JP3249314B2 - Recognition method of dot character identification symbol of optical disk - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method for recognizing dot characters, and more particularly, to a method for recognizing an identification symbol attached to a ring-shaped mirror surface portion of an optical disk by a reflection film.

[0002]

2. Description of the Related Art An optical disc is produced through a process in which aluminum is deposited as a reflective film on a molded signal forming surface and a protective coating material is applied on the upper surface in order to prevent oxidation of the reflective film. , In general. Then, an identification symbol for identifying what is recorded on each optical disk is provided on a ring-shaped mirror surface portion 12 formed by a reflective film in a portion adjacent to the signal forming surface 11 as shown in FIG. , Which are arranged in an arc. The identification symbol includes an engraved character or a bar code transferred from a disk molding stamper, a character printed by an ink jet printer, and the like. The characters printed by the ink jet printer may be printed on a transparent part other than the ring-shaped mirror part, but are usually represented by a dot pattern (standard form) as shown in FIG. In the case of FIG. 2, various characters are expressed according to which dot position the ink is radiated for 35 dots of 7 dots vertically and 5 dots horizontally, and thereafter, it is represented by a group of such dots. Characters will be referred to as “dot characters”.

When dot characters are arranged in an arc shape on a disk such as an optical disk to form an identification symbol, an ink jet nozzle of a printer is held at a predetermined position.
A dot character as shown in FIG. 3 is printed by rotatably supporting the disk in front of the disk and rotating the disk at a constant speed and emitting ink to a desired position. When printing on this disk (work), various deformed print characters with different sizes and inclinations are printed on the work depending on printing conditions such as unevenness in the speed of rotation of the work and variations in the distance between the print nozzle of the printer and the work. Is done. It is necessary to surely recognize such deformed printed characters and check the product name and serial number of the disk. Conventionally, in order to image-recognize the identification symbol string 10 printed with such dot characters and to judge the quality of each symbol and to determine the type of the optical disk 1, first, a ring-shaped flat portion provided with the identification symbol is used. , The center coordinates in the X and Y directions of the ring center of the ring-shaped plane portion are obtained, and starting from a predetermined position of the ring-shaped image as a starting point, the ring-shaped image is converted from a polar coordinate system based on the ring center to an XY orthogonal coordinate system Then, they are arranged in a straight line on the XY coordinates.
Then, the identification symbol image is cut out from the converted linear plane portion image, and the dots are expanded and contracted a predetermined number of times to form a linear character in which the dots are joined for each dot character, and then the identification symbol is extracted. Detect the beginning of an image sequence. Thereafter, the identification symbol is geometrically corrected using the size of the identification symbol image, and the corrected identification symbol image and the corresponding model character (a previously input recognition target character font) are extracted from the first symbol. They are compared in order, and if the degree of coincidence falls within a predetermined allowable range, it is recognized as a model character. Such a method was adopted.

[0004]

In the above-described method of recognizing identification symbols, uniform characters and well-formed characters can be accurately recognized, and the type of disc can be determined. For dot characters transformed by
Even though there was no problem with the character, the character was sometimes rejected in view of the matching degree with the model character. Further, the deformed dot character is subjected to excessive expansion processing, the dot character is crushed, and the degree of coincidence with the model character is out of an allowable range, so that there is a case where the character is rejected. The present invention takes such points into consideration and detects and corrects the inclination of a character for each disk even if the dot character shape is deformed and causes individual variations, and also adjusts the dot size and the size of the deformed dot character. It is an object of the present invention to provide a method for accurately recognizing the identification symbol of an optical disk by executing the number of times of expansion and contraction suitable for the variation even if the interval occurs, and properly performing the normalization.

