JP2563865B2 - Image recognition apparatus and method - Google Patents

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates generally to an image recognition apparatus and method, and more specifically, to human recognition of an object (or area) which is not good at conventional image processing techniques. The present invention relates to an image recognition device and method that can be realized at high speed by using a radial projection method that imitates initial visual perception.

Radial projection is a method of concentric curves and radiation.
From either or both of the straight lines
It consists of a radial frame that expresses the size, shape, and shade of the object, projection of the features of the object onto the radial frame, and judgment of the boundary of the object using the projection. By using this method, it is possible to detect objects of various shapes and sizes in an image at high speed and accurately,
Further, it is possible to instantly judge the rough shape and size of the detected object. It should be noted that the present invention includes a method for applying this radial projection method to the recognition of defects and cracks in a material and an apparatus for capturing an object at high speed using the radial projection method.

[0003]

2. Description of the Related Art The following techniques are conventionally known as a method for recognizing an object or region in an image, and more specifically a method for recognizing defects and cracks in a material at high speed.

(1) Prior Art for Extracting Defect Areas As an explanation of the prior art, automatic extraction of defects such as flaws or cracks existing on the surface or inside of a material using image processing technology will be taken up. Usually, an image including these defects has a background, and the sizes of the defects vary in size and shape. In a grayscale image (black and white), the defect part has a different color from the surroundings (for example, it is represented as a dark region or a long dark line) and can be easily identified visually. However, it is very difficult to directly recognize such a defect in the conventional image processing technique because the size of the defect varies. Taking recognition of a defective portion from an X-ray transmission photograph of a welded portion, which will be described later, as an example, the prior art can be summarized as shown in FIGS. 24 to 26.
Such conventional technologies are described in Yamato Koshimizu and Kazuto Murakami, "Welding image processing system", Automated Visual Inspection Technical Research Committee: "Casebook of visual inspection automation by image processing", New Technology Communications, (1991.3), pp.22-32. In FIG. 24, the following processes are sequentially performed on the original image input to the image memory.

(A) Noise removal / smoothing process: This is a process that is always performed before performing the next enhancement process on an image that contains a lot of noise, but it can be visually recognized as only a slight change in shading. Small cracks that do not exist may not be detected later by this process.

(B) Enhancement processing: The main enhancement processing uses a two-dimensional spatial filter as shown in FIG. Although one or more various spatial filters are used in combination with the image characteristics of the detection target taken into consideration as much as possible, the size of the operator is limited in terms of calculation time and effect.
Usually, the size of 3 × 3 to 5 × 5 is mainly used because it is realized as hardware. However, for an object such as a defect in which the size of the detection target is not fixed, the operator The optimal choice of is impossible. Meanwhile, the figure
There is an enhancement process that uses the characteristics of the density cross-sectional shape of the image as in 25, but it is difficult to respond to the change in the size of the detection target, and it takes a considerable amount of calculation time to create a smooth curve. There are essential problems such as the fact that the least squares method is used.

(C) Extraction of defect candidate area (threshold value): Since the emphasis processing of (b) above does not essentially catch the entire shape of the detection target, the sensitivity of extraction of the defect candidate area If the value is raised (realized by changing the threshold value), many healthy parts that are not defective may be extracted. On the other hand, if the sensitivity is lowered, the number of defects that cannot be extracted increases, and it cannot be used for defect inspection.

(D) Calculation of feature amount: Since the defect candidate region extracted in (c) above may include many healthy parts, the feature amount for expressing the difference between the defect part and the healthy part. Needs to be calculated. Further, since there are various kinds of defects in the defects of the welded part, which will be described later, many feature amounts need to be calculated in order to distinguish the defective part from the sound part.

As described above, the conventional technique is extremely ineffective against defects having indefinite size and shape. And in order to cover the weakness, depending on the target such as the defect of the welded part to be described later, the process after the extraction of the defect candidate region becomes very complicated and enormous and it is impossible to deal with it unless an expert system is constructed. Is. This point is as disclosed in the following two documents, for example. That is, Yuhei Kato, Takaaki Okumura, Kosuke Itaga, Tetsuzo Harada, Koji Sugimoto, Koji Dojo, Sadao Inai: "Development of Automatic Pass / Fail Judgment System for Radiographic Images (1st Report) Extraction of Defect Image by Image Processing", Non Destruction inspection, vol.41, No.4, (1992.4), p
p.186 / 195. and Yuhei Kato, Takaaki Okumura, Kosuke Itoga, Tetsuzo Harada, Koji Sugimoto, Koji Dojo, Seijiro Kawano: “Development of Automatic Pass / Fail Judgment System for Radiographic Images (2nd Report) Classification of Weld Defects” Function Development ", Nondestructive Inspection, vol.41, No.4, (199
2.4), pp.196 / 206.

(2) Region of interest imitating a part of visual function
High-speed recognition method for efficient ( high-speed ) recognition of regions of interest (defects) in the image by changing the spatial resolution used for observation, observing coarsely at first, and gradually observing regions of interest Hierarchical methods called pyramid method and quadtree method have been proposed for a long time as a method of imitating a part of human visual function. Regarding this point, for example, Tsuguo Kono: “Surface defect inspection method in advanced industry”,
IPC, (1989.12), pp. 57/90. However, the size of the defect varies, and a minute defect including a crack or the like is often expressed as a subtle color tone in an image, so that it may be overlooked at the time of rough observation. Therefore, this method is not suitable for defect inspection.

