JPH0792813B2 - Stamped stamp detection method and device - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION [Industrial application] The present invention selects a single embossing material from a plurality of embossing materials on which an embossed print image is formed, and detects the embossing mark. More particularly, the present invention relates to a method and a device for detecting an embossed mark in which a marking engraved on a relatively small-sized primary rolled steel material is photographed by a television camera and the image is processed to recognize the content.

[Prior Art] For example, a relatively small primary rolled steel material (for example, billet,
Bloom) is marked with numbers, letters, symbols, etc., and this marking is automatically read and recognized, and used for manufacturing, processing, inventory control, etc.

To form this marking, press a marking member (character die) in which numbers, letters, symbols, etc. are formed on the left and right sides against the end surface of the primary rolled steel material and engrave it. It is formed in a groove shape.

As one of the methods, an embossed print image formed on a primary rolled steel material (hereinafter referred to as an engraved material) is obtained as a multi-valued original image signal by an image pickup device such as a television camera, and a binary image obtained by conversion is obtained. Some recognize characters using the final image. As image processing for obtaining a final image for character recognition, there is, for example, JP-A-61-80372. The technique shown therein uses one threshold value for the entire image in the binarization process for converting a multivalued original image into a binary final image, and this threshold value is used as the final image. It is characterized in that it is updated and determined until the number of low-luminance areas in (3) matches the set value.

[Problems to be Solved by the Invention] However, in the conventional marking detection device as described above, when a plurality of marking materials are simultaneously conveyed to the imaging region,
Imprint detection cannot be performed because one of them cannot be specified.

In addition, since the binarization process is performed on the entire image using only one threshold value, there is a case where erroneous recognition is performed.
That is, the engraved surface is not flat, and rust and contamination are often generated, and the degree of occurrence and the state of formation are not constant. For this reason, stains and the like are detected together with the marking, resulting in erroneous recognition and unrecognizable result.

The present invention has been made to solve the problems of the prior art. Even if a plurality of marking materials arrive in the image capturing area at the same time, one of them can be specified to detect the marking. An object of the present invention is to provide a method and an apparatus for detecting an inscription.

[Means for Solving the Problems] In order to achieve the above-mentioned object, the present invention provides an image pickup signal by simultaneously picking up an embossing surface of a plurality of embossing materials on which an embossed print image is formed. A plurality of inspection areas are set radially from the center of the imaged area, each imaging signal in this inspection area is binarized, and the site where the change point appears most strongly is specified as the marking surface of the marking material to be inspected. A method for performing a binarization process for character recognition only on the specified marking surface, and an imaging means for illuminating the embossing surface of a plurality of embossing materials on which an embossed print image is formed from an oblique direction and capturing the image. A plurality of inspection areas are set radially from the center of the imaging area obtained by the imaging means, and the imaging signals obtained by the imaging means in the inspection area are binarized; Change in binary signal This is an apparatus provided with a character recognition means for limiting a specific embossing material by points and binarizing an embossed print image on the embossing material for character recognition.

[Operation] With the above configuration, when a large change point is detected in any of the set inspection areas among the plurality of engraved surfaces in the captured image, the change point is surrounded by each change point. The part is specified as one marking surface. Information for character recognition can be obtained by subjecting only the specified marking surface to binarization processing and, if necessary, accompanying processing. Therefore, even when a plurality of marking surfaces are included in the captured image, one of them can be specified, and the marking detection can be automated.

[Embodiment] FIG. 1 is a block diagram showing an embodiment of the present invention.

The image pickup apparatus 1 is for photographing the stamped surface of one of a plurality of marking materials (in this embodiment, a billet is exemplified), and for example, a television camera is used. Imaging device 1
An embossing detection device 2 is connected to the embossing detection device 2, and character recognition processing units 3 _{-1 to} 3 _-N are connected to the embossing detection device 2.

As shown in FIG. 2, the image pickup apparatus 1 is arranged such that at least one of the marking materials 4 has a marking surface as an imaging area, and a plurality of marking materials are illuminated to illuminate the marking surface. A lamp 5 is provided.

