the cell S (6, 2), the 4th fit of the first block corresponds to the cell S (8, 2), the 5fit of the first block corresponds to the cell S (10, 2), and the 6th fit of the first block is the cell. Corresponding to S (12,2), the 7th fit of the first block corresponds to the cell S (14,2). As described above, the mth fit of the nth block may correspond to the cell S (2m, 2n).

  For example, when mfit of the nth block is a first value (for example, 1), a point is placed in the corresponding cell S (2m, 2n), and when it is a second value (for example, 0), The corresponding cell S (2m, 2n) may not be pointed, and the value of each bit of the binary data string may be associated with the main layer cell according to a predetermined rule.

  Alternatively, a parity layer PL may be set in addition to the main layer ML of the two-dimensional area 200, and points may be arranged based on parity information at point arrangement reserved positions belonging to the parity layer PL.

  For the two-dimensional area of the main layer ML, a parity layer having a cell as a minimum constituent unit may be set according to a predetermined rule, and a point corresponding to a parity bit may be arranged in the parity layer. For example, as shown in FIG. 21, the parity bit may be set around the main layer ML (cells Si, j (i + j = even cells) in the outermost peripheral portion (hatched portion)) as a parity layer.

  Further, as shown in FIG. 21, a sublayer SL is set in addition to the main layer ML of the two-dimensional area 200, and dummy points are arranged at the point arrangement reserved positions belonging to the sublayer SL according to preset dummy point arrangement conditions. You may do it.

2-4. Data Arrangement on Main Layer FIG. 22 is a diagram for explaining the arrangement of each bit information of a binary data string (bit string) on the main layer.

  Data (binary data string) after being converted into standard Fibonacci representation is arranged (developed on a two-dimensional plane) in the main layer ML according to the rules. Here, as shown in FIG. 20, the case where even-numbered rows and even-numbered columns of cells are arranged as main layer ML and binary data is arranged in a horizontal 7 fit × vertical 11 block will be described as an example.

  Place a "stone" (the entity is a "point" that represents the presence or absence of data, but this object is called "stone" for the sake of explanation below) at the position of "1" represented by fit, Do not place “stone” in the position.

  For example, if the fit column of the first block is “0010100”, the 1st fit, 2fit, 4fit, 6fit, and 7fit of the first block are “0”, so the corresponding cell S (2, 2 ), Cell S (4,2), cell S (8,2), cell S (12,2), and cell S (14,2) are not placed with stones. Since the third fit and the fifth fit of the first block are “1”, stones are placed in the corresponding cells S (6, 2) and S (10, 2).

  In this embodiment, since the converted data is arranged in the standard Fibonacci representation, when the horizontal line is viewed, 1 does not appear continuously in the binary data string (see FIG. 19). Therefore, when “stones” are arranged in the cells of the main layer, “stones” are not arranged continuously. In addition, since the cells in the main layer are arranged in a line in the horizontal direction, “stones” and “stones” are arranged at intervals of at least three cells.

  Here, the case where the cells are regularly arranged in a lattice shape has been described as an example, but the application of the present invention is not limited to this.

2-5. Setting parity information Dividing a two-dimensional area into multiple areas, setting parity information based on points placed in areas other than a given area, and placing points in the parity layer of a given area May be.

  Points arranged in areas other than a given area may include dummy points or may not include them.

  Look at the placement of “stones” placed in the main layer, and place “stones” in the parity layer according to the rules.

  A two-dimensional area is divided into a plurality of areas, and a parity layer of a given area is based on points (may or may not include dummy points) arranged in areas other than the area. Parity information may be set, and points may be arranged in the parity layer of a given area based on the parity information.

  23 and 24 are diagrams for explaining the parity bit setting method, and FIG. 25 shows a state in which stones are arranged in the parity layer based on the parity information when the arrangement of points in the main layer is FIG. FIG.

  Here, as shown in FIG. 20, a case where a parity bit is set with a cell S (i, j) (i + j = even number cell) around the main layer ML (the outermost peripheral portion (hatched portion)) as a parity layer PL. For example, place stones in the parity layer according to the following rules:

  (1) When the main layer is largely divided into four parts, top, bottom, left and right, “stones” placed in areas that do not belong to itself are counted (the “stones” on the boundary lines of the areas are counted).

  For example, as shown in FIG. 23, a two-dimensional region is divided into four regions R1, R2, R3, and R4 by a dividing line 250 in the vertical direction and a dividing line 252 in the horizontal direction.

  (2) The parity “stone” in the vertical column (both left and right ends) is an even sum of the number of “stones” in the horizontal direction (the row with the same Y coordinate and the row with the point-symmetric Y coordinate). Sometimes placed.

  (3) The parity “stone” in the horizontal row (upper and lower ends) is the sum of the number of “stones” in the vertical direction (the same X-coordinate column and the column in the point-symmetric X coordinate). Sometimes placed.

  For example, paying attention to the two points 260 and 270 at the lower left (the leftmost end), consider whether or not to put a parity “stone”.

  For example, for the parity stone placed in the cell 260 in the vertical column (both left and right) in FIG. 23, the total number of “stones” in the row 262 having the same Y coordinate as that of the own 260 and the row 264 in the point-symmetric Y coordinate. Is placed when is even. Here, with respect to the row 262 having the same Y coordinate as that of the subject, the portion other than the region R4 to which the subject 260 belongs is targeted. Since the total number of stones in the rows 262 and 264 is four, the stone 261 is placed in 260 as shown in FIG.

  Also, for example, for the parity stone placed in the cell 270 in the vertical column (both left and right ends) in FIG. 24, the number of “stones” in the row 272 having the same Y coordinate as that of the own 270 and the row 274 in the point-symmetrical Y coordinate. Set when the sum is even. Here, with respect to the row 272 having the same Y coordinate as that of itself, a portion other than the region R4 to which the own 270 belongs is targeted. Since the total number of stones in rows 272 and 274 is five, no stones are placed in 270 as shown in FIG.

  In this way, it is decided whether or not to place parity “stones” on all outermost circumferences.

  In this embodiment, as a countermeasure against cut and paste forgery, it is avoided that the parity is determined only around the parity “stone” (that is, only by local information), and is intentionally influenced by the information of the distant line. ing. Incidentally, if the area to which the user belongs is also included in the counting object, the parity of the four areas becomes the same (= symmetric) (information becomes redundant), so this is also made asymmetric. One “stone” placed (or not placed) in the main layer affects a total of six parities, which are also helpful hints for error correction.

2-6. Placement of dummy data in sub-layers Look at the placement of “stones” in the main layer and parity layer, and place “stones” in the sub-layer according to the rules.

  In the sub-layer, as in the main layer and the parity layer, a place where “stone” can be placed is clearly defined.

  The rule for placing stones in the sub-layer is that the cell where the “X-coordinate + Y-coordinate” of the cell Sxy is an even number is the first (since it includes at least cells reserved for the main layer and parity layer) Exclude from.

  Pay attention to the cells where no “stone” is placed in the main layer and parity layer, and apply to the surrounding cells (5 cells if touching the wall, 8 cells if not touching the wall) as well. If no "stone" is placed, put "stone" on that sub-layer.

  FIG. 26 is a diagram for explaining the arrangement of dummy data (dummy stones) in the sublayer.

  In FIG. 25, RA is a reserved area. Here, areas other than the reserved area RA are set as sublayers.

  Since the cell S (1, 0) of the sublayer is a cell in contact with the wall, the cell sharing the side or vertex with the cell (referred to as surrounding cells) is S (0, 0), S ( 2, 0), S (0, 1), S (1, 1), and S (2, 1). If there is no “stone” in the main layer and parity layer of these five cells, a stone is placed in the cell S (1, 0), and “stone” is placed in at least one of the five cells. When placed, no stone is placed in the cell S (1, 0). In FIG. 25, none of the surrounding cells S (0,0), S (2,0), S (0,1), S (1,1), S (2,1) are stoned. Therefore, a stone is placed in the cell S (1, 0) as indicated by 310 in FIG.

  In FIG. 25, since the cell S (2, 5) of the sublayer is a cell that is not in contact with the wall, the cell sharing the side or the vertex with the cell (referred to as a surrounding cell) is S (1, 4). ), S (2,4), S (3,4), S (1,5), S (3,5), S (1,6), S (2,6), S (3,6) There are 8 cells. If there is no “stone” in the main layer and parity layer of these 8 cells, the stone is placed in the cell S (2, 5), and “stone” is placed in at least one of the 8 cells. When placed, no stone is placed in the cell S (2,5). In FIG. 25, since a stone is placed in one cell S (2, 4) of the surrounding cells, no stone is placed in the cell S (2, 5) as indicated by 320 in FIG.

2-7. Bridge building process (connection process)
In the present embodiment, processing is performed in which the points arranged in the two-dimensional region are connected by lines according to preset connection conditions.

  When the necessary condition that a straight line connecting a given point and another point placed in a two-dimensional area does not cross the point placement reservation area is satisfied, a connection process that connects the given point and another point with a line is performed. You may do it. A line connecting a given point with another point may be a straight line.

  In this way, points can be connected with lines so that the information on the point arrangement reserved position is not broken with lines.

  In addition, another point that satisfies the requirement that a straight line connecting each point and another point does not pass through the main layer may be used as a connection target point of each point.

  The point and the point are connected by a line according to a predetermined rule set so that the line does not cross the cell to which the value of each bit of the binary data string is associated or the cell of the main layer where the point is not placed. May be.

  The dummy point and the dummy point may be connected by a line according to a predetermined rule set so that the line connecting the dummy point and the dummy point by a line other than the main layer.