(3) Recognition of size and shape of object Calculation of a feature amount for a binary graphic image is attached to software of a normal image processing apparatus, and the perimeter, area,
Various calculations such as maximum diameter, minimum diameter, and center of gravity can be performed. However, if you try to do the same thing even if you can easily express what kind of shape the figure is like, for example, it can be easily visualized as if it is round or square, the conventional method Then, it requires a very difficult calculation. For example, when trying to determine whether the figure shape is a circle or a square, a straight line is fitted to the contour, and when the contour is composed of four straight lines, it is determined to be a quadrangle. It is projected to another space and the feature amount there is used to judge whether the shape is a circle. This point is as disclosed in the following documents, for example. That is, Kazuto Murakami, Yamato Koshimizu: "Houg for image feature extraction
h conversion program library ", Japan Nondestructive Inspection Society No. 6
Image Sensing Technology Symposium on Industrial Skills, (199
1.7), pp.131 / 136. The following are conventional techniques of image recognition devices for recognizing an object or area in an image.

A device for capturing an object at high speed. At present, basic image processing operations (logical operations between images, various spatial filter operations) are executed at high speed using a dedicated LSI, so object recognition by pattern matching after conversion to binary images Is becoming faster. This point is disclosed in the following documents. That is, “Visual Inspection Automation Technology Review Committee”: “Automated Cases of Visual Inspection Automation by Image Processing”, New Technology Communications, (1991.3). Pattern matching is a method for recognizing an object by directly comparing a grayscale image of a characteristic part with a target image, and a comparison operation (calculation of normalized correlation coefficient) for that purpose is performed at high speed by a dedicated LSI. It becomes possible to capture an object at high speed in a limited environment. This point is disclosed in the following documents. That is, Eiji Mizutani: “FA using grayscale pattern matching
Image processing device for application and its application ", New Technology Communications, No. 141, (1991.8), pp.141 / 152. However, as described in (2) above, both devices are When the size and shape are indefinite, it is impossible to capture an object at high speed.

[0013]

DISCLOSURE OF THE INVENTION The present invention is an object (or area) that is not good at conventional image processing techniques.
It is an object of the present invention to provide an image recognition apparatus and method for realizing high-speed image recognition by using a radiation projection method that imitates human initial visual perception. Furthermore, to provide a specific object, to realize high-speed extraction of defects and cracks in the material, and more specifically to provide an image recognition apparatus and method applicable to, for example, defect detection of a welded portion of a metal material. It is an object.

[0014]

[Means for Solving the Problems] (1) An object or a region
How to recognize. For the recognition of an object (or region), which is not good at conventional image processing technology, the "radiation projection method" that imitates human initial visual perception is used. That is, for the shape of the object like the initial visual perception, for the color tone (including black and white shading) as if it was simply round or elongated,
Replace it with a visual expression such as blackish or dim, and geometrically reflect that expression in a "radial frame" (see Fig. 3) used in the radial projection method, and the features of the object are reflected in the radial frame. Recognize an object by projecting it on the screen and making the boundary of the object judged by the projection.
The size and shape of the radial frame can be changed freely, so it is based on the size, shape, and color of the object to be recognized.
It is possible to perform the recognition that brute.

(2) In the material using the method of (1) above
A method for recognizing defects and cracks at high speed. Radiation projection is applied to defects and cracks in materials. Defects and cracks always have a lower density (or higher density) than the surrounding sound areas on the image, even if their outer shapes are complicated.
Since it is expressed as a region, this feature is reflected in the radial frame. Also, since cracks are very narrow compared to their length, they are difficult to detect because they show a subtle color tone on a pixel-by-pixel basis. By reflecting the (orientation) in the radial frame, recognition is performed at the same level as or higher than the visual sense.

(3) High speed using the method of (1) above
A device for capturing objects. It is an image recognition device that programs the method of (1). The calculation for recognition may be hardened . By using the image input system as an integrated image recognition device, it is possible to recognize an object at an extremely high speed.

Therefore, the structure of the present invention is as follows. That is, the present invention includes an image recognition object and a camera that form an image input system, a control computer, an image output monitor, and an image recognition processing device, and the image recognition processing device and the control computer. The image output monitor may be a group of curves with concentricity or a group of curves with concentricity.
Each song that consists of a group of straight lines that extends in a radial pattern and that constitutes the group of curves
Neighboring area including on the line, or the curve group and the straight line group
Each line segment consisting of a curved line part and a straight line part divided by
By projecting the features of the object onto the neighborhood, including on the line
It is configured as an image recognition device characterized by being controlled by an image recognition program which judges whether or not a boundary of an object exists and recognizes an object or an area in an image.

Alternatively, it is composed of an image recognition object and a camera constituting an image input system, a control computer, an image output monitor, and an image recognition processing device, and the image recognition processing device is an image frame memory. Alternatively, the image recognition processing device, the control computer, and the image output monitor, which include the image recognition operation chip and include the image frame memory or the image recognition operation chip, are a group of curves having concentricity.
It consists of a group of curves with concentricity and a group of straight lines extending radially.
A neighborhood area including on the line of each curve constituting the curve group,
Alternatively, a curve part divided by the curve group and the straight line group
It is controlled by an image recognition program that determines whether an object boundary exists by projecting the features of the object onto a neighboring area that includes each line segment consisting of a segment and a straight line and recognizes the object or the area in the image. The calculation chip for image recognition has hardware for the calculation of projection for image recognition and the calculation of boundary determination by the projection, and has a structure as an image recognition device integrally configured from an image input system.