In order to reliably extract the stamped image, it is desired that the density difference (contrast) between the background and the character is large.
This density difference is the effective straight line length of a character that is determined by the direction of illumination light and the shape of the character. (Here, when a straight line parallel to each lighting direction is considered, the straight line and the character are the longest to overlap. The thing is defined as the effective straight line length), and is related to the character's embossing depth. In order to improve the extraction, it is preferable that the characters are deeply stamped and the effective straight line length is shortened. In order to shorten the effective straight line, the illumination by the lamp 5 is oblique to the stamped surface. Good to do.

The embossing detection device 2 is an end face mask image reproduction unit 6 that specifies only one of the plurality of engraving materials 4 included in the original image signal 11 from the image pickup device 1, and an engraved image that performs processing for emphasizing only the engraved image. The enhancement processing unit 7, the AND circuit 8, the marking material orientation detection processing unit 9, the marking position detection unit 10, the marking image separation processing unit 11, and the binarization processing units 12 _{-1 to} 12 _-N .

Next, the general operation of the configuration shown in FIG. 1 will be described.

First, the engraving surface of the engraving material 4 is imaged from the direction shown in FIG. 2 by the imaging device 1, and the engraved image is obtained as a multivalued original image signal 13. On the other hand, the end face mask image generation unit 6 extracts only the marking material 4 in which the entire marking surface is within the imaging region,
An end face mask image 14 is output.

On the other hand, the original image signal 13 is subjected to a process of emphasizing the imprinted image (image of characters, numbers, symbols, etc.) by the imprinted image emphasizing processing unit 7, and the imprinted image emphasizing signal 15 is output. Then,
The AND circuit 8 allows only the stamped image enhancement signal 16 of the stamped image (characters, numbers, symbols, etc.) included in the coordinates Z (x, y) of the end face mask image 14 specified by the end face mask image generation unit 6 to pass through the gate. .

Then, the marking material orientation detection processing unit 9 detects the orientation of the marking material and outputs the marking material orientation information 17.

Further, the marking position detection processing unit 10 detects the marking position based on the marking image enhancement signal 16 and the marking material orientation information 17. Based on the marking position information 18 and the original image signal 13 obtained by the marking position detection processing unit 10, the marking image separation processing unit 11 separates the original image signal 13 for each marking, and N marking-specific image signals. Get 19 Image signal according to this stamp 19
Contains only one of the N imprints. Therefore, the binarization processing units 12 _{-1 to} 12 _-N independently perform binarization processing on each marking to obtain the final images 20 _{-1 to} 20 _-N.
Is obtained. The character recognition processing units 3 _{-1 to} 3 _-N perform character recognition processing on the final images 20 _{-1 to} 20 _-N .

Next, the processing of the end face mask image generation unit 6 will be described with reference to FIGS.

In this case, as shown in FIG. 3, when three marking materials are in the photographing area, one marking material is located in the center of the photographing area, and two marking materials are located on both sides of the marking material with a predetermined gap. Will be described as an example. Then, narrow frames w10, w20, w30, w40 as inspection regions are set in a cross shape vertically and horizontally from the center of the imaging region.

The resolution of the printed image is, for example, 0.305 × 0.305 mm / 1 pixel level, the width of the frame w is 100 pixels (pix), and the length of the frame is 256 pixels.

The three marking materials are bundled in close contact with each other, but since the peripheral edges of both ends are rounded, a groove deeper than the marking is formed between the adjacent markings and outside the peripheral edges. ing. Therefore, when the inside of the frame is binarized, a change point of the binarization level that is clearly different from the marking occurs, and this change point position can be regarded as the peripheral edge of the marking surface.

Specifically, first, binarization processing is performed on each image in the above-mentioned frames w10, w20, w30, w40 by the discrimination threshold method (S31). Then, using the binarization result, the frame w10, w20, w3
For each of 0 and w40, the profile was sequentially measured from the center to the outside in the length direction, and as shown in FIG. 4, the periphery of the marking surface of the marking material 4 to be extracted and the marking The profile changes greatly at the position where the gap between the materials (or between the open spaces) comes into contact, and the change point h1 (frame w1
Existing in 0), change point h2 (existing in frame w20), change point h3 (existing in frame w3
Existing in 0) and the change point h4 (existing in frame w40) are obtained (S3
2). The portion surrounded by the change points is determined to be the end face of the marking material 4 (S33), and this is set to white as shown in FIG. 6 in image processing, and this is output as the end face mask image 14.