  In this way, a “bridge” is built between the “stones” placed on the three layers according to the rules. This “bridge” is the “visible part (or part that can be recognized by infrared rays)” = “image recognition target” of the two-dimensional code of the present embodiment.

  As preset connection conditions, for example, the following rules (connection conditions, connection rules) for bridging can be set.

  FIGS. 27-30 is a figure for demonstrating the rule which bridges.

  Rule 1: Pay attention to the “stone” placed in the main layer or parity layer, and “stone” (regardless of the layer) ), Build a bridge.

  For example, in FIG. 27, if 350P is a “stone” placed in the main layer or parity layer, the cells 360, 361, 362, 363, 364, 365, 366, 367 of the “position of Keima” around it If there are stones in the cells 370, 371, 372, and 373 at "positions that are 45 degrees diagonally apart", a bridge is formed (connected).

  As shown in FIG. 28, since the stone (point) 360P is placed in the cell 360 in the “position of Keima” with respect to the stone (point) 350P, the stone (point) 350P and the stone (point) 360P are lined up. Connect (connect) with L1.

  In addition, since the stone (point) 371P is placed in the cell 371 at the position of 45 degrees diagonally with respect to the stone (point) 350P, the stone (point) 350P and the stone (point) 371P Are connected (connected) by a line L2.

  Rule 2: Pay attention to the “stone” placed on the sub-layer, and if there is a “stone” (should be limited to the sub-layer) in the “up / down / left / right position”, then “bridge” I can build. However, if there is a possibility that the “bridge” may hide the information on the presence of “stone” on the main layer or parity layer, the “bridge” is not built.

  For example, in FIG. 29, if “380P” is placed on the sublayer in FIG. 29, cells around “positions left and right, up and down, left and right” around it (should be limited to the sublayer) 390, 391, 392 If there is a stone at 393, build a bridge (connect).

  The stone (point) 390P and the stone 380P are placed in the cell 390 at the position of “up and down, left and right positions with 1 square space” with respect to the stone (point) 380P placed on the sublayer. (Point) Connect (connect) 390P with line L3 (see FIG. 30).

  In addition, a stone (point) 391P is placed in a cell 391 at a position “left and right, up and down, left and right” with respect to a stone (point) 380P placed on the sublayer. However, if the stone (point) 380P and the stone (point) 391P are connected (connected) with a line, there is a possibility that the stone (point) 410 of the main layer may be obscured, so no bridge is formed (see FIG. 30).

  Rule 3: Pay attention to the “stones” placed on the parity layer. For the upper and lower ends (four sides that make up the rectangle of the parity layer), there should be “stones” at the “up and down positions”. For example, build a bridge. Similarly, for the left and right ends, if there is a “stone” in the “left and right position with 1 square space”, a “bridge” is built.

  FIG. 31 shows a state in which the points of the two-dimensional region are connected by lines in this way. Here, the thickness of the line can be arbitrarily set to a width smaller than the width of the cell, but it is desirable to finally adjust the width to be suitable for the image recognition system using the two-dimensional code.

  In FIG. 31, “stone” which is an element other than “bridge” is also visible, but only the line of “bridge” is actually visible.

  Then, by building a “bridge” from the point placed on the outermost periphery to the surrounding “frame”, a two-dimensional code as shown in FIG. 32 is completed.

  The two-dimensional code of the present embodiment is characterized in that there is no extremely “dense” or “rough” portion of the line. Nevertheless, the position of the “stone” (main layer stone) with important information is “black” or “white”. (In other words, even if it is blurred or distorted), “stones” and “bridges” are arranged so that the minimum necessary information can be obtained.

3. Two-dimensional Code Generation System FIG. 33 shows an example of a functional block diagram of the two-dimensional code generation system of this embodiment. Note that the two-dimensional code generation system of this embodiment may have a configuration in which some of the components (each unit) in FIG. 33 are omitted.

  The printing unit 650 performs processing for printing the generated two-dimensional code image with visible or invisible ink.

  The operation unit 660 is for inputting operation data, and its function can be realized by a lever, a direction instruction key, a button, or the like.

  The storage unit 670 serves as a work area for the processing unit 600, the communication unit 696, and the like, and its function can be realized by a RAM (VRAM) or the like.

  An information storage medium 680 (a computer-readable medium) stores programs, data, and the like, and its function can be realized by an optical disk (CD, DVD), a memory card, a hard disk, a memory (ROM), or the like. . The processing unit 600 performs various processes of the present embodiment based on a program (data) stored in the information storage medium 680. That is, the information storage medium 680 stores a program for causing a computer to function as each unit of the present embodiment (a program for causing a computer to execute processing of each unit).

  The display 690 is for displaying and outputting an image generated according to the present embodiment.

  The sound output unit 692 outputs the sound generated by the present embodiment, and its function can be realized by a speaker, headphones, or the like.

  The portable information storage device 694 stores player personal data, game save data, and the like. Examples of the portable information storage device 694 include a memory card and a portable game system.

  The communication unit 696 performs various controls for communicating with the outside (for example, a host device or other game system), and functions thereof are hardware such as various processors or communication ASICs, programs, and the like. Can be realized.

  Note that a program (data) for causing a computer to function as each unit of the present embodiment is distributed from the information storage medium of the host device (server) to the information storage medium 680 (storage unit 670) via the network and communication unit 696. May be. Use of the information storage medium of such a host device (server) can also be included in the scope of the present invention.

  The processing unit 600 (processor) performs game calculation processing, image generation processing, sound generation processing, and the like based on operation data, a program, and the like from the operation unit 660. The processing unit 600 performs various processes using the storage unit 670 as a work area. The functions of the processing unit 600 can be realized by hardware such as various processors (CPU, DSP, etc.), ASIC (gate array, etc.), and programs.

  The processing unit 600 includes a two-dimensional code generation unit 610, an image generation unit 630, and a sound generation unit 640.

  The two-dimensional code generation unit 610 includes a binary data string generation processing unit 620, a point arrangement processing unit 622, a connection processing unit 624, a reference position setting processing unit 626, and an orientation information setting processing unit 628.

  The binary data string generation processing unit 620 generates a binary data string uniquely associated with the given data based on the given data, and the point arrangement processing unit 622 arranges the points in the two-dimensional area. The point arrangement reserved position that may be transmitted is set, a point is arranged at the point arrangement reserved position of the two-dimensional area in accordance with a binary data string arrangement condition set in advance based on the binary data string, and the connection processing unit 624 For each point arranged in the two-dimensional area, a point to be connected is extracted, and a connection process is performed to connect each point and the point to be connected according to a preset connection condition.

  The point arrangement processing unit 622 sets a matrix based on the binary data string, associates the point arrangement reserved position with each element of the matrix, and sets the value of each element of the matrix to the associated point arrangement reserved position. You may make it arrange | position a point based on.

  Further, the point arrangement processing unit 622 may divide the two-dimensional region into a plurality of cells arranged in a lattice shape, and set the lattice point or the representative point of each cell as the point arrangement reserved position.

  The connection processing unit 624 sets other points satisfying the requirement that the straight line connecting each point and the other points does not cross the point arrangement reservation area including the point arrangement reservation positions of the other points as connection target points of the respective points. In addition, a connection process may be performed in which connection target points satisfying predetermined conditions and each point are connected by lines (straight lines).

  The point arrangement processing unit 622 may set a main layer in a two-dimensional area and arrange points on the point arrangement reserved position belonging to the main layer based on the binary data string.

  When the given point arrangement reserved position belongs to the main layer, the point arrangement processing unit 622 sets the main layer so that the point arrangement reserved position within the predetermined range around the point arrangement reserved position does not become the main layer. You may make it set.

  The point arrangement processing unit 622 may set a sublayer in addition to the main layer of the two-dimensional area, and arrange dummy points at the point arrangement reserved positions belonging to the sublayer according to preset dummy point arrangement conditions. Good.

  The point arrangement processing unit 622 may set a parity layer in addition to the main layer of the two-dimensional area, and arrange points on the point arrangement reserved positions belonging to the parity layer based on the parity information.

  The point arrangement processing unit 622 divides the two-dimensional area into a plurality of areas, sets parity information based on points arranged in areas other than the given area, and places points on the parity layer of the given area You may make it do.

  The binary data string generation processing unit 620 converts the given data into the standard Fibonacci expression, and generates a binary data string uniquely associated with the given data.

  The reference position setting processing unit 626 performs processing for setting information indicating the reference position of the two-dimensional area.

  Then, the image generation unit 630 generates a two-dimensional image including information indicating the reference position.

  The orientation information setting processing unit 628 performs processing for setting information indicating the orientation of the two-dimensional area.

  Then, the image generation unit 630 generates a two-dimensional image including information indicating the direction.

  The image generation unit 630 functions as a two-dimensional image generation unit that generates a two-dimensional image by giving a width to a line connecting the points.

  The sound generation unit 642 performs sound processing based on the results of various processes performed by the processing unit 600, generates game sounds such as BGM, sound effects, and sounds, and outputs the game sounds to the sound output unit 192.

4). Image recognition processing 4-1. Flow of Image Recognition Processing FIG. 34 is a flowchart showing the flow of image recognition processing including a two-dimensional code image (recognition target image).

  First, an image including a recognition target card is captured to acquire image data. (Step S210).

  FIG. 2A is a diagram for describing imaging of a recognition target by the imaging unit. The imaging unit 150 images a plurality of cards 14 (recognition objects) arranged on the stage 12 by the player from below the stage 12. The stage 12 is made of a transparent glass plate or the like so that the imaging unit 150 can image the card 14.