Alternatively, the present invention provides a concentric curve.
Group, or a group of curves with concentricity and a group of straight lines extending radially
And the neighborhood including on the line of each curve that constitutes the curve group
Area, or divided by the group of curves and the group of straight lines
A neighborhood area that includes each line segment consisting of curved and straight lines
A method of recognizing an object or a region in an image by determining whether or not a boundary of the object exists by projecting a feature of the object onto a region, and (i) selecting a radial frame, ii) a shape including the directionality of the object to the radial frame,
Image recognition characterized by comprising the steps of projecting a hue feature and (iii) determining an object boundary using the projection, and performing recognition based on the size, shape, and hue of the object. It has a structure as a method.

Alternatively, the present invention constructs the group of curves in step (i) of selecting the radial frame.
For each concentric curve shape, if the shape of the object or region has no directionality, select a concentric circle or a concentric square,
In the case of a long and thin shape with directionality, select concentric rectangles or concentric elliptical shapes whose major axis directions match, and the size of each concentric curve is the minimum and maximum size of the assumed object or area. is to select the minimum and maximum concentric curve to correspond, the number and spacing of the concentric curve initially selected so that it is clear size of the object or area, release constitutes a straight line group
Regarding the position and number of radial straight lines, the shape of the object to be recognized
And the background of the object in consideration of the selection,
A neighborhood area that includes the lines of the curves that make up the line group, or
A curve portion and a straight line divided by the curve group and the straight line group
Configuration as an image recognition method characterized by recognizing the shape of an object by determining whether or not the boundary of the object exists by projecting the characteristics of the object onto a neighborhood area including each line segment of a part Have.

Alternatively, in the present invention, in the step (ii) of projecting a feature including a directionality of the object and a characteristic of the hue onto the radial frame, the boundary of the object forms the group of curves.
Between neighboring areas including the line of each curve to be formed, or the curve
Group and a straight line part divided by the straight line group
Grasped by comparison of the concentration between neighboring region including the line of Ranaru each line segment, when the comparison of the area, of the near-neighbor regions Rights
A projected projection that represents a uniform density as a representative value of the neighborhood area.
It has a configuration as an image recognition method characterized by including a step .

Alternatively, in the present invention, in the step (iii) of judging the boundary of the object, the boundary area is binarized at an appropriate density, and the object or the entire area is extracted as a binary graphic image. Then, the center of the radial frame is superimposed on the center of gravity of the extracted graphic image to form a radial straight line group.
A line segment neighborhood region r _ij where each straight line and the graphic image intersect is searched, and the region r _ij is all sandwiched by a set of adjacent concentric curves.
Its shape if the region has a generally recognized to be the same as the concentric curve, configuration of an image recognition method and recognizes simultaneously at intervals of precision concentric curves constituting the size even curve group.

Alternatively, according to the present invention, the width of the region in the vicinity of each concentric curve forming the group of curves in the radial frame is determined.
The present invention has a configuration as an image recognition method characterized by recognizing an unclear object or region by increasing the width or increasing it sequentially and obtaining the feature amount for the wider region.

[0024] Alternatively, the present invention has a configuration of an image recognition method, characterized in that the object or area in the image are defective and cracks in the material.

[0025] Alternatively, the present invention is, defects and cracks of the material is, blowholes steel weld slag insertion,
It has a structure as an image recognition method characterized by including welding defects such as poor fusion, insufficient penetration, hot cracking, and lateral cracking.

Alternatively, according to the present invention, in selecting a radial frame, the shape of each concentric curve forming the curve group is selected.
Is characterized by selecting a circle or a square for a three-dimensional defect, and selecting an elongated ellipse or a rectangle for a hot defect such as a crack that has a particularly strong directionality such as a hot crack. It has a configuration as an image recognition method for performing.

[0027]

With the present image recognition apparatus, the following recognition processing is performed on an image input by a camera or the like.

[0028] 1) for objects to be detected, first, performs a rough distinction as Toka elongated ish Toka ish square Toka ish circles the outline, if there is directionality to the object, it is also considered Select the radial frame you have selected. here
Is a radial flare based on the features of the object that the user wants to detect.
The image recognition device recognizes the
It is not processing.

[0029] 2) The determination of the boundaries of the object by an inside and outside of each region of the radial frames classified by performing a comparison of the concentration in order to recognize the object. If it is not a boundary, the radial frame is sequentially expanded, and if the boundary is not found even in the maximum frame assumed in advance, it is determined that there is no object in the frame, the coordinate is moved to the next coordinate, and the same process is repeated.

[0030] 3) For all the captured area boundary of the object, and displays the boundary area in a pixel unit, if necessary, display and recognize the size and shape.

[0031]

[Outline of the Invention] The outline of the contents explained in the embodiments of the following items is shown below. First, a device for capturing an object or a region at high speed is described.

Next, after a brief description of the method of recognition of the boundary of the selection method and the object or area by its radial frame used in the radiation projection by performing formulation of boundary definition, further, actual The method of recognizing an object or a region, the method of recognizing the size and shape of an object or a region, and the recognition of an unclear object or region are described.