[0005]

In the method of recognizing identification symbols of an optical disk according to the present invention, a ring-shaped plane portion is imaged together with identification symbols in which dot characters are arranged in an arc shape, the center of the ring is detected, and a ring-shaped image is obtained. The ring-shaped image is converted from the polar coordinate system based on the center of the ring to the XY orthogonal coordinate system with the predetermined position as a starting point, and arranged linearly on the XY coordinates. Then, a dot character image sequence is cut out from the converted linear plane portion image, the head of the character image sequence is detected, and for each dot character image, the principal axis of inertia passing through the center of gravity of the image is obtained, and the principal axis of each principal axis is determined. Calculate the median of the slope values. A straight line array axis of the plane image and an angle obtained by subtracting the angle indicated by the median from 90 ° are used as initial projection axes, and a straight line intersecting at predetermined coordinates is used as an initial projection axis. The projection axis is rotated about the center, and the image length of the dot character string projected on the projection axis for each angle is calculated. The smallest image length of the calculated dot character string is detected, and the angle between the projection axis and the array axis at that time is subtracted from 90 °, and this is defined as the tilt angle of the dot character image. Further, in each dot character image, the dot image is subjected to expansion and contraction processing a predetermined number of times to obtain a character image in which dots are connected to each other, and the size of the character image in which the inclination angle and the dots are connected. Then, the character image is normalized by performing geometric correction on the character image, and each of the normalized character images is compared with the corresponding model character. If it is within the range, it is recognized as a model character.

In the method for recognizing an identification mark of an optical disk according to the present invention, when setting the number of times of expansion / contraction processing of a dot image as described above, the dots of the standard dot characters are connected to form an appropriate linear character. The number of times that each dot character image is diffused or shrunk in the X and Y directions with respect to the corresponding standard type dot character image, A character recognition method.

[0007]

The tilt angle of the identification symbol image by the dot character and the number of times of expansion / contraction processing suitable for converting the dot character into a linear character are detected for each optical disk. The dot character image is converted into a linear character image according to the number of times of expansion and contraction, and is then geometrically corrected to the tilt angle and size of the model character based on the detected tilt angle and the linear character. Thereafter, the character image is compared with the corresponding model character, and it is recognized whether or not the degree of matching between the two is within a predetermined allowable range.

[0008]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment in which the dot character recognition method of the present invention is applied to an optical disk identification symbol recognition method will be described with reference to the drawings. FIG. 1 is a plan view of an optical disk 1, and FIG. 4 is a schematic configuration diagram for implementing a method of recognizing an identification symbol of the optical disk.
Is an image recognizing device for recognizing an image captured by the image capturing means 3 from above, and 3 is an image capturing means for capturing the optical disk 1 mounted on the table 2 from above.
As shown in FIG. 1, the imaging means 3 is arranged at a distance enough to allow the ring-shaped mirror portion 12 of the optical disk to enter the field of view 13. Further, a ring-shaped surface light source may be arranged between the imaging means 3 and the table 2 in order to improve the quality of the image to be taken. The image recognition device 4 detects the center position of the optical disk 1 from the image information captured by the imaging means 3, recognizes the dot character of the identification symbol attached to the ring-shaped mirror surface, determines the quality of the character, and determines the type of the optical disk. The type is performed.

The operation of the present embodiment will be described. The optical disk 1 is mounted on the table 2 by a transfer unit (not shown), and the imaging unit 3 captures an image of the optical disk surface existing within the visual field 13. The captured image is input to the image recognition device 4, and the image recognition operation is started. The image recognizing device 4 firstly sets the ring-shaped mirror surface portion 12 to which the identification symbol is attached.
In order to cut out the reflected light image from another image, a density histogram of the input image is created, and a threshold value at which the reflected light image can be separated is determined. Then, the image is binarized using the threshold value, and a ring-shaped reflected light image 120 including the identification symbol image 100 shown in FIG. 5 is recognized. further,
The center of the ring is determined by a known method.