  FIG. 2B is a diagram for explaining a card that is a recognition object in the present embodiment. A pattern 16 for identifying each card is printed on the back surface of the card 14 (the surface in contact with the stage 12). A blank portion 18 having a predetermined width is provided around the pattern 16. In the present embodiment, the shape (rectangle) of the outer edge of the pattern 16 represented on each card 14 is determined from image data obtained by imaging a plurality of cards 14, and corresponds to the area of the pattern 16 (area surrounded by the blank portion 18). The image data to be extracted is extracted as a recognition target image.

  The card on which the two-dimensional code of this embodiment is printed can accurately detect the position and rotation angle of the card even if various objects other than the card are present around the card unless the card itself is concealed. In shooting, “uniform color paper or cloth” used as a background is not necessary, and the table surface of an arcade game machine that does not know what can be placed (usually “hands” are placed on it, and light and darkness due to ceiling lighting (The difference also has an adverse effect), which is suitable for an application in which a card printed with visible or invisible ink is placed and an image is taken from under the table.

  Next, a filtering process is performed on the captured image data (step S220).

  In general, it is difficult to uniformly illuminate the table surface to be photographed due to the influence of disturbance or restrictions on the housing design. Therefore, avoid unevenness caused by the arrangement of illumination (especially infrared illumination whose sensitivity is substantially reduced due to the characteristics of the image sensor), noise generated when shooting in the dark or using an inexpensive camera. I can't.

  Therefore, in this embodiment, before entering the image recognition process, only necessary information (“frame” and “bridge” of the dimension code in this embodiment) is extracted to suppress unnecessary information (illumination unevenness and noise). Perform pre-processing with the filter. Specifically, the pre-processing includes three steps of secondary differentiation processing, blurring processing, and binarization processing.

  Specifically, it will be described in the section “4-2. Filtering process”.

  Next, a recognition target image is extracted from the filtered image data (step S230).

  When scanning from the upper left point of the input image (which should have become a black and white binary as a result of preprocessing) and an object (white) different from the background color (black) is found, that point is used as a reference. The outline of the object is traced counterclockwise, and it is determined whether or not the trace result is a card shape (rectangle having four vertices).

  (1) If it is not the shape of the card → Delete only the outline that was just traced. → Then continue scanning.

  (2) If the card shape → Read the card contents. As a result, it branches into the following two.

  (3) If it is the two-dimensional code of this embodiment, the decoding result is returned and the whole contents are erased. → Then continue scanning.

  (4) If it is not the two-dimensional code of the present embodiment, only the outline that has been traced is deleted. → Then continue scanning.

  The above operations (1) to (4) are repeated until all points are traced (that is, until the lower right point is reached).

  FIGS. 35A to 35D are diagrams for explaining the concept of the recognition target image extraction process (main process) according to the present embodiment (in this figure, black and white are inverted for convenience).

  As shown in FIG. 35A, when there is a line noise 510 of thickness 1 in the input image data, it is erased instantly (in one time).

  Further, as shown in FIG. 35B, when there is an obstacle 520 having a line width of 2 or more in the input image data, it is determined whether or not the outline is a rectangle (card). Although the process of (D) is performed, other than that is determined as an obvious obstacle, and the process of FIG. 35 (C) is performed.

  In FIG. 35C, a process is performed in which lines having a line width of 2 or more in thickness are peeled off one by one like a skin.

  In FIG. 35D, it is determined whether the image is a recognition target. If the rectangular internal image is the two-dimensional code of this embodiment (for example, if there is no error after performing recognition processing), the rectangular interior is erased at once. If the rectangular internal image is not the two-dimensional code of the present embodiment (for example, if an error occurs after performing recognition processing), it is peeled off one by one to check whether the rectangular internal image is the two-dimensional code of the present embodiment. .

  Specifically, it will be described in the section “4-3. Recognition target image extraction process (main process)”.

  Next, recognition processing for the recognition target image and error correction processing are performed (step S240).

  Specifically, it will be described in the section “4-4. Recognition processing and error correction processing of recognition target image”.

  Next, recognition direction detection processing is performed (step S250).

  Specifically, this will be described in the section “4-5. Direction Detection Processing for Recognition Target Image”.

4-2. Filtering Process An example of the filtering process of the present embodiment will be described assuming that FIG. 36 is an input image that is a captured image.

  First, secondary differential processing is performed on the image data of the input image, and image data after secondary differentiation as shown in FIG. 37 is acquired.

  FIG. 3 is a diagram illustrating a specific example of a 3 × 3 secondary differential operator used when performing the secondary differential processing. In this embodiment, the weighting coefficient “8” is set for the pixel of interest at the center, and the weighting coefficient “−1” is set for each of the eight adjacent pixels, and the sum of the values obtained by multiplying these pixels by the weighting coefficient is the sum. Then, by multiplying by a predetermined gain (for example, 1), secondary differential data corresponding to this pixel of interest is obtained. It should be noted that for the target pixel in the outer peripheral portion where there are no eight adjacent pixels in the surrounding area, the calculation may be performed on the assumption that there are adjacent pixels having the same gradation data as each target pixel. The secondary differentiation process may not be performed on the pixel.

  Next, blur processing is performed on the image data after the secondary differentiation processing, and image data after blur processing as shown in FIG. 38 is acquired.

  The blurring process using the secondary differential data of the pixel of interest and the surrounding pixels is performed on the secondary differential data subjected to the secondary differential process.

  FIG. 4 is a diagram illustrating a specific example of a blur filter used in the blur process. In the present embodiment, the same weighting is applied to each of the pixel of interest at the center and eight neighboring pixels around it. Specifically, by summing the values obtained by multiplying the secondary differential data of the pixel of interest and each of the eight adjacent pixels by the coefficient value “1”, this is multiplied by a predetermined gain (for example, 1/9). New secondary differential data of the pixel of interest is obtained. That is, a blurring process for averaging the gradation data for nine pixels including the target pixel is performed. Note that the calculation is performed on the target pixel in the outer peripheral portion where there are no eight adjacent pixels in the periphery, assuming that there is an adjacent pixel having the same gradation data as the target pixel. This blurring process may be applied multiple times.

  For example, this embodiment is applied three times. The line width extracted as a “bridge” is adjusted according to the number of times it is applied. (Here, for example, a method of adjusting the blur processing with the radius of Gaussian blur and applying the blur filter only once may be used).

  Next, the binarization process is performed on the image data after the blurring process, and the image data after the binarization process as shown in FIG. 39 is acquired. In FIG. 39, “the horizontal line of the blind behind the person” having a weak contrast can also be extracted strongly.

  In the binarization processing, the second-order differential data after the blurring processing is converted into binary data by comparing it with a predetermined threshold value STH. When secondary differential data> STH, binary data = 1 is set. When secondary differential data ≦ STH, binary data = 0 is set.

  Note that the binarization processing may be performed by performing type conversion (casting) to unsigned integers for the second-order differential data after the blurring processing. By performing type conversion to an unsigned integer, the negative value of the new secondary differential data can be made near the maximum positive value, and the contrast of the image after binarization processing can be increased.

  FIG. 5 is a diagram for explaining the contents of processing by the differentiation processing unit 121, the blurring processing unit 122, and the binarization processing unit 123 described above. As shown in FIG. 5A, the second order differential operator shown in FIG. 3 is used for the image data for the two boundary portions where the pixel color changes from white to black and from black to white. When differential processing is performed, secondary differential data corresponding to the shape shown in FIG. 5B is obtained. When the blur filter shown in FIG. 4 is applied three times to the secondary differential data, new secondary differential data corresponding to the shape shown in FIG. 5C is obtained. When the blurred second-order differential data is cast to an unsigned integer, second-order differential data in which the negative value of the boundary portion is near the maximum positive value as shown in FIG. 5D is obtained. When binarization processing is performed with the cast secondary differential data as the threshold value STH = 0, binary data in which the boundary portion is emphasized as shown in FIG. 5E can be obtained. Comparing the binary data after the binarization processing with the original image data shown in FIG. 5A, it can be seen that the color of the pixel is reversed in black and white.

  Since the negative differential value and the blurring process produce negative values especially near the edges (bright and dark “boundary” parts), by making the small negative value close to the maximum positive value by casting, the input image An image obtained by extracting and emphasizing the edge can be obtained (there is also an effect that the overall contrast is increased). After that, simply cut off with the threshold. As a result, an output image in which the two-dimensional code portion is reversed in black and white is obtained. Of course, in reality, not only black and white reversal, but also the adverse effects due to uneven illumination disappear, and areas where miscellaneous objects other than two-dimensional codes are reflected are also suitable for the removal process of dust, noise, etc. in the recognition target image extraction process It is divided into many small areas.

  Note that this filtering process depends on the thickness of the “frame” and “bridge” of the two-dimensional code (determined according to the thickness of the captured image, the line width of the actual card, and the shooting distance). Is mentioned.

  In addition, since the two-dimensional code of this embodiment is required to emphasize the lines of “frame” and “bridge” thickness, the line thickness (number of pixels) of the two-dimensional code is determined. Accordingly, it is necessary to adjust the filter strength of the blurring process (for example, the number of times the blurring process is performed) and the threshold value of the binarization process. On the other hand, when the line thickness does not change, these adjustments are unnecessary. For example, if 4x8 cards can be successfully laid out with VGA, 2x4 cards can be recognized with the same accuracy with QVGA (the smaller the area, the faster!). It is.

  It should be noted that the processing can be facilitated by providing a slight blank portion (a white edge if the “frame” or “bridge” on the original card is black) around the two-dimensional code of the present embodiment. Is possible.