[0033] Finally, it has been described by using an image of the defects and cracks in the material from the X-ray radiograph films butt welds of steel how to recognize a high speed. Specifically, the explanation of the detection target and the image input method, the defect detection algorithm, and the recognition method for the crack, which is very difficult to detect by the conventional method, are described.

[0034]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Details of the present invention will be specifically described below with reference to the drawings.

[0035] (1) to capture an object or area in a high speed
Device FIG 1 eye shows a schematic diagram of an image recognition apparatus as an embodiment of the present invention. In FIG. 1, 1 is a phenomenon film, 2 is I
Reference numeral 3 is a TV camera, 3 is a transmitted light illumination box, 4 is a control personal computer, 5 is an image output monitor, and 6 is an image recognition processing device including an image frame memory or an image recognition arithmetic chip.

FIG . 1 shows an embodiment of the present invention, and an object or area on a developing film is assumed as a recognition object. More generally, the components 1 to 3 may be only the recognition object and the camera. The image recognition processing device 6 is a component that executes an image recognition program for recognizing the shape, color tone, etc. of the recognition target by using the radial frame together with the control computer 4 and the image output monitor 5. For this reason, an arithmetic chip for image recognition may be included, and the arithmetic for image recognition may be partially hardened.

[0037] (2) recognizes the object or area in the image
Method A method of recognizing an object or region in an image according to the present invention will be described with reference to FIGS. 2 to 9.

[0038] Humans When viewed images in, to distinguish an area easily by the difference of brightness can be found boundaries that change in brightness. In addition, a person can easily recognize a rotated or enlarged / reduced figure. As a means for realizing the object recognition method using such characteristics of human initial visual perception, the radial projection method using the radial frame shown in FIG. 4 which is one of the present invention is used. The radial frame has a double structure composed of concentric curves shown in FIG. 2 and straight lines extending radially from the center of the frame shown in FIG. As the concentric curve group, various curves such as a square group, a rectangle group, and an ellipse group can be used in addition to the circular group as shown in FIGS. On the other hand, the radial straight line group can judge the boundary of the object,
It is used to recognize the approximate shape. However, the radial frame does not always have to have a double structure, and may consist of only concentric groups of curves or only groups of straight lines, depending on the object to be recognized or the problem.

A method of recognizing an object or area having an arbitrary shape and size using the radial projection method using such a radial frame will be described with reference to FIG.

[0040] by (a) (including the direction) size and shape of the object or area to be selected recognition radial frame, selects a radial frame. If the approximate shape of the object or region is round, or if the shape is not round but has no directionality, then concentric circles or concentric squares are selected. The reason for using a square is that the calculation of coordinates on a frame is easier than that for a circle.
If the shape is long and thin with directionality, a rectangular or elliptical shape whose long axis directions coincide with each other is selected. As the size of the concentric curve, the minimum and maximum concentric curves are selected so that the minimum and maximum sizes of the assumed object or area correspond. The number and intervals of concentric curves are initially selected so that the approximate size of the object or area can be known.

[0041] The radial line is selected in consideration of the contrast between the background shape and object of the object to be recognized for the number of position-. This is to judge whether the boundary of the object exists by projecting the feature of the object on each curve divided by the concentric curve and the radial straight line, and to recognize the rough shape of the object. .

[0042] (b) in many cases the recognition of the boundary of the object or area, humans in recognizing an object (or region) is by utilizing a difference in the brightness of the inside and outside of the boundary. The same will be done with the radial frame of FIG. Now, consider a case where the innermost concentric circle k1 exists in the object to be recognized and the average brightness (density) of the object is lower than that of the surroundings. The boundary of the object can be grasped by comparing the densities between the concentric circles and the curved regions divided by the radial straight lines. For example, arcs aa ', b
Comparing the averages of the concentrations on b ', cc', dd ' with the inner ones in order, it can be seen that the boundary XX' lies between the arcs cc 'and dd'. The boundary XX 'can also be obtained by comparing the averages of shades on the straight lines oa and oa' with the circular arc bb ', with the straight lines ab and a'b' with the circular arc cc ', and with the straight lines bc and b'c' and the circular arc dd '. Can be recognized. Note that in comparing areas, the average density of that portion is used as the feature amount on the divided curves, and expressing such feature amount as a representative value on the curve is called "projection". I'm out. The width on the curve is the object
Alternatively, it depends on the contrast of the area.

[0043] (c) in order to provide generality in the description of the above formulation of boundary definition, generalized as follows projection to any radial frame.

[0044] First, represent the i-th concentric curve of the radial frames, a radial straight line as follows. k _i (i = 1, ..., c) and r _i (i = 1, ..., s) c and s are the numbers of concentric curves and radial straight lines, respectively.

Next, in the i-th concentric curve k _i, 2
A section of the book sectioned by radial straight lines r _j and r _{j + 1}
(A circular arc if the concentric curve is a circle) is represented by k _ij , and a section divided by the two concentric curves k _j and k _{j + 1} on the i-th radial straight line r _i is represented by r _ij . At this time, the concentric curve
k _i and average projection density each P _i of the partitioned section k _ij on, expressed as P _ij. Also, r _ij
The projection of the average density on top is denoted as R _ij .

[0046] normal bounds recognition P _ij and P _i'j, P _ij and P _i ', P _ij and R _ji' and R
The boundary of a normal object or area is recognized by comparing _{(j + 1), i '} (where i'<i), or comparing linear combinations of these.