The image recognition device 4 converts the ring-shaped image from a polar coordinate system based on the center of the ring to an XY orthogonal coordinate system starting from a predetermined position of the ring-shaped image 120 and, as shown in FIG. Arrange in a straight line. In the present embodiment, in the ring-shaped image 120 in FIG. 5, the phase of a straight line extending downward from the center of the ring in parallel with the Y axis is defined as a starting point (phase angle 0 °), and a certain point is located at any phase from the starting point. This is converted from the polar coordinate system to the XY orthogonal coordinate system by using the X axis as the X axis and the distance from the center of the ring as the Y axis. Then, the converted linear mirror image 121 is binarized with an appropriate threshold value, the identification symbol image 101 is cut out from the strip-shaped mirror image, and the head of the identification symbol image sequence is detected. The start of the image sequence is detected in FIG.
Within a predetermined distance to the left of an extracted identification symbol image,
Judgment is made based on whether or not another identification symbol image exists, and when the identification symbol image does not exist, the identification symbol image is set as the head of the image sequence.

As shown in FIG. 6, the image recognition device 4
The feature analysis is performed on each of the cut-out identification symbol images (dot character images) in order from the top. The center of gravity of each dot character image area is calculated by a well-known method, and the center of gravity is set as the origin, and a straight line having a slope value through which the center of inertia of the image area is minimized (hereinafter referred to as a main axis of inertia) ). The principal axis of inertia of each character image obtained is
As shown in FIG. 7, the inclination direction of the image is shown, and the degree of inclination of each dot character image with respect to the XY orthogonal coordinates is shown. (See "Digital Image Processing Optics" by Keiichi Tezuka, Tadahiro Kitahashi and Hideo Ogawa, published by Nikkan Kogyo Shimbun, pp. 121-123)

The image recognizing device 4 obtains the inclination values of the principal axes of inertia of the dot character images and calculates their median values.
Assuming that the principal axis of inertia shown in FIG. 7 indicates the median value, the image recognition device 4 determines that the linear arrangement axis of the mirror image is 9
A straight line intersecting at predetermined coordinates is defined as an initial projection axis with an angle φ obtained by subtracting the angle θ indicated by the median from 0 °. Then, the projection axis is rotated about the predetermined coordinates at a predetermined angle pitch from there, and the image lengths L1, L2, and L3 of the character strings projected on the projection axis at each angle are obtained. The sum L = L1 + L2 + L3 is obtained.
(The hatched figure on the projection axis indicates the density distribution of each projected dot character image.) Obtain the angle φ of the projection axis that minimizes the sum L of image lengths of the obtained character strings, and calculates the angle φ from 90 °. The angle θ obtained by subtracting φ is defined as the inclination angle of the dot character image. FIG. 8 shows an example in which a dot character image is projected on a projection axis at an angle different from that in FIG. 7. In this case, the lengths L1 ′, L2 ′, and L3 ′ of the symbol images projected on the projection axis are shown. The sum is greater than in FIG. This is because when the projection image of the image inclined at the angle θ is projected on a projection axis orthogonal to the principal axis of inertia (see FIG. 7), the image length becomes the shortest.

The image recognizing device 4 sequentially cuts out each dot character image one by one from the head of the dot character image sequence cut out linearly as shown in FIG. 6, and converts the dot character image into a linear character image. Expansion / contraction processing is performed. First, a method for calculating the number of times of expansion / contraction processing required for performing the expansion / contraction processing will be described below. For example, as shown in FIG. 9, the width of a dot character image cut out one character at a time.
Find wx and height hx. In addition, the image processing apparatus 4 previously stores the width ws and height hs of the dot characters at the standard dot interval (hereinafter referred to as standard dot characters), the number of dots Dw in the width direction of the standard dot characters, and the height. The number of dots Dh in the vertical direction is input, and the number of expansion / contraction processes Ms suitable for connecting the dots of the standard-form dot characters and converting them into linear characters is recognized in advance. The number of processing times Ms of this standard type dot character and the width w of the dot character image
x and height hx, width ws and height hs of standard dot characters,
By the number of dots Dw in the horizontal direction and the number of dots Dh in the height direction of the standard dot characters, the number of expansion / contraction processes Mx suitable for converting to a linear character for each dot character image is expressed by the following equation. Is calculated as follows.