4-3. Recognition Target Image Extraction Processing FIG. 6 is a diagram showing a specific example of an image (binarized image) on which binarization processing has been performed. In FIG. 6, each square area corresponds to each pixel. In addition, pixels in the hatched area are pixels with binary data (pixel information) = 0, and other areas are pixels with binary data (pixel information) = 1. The binarized image shown in FIG. 6 is a case where the number of pixels is reduced in order to simplify the binarization processing and the contour extraction processing described later. The case of being arranged on 12 is shown. In this example, not only the card 14 but also images other than the card are mixed. In the following description, a pixel with binary data = 1 is referred to as a “white pixel”, and a pixel with binary data = 0 is referred to as a “black pixel”.

  In the contour extraction process, the pixels constituting the binarized image are scanned in a predetermined order to detect the first white pixel that arrives first, and other white pixels adjacent to the white pixel are returned to the first white pixel. The process of extracting the outline of the pixel group composed of adjacent white pixels is performed by tracing (tracing) in order.

  FIG. 7 is a diagram illustrating a specific example of the contour extraction process. In the example shown in FIG. 7, the scan start point SS is set at the upper left of the binarized image, each pixel is scanned sequentially in the right direction, and finally ends at the lower right scan end point SE. To do. In such a scanning operation, the contour extraction unit 125 extracts the first detected white pixel as the trace start point TS1, and again reaches the trace start point TS in the order indicated by the solid line arrow in FIG. A process of tracing white pixels is performed.

  Details of the contour extraction process will be described below. First, the contour extraction unit 125 examines the surrounding eight pixels centering on the position of the white pixel at that time, and determines the position of the white pixel to be traced next.

  FIG. 8 is a diagram for explaining a method of determining the next white pixel in the contour extraction process described above. In FIG. 8, “C” indicates the current pixel of interest (white pixel), and “P” indicates the position of the pixel (white pixel) immediately before the current pixel. The numbers “1” to “8” indicate the priority order of selection of white pixels to be followed next. For example, if the immediately preceding white pixel is located directly above the current pixel of interest, look at each of the upper left, left, lower left, lower, lower right, right, upper right, and upper pixels in order. The white pixel that appears is determined as the white pixel to be followed next. However, since the pixel corresponding to “1” will not be the white pixel to be traced next no matter where the immediately preceding white pixel is located, It is sufficient to examine seven pixels “2” to “8”.

  In this way, when the process of tracing the white pixels in order from the trace start point TS1 is completed, the contour extracting unit 125 extracts the contour based on the coordinate values of the white pixels traced in order.

  Further, after the process of changing each white pixel constituting the outline to a black pixel by the pixel information change process described later, or after the process of changing each pixel in the inner area of the outline to the black pixel, The contour extraction process is restarted from the pixel on the right of the trace start point TS1 (next scan target pixel).

  9 to 12 are diagrams for explaining the flow of the contour extraction process. In FIG. 9, since it is determined that the shape of the contour locus extracted in FIG. 7 is not a predetermined shape, the pixel information changing unit 127 described later changes the white pixels constituting the contour starting from TS1 to black pixels. Has been. The contour extraction unit 125 resumes the scanning operation from the pixel immediately to the right of the trace start point TS1, extracts the next detected white pixel as the trace start point TS2, and traces the white pixels in the order indicated by the solid line arrows. A process for extracting a contour based on the coordinate value of each traced white pixel is performed.

  In FIG. 10, since it is determined that the shape of the contour locus extracted in FIG. 9 is not a predetermined shape, the pixel information changing unit 127 described later changes the white pixels constituting the contour starting from TS2 to black pixels. Has been. The contour extraction unit 125 restarts the scanning operation from the pixel immediately to the right of the trace start point TS2, extracts the next detected white pixel as the trace start point TS3, and traces the white pixels in the order indicated by the solid line arrows. A process for extracting a contour based on the coordinate value of each traced white pixel is performed.

  In FIG. 11, since it is determined that the shape of the contour trajectory extracted in FIG. 10 is not a predetermined shape, the pixel information changing unit 127 described later changes the white pixels that have formed the contour starting from TS3 to black pixels. Has been. The contour extraction unit 125 resumes the scanning operation from the pixel right next to the trace start point TS3, extracts the next detected white pixel as the trace start point TS4, and traces the white pixels in the order indicated by the solid line arrows. A process for extracting a contour based on the coordinate value of each traced white pixel is performed.

  In FIG. 12, since it is determined that the shape of the contour locus extracted in FIG. 11 is a predetermined shape and the inside is a correct two-dimensional code, a pixel information changing unit described later is extracted after the recognition target image is extracted. In 127, each pixel in the inner area of the contour is changed to a black pixel. The contour extraction unit 125 restarts the scanning operation from the pixel adjacent to the right of the trace start point TS4, scans to the scan end point SE, and ends.

  The contour determination unit 126 performs a process of determining whether or not the shape of the contour locus extracted by the contour extraction unit 125 is a predetermined shape. In this embodiment, in order to extract the pattern 16 printed on the card 12 as the recognition target image, it is determined whether or not the shape of the contour locus is a rectangle. Here, the determination as to whether or not the object is a rectangle is made by detecting the vertices of the rectangle included in the pixel row constituting the contour.

  Details of the process for determining the shape will be described below. In the contour determination process, the partial pixel sequence having a predetermined length L is moved along the extracted contour so as to correspond to the head (leading portion) and tail (tail portion) of the partial pixel sequence. The inner product value IP of the two set vectors is calculated.

  FIG. 13 is a diagram illustrating a specific example of a partial pixel column that moves along an outline. For example, assuming that the length L = 10, a partial pixel string composed of 10 pixels along the contour is generated. In addition, two vectors A and B having a predetermined length M (head vector A is VA and tail vector B is VB) are set in the head and tail of this partial pixel column, respectively. Yes. For example, when the length M = 3, the VA has a direction in which the first pixel of the partial pixel column is the end point and the third pixel is the start point. VB has a direction in which the last pixel in the partial pixel column is the start point and the third pixel from the back is the end point.

By the way, each of VA and VB can be expressed as follows.
VA = (difference of X component of VA, difference of Y component of VA)
= (Vax, vay)
VB = (VB X component difference, VB Y component difference)
= (Vbx, vby)
Therefore, the inner product IP of VA and VB is
IP = VA / VB = vax × vbx + vay × vby
It becomes. In the contour determination process, the inner product value IP is compared with a predetermined threshold value TIP. When | IP | ≦ TIP, the angle formed by VA and VB is almost a right angle, and the vertex of the rectangle is a partial pixel sequence. If | IP |> TIP, it is determined that the vertex of the rectangle is not included in the partial pixel column.

  More precisely, since the angle θ formed by VA and VB is calculated by the equation arccos (IP / (| VA | × | VB |)), the length of the vector is calculated or division is performed. Although it is necessary, since it is known that the length of the vector is included in the range of 2 to 2√2 when considering VA and VB, in this embodiment, the value of TIP is set to 2. These troublesome calculations are omitted.

  In this way, when the vertex of a rectangle is detected by moving the partial pixel row along the contour, and the four rectangular vertices are detected while the partial pixel row is moved along the contour, the contour locus is detected. It is determined that the shape of the contour is a rectangle. Otherwise, it is determined that the shape of the contour locus is not a rectangle.

  In the recognition target image extraction processing, when the contour determination processing determines that the shape of the contour locus is a rectangle, processing for extracting binary data corresponding to each pixel in the inner region of the contour as a recognition target image I do.

  When it is determined by the contour determination process that the shape of the contour locus is not rectangular, pixel information change processing is performed to change each white pixel constituting the contour to a black pixel. Here, the change to the black pixel is performed by setting the binary data corresponding to each white pixel that the contour extraction processing has followed in order to 0.

  In addition, when binary data of each pixel in the inner area of the contour is extracted, pixel information change processing is performed to change each pixel in the inner area of the contour to a black pixel. For example, as shown in FIG. 14, the minimum value Xmin and the maximum value Xmax of the X coordinate of each white coordinate constituting the contour, the minimum value Ymin and the maximum value Ymax of the Y coordinate are extracted, and each Y coordinate from Ymin to Ymax is extracted. , The binary data corresponding to each pixel from the corresponding Xmin to Xmax is set to 0.

  FIG. 15 is a flowchart for explaining an example of processing of this embodiment. Here, the processing after the binarization processing unit 123 performs the binarization processing will be described.

  Scanning of each pixel constituting the binarized image obtained by the binarization processing unit 123 is started, and it is determined whether or not all the pixels have been scanned (step S110). If all the pixels have not been scanned, the next pixel is scanned (step S120). It is determined whether the pixel information of the scanned pixel satisfies a predetermined pixel condition (whether it is a white pixel) (step S130). If not satisfied (if it is a black pixel), the process returns to step S110.

  If the pixel information of the scanned pixel satisfies a predetermined pixel condition (if it is a white pixel), the pixel is extracted as a trace start point, and the predetermined pixel condition is sequentially reached from the trace start point to the trace start point again. A pixel (white pixel) having pixel information that satisfies the above is traced (step S140). Next, a contour is extracted based on the coordinate value of each traced pixel (each white pixel) (step S150). Next, the vertex of the extracted contour is detected, and it is determined whether or not the shape of the contour locus is a predetermined shape (rectangle) based on the detected vertex. (Step S160) If the shape of the contour trajectory is not a predetermined shape (rectangular), the pixel information of the pixels constituting the contour (traced white pixels) other than the pixel information satisfying the predetermined pixel information (two Processing to change to value data = 0) is performed (step S170), and the process returns to step S110.

  If the shape of the extracted contour locus is a predetermined shape (rectangular), a process of extracting binary data corresponding to each pixel in the inner region of the contour as a recognition target image is performed (step S180).