It is also possible to recognize the boundary by directly comparing the boundary recognition P ₁ when there is no noise or density fluctuation in the image with the density of each pixel of the radial frame.

[0048] by the method of (d) recognizing said object or region (c), can recognize the boundary, in the case of recognizing the entire object or area, the problem given, how to compare different projections There is. For example, if only an object or area of a specific size is extracted from an object or area of an arbitrary size, P ₁ and P _c
Only comparisons are sufficient. Further, for an object or region having an arbitrary shape, it is necessary to compare P ₁ and P _ij (i> 1). As a conditional expression for recognizing the whole object by using these comparison methods, for example, as a conditional expression for an object or region having a low density to exist inside the concentric circle k ₄ , P ₁ <P _{4, j} j = 1, ..., 8 (see FIG. 5) Alternatively, the following conditional expression can be set according to the problem.

[Equation 1]

[0049] (e) sure object or area of the size and shape
Recognition Method Next, a method for recognizing the size and shape of an object or region will be described with reference to FIGS. 6 and 7. Above (2)
The object or area is recognized by the method. If the boundary area is binarized with an appropriate density, the object or the entire area is
The value can be extracted as a graphic image. The center of the radial frame is superimposed on the center of gravity of the extracted graphic image, and a region r _ij where each radial line intersects with the graphic image is searched for. If the regions are all between the same concentric curves,
The shape can be recognized to be almost the same as the concentric curve of the radial frame, and the size can be recognized at the same time although the accuracy of the interval between the concentric curves can be recognized.

[0050] For example, since the intersection area 6 is the two radial straight line r ₃ and r ₇ between k ₁ and k ₂ are four lines between k ₂ and k ₃ is on, It can be easily recognized that the shape of the figure is horizontally long. Further, in FIG. 7, since all the radial straight lines are in the same area, it can be recognized that the shape is circular.

[0051] (f) not clear the object or area recognition now of, with reference to FIGS. 8 and 9, will be described recognition of the object or region is not clear. There are two possible cases in which an object or region cannot be clearly recognized visually. One is a case where the contrast of an object or a region itself is low or a case where a large amount of noise is included, and is visually expressed as if it is blurred or faint. On the other hand, the center of the object or region is clear, but the contrast sharply decreases toward the boundary.

[0052] Radial frame for such a case can be constructed very effectively. That is, by projecting concentric curves with a width as shown in FIGS. 8 and 9, a statistical effect is produced and an object or region can be easily recognized. When the contrast is low as a whole, FIG.
As shown in FIG. 9, the concentric curve has a width, and when the contrast decreases from the center toward the boundary, the width is sequentially increased as shown in FIG.

[0053] In addition, the form of the radial frame without changing,
The effect of noise can be reduced by using a linear combination of region judgments.

[0054] Thus, the radiation projection method can be easily realized ambiguous visual representation of the shape and color.

[0055] (3) recognized by the high speed of the defects and cracks in the material
Method of Doing Next, with reference to FIG. 1, FIG. 10 to FIG. 23 and Tables 1 and 2, a method for recognizing defects and cracks in the material of the present invention at a high speed will be described based on an actual application example.

[0056]

[Table 1] Classification of defects in steel welds * JIS Z3104 (Radiation transmission test method for steel welds and classification method for transmission photographs 3. Classification method for transmission 8 photographs 3.2 Excerpt from defect classification)

[0057]

[Table 2] Names and abbreviations of internal defects in welds and their appearance on the image

[0058] (a) the detection target and an image input method Figure 1, the detection target and an image input method will be described with reference to FIGS. 10 to 16 and Tables 1 to 2.

[0059] defects and cracks in the material targeted are defects generated in the interior of the butt weld of the steel plate. For non-destructive inspection of steel welds by radiation transmission test, JIS
FIG. 10 shows the appearance of an X-ray transmission photographic film which has been specified in accordance with Z3104 of No. 3, and which is sampled according to this specification. FIG.
The part sandwiched between the two welding boundary lines is the welded part. To input the image, place the developing film on the transmitted light illumination box as shown in Fig. 1 and weld it as shown in Fig. 10. Square frame area straddling the line (512 pixels in the direction perpendicular to the welding line,
Input with 480 pixels in the welding line direction and a density gradation of 256. It should be noted that the size of one pixel is 63.5 μm square and corresponds to the resolution of 400 DPI of the copying machine for the recent OA) is stored in the image frame memory in the image recognition device through the ITV camera.

[0060] An example of an image including a defect shown in FIGS. 11 to 16. The left side of each photo is the input original image. In the figure, the vertical direction is the welding line direction, and the bright band-shaped region is the welded portion. The defect is observed as a region of lower brightness than the surroundings in a bright band. The large curved lines shown in FIGS. 12 and 13 are lines drawn by a pencil on the film by an inspector in order to clearly indicate the defect position. The right side of each photograph is the analysis result obtained by extracting only the defective portion by the method described later, and only the defective portion is white (density gradation 255).
it's shown.

[0061] The third type of defect of the steel welds are first and second kind of defects and planar defects defined and, three-dimensional shape in the aforementioned JIS Z3104, as shown in Table 1 There are seed defects. Of these, the third type of defect is a fatal defect that may directly lead to destruction, and is a defect that cannot be overlooked in inspection. There are various types of welding defects depending on the cause, but the main defects are the defects shown in Table 2. With the exception of blowholes and slag inclusion, if the size is small, it will be very difficult to detect with conventional methods. is there.