Next, details of the stamped image enhancement processing unit 7 will be described.

The marking formed on the marking material 4 is captured as an image by photographing a shadow generated by illumination (hereinafter, an image formed by this shadow is referred to as a marking image). Therefore, if the marking image is sufficiently clear for the marking material orientation detection processing and the marking position detection processing, the image pickup apparatus 1 does not need the marking image enhancement processing. However, it is generally difficult to obtain a marked image clearly, and good image detection cannot be obtained unless the marked image enhancement processing is performed.

The processing performed by the marking image enhancement processing unit 6 can be represented by a mathematical expression as follows.

That is, the density value of the coordinates (x, y) of the image signal 13 is f (x,
y), the density value g of the coordinates (x, y) of the marking-enhanced image
(X, y) is given by the following equation.

Here, xi and yi are movement amounts in the x and y directions when the original image signal is subjected to image movement processing, and ai is a weighting constant. Further, the constant (N, xi, yi, ai) in the above equation can determine the target image signal from the characteristics. By selecting an appropriate constant, it is possible to enhance only the imprinted image without enhancing the noise component.

Next, details of the marking material orientation detection processing unit 9 will be described with reference to FIG.

The marking of the marking material 4 (in this embodiment, a combination of numbers in three stages, the first stage is 5 digits, the second stage is 2 digits, and the third stage is 1 digit) is optimal for the image pickup apparatus 1. It does not come off when it is sent at the location. Therefore, the vertical or horizontal direction is determined from the image of the stamped image enhancement signal 16, and the image is converted into the image at the normal position. Specifically, the density projections in the vertical and horizontal directions of the stamped image are obtained, and the markings are point-symmetrically arranged with the center of the stamping material 4 as the center of rotation and the point pair as the center of rotation of the stamping material 4. If not, depending on the orientation of the marking material 4, the maximum value position of the vertical and horizontal integrated values a and b
c, d or different size.

By performing an analysis based on this information, the orientation of the marking material 4 can be detected. For example, it is determined that the rotation angle is 0, 90 degrees, 180 degrees, or 270 degrees depending on whether the revolution of the maximum value position is at the upper left, upper right, lower right, or lower left of the marking material 4. .

Next, details of the processing of the marking position detection processing unit 8 will be described with reference to FIG.

This process is performed by using the stamped image enhancement signal 16 or stamped material orientation information.
On the other hand, with respect to 17, a specific range of the marking material 4 (in this embodiment,
The density projection is calculated for the density projection calculation range 1) in the figure,
The position of the marking is detected by detecting the unevenness of the integrated value. In FIG. 8, the five numbers in the upper row of the marking are detected, but the positions of all the markings can be detected by repeating the same processing.

Next, details of operations of the binarization processing units 10 _-1 to 10 _-N will be described.

The general operation in this configuration is an image by marking (multivalued image)
The density histogram is calculated, and the marking-based image is binarized based on the binarization threshold determined by the density histogram. As it is, since various noises are included, noise removal processing is performed on the binarized image by a noise removal processing unit (not shown).

This binarization process will be described with reference to FIGS. 9, 10A, 10B and 11 by taking each billet shown in FIG. 7 as an example.

As shown in FIG. 9, the input image is divided so that each character is surrounded by a frame, and the frames w1 to w8 are assigned. This frame w1
For each of w8 to w8, the inside of the frame is binarized by the discriminant threshold method (threshold value: th1, separation b1), and a binarized image wa1 is obtained (S
41). Then, measure the area ar1 of the remaining region (S42),
As shown in FIG. 11, binarization processing (threshold value: th2, separation degree: b2) by the threshold value method (the number of pixels) for the points having the density equal to or greater than the threshold value th1 in the frame, A binarized image wa2 is obtained (S43).

Subsequently, the area ar2 of the remaining region is measured (S44), and the separation degree b1
And b2 are compared (S45). In S45, if b1> b2, the process moves to the flow of FIG. 10B, and if b2> b1, it moves to 10B.
Move to the flow in the figure.

In the flow, the area ar1 is compared with the area threshold arth, and ar1
If it is arth, the image to be processed thereafter is set to wa1 (S4
7). If ar1> arth, the subsequent processing target image
Set to wa2 (S48). The process of S48 is also executed when the flow is selected in S46.