  Next, if the extracted recognition target image is the two-dimensional code of the present embodiment, the process of step S190 is performed (step S182). A determination condition for determining the two-dimensional code of the present embodiment may be set in advance, and if the condition is satisfied, the two-dimensional code of the present embodiment may be determined.

  If it is not the two-dimensional code of this embodiment (step S182), error correction is attempted (step S184), and it is determined again whether or not it is the two-dimensional code of this embodiment. Step S190 is performed (Step S186). If it is not the two-dimensional code of this Embodiment, the process of step S170 will be performed.

  For example, a method as described in “4-4. Recognition processing and error correction processing of recognition target image” can be used for determining whether or not the code is a two-dimensional code according to the present embodiment.

  If the recognition target image is the two-dimensional code of the present embodiment, a process of acquiring the card identification number, position, etc. from the extracted recognition target image is performed (step S190). Next, a process of changing the pixel information of each pixel in the inner region of the outline to pixel information (binary data = 0) other than the pixel information that satisfies a predetermined pixel condition is performed (step S200), and the process returns to step S110. Then, when all the pixels have been scanned, the process ends.

4-4. Recognition processing of recognition target image and error correction processing In the present embodiment, a reference point corresponding position of a recognition target image is detected, and a point of interest (for example, a point arrangement scheduled) set in association with the reference point based on the reference point corresponding position The target point corresponding position on the recognition image corresponding to the position) is calculated, the pixel information of the recognition target image is detected based on the calculated target point position corresponding position, and is correlated with the two-dimensional code based on the extracted pixel information. Calculate the corresponding data.

  40 to 43 are diagrams for explaining the attention point pixel information detection processing. K 1 ′, K 2 ′, K 3 ′, and K 4 ′ are reference point corresponding positions of the recognition target image 400. The reference points may be set, for example, at the four corner vertices (K1, K2, K3, K4 in FIG. 41) of the two-dimensional region. In the case where the two-dimensional region is a rectangle (including a square), the shape can be specified by three vertices or two vertices (vertical vertices) constituting the rectangle, so that the reference point may be three vertices or two vertices.

  The reference point corresponding position of the recognition target image may be determined by the outer peripheral edges (vertices) E1, E2, E3, E4 of the frame line and the frame width. Alternatively, an inner peripheral edge of the frame line 410 may be detected and determined as a reference point corresponding position.

  Here, by setting the point of interest as the point arrangement planned position (250 in FIG. 41) of the main layer, information on whether or not the point is arranged can be acquired from the recognition target image.

  As shown in FIG. 41, the point arrangement planned position 250 of the main layer in the two-dimensional area is determined relative to the reference positions K1, K2, K3, and K4.

Here, it is assumed that the center point of the cell S (2, 2), which is the planned point arrangement position of the main layer in FIG. The relative position of the point P on the two-dimensional image from the reference point K1 is (x, y) (see FIG. 41), and the relative position of the point P ′ on the recognition target image from the reference point corresponding position K1 ′ is If (x ′, y ′), the following equation is established.
x: x ′ = L: L ′
y: y ′ = L: L ′

  Therefore, if the distance L between the reference positions in the two-dimensional region and the distance L ′ between the corresponding positions corresponding to the reference points in the recognition target image are obtained, the point arrangement planned position of the main layer of the recognition target image can also be obtained.

  For example, in FIG. 40, the center point of the cell S (2, 2), which is the planned point arrangement position of the main layer, is the corresponding position on the P recognition target image. ) Can detect that no points are arranged.

  By performing the same processing for all the point arrangement planned positions constituting the main layer, the binary data string arranged in the main layer can be obtained.

  Then, by obtaining data having the obtained binary data string as a standard Fibonacci expression, correspondence data associated with the two-dimensional code can be obtained.

  For example, a standard Fibonacci expression and decimal number correspondence table as shown in FIG. 19 may be stored, and decimal number correspondence data corresponding to the standard Fibonacci expression may be obtained by referring to the correspondence table.

  Further, in the present embodiment, points are arranged at the point arrangement reserved positions in the two-dimensional area according to preset binary data string arrangement conditions based on the binary data string obtained from the recognition target image and set in advance. A connection simulation process is performed to connect each point to the connection target point according to the connection condition, and the connection state of the sampled point detected from the recognition target image is compared with the connection state of the sampled point obtained by the connection simulation process. Thus, at least one of error detection and error correction may be performed.

  That is, the image recognition system also has a point arrangement and connection algorithm when performing two-dimensional code generation, and arranges points in a two-dimensional area based on a binary data string obtained from a recognition target image, A connection simulation process for connecting according to the connection conditions is performed.

  FIG. 42 is a diagram illustrating a state in which points are arranged in a two-dimensional area based on a binary data string obtained from a recognition target image by a connection simulation process. FIG. 43 shows a recognition target image. When attention is paid to the point arranged in the cell S (6, 4) of the main layer and the point arranged in the cell S (8, 3) of the sublayer, the two points satisfy the connection conditions described in FIG. Since it meets, it is connected with a line. Therefore, the two points SP1 and SP2 on the line are sampled, and the position of the point SP1'SP2 'on the recognition image corresponding to SP1 and SP2 is obtained. The method of obtaining the position is the same as the method described with reference to FIGS. Then, the pixel information corresponding to the position obtained from the recognition target image is detected, and it is determined whether or not the detected pixel information indicates the presence of a line (for example, whether the pixel is a black pixel). You may make it perform.

  Possible causes of errors include a forged card and an image recognition error due to noise or the like.

  When an error is detected based on the comparison result, recognition as an error may be stopped, or error correction may be performed.

  For example, when the cause of the error is a counterfeit card, there is no need to correct the error, so that the counterfeit card cannot be used by stopping the recognition as an error.

  If the cause of the error is an image recognition error due to noise or the like, error correction can be performed by changing the position of the stone and performing a connection simulation process until the error disappears.

  In this embodiment, at least one of error detection and error correction is performed on the binary data sequence obtained from the recognition target image based on the condition of the binary data sequence expressed in standard Fibonacci expression. Also good.

  For example, in the standard Fibonacci representation, 1s are not adjacent in the data string. Accordingly, it is possible to determine that an error has occurred when dots are continuously arranged at the point arrangement reserved positions of the main layer.

  Also in this case, recognition as an error may be stopped, or error correction may be performed.

  For example, when the cause of the error is a counterfeit card, there is no need to correct the error, so that the counterfeit card cannot be used by stopping the recognition as an error.

  If the cause of the error is an image recognition error due to noise or the like, the error correction can be performed by changing the position of the stone based on the condition of the binary data string represented by the standard Fibonacci expression.

  In addition, a simulation process is performed in which dummy points are placed under preset dummy point placement conditions at a point placement reserved position belonging to a sub-layer set other than the main layer of the two-dimensional region, and sampling detected from the recognition target image is performed. The position of the dummy point and the position of the dummy point obtained by the dummy point simulation process may be compared to perform at least one of error detection and error correction.

  The placement of dummy points in the sublayer may be in accordance with the placement conditions related to the placement of points in the main layer and parity layer, or in accordance with rules and conditions unrelated to the placement of points in the main layer and parity layer. It may be arranged.

  In the former case, based on the binary data sequence obtained from the recognition target image, a point placement simulation on the main layer and parity layer is performed, and then a dummy point placement simulation on the sublayer is performed. May be.

  Then, a position on the recognition target image corresponding to the dummy point obtained by the dummy point simulation processing is obtained, pixel information corresponding to the position obtained from the recognition target image is detected, and the detected pixel information is the presence of the dummy point. Error detection or error correction may be performed by determining whether or not the error is indicated (for example, whether the pixel is a black pixel).

  FIG. 44 is a flow chart for explaining the flow of recognition target image recognition processing and error correction processing according to the present embodiment.

  First, the reference point corresponding position of the recognition target image is detected (step S310).

  Next, the point arrangement planned position on the recognition image corresponding to the point arrangement planned position belonging to the main layer set in association with the reference point based on the reference point corresponding position is calculated (step S320).

  Next, pixel information of the recognition target image is detected based on the calculated point arrangement planned position (step S330).

  Next, a binary data string is obtained based on the detected pixel information (step S340).

  Next, at least one of error detection and error correction is performed based on the condition of the binary data string represented by standard Fibonacci expression for the obtained binary data string (step S350).

  Next, a simulation process is performed in which dummy points are placed under preset dummy point placement conditions at point placement reserved positions belonging to sublayers set other than the main layer of the two-dimensional region (step S360).

  Next, the position of the sampled dummy point detected from the recognition target image is compared with the position of the dummy point obtained by the dummy point simulation process, and at least one of error detection and error correction is performed (step S370).

  Next, based on the obtained binary data string, a point is arranged at a point arrangement reserved position in the two-dimensional area according to a preset binary data string arrangement condition, and each of the points and a connection target are arranged according to a preset connection condition. A connection simulation process for connecting the points is performed (step S380).

  Next, the connection state of the sampled points detected from the recognition target image is compared with the connection state of the sampled points obtained by the connection simulation process, and at least one of error detection and error correction is performed (step S390).

  It is not necessary to perform all of the above steps, and can be omitted as appropriate according to the recognition level described later.

4-5. Recognition Level of Two-Dimensional Code The two-dimensional code of the present embodiment is scalable in its recognition depth. By looking only at the superficial part, it can be realized at low speed but at high speed, and it can be realized at high speed but at low speed by looking at the deep part. The image quality of the input image can be reduced even if it is the former, but the higher the image quality, the more the latter is required. The level of implementation to be used may be comprehensively determined in consideration of usage and cost.

  The “security level” described below indicates the strength against “cut and paste forgery”.