[0062] To explain the algorithm for defect detection using (b) defect detection algorithm 17 to 18. An example of the program list and the flowchart diagram are summarized in the attached supplementary document, so please refer to it as an example of the program.

FIG . 17 is a flow chart in the case of performing defect detection using the radial projection method described in (2) above. The defect detection algorithm will be described by supplementing only points specific to the defect detection.

Image input

Selection of Parameter / Selection of Radial Frame The type of concentric curve is selected according to the shape of the defect. Since it is possible to use multiple frames at the same time,
For the above-mentioned three-dimensional defect, a circle or a square is selected, and for a planar defect such as a crack, which has a particularly strong directionality, such as hot cracking, it can be seen in FIGS. 19 to 23 described later. Select an elongated ellipse or rectangle like this. The number of radial straight lines is not so large as it is not necessary to recognize the shape of the defect.・ Selection of frame size Select in consideration of the inspection standard and the size that can be detected by visual inspection.・ Projection value area judgment condition ・ Search interval ・ Binarization condition of defect area of detection area

Designation of Search Coordinates As shown in FIG. 18, when the defect detection process is normally moved laterally by the search interval from the upper left, and when the process reaches the right end, the defect detection process is performed again from the left end lowered by the search interval. Specify. However, where a defect area has already been designated during the search, it is not necessary to perform the search again, and therefore processing that removes the coordinates enables more efficient defect detection.

[0067] By using the property that the lowest concentration of the central portion of the area determining defects, comparison region determination projection concentric curve k ₁ innermost P ₁
It can be judged that the region k _ij where P ₁ + T _h <P _ij (j = 1, ..., S) is outside the defect. Here, T _h is the threshold value when the region determination.

Display of Defective Portion The above-described processing makes it possible to display the concentric curve outside the defective area and the location where the defect exists on the radial frame, so that they can be displayed. However, in the case of displaying the boundary of the defect precisely, an appropriate binarization process is required in the area between the area k _ij outside the boundary and the inside k _{i-1, j} . For example, for welding defects, the outer concentric curve of the defect
Each pixel is based on the minimum density g _min inside k _i.
A pixel in which the density value g (x, y) of (x, y) satisfies g _min + _Th > g (x, y) is set as a pixel in the defective area, and FIGS.
The defect extraction result is displayed as shown on the right of the photo.

[0069] Recognition of the cracks will be described with reference to (c) cracking of recognition 19 to 21 and 22 to 23. Since the crack is a planar defect, if it is in a position parallel to the X-ray irradiation direction, it will appear as an extremely thin line on the photographic film and as an image with low contrast, so it will not be detected visually even if it is detected. Requires skill. However, the radial projection method can detect such cracks by making various efforts as follows.

Features of cracks on image Cracks are planar as a whole, but when observed finely, they have a three-dimensional shape with undulations. And the width is changing. On the image, 2 at a specific density level as shown in Figs.
If digitization is performed, a discontinuous image may be generated. However, cracks are usually strongly directional. In the weld, vertical cracks (mainly hot cracks) that appear parallel to the weld line direction and transverse cracks that are orthogonal to each other mainly occur. Horizontal cracks can be easily detected by using circles or squares as concentric curves, but vertical cracks may not be detected by those concentric curves. Therefore, vertical cracks can be recognized by using vertically long concentric curves as shown in FIGS. 19 to 23.

Radial Projection Methods for Recognizing Cracks Several radial projection methods for recognizing cracks will be described with reference to FIGS. 19 to 21 and 22 to 23. 19 and 20 show a method in which the shape of the concentric curve is changed to a vertically long rectangle and an ellipse, and the method of projection and area determination is the same as the method described in (2). In FIG. 21, there are no upper and lower sides except for the concentric curve k _1.
(No projection on the upper and lower sides), No projection on the radial straight line. The projections are the projection P ₁ into k ₁ and the left and right sides. Comparison of area judgment is shaped so as to sandwich the region, 'the projection P _{bb of'} P ₁ and aa 'of the projection P _aa' and bb 'projection P _{cc of'} P ₁ and cc and dd 'of the projection P _{dd' ,} .. ..

In FIG . 22, one of the simple radial frames is used, and three radial straight lines (aof, bo) are used as a reference for comparison.
e, cod), P ₀ = minimum (P _aof, P _boe, P _cod ) (P _{i, 1} > P ₀ ) & (P _{i, 2} > P ₀ ) & (P _{i, 3} > P ₀ ) & (P _{i, 4} > P ₀ ) (i = 2, ..., c) if there exists a minimum i, then the partitioned concentric
It is determined that the curve k _ij (j = 1, 2, 3, 4) is outside the crack area. Even if there is some inclination in the crack direction, the crack can be detected.

In FIG . 23, when a crack having a crack width of ω or more is detected, P _ij > P ₁ (i = 2, ..., c; j = 1, 2, 3, 4) is satisfied. If it is outside the cracked area, it is judged.

[0074] One example of a result of detection of defects in the weld using the detection result this method of (d) defects FIG
This will be described with reference to 11 to 16. Since any defects can be detected satisfactorily, only the problems will be pointed out.

In FIG . 11, the defects are detected sufficiently well, but the defects other than those detected by this method can be visually recognized. This is because an unclear defect is recognized as an extension of a clearly visible defect, and if only that part exists, it is likely to be overlooked by the visual inspection.