When the processing of S46 or S48 is completed, the feature amount in the processing target image is measured (S49). Then, those with an area of less than 30 pixels (pix: pixels) are removed (S50), and the area ratio is
Removes 0.5 or more (S51). S49 to S51 correspond to the noise removal processing.

Next, specific examples of the present invention will be described.

Here, it is assumed that each stamp 4 is a square billet of about 1200 mm × 1200 mm, and the product number is stamped on the end face. The product number is detected by the stamping detector 2, and this is detected by the character recognition processing unit 3 _-1. ~ 3 _-N recognizes characters. Further, the respective constants in the marking image enhancement processing unit 7 are set as follows.

N = 5 (xi, yi, ai) = (0,0,4), (4,0, -1), (-4,0, -1), (0,4, -1), (0, -4, -1) As a result, in the detection by the conventional technique, partial rust or stain remained on the final image, and the recognition rate was about 76%. However, in the detection according to the present invention, it was confirmed that a clear final image having only the marking can be obtained, and the recognition rate reaches 95%.

[Effects of the Invention] As is clear from the above, according to the present invention, the embossing surfaces of a plurality of embossing materials on which an embossed print image is formed are simultaneously imaged to obtain an image pickup signal, and the image pickup area is recorded. A plurality of inspection areas are set radially from the center, each imaging signal in this inspection area is binarized, and the part where the change point appears most strongly is specified as the marking surface of the marking material to be inspected, and the specified marking Since the binarization process for character recognition is applied only to the surface, even if the captured image contains multiple marking surfaces, one of them can be specified, and the marking detection can be automated. Will be possible.

[Brief description of drawings]

FIG. 1 is a block diagram showing an embodiment of the present invention, FIG. 2 is an explanatory view showing the mounting and illuminating means of the image pickup apparatus 1 shown in FIG. 1, and FIG. 3 is one target from a plurality of marking materials. 4 is an explanatory view showing a process for specifying a change point, FIG. 4 is a change point detection characteristic diagram showing a profile process for specifying a marking material, FIG. 5 is a flow chart showing a process for obtaining a change point, and FIG. 6 is a change point. FIG. 7 is an explanatory view showing the processing of the marking material orientation detection processing unit 9, FIG. 8 is an explanatory view showing the processing of the marking position detection processing unit 10, and FIG. Explanatory drawing showing framing processing of input image, FIGS. 10A and 10B
FIG. 11 is a flow chart showing the processing of the binarization processing unit, and FIG. 11 is an explanatory diagram showing threshold setting. In the figure. 1: Imaging device, 2: Stamp detection device 3 _{-1 to} 3 _-N : Character recognition processing unit 4: Stamping material, 5: Lamp 6: Edge mask image generation unit 7: Stamped image enhancement processing unit 8: AND circuit 9 : Engraved material orientation detection processing unit 10: Engraved position detection processing unit 11: Engraved image separation processing unit 12 _{-1 to} 12 _-N : Binarization processing unit 13: Original image signal 14: End face mask image 15, 16: Engraved image Emphasis signal 17: Marking material orientation information 18: Marking position information 19: Image signal for each marking 20 _{-1 to} 20 _-N : Final image

Claims (2)

[Claims] 1. An imaging signal is obtained by simultaneously imaging the embossing surfaces of a plurality of embossing materials on which an embossed print image is formed, and a plurality of inspection areas are set radially from the center of the imaged area, Each image pickup signal in this inspection area is binarized, the site where the change point appears most strongly is specified as the marking surface of the marking material to be inspected, and the binarization processing for character recognition is performed only on the specified marking surface. A method for detecting an embossing mark, which is characterized in that 2. An imaging means for illuminating an embossing surface of a plurality of embossing materials on which an embossed print image is formed, in an oblique direction, and a radial shape from a center of the imaging area obtained by the imaging means. Means for setting a plurality of inspection areas and binarizing each image pickup signal obtained by the image pickup means in this inspection area, and a specific engraving material by a change point of the binarized signal obtained by this means An embossing mark inspection device, which is provided with a character recognizing means for binarizing an embossed printed image on the embossed material for character recognition.