  Level 1: Use only “Stone” information in the main layer.

  Even if the condition (that is, the image quality) of the image to be recognized is poor, the ID can be acquired somehow. However, only a minimum error check is executed (specifically, “whether it is standard Fibonacci expression”). In addition, since the security level is also lowered, it is actually desirable to use it under limited conditions.

  Level 2: In addition to Level 1, parity layer “stone” information is also used.

  Even if a little loud noise is on the main layer, the possibility of detection is increased. However, the security level is about the same as level 1.

  Level 3: In addition to level 2, sub-layer “stone” information is also used.

  ID detection is at a level that does not cause any problems, including error detection. Medium security level.

  Level 4: In addition to Level 3, sample several points from each “bridge” and acquire / verify connection information between “stones”.

  In terms of security level, there is no practical problem. Good balance between processing speed and ID detection / security level.

  Level 5: View the entire shape of the “bridge”.

  The highest security level. However, since the details are verified as a two-dimensional image (compared with a standard pattern), the processing becomes heavy.

  Specifically, it can be broadly divided into a method of collating “the edge of the bridge” (see only the boundary portion) and a method of collating “the presence / absence of pixels that form the bridge” (see the entire card). In any case, since all the continuity of the line made by the bridge will be examined, it is virtually impossible to forge and paste.

  FIG. 45 is a comparison table of two-dimensional code recognition levels.

4-6. Error correction in pixel units (pre-processing)
Originally, the “bridge” itself has a thickness, so at this point, you can remove the small pixel-level noise on the “bridge” at this point. (Of course, you can also diminish the noise other than the “bridge”.) ).

  Specifically, surrounding pixels may be referred to (for example, “blur filter” is applied).

  If the camera has a low pixel count or a low quality lens, it will be optically "blurred filter", so noise can be removed at the speed of light.

4-7. Error correction in 2D code (this processing)
For example, due to the nature of the standard Fibonacci expression, there must be at least one gap (3 squares or more) between the “stones” of the main layer in the horizontal direction. If there is no gap, You can detect that a problem has occurred (the parsing is more than the permissible amount = that part of the card is floating, tilting, loud noise, counterfeit card ...).

  In this case, move the “stone” of the main layer to a position where one or more gaps (3 squares or more) can be secured, or remove the “stones” temporarily by moving the “stone” in the main layer. The degree of agreement with the sub-layer “stone” and parity layer “stone” (of course, information on the “bridge” between them) is also used. ) And the arrangement with the least error is returned as the recognition result after error correction. In normal cases, if it can be corrected well, the error will be zero or approach zero. On the other hand, if the error does not fall below the threshold value with some corrections, there is a high possibility that the imaging system is troubled or a forged card is cut and pasted.

  Of course, this correction method not only detects errors due to the nature of the standard Fibonacci representation as in the example above, but also all the “stones” and “bridges” (or bridges) in the main layer, sub layer, and parity layer (or This is also effective for black-and-white reversal (where black and white are reversed due to noise or the like) of “stone” or “bridge”.

  By the way, the point here is that the routine for encoding is built in the implementation that decodes this two-dimensional code, and the simulation is performed if necessary (and aiming at the minimum error). is there. In other words, it can be said to be error correction by total war, using the entire shape of the aggregate of “bridges” constituting this two-dimensional code. The presence or absence of one “stone” greatly affects the surroundings and parity, so it does not depend on the local area (which affects the surroundings in a chain reaction).

4-8. Sister ID and card orientation In this embodiment, orientation determination information relating to the relationship between the value of the binary data string and the orientation of the recognition target image is stored, and the recognition target image is identified based on the obtained binary data string and the orientation determination information. Processing to determine the direction is performed.

  It holds the relationship between the sister ID (the forward direction ID when recognized in the forward direction and the backward direction ID when recognized in the reverse direction) and the orientation as the direction determination information, and which is the recognized data? To determine the direction. For example, if the obtained data is the reverse direction ID, it may be determined that the direction of the card is the reverse direction.

  Further, as the direction determination information, conditions that can be taken by the positive direction ID (for example, range) for the sister ID are stored, and the conditions that can be taken by the negative direction ID are stored, and the direction is determined depending on which condition the recognized data satisfies. It may be.

  The sister ID can be used particularly when the card printed with the two-dimensional code of this embodiment is applied to a card game machine or the like. In general, a two-dimensional code has two types of IDs when it is read from the normal position and when it is read from the reverse position. At this time, the ID of the reverse position as viewed from the normal position ID (or vice versa) is set to “sister. Called “ID”. If the ID of the normal position is determined, the ID of the reverse position is also uniquely determined (of course, the reverse is also true). Practical merits include that it is important information for knowing the card orientation, and that the card is recognized at both the forward and reverse positions to increase the recognition accuracy (redundancy). It is done. The ID at the normal position and the ID at the reverse position can be converted to each other at high speed by purely arithmetic logic operation.

  Note that there are some that have only the forward position ID and no reverse position ID, but this is referred to as “no sister ID”. This is because, for example, in the case of 7fit, “32” (1010100) is not used.

  Incidentally, it is possible to mount so that the recognition engine detects only the card having the ID of the normal position. In this case, it can be handled that “the card exists on the table of the housing only when the card is in the normal position”. If you flip the same card upside down and put it in the opposite position, the card will disappear (use like a switch). Of course, the same effect can be obtained with a card having a sister ID. Therefore, if it is desired to keep track of the positions and rotation angles of all the cards, the card may be composed only of cards having a sister ID.

5. Image Recognition Device FIG. 1 shows an example of a functional block diagram of a game system to which the image recognition device of this embodiment is applied. Note that the game device of this embodiment may have a configuration in which some of the components (each unit) in FIG. 1 are omitted.

  The imaging unit 150 is for imaging a recognition object, and the function can be realized by a camera using a CCD as an imaging element. In addition, the imaging unit 150 performs a process of outputting image data, which is a set of grayscale gradation data (pixel information) corresponding to pixels of each coordinate in the imaging range, to the processing unit 100.

  The operation unit 160 is for a player to input operation data, and the function can be realized by a lever, a direction instruction key, a button, or the like.

  The storage unit 170 serves as a work area for the processing unit 100, the communication unit 196, and the like, and its function can be realized by a RAM (VRAM) or the like.

  An information storage medium 180 (a computer-readable medium) stores programs, data, and the like, and the function can be realized by an optical disk (CD, DVD), a memory card, a hard disk, a memory (ROM), or the like. . The processing unit 100 performs various processes of the present embodiment based on a program (data) stored in the information storage medium 180. That is, the information storage medium 180 stores a program for causing a computer to function as each unit of the present embodiment (a program for causing a computer to execute processing of each unit).

  The display 190 is for displaying and outputting an image generated according to the present embodiment.

  The sound output unit 192 outputs the sound generated by the present embodiment, and its function can be realized by a speaker, headphones, or the like.

  The portable information storage device 194 stores player personal data, game save data, and the like. Examples of the portable information storage device 194 include a memory card and a portable game system.

  The communication unit 196 performs various controls for communicating with the outside (for example, a host device or other game system), and functions thereof include hardware such as various processors or communication ASICs, programs, and the like. Can be realized.

  Note that a program (data) for causing a computer to function as each unit of this embodiment is distributed from the information storage medium of the host device (server) to the information storage medium 180 (storage unit 170) via the network and communication unit 196. May be. Use of the information storage medium of such a host device (server) can also be included in the scope of the present invention.

  The processing unit 100 (processor) performs game calculation processing, image generation processing, sound generation processing, and the like based on operation data from the operation unit 160, a program, and the like. The processing unit 100 performs various processes using the storage unit 170 as a work area. The functions of the processing unit 100 can be realized by hardware such as various processors (CPU, DSP, etc.), ASIC (gate array, etc.), and programs.

  The processing unit 100 includes a game calculation unit 110, an image generation unit 140, and a sound generation unit 142.

  The game calculation unit 110 performs game calculation processing for generating game images and game sounds. Here, as the game calculation process, a process for determining the game content and game mode, a process for starting the game when the game start condition is satisfied, a process for proceeding with the game, and a game parameter that changes depending on the game play are calculated. There is a process or a process of ending a game when a game end condition is satisfied.

  The game calculation unit 110 includes an image recognition unit 120. The image recognizing unit 120 extracts image data corresponding to the pattern portion of the card from the image data output by the image capturing unit 150 as a recognition target image, and identifies identification information and position of the card imaged from the extracted recognition target image. Perform the acquisition process. And the game calculation part 110 performs game calculation based on the identification information, position information, etc. of the acquired card | curd.

  The image recognition unit 120 includes a differentiation processing unit 121, a blur processing unit 122, a binarization processing unit 123, a contour extraction unit 125, a contour determination unit 126, a pixel information change unit 127, a recognition target image extraction unit 128, and target pixel information. A detection unit 130, a corresponding data calculation unit 132, a simulation processing unit 134, an error detection / correction processing unit 136, and a direction determination unit 138 are included.

  The differential processing unit 121 performs secondary differential processing using the gradation data (pixel information) of the pixel of interest and surrounding pixels on the image data output from the imaging unit 150.

  The blurring processing unit 122 performs blurring processing on the secondary differential data that has been subjected to the secondary differential processing by the differential processing unit 121, using the secondary differential data of the pixel of interest and its surrounding pixels.

  The binarization processing unit 123 converts the new secondary differential data output from the blurring processing unit 122 into binary data by comparing it with a predetermined threshold value STH. When secondary differential data> STH, binary data = 1 is set. When secondary differential data ≦ STH, binary data = 0 is set.