In FIG . 14, the object is very difficult to see by visual observation, but it is detected very well.

In FIG . 15, finer cracks than the visual observation are captured. On the other hand, in Figure 16, the judgment of the defective area is made strict.
(The value of T _h is increased), the case having a reduced detection sensitivity. Although the detection result varies considerably depending on the threshold value, note that over-detection of parts other than cracks hardly occurs even if the threshold value is made small and the detection sensitivity is increased.

[0078]

Since the present invention is constructed as described above, according to the image recognition apparatus and method of the present invention, curved lines having concentricity can be used.
Group or radial group, either or both
And the projection of the feature of the shape and shade including the directionality of the object onto the radial frame that expresses the size, shape and shade of the object and the boundary of the object using the projection. Since the judgment is made,
An object of a size can be detected accurately at high speed. Further, the shape and size of the detected object can be instantly judged. Since the size and shape of the radial frame can be freely changed, it is possible to perform recognition based on the size, shape and color of the object to be recognized. More specifically, it is effective in the following fields.

Surface defects and internal defects by non-destructive testing
Fields that detect pits include non-destructive tests such as appearance tests, radiation transmission tests, ultrasonic flaw detection tests, magnetic particle flaw detection tests, and penetrant flaw detection tests.When recognizing defects by these tests, the size and shape of the defects are conventionally used. It is effective to apply the present invention in a field in which a visual inspection by an inspector is required because the description of v. Is ambiguous.

As another specific example, (a) detection of contamination of semiconductor wafer It is effective to apply the present invention in the field of detecting contamination of the wafer surface at each semiconductor processing stage from the stage of the bare wafer.

[0081] it is effective to apply the present invention in (b) fields where especially high speed inspection and identification of the defect in the inspection process of manufacturing the surface dirt and surface flaw of the thin is required.

Field of medical diagnosis using images As a specific example, there is extraction of an abnormal portion from a medical X-ray transmission photographic film, and it is required to extract an abnormal portion of low contrast which is easily overlooked by visual inspection. It is effective to apply the present invention in.

Fields of monitoring work: Specific examples include day and night aircraft take-off and landing route monitoring, traffic monitoring on the road, abnormalities such as human fall on a railway platform, and others. The present invention is characterized in that it is effective in the fields of visual alert work, search work for drifters, and the like.

[0084] In the field of performing sorted objects or parts utilizing high-speed recognition of rough size and shape of the field object sorting of objects, it is characterized in that it is effective to apply the present invention.

The present invention is not limited to the above-described embodiments, but includes all modifications embodied by those skilled in the art from the description of the specification and the drawings.

[Brief description of drawings]

FIG. 1 is an image recognition apparatus as an embodiment of the present invention.

FIG. 2 is a structural diagram of a radial frame composed of concentric curves.

FIG. 3 is a configuration diagram of a radial frame composed of a group of straight lines extending radially from the center of the frame.

FIG. 4 is a configuration diagram of a radial frame in which FIGS. 2 and 3 are combined.

FIG. 5: Method for recognizing boundary of object by radial frame

FIG. 6 is a method for recognizing the shape and size of a captured object.
(In case of oval shape)

FIG. 7: Method for recognizing shape and size of captured object
(For circular shape)

FIG. 8: Radial frame configuration when recognizing an object with low contrast or an object containing noise (when the width is constant)

FIG. 9: Configuration of a radial frame when recognizing an object with low contrast or an object containing noise (when the width is sequentially increased)

FIG. 10 Appearance of welded X-ray film and size of input image

FIG. 11: X-ray photograph including internal defect of welded part (left side: original
Image right side: Detection result) (Part 1) (Blowhole)

FIG. 12: X-ray photograph including internal defect of weld (left side: original
Image right side: Detection result) (Part 2) (Slag inclusion)

FIG. 13 is an X-ray photograph including an internal defect of a welded portion (left side: original)
Image right side: Detection result) (Part 3) (Horizontal crack)

FIG. 14: X-ray photograph including internal defect of weld (left side: original
Image right side: Detection result) (Part 4) (Hot cracking)

FIG. 15: X-ray photograph including internal defect of weld (left side: original
Image right side: Detection result) (Part 5) (Hot cracking)

FIG. 16 is an X-ray photograph containing internal defects of the welded portion (FIG. 15 and
Detection results when the detection sensitivity is lowered for the same original image
Fruit) (Part 6)

FIG. 17 is a flowchart used to detect a defect in a welded portion.

FIG. 18: Method of moving frame for detection

FIG. 19: Crack detection frame (when the concentric curve shape is a vertically long rectangle)

FIG. 20: Crack detection frame (when the concentric curve shape is an ellipse)

FIG. 21 is a frame for crack detection (an example in which there is no upper and lower sides other than the concentric curve k1, and projection P1 into k1 and projection to each side)

FIG. 22: Special frame for crack detection (example using three radial straight lines)

[Fig. 23] Special frame for crack detection (when a crack with a crack width of ω or more is detected)

FIG. 24: Image processing method of defect extraction by conventional method (flow chart)

FIG. 25: Image processing method (brightness value) for defect extraction by the conventional method

FIG. 26: Image processing method (operator) for defect extraction by the conventional method

[Explanation of symbols]

 1 Development Film 2 ITV Camera 3 Transmitted Light Illumination Box 4 Control PC 5 Image Output Monitor 6 Image Recognition Processing Device