Number of times of appropriate expansion / contraction processing in the width direction; Mxw
= [(Wx-ws) / Dw] + Ms where the decimal point in parentheses is rounded up.

Appropriate number of expansion / contraction processes in the height direction; Mx
h = [(hx−hs) / Dh] + Ms where the decimal point in parentheses is rounded up.

The number of times of expansion processing Mxw and the number of times of contraction processing M
xh and compare the number of times
The expansion / contraction processing is performed as the number of times of contraction processing Mx, and each dot character is converted into a linear character image. Then, using the above-described inclination angle θ and the size of each dot character image, the character image is subjected to geometric correction to be normalized. FIG. 10 is an explanatory diagram showing this geometric correction, in which the coordinates (X ′, Y ′) of a certain point of the character image shown in FIG.
And the corresponding coordinates (X, Y) of the normalized image shown in the right figure (b) are represented by the following equation. “A”, “b”, “c”, “d”, “e”, and “f” in the expression are coefficients determined by a correlation between the inclination angles of both images and the sizes of the images.
(System Research Institute No. 127, published by System Research Institute, Satoshi Minami, Image Information Processing Technology, see pages 20-21)

X = ax ′ + by ′ + c, y = dx ′ + ey ′ + f

According to the above relational expression, geometric correction is performed in order from the leading character image, and the character image is normalized. Compares the normalized character image with the model characters (a dictionary pattern in which a standard character font corresponding to the identification symbol has been entered in advance), and determines whether the degree of matching falls within a predetermined allowable range. If it fits, it is recognized as a model character.

In the above-described geometric correction, even if the geometrical correction is performed according to the relational expression, the grid points of the image before correction correspond to the grid points of the image after correction. Therefore, interpolation is performed using the density values of adjacent pixels by a known method. As shown in FIG. 11, in the present embodiment, f (i, j) is set such that the density value f (i, j) of the grid point (i, j) after correction corresponds to the image before correction (on the captured image). , J), the density values f (m, n), f of the four grid points on the captured image
(M + 1, n), f (m, n + 1), f (m + 1, n +
Interpolating from 1), f (i, j) is calculated by the following equation. Α and β in the expression are internal division ratios indicating the position of the point (i, j) with respect to the grid of the captured image coordinate system surrounding the point, where α is the position in the X direction and β is the position in the Y direction. It shows the direction position.

F (i, j) = f (m, n) · (1−α) · (1
−β) + f (m + 1, n) · α · (1-β) + f (m, n + 1) ·
(1-α) · β + f (m + 1, n + 1) · α · β

As described above, the image recognizing device 4 obtains the density value of each grid point of a pixel from the density values of four adjacent pixels of the captured image corresponding to the grid point at the time of geometric correction of the image. Then, after performing geometric correction and density value interpolation,
It may be determined whether or not the degree of coincidence with the corresponding model character falls within a predetermined allowable range, and if it does, it may be recognized as a model character.

In this embodiment, the case where dot characters are printed on the ring-shaped mirror surface portion by the reflection film of the optical disk has been described. By changing the threshold, it can be easily applied. In the present embodiment, the case where the present invention is applied when recognizing the identification symbol of the optical disk has been described. However, the present invention can be easily applied to, for example, image recognition of a type symbol attached to a ring-shaped flat surface of a bearing. It is possible. In short, the present invention can be applied to various cases in which character strings arranged in a ring shape are image-recognized.

According to the present invention, the inclination angle of the dot character image
Since the minimum number of expansion / contraction processes required to convert dot characters into linear characters is accurately detected for each optical disc, proper normalization of character images such as geometric correction is performed. Thus, the comparison with the model characters can be reliably performed, and even if the shapes and intervals of the printed dots vary, the characters can be recognized with high accuracy.

[Brief description of the drawings]

FIG. 1 is a plan view of an optical disc according to an embodiment of the present invention.

FIG. 2 is an explanatory diagram showing dot characters.

FIG. 3 is an explanatory diagram showing a state in which dot characters are arranged in an arc shape.