  Note that the new binarized data output from the blurring processing unit 122 may be subjected to the above binarization processing by performing type conversion (cast) to an unsigned integer. By performing type conversion to an unsigned integer, the negative value of the new secondary differential data can be made near the maximum positive value, and the contrast of the image after binarization processing can be increased.

  The contour extraction unit 125 scans each pixel constituting the binarized image in a predetermined order to detect the first white pixel that reaches first, and returns other white pixels adjacent to the white pixel to the first white pixel. The process of extracting the outline of the pixel group consisting of adjacent white pixels is performed by tracing (tracing) in order until it comes.

  When the contour determination unit 126 determines that the shape of the contour locus is a rectangle, the recognition target image extraction unit 128 extracts binary data corresponding to each pixel in the inner region of the contour as a recognition target image. Perform the process.

  When the contour determining unit 126 determines that the shape of the contour locus is not rectangular, the pixel information changing unit 127 performs a process of changing each white pixel constituting the contour to a black pixel. Here, the change to the black pixel is performed by setting the binary data corresponding to each white pixel traced in order by the contour extraction unit 125 to 0.

  Further, the pixel information changing unit 127 changes each pixel in the inner area of the contour to a black pixel when the recognition target image extracting unit 128 extracts binary data of each pixel in the inner area of the contour. Perform the process. For example, as shown in FIG. 14, the minimum value Xmin and the maximum value Xmax of the X coordinate of each white coordinate constituting the contour, the minimum value Ymin and the maximum value Ymax of the Y coordinate are extracted, and each Y coordinate from Ymin to Ymax is extracted. , The binary data corresponding to each pixel from the corresponding Xmin to Xmax is set to 0.

  The point-of-interest pixel information detection unit 130 detects a reference point corresponding position of the recognition target image, and recognizes an image corresponding to a point of interest (for example, a point arrangement planned position) set in association with the reference point based on the reference point corresponding position. The upper attention point corresponding position is calculated, and the pixel information of the recognition target image is detected based on the calculated attention point position corresponding position.

  The correspondence data calculation unit 132 performs processing for calculating the correspondence data associated with the two-dimensional code based on the pixel information detected by the attention point pixel information detection unit 130.

  The point-of-interest pixel information detection unit 130 calculates the point arrangement planned position on the recognition image as the point-of-interest corresponding position using the point arrangement planned position belonging to the main layer as the point of interest, and the recognition target image based on the calculated point arrangement planned position Pixel information is detected, and the corresponding data calculation unit 132 obtains a binary data string based on the detected pixel information, and obtains given data uniquely associated with the obtained binary data string as corresponding data. You may do it.

  Based on the binary data sequence calculated by the corresponding data calculation unit 132, the simulation processing unit 134 arranges points at the point arrangement reserved positions in the two-dimensional area according to preset binary data sequence arrangement conditions, and sets them in advance. A connection simulation process for connecting each point and a point to be connected may be performed in accordance with the connected condition.

  The simulation processing unit 134 performs a dummy point simulation process in which dummy points are arranged in a preset dummy point arrangement condition at a point arrangement reserved position belonging to a sublayer set other than the main layer of the two-dimensional area. May be.

  The error detection / correction processing unit 136 compares the connection state of the sampled points detected from the recognition target image with the connection state of the sampled points obtained by the connection simulation process, and detects at least one of error detection and error correction. May be performed.

  The error detection / correction processing unit 136 performs at least one of error detection and error correction on the binary data string calculated by the corresponding data calculation unit 132 based on the condition of the binary data string expressed in standard Fibonacci expression. May be performed.

  The error detection / correction processing unit 136 compares the sampled dummy point position detected from the recognition target image with the dummy point position obtained by the dummy point simulation process, and performs at least one of error detection and error correction. You may make it perform.

  The orientation determination unit 138 performs processing for determining the orientation of the recognition target image based on the binary data sequence calculated by the corresponding data calculation unit 132 and the orientation determination information.

  The image generation unit 140 performs drawing processing based on the results of various processing (game processing and image recognition processing) performed by the processing unit 100 and outputs the result to the display 190. In this case, the image generated by the image generation unit 130 may be a so-called two-dimensional image or a three-dimensional image.

  The sound generation unit 142 performs sound processing based on the results of various processes performed by the processing unit 100, generates game sounds such as BGM, sound effects, or sounds, and outputs the game sounds to the sound output unit 192.

  The present invention is not limited to that described in the above embodiment, and various modifications can be made. For example, terms cited as broad or synonymous terms in the description in the specification or drawings can be replaced with broad or synonymous terms in other descriptions in the specification or drawings.

  In the above-described embodiment, the two-dimensional code having a configuration in which the points arranged in the two-dimensional region are connected by lines, and the generation method and the recognition method thereof are described as examples, but the present invention is not limited thereto.

  For example, given data is a two-dimensional code encoded as a two-dimensional image, and based on a binary data string uniquely associated with the given data, the main layer set in the two-dimensional area An image component includes a point arranged at a point arrangement reserved position to which it belongs and a dummy point arranged at a point arrangement reserved position belonging to other than the main layer of the two-dimensional area, and gives a given pattern to the point. A two-dimensional code that has been converted into a two-dimensional image and a method for generating and recognizing the same are also within the scope of the present invention.

The example of the functional block diagram of the game system to which the image recognition apparatus of this embodiment is applied. The figure for demonstrating imaging of the recognition target object by an imaging part. A specific example of a 3 × 3 secondary differential operator used when performing secondary differential processing. A specific example of a blur filter used in blur processing. The figure for demonstrating the content of the process by a differentiation process part, a blurring process part, and a binarization process part. A specific example of a binarized image (binarized image). A specific example of contour extraction processing. The figure for demonstrating the method of determining the next white pixel in an outline extraction process. The figure for demonstrating the flow of an outline extraction process. The figure for demonstrating the flow of an outline extraction process. The figure for demonstrating the flow of an outline extraction process. The figure for demonstrating the flow of an outline extraction process. The specific example of the partial pixel row | line | column which moves along an outline. A specific example of pixel information change processing. The flowchart for demonstrating an example of the process of this embodiment. FIGS. 16A to 16C are examples of the two-dimensional code of the present embodiment. FIGS. 17A and 17B are examples of a simplified two-dimensional code according to the present embodiment. The flowchart which shows the flow of a production | generation process of a two-dimensional code. It is a correspondence table of decimal number, binary number, and standard Fibonacci expression. The figure for demonstrating an example of the two-dimensional area | region of this Embodiment. The figure for demonstrating an example of the two-dimensional area | region of this Embodiment. The figure for demonstrating arrangement | positioning of the binary data sequence to a main layer. The figure for demonstrating the setting method of a parity bit. The figure for demonstrating the setting method of a parity bit. The figure which shows a mode that the parity information was set based on arrangement | positioning of the point of a main layer, and the stone was arrange | positioned to the parity layer. It is a figure for demonstrating arrangement | positioning of the dummy data (dummy stone) to a sublayer. It is a figure for demonstrating the rule which bridges. It is a figure for demonstrating the rule which bridges. It is a figure for demonstrating the rule which bridges. It is a figure for demonstrating the rule which bridges. The figure showing a mode that the point of the two-dimensional area was connected with the line. Completion drawing of 2D code. The functional block diagram of a two-dimensional code generation system. The flowchart which shows the flow of the recognition process of the image containing a two-dimensional code image (recognition target image). FIGS. 35A to 35D are views for explaining the concept of recognition target image extraction processing (main processing) according to the present embodiment. An input image that is a captured image. Image data after second order differentiation. Image data after blur processing. Image data after binarization processing. The figure for demonstrating attention point pixel information detection processing. The figure for demonstrating attention point pixel information detection processing. The figure for demonstrating attention point pixel information detection processing. The figure for demonstrating attention point pixel information detection processing. The flowchart for demonstrating the flow of the recognition process of a recognition target image, and an error correction process. It is a comparison table of the recognition level of a two-dimensional code. The figure for demonstrating the conventional card | curd using a two-dimensional code.

Explanation of symbols

100 processing unit 110 game calculation unit 120 image recognition unit 121 differentiation processing unit 122 blur processing unit 123 binarization processing unit 125 contour extraction unit 126 contour determination unit 127 pixel information change unit 128 recognition target image extraction unit 130 attention point pixel information detection Unit 132 corresponding data calculation unit 134 simulation processing unit 136 error detection / correction processing unit 138 orientation determination unit 140 image generation unit 142 sound generation unit 160 operation unit 170 storage unit 180 information storage medium 190 display 192 sound output unit 194 portable information storage Device 196 communication unit

Claims (20)