 ─────────────────────────────────────────────────── ─── Continuation of front page (56) Reference JP-A-62-125481 (JP, A) JP-A-3-26237 (JP, A) JP-A-3-288278 (JP, A) JP-A-1- 150987 (JP, A) JP 1-108683 (JP, A) JP 61-20845 (JP, A) JP 48-26334 JP, A) JP 59-9505 (JP, A) JP 59-62980 (JP, A) JP-A-2-122380 (JP, A)

Claims (10)

(57) [Claims] 1. An image recognition object and a camera constituting an image input system, a control computer, an image output monitor, and an image recognition processing device. The image recognition processing device, the control computer, and the image. Output monitor is a group of curves with concentricity or a curve with concentricity
Consists of a group of curved lines and a group of straight lines extending radially
Area including the line of each curve, or the curve group and
Consists of a straight line part and a curved part divided by a straight line group
It is characterized by being controlled by an image recognition program for deciding whether or not there is a boundary of an object by projecting the feature of the object onto a neighboring area including each line segment and recognizing the object or the area in the image. Image recognition device. 2. An image recognition object and a camera constituting an image input system, a control computer, an image output monitor, and an image recognition processing device, wherein the image recognition processing device is an image frame memory or The image recognition processing device including the image recognition arithmetic chip, the image recognition processing device including the image recognition arithmetic chip, the control computer, and the image output monitor are concentric curves or concentric curves.
Consists of a group of curved lines and a group of straight lines extending radially
Area including the line of each curve, or the curve group and
Consists of a straight line part and a curved part divided by a straight line group
An image recognition arithmetic chip that is controlled by an image recognition program that determines whether or not a boundary of an object exists by projecting the feature of the object onto a neighboring region including each line segment and recognizes the object or region in the image. An image recognition device in which the calculation of a projection for image recognition and the calculation of a boundary determination by the projection are hardened and integrated from an image input system. 3. Concentric curves or concentric curves
Consists of a group of curves and a group of straight lines extending radially,
Neighboring region including the line of the curve formed, Moshiku the curve group
From the curve part and the straight line part divided by the straight line group
An image recognition method for recognizing an object or a region in an image by determining whether or not a boundary of the object exists by projecting the feature of the object onto a neighboring region including each line segment of Selecting a frame, (ii) a shape including the directionality of the object to the radial frame,
Image recognition characterized by comprising the steps of projecting a hue feature and (iii) determining an object boundary using the projection, and performing recognition based on the size, shape, and hue of the object. Method. 4. In the step (i) of selecting the radial frame, each concentric curve shape forming the group of curves is selected from a concentric circle or a concentric square when the shape of the object or the region has no directionality. However, if the shape is long and thin with directionality, select concentric rectangles or concentric ellipses whose major axis directions match, and set the size of each concentric curve to the minimum and maximum of the assumed object or area. The minimum and maximum concentric curves are selected so that the size of each of them corresponds, and the number and intervals of the concentric curves are selected so that the size of the object or area is known at first, and the radial straight lines forming the straight line group are selected. For the position and number of
The contrast between the shape of the object to be recognized and the background of the object
Select in consideration, and include the line of each curve that composes the curve group.
A neighborhood area, or divided by the group of curves and the group of straight lines
Includes each line segment consisting of a curved line part and a straight line part
4. The image recognition method according to claim 3, wherein the shape of the object is recognized by determining whether or not the boundary of the object exists by projecting the characteristics of the object onto the neighboring area . 5. In the step (ii) of projecting a feature including a directionality of an object and a hue to the radial frame, a boundary of the object includes a line of each curve forming the curve group.
Divided between neighboring areas or by the group of curves and the group of straight lines
Includes each line segment consisting of a curved line part and a straight line part
Grasping is performed by comparing the densities of neighboring areas, and when comparing areas, the average density of the neighboring areas is calculated.
The image recognition method according to claim 3 , further comprising a step of projecting, which is represented as a representative value of the neighborhood area . 6. A step of determining a boundary of the object (ii)
In i), the boundary area is binarized at an appropriate density, the object or the entire area is extracted as a binary graphic image, the center of the radial frame is overlapped with the center of gravity of the extracted graphic image, and The straight lines that make up the straight line group and the graphic image
If a region r _ij near the intersecting line segment is searched and the region r _ij is a region sandwiched by a pair of adjacent concentric curves, its shape
Recognizes that is substantially the same as the concentric curve, also the size curved
4. The image recognition method according to claim 3, wherein the recognition is performed simultaneously with the accuracy of the intervals of the concentric curves forming the line group . 7. The group of curves is formed in a radial frame.
The width of the area near each concentric curve
Increases, the image recognition method according to claim 3, wherein recognizing the object or region is not clear by obtaining a feature amount for a larger area. 8. The image recognition method according to claim 3, wherein the objects or regions in the image are defects and cracks in the material. 9. The defects and cracks in the material include welding defects such as blowholes, slag inclusions, poor fusion, insufficient penetration, hot cracks, and lateral cracks in steel welds. Item 8. The image recognition method according to Item 8. 10. When selecting a radial frame, the shape of each concentric curve forming the group of curves is selected as a circle or a square for a three-dimensional defect, and a planar defect such as a crack is particularly directional. 10. The image recognition method according to claim 8 or 9, wherein an elongated ellipse or a rectangle is selected for a strong hot crack or the like.