FIG. 4 is a schematic configuration diagram when the method of recognizing an optical disc identification symbol of the present invention is performed.

FIG. 5 is a diagram illustrating a reflected light image of a ring-shaped mirror surface portion of an optical disc.

FIG. 6 is an explanatory diagram when a reflected light image of a ring-shaped mirror portion is subjected to polar coordinate conversion.

FIG. 7 is an explanatory diagram showing a method of obtaining a tilt angle of a bit character image.

FIG. 8 is an explanatory diagram showing another mode in FIG. 7;

FIG. 9 is an explanatory diagram showing a method of calculating an appropriate number of times of expansion / contraction processing.

FIG. 10 is an explanatory diagram showing a geometric correction method.

FIG. 11 is an explanatory diagram showing a density interpolation method.

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 1 Optical disc 10 Identification symbol (dot character) 12 Ring-shaped mirror part (ring-shaped flat part) 100 Identification symbol (dot character image) 101 Polarized coordinate-converted identification symbol image (dot character image) 120 Reflected light of ring-shaped mirror part Image (reflected light image from ring-shaped flat part) 2 Table 3 Imaging device 4 Image recognition device

────────────────────────────────────────────────── (5) References JP-A-3-282788 (JP, A) JP-A-4-44187 (JP, A) JP-A-4-38587 (JP, A) US Pat. , A) (58) Field surveyed (Int. Cl. ⁷ , DB name) G06K 9/00-9/82

Claims (4)

(57) [Claims] 1. A dot character recognition method characterized by recognizing dot characters arranged in an arc concentric with the center of a ring on a ring-shaped plane according to the following procedure. a. The ring-shaped plane is imaged, and the center of the ring is detected. b. Starting from a predetermined position of the ring-shaped plane image as a starting point, the ring-shaped plane image is converted from a polar coordinate system based on the ring center to an XY orthogonal coordinate system, and arranged linearly on XY coordinates. c. The dot character image sequence is cut out from the converted linear planar image, and the head of the dot character image sequence is detected. d. For each dot character image, a principal axis of inertia passing through the center of gravity of the image is determined, and the median of the inclination values of each principal axis is calculated. e. A straight line array axis of the plane image and an angle obtained by subtracting the angle indicated by the median from 90 ° are used as initial projection axes, and a straight line intersecting at predetermined coordinates is used as the initial projection axis. The projection axis is rotated about the center, and the image length of the dot character string projected on the projection axis for each angle is calculated. f. The smallest one of the calculated image lengths of the dot character string is detected, and the angle between the projection axis and the array axis at that time is subtracted from 90 °, and this is defined as the inclination angle of the dot character image. g. The expansion / contraction process is performed a predetermined number of times from the leading dot character image detected in step c, and a dot-to-dot character image is formed. h. The character image is normalized by performing geometric correction using the size of the character image in which the inclination angle and the dot are connected, and the normalized character image is compared with the corresponding model character. If the degree of coincidence falls within a predetermined allowable range, it is recognized as a model character. 2. The method according to claim 1, wherein the number of times of expansion / contraction processing of the dot character image in step g is set as
Each dot character image corresponds to the standard character dot character image corresponding to the predetermined number of times of expansion and contraction processing required to connect the dots of the standard type dot character and convert the character into an appropriate linear character. A character recognition method characterized in that the number of times is determined by taking into account the degree of diffusion or contraction in the XY directions. 3. The method according to claim 1, wherein, at the time of the geometric correction, the density value of each grid point by the corrected pixel is calculated by the density of four adjacent grid points before correction corresponding to the grid point. A dot character recognition method for normalizing the character image by performing interpolation of the density value in addition to the geometric correction in step h. 4. The method according to claim 1, wherein the ring-shaped planar image is a reflected light image from a ring-shaped planar portion of an optical disk, and the dot characters are arranged in an arc shape. A discriminating symbol provided on the ring-shaped flat portion of the optical disc in an arc shape.