Two-dimensional code in which given data is encoded as a two-dimensional image,
In accordance with a preset binary data string arrangement condition, a point arranged at a point arrangement reserved position in a two-dimensional area based on a binary data string uniquely associated with given data;
The image component includes a line that is connected in accordance with a predetermined connection condition for each point and a point to be connected,
A two-dimensional code formed into a two-dimensional image by giving a given width to a line connecting the points. In claim 1,
The line is
The other points satisfying the requirement that the straight line connecting each point and the other point does not cross the point arrangement reserved area including the point arrangement reserved position of the other points is set as the connection target point of each point, and the predetermined condition is satisfied. A two-dimensional code characterized in that it is a line connecting between a connection target point and each point. In any one of Claims 1 thru | or 2.
The point is
A two-dimensional code comprising a point arranged at a point arrangement reserved position belonging to a main layer set in a two-dimensional area based on the binary data string in accordance with a preset binary data string arrangement condition . Two-dimensional code in which given data is encoded as a two-dimensional image,
Uniquely associating et al is the given data, arranged in standard Fibonacci based on the binary data string generated based on the representation, the arrangement reservation location points belonging to the main layer set in the two-dimensional region of a given data And the point
A dummy point arranged at a point arrangement reserved position belonging to other than the main layer of the two-dimensional area, and the image component,
A two-dimensional code that is formed into a two-dimensional image by giving a given pattern to the point. In any one of Claims 1 thru | or 3 ,
The binary data string is generated based on a standard Fibonacci representation of given data. A program for recognizing a two-dimensional code,
The target point corresponding position of the recognition target image is detected, the target point corresponding position on the recognition image corresponding to the target point set in association with the reference point is calculated based on the reference point corresponding position, and the calculated target point corresponding position A point-of-interest pixel information detection unit that detects pixel information of the recognition target image based on
Causing the computer to function as a corresponding data calculation unit that calculates corresponding data associated with the two-dimensional code based on the detected pixel information ;
The attention pixel information detecting unit
Using the planned point placement position belonging to the main layer as the point of interest, calculating the point placement planned position on the recognition image as the point of interest correspondence position, detecting the pixel information of the recognition target image based on the calculated point placement planned position,
The corresponding data calculation unit is
A program characterized in that a binary data string is obtained based on detected pixel information, and given data uniquely associated with the obtained binary data string is obtained as corresponding data. In claim 6 ,
Based on the binary data string calculated by the corresponding data calculation unit, the point is arranged at the point arrangement reserved position of the two-dimensional area according to the preset binary data string arrangement condition, and the point according to the preset connection condition A connection simulation processing unit for performing a connection simulation process for connecting each point and a point to be connected;
A line error detection / correction processing unit that compares at least one of error detection and error correction by comparing the connection state of the sampled points detected from the recognition target image with the connection state of the sampled points obtained by the connection simulation process. program for causing a computer to function as a. In claim 6 or 7 ,
A Fibonacci error detection / correction processing unit that performs at least one of error detection and error correction on the binary data sequence calculated by the corresponding data calculation unit based on the condition of the binary data sequence expressed in standard Fibonacci expression; A program that causes a computer to function . A program for recognizing a two-dimensional code,
The target point corresponding position of the recognition target image is detected, the target point corresponding position on the recognition image corresponding to the target point set in association with the reference point is calculated based on the reference point corresponding position, and the calculated target point corresponding position A point-of-interest pixel information detection unit that detects pixel information of the recognition target image based on
A corresponding data calculation unit for calculating corresponding data associated with the two-dimensional code based on the detected pixel information ;
A dummy point placement simulation processing unit for performing a simulation process for placing a dummy point in a preset dummy point placement condition at a point placement reserved position belonging to a sublayer set other than the main layer of the two-dimensional region;
A dummy point error detection / correction processing unit that compares at least one of error detection and error correction by comparing the position of the sampled dummy point detected from the recognition target image and the position of the dummy point obtained by the dummy point simulation process. A program characterized by causing a computer to function. A program for recognizing a two-dimensional code,
The target point corresponding position of the recognition target image is detected, the target point corresponding position on the recognition image corresponding to the target point set in association with the reference point is calculated based on the reference point corresponding position, and the calculated target point corresponding position A point-of-interest pixel information detection unit that detects pixel information of the recognition target image based on
A corresponding data calculation unit for calculating corresponding data associated with the two-dimensional code based on the detected pixel information ;
An orientation determination information storage unit that stores orientation determination information related to the relationship between the value of the binary data string and the orientation of the recognition target image;
A program that causes a computer to function as a direction determination unit that determines the direction of a recognition target image based on a binary data string calculated by a corresponding data calculation unit and the direction determination information. A program for recognizing a two-dimensional code,
The target point corresponding position of the recognition target image is detected, the target point corresponding position on the recognition image corresponding to the target point set in association with the reference point is calculated based on the reference point corresponding position, and the calculated target point corresponding position A point-of-interest pixel information detection unit that detects pixel information of the recognition target image based on
A corresponding data calculation unit for calculating corresponding data associated with the two-dimensional code based on the detected pixel information ;
Causing the computer to function as a recognition target image extraction unit for extracting a recognition target image from the input image data;
The recognition target image extraction unit includes:
A contour extraction unit that performs a contour extraction process for extracting a contour of a pixel group including continuous pixels having pixel information satisfying a predetermined pixel condition from the image data;
A contour determining unit that determines whether or not a contour locus extracted by the contour extracting unit satisfies a predetermined locus condition;
Pixel information other than the pixel information satisfying the predetermined pixel condition is set as the pixel information of each pixel constituting the outline extracted by the contour extraction unit when the contour determination unit determines that the predetermined locus condition is not satisfied. A pixel information changing unit to be changed to,
An extraction unit that extracts, as the recognition target image, image data corresponding to an inner region of the contour extracted by the contour extraction unit when the contour determination unit determines that a predetermined trajectory condition is satisfied. A featured program. In claim 11 ,
Causing a computer to function as a binarization processing unit that performs binarization processing on the image data;
The contour extraction unit
A program for extracting the contour from image data that has been binarized by the binarization processing unit. In claim 1 2,
A differential processing unit for performing differential processing on the image data;
A blur process for performing blur processing on the image data that has been subjected to differentiation processing by the differentiation processing unit, by averaging pixel information of the pixel of interest and surrounding pixels arranged in the vicinity thereof to obtain new pixel information of the pixel of interest. The computer as a part,
The binarization processing unit
A program for performing binarization processing on image data subjected to blur processing by the blur processing section. According to claim 1 3,
Causing the computer to function as a line width detection unit that detects the width of the lines constituting the recognition target image extracted by the recognition target image extraction unit;
The blur processing unit
A program characterized by determining the number of blurring processes based on the detected line width and performing the blurring process for the determined number of times. In claim 1 2,
Causing the computer to function as a line width detection unit that detects the width of the lines constituting the recognition target image extracted by the recognition target image extraction unit;
The binarization processing unit
A program characterized in that a threshold value used for binarization processing is determined based on a detected line width, and binarization processing is performed using the determined threshold value. A computer-readable information storage medium, wherein the program according to any one of claims 6 to 15 is stored. An image recognition device for recognizing a two-dimensional code,
The target point corresponding position of the recognition target image is detected, the target point corresponding position on the recognition image corresponding to the target point set in association with the reference point is calculated based on the reference point corresponding position, and the calculated target point corresponding position A point-of-interest pixel information detection unit that detects pixel information of the recognition target image based on
A corresponding data calculation unit that calculates corresponding data associated with the two-dimensional code based on the detected pixel information ,
The attention pixel information detecting unit
Using the planned point placement position belonging to the main layer as the point of interest, calculating the point placement planned position on the recognition image as the point of interest correspondence position, detecting the pixel information of the recognition target image based on the calculated point placement planned position,
The corresponding data calculation unit is
An image recognition apparatus characterized in that a binary data string is obtained based on detected pixel information, and given data uniquely associated with the obtained binary data string is obtained as corresponding data. An image recognition device for recognizing a two-dimensional code,
The target point corresponding position of the recognition target image is detected, the target point corresponding position on the recognition image corresponding to the target point set in association with the reference point is calculated based on the reference point corresponding position, and the calculated target point corresponding position A point-of-interest pixel information detection unit that detects pixel information of the recognition target image based on
A corresponding data calculation unit for calculating corresponding data associated with the two-dimensional code based on the detected pixel information ;
A dummy point placement simulation processing unit for performing a simulation process for placing a dummy point in a preset dummy point placement condition at a point placement reserved position belonging to a sublayer set other than the main layer of the two-dimensional region;
A dummy point error detection / correction processing unit that compares at least one of error detection and error correction by comparing the position of the sampled dummy point detected from the recognition target image and the position of the dummy point obtained by the dummy point simulation process. And an image recognition apparatus. An image recognition device for recognizing a two-dimensional code,
The target point corresponding position of the recognition target image is detected, the target point corresponding position on the recognition image corresponding to the target point set in association with the reference point is calculated based on the reference point corresponding position, and the calculated target point corresponding position A point-of-interest pixel information detection unit that detects pixel information of the recognition target image based on
A corresponding data calculation unit for calculating corresponding data associated with the two-dimensional code based on the detected pixel information ;
An orientation determination information storage unit that stores orientation determination information related to the relationship between the value of the binary data string and the orientation of the recognition target image;
An image recognition apparatus comprising: a binary data string calculated by a corresponding data calculation means; and a direction determination unit that determines a direction of a recognition target image based on the direction determination information . An image recognition device for recognizing a two-dimensional code,
The target point corresponding position of the recognition target image is detected, the target point corresponding position on the recognition image corresponding to the target point set in association with the reference point is calculated based on the reference point corresponding position, and the calculated target point corresponding position A point-of-interest pixel information detection unit that detects pixel information of the recognition target image based on
A corresponding data calculation unit for calculating corresponding data associated with the two-dimensional code based on the detected pixel information ;
A recognition target image extraction unit for extracting a recognition target image from the input image data,
The recognition target image extraction unit includes:
A contour extraction unit that performs a contour extraction process for extracting a contour of a pixel group including continuous pixels having pixel information satisfying a predetermined pixel condition from the image data;
A contour determining unit that determines whether or not a contour locus extracted by the contour extracting unit satisfies a predetermined locus condition;
Pixel information other than the pixel information satisfying the predetermined pixel condition is set as the pixel information of each pixel constituting the outline extracted by the contour extraction unit when the contour determination unit determines that the predetermined locus condition is not satisfied. A pixel information changing unit to be changed to,
An extraction unit that extracts, as the recognition target image, image data corresponding to an inner region of the contour extracted by the contour extraction unit when the contour determination unit determines that a predetermined locus condition is satisfied. An image recognition apparatus.