JP2010029958A - Apparatus, method and program for extracting contour - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To know a shape of a wrinkle and also make effective use of a wrinkled part. <P>SOLUTION: Contour points are extracted from an image of a sheet material imaged by a camera, and an outer contour exhibiting an outline of the sheet material and an inner contour inside it are found. An area between the inner and outer contours is recognized as a wrinkle. A ratio of a longer diameter and a shorter diameter of the found wrinkle shape is calculated. A wrinkle with a large ratio is specified as a strong wrinkle, while a wrinkle with a small ratio is specified as a weak wrinkle. Parts to be cut are assigned on the sheet material depending on the rank of the wrinkles. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to extracting a contour from a sheet material such as leather or fabric.

  The applicant has developed a sheet material cutting device. Patent document 1: In WO2004 / 010807, it was examined to optimally arrange parts to be cut with respect to a sheet material. Patent Document 2: WO 2006/051764 examined how to arrange parts for cutting on an irregularly shaped sheet material such as leather.

The inventor examined wrinkles of the sheet material. FIG. 18 shows an example of leather wrinkles, where 102 is a strong wrinkle and marked with tape 104, and 106 and 108 are weak wrinkles. Wrinkles occur because the original three-dimensional leather is cut and deployed on a two-dimensional table. For example, when a three-dimensional object such as a balloon or ball is cut and placed on the table It ’s the same as somewhere. Although the nature of the leather may be different from other parts in the wrinkled part, the leather is raised by the wrinkle rather than that, and it is more difficult to cut into an accurate shape. The inventor obtained the shape of the wrinkle and evaluated the degree of the wrinkle so that the wrinkle portion could be used as a part.
WO2004 / 010807 WO2006 / 051764

An object of the present invention is to obtain a wrinkled portion of a sheet material by obtaining a wrinkle shape and a wrinkle degree.
An additional problem of the present invention is to enable the wrinkle shape to be obtained efficiently.
An additional object of the present invention is to make it possible to use the wrinkled portion more effectively.

The present invention is an apparatus for extracting contour points by filtering from an image of a sheet material imaged by a camera, connecting the extracted contour points and outputting them as a contour line of a sheet material,
Contour extracting means for obtaining an outer contour line representing the outer shape of the sheet material and an inner contour line inside the outer contour line;
Means for determining the wrinkle shape of the sheet material from the outer contour line and the inner contour line;
A wrinkle shape evaluation means for obtaining an amount representing a ratio between a major axis and a minor axis of the obtained wrinkle shape;
Ranking means for ranking the wrinkles so that the amount representing the ratio is a large wrinkle, and the amount representing the ratio is a weak wrinkle;
An assigning means for assigning parts to be cut from the sheet material to the sheet material in accordance with the wrinkle ranking is provided.

Furthermore, the present invention relates to a program for an outline extraction device that extracts an outline point by filtering from an image of a sheet material imaged by a camera, outputs the outline point by connecting the extracted outline points,
When read into the contour extraction device, the contour extraction device is
Contour extracting means for obtaining an outer contour line representing the outer shape of the sheet material and an inner contour line inside the outer contour line;
Means for determining the wrinkle shape of the sheet material from the outer contour line and the inner contour line;
A wrinkle shape evaluation means for obtaining an amount representing a ratio between a major axis and a minor axis of the obtained wrinkle shape;
Ranking means for ranking the wrinkles so that the amount representing the ratio is a large wrinkle, and the amount representing the ratio is a weak wrinkle;
It is characterized by functioning as an assigning means for assigning parts to be cut from the sheet material to the sheet material in accordance with the wrinkle ranking.

Further, the present invention is a method for extracting a contour point by filtering from an image of a sheet material imaged by a camera, and connecting the extracted contour points to output as a contour line of the sheet material.
By the contour extracting means, an outer contour line representing the outer shape of the sheet material and an inner contour line inside the outer contour line are obtained,
By means for obtaining the wrinkle shape, the wrinkle shape of the sheet material is obtained from the outer contour line and the inner contour line,
By using the wrinkle shape evaluation means, an amount representing the ratio between the major axis and the minor axis of the obtained wrinkle shape is obtained,
The ranking means ranks the wrinkles so that the amount representing the ratio is a large wrinkle and the amount representing the ratio is a weak wrinkle,
The assigning means assigns parts to be cut from the sheet material to the sheet material according to the wrinkle ranking.
In this specification, the description regarding the contour extracting apparatus also applies to the contour extracting method and the contour extracting program as it is, and the description regarding the contour extracting method also applies to the contour extracting apparatus and the contour extracting program.

  In the present invention, the wrinkle shape is obtained from the outer contour line and the inner contour line of the sheet material. When the wrinkle is in contact with the original outline of the sheet material, the area surrounded by the outer outline and the inner outline is wrinkled, and the outer outline is the original outline of the sheet material. When wrinkles are present in isolation within the sheet material, the inner contour line is closed and the inner side is wrinkled.

  From the shape of the wrinkle, the degree of wrinkle, that is, the strength of the wrinkle is obtained. The elongated wrinkles are generally sharp and strong wrinkles, such as the wrinkles 102 in FIG. Wrinkles close to a wide circle are gentle wrinkles with small undulations, such as wrinkles 106 and 108 in FIG. From the ratio of the major axis of the wrinkle to the minor axis, or equivalent data, such as the ratio of the major axis of the wrinkle to the circumference of the wrinkle, the ratio of the major axis of the wrinkle to the half power of the minor axis of the wrinkle The degree of wrinkles is obtained. The ratio of the major axis to the circumference of the wrinkles is the reciprocal of the circumference ratio π for circular wrinkles and approaches 1/2 for elongated wrinkles. In the ratio of the major axis of the wrinkle to the 1/2 power of the minor axis of the wrinkle, the long wrinkle is a strong wrinkle, and when the shape of the wrinkle is similar, the larger wrinkle is made a stronger wrinkle. When wrinkles are ranked as described above, wrinkles can be used for parts within a range corresponding to the ranking. Therefore, in the present invention, the shape of the wrinkle can be obtained, and the wrinkle portion can be allocated to the part and effectively used.

Preferably, the contour extracting means extracts a contour line from the inside to the outside of the sheet material, and a contour line whose chromaticity difference between the inside and outside of the contour line is equal to or less than a predetermined condition is set as the inside contour line. At the same time, a contour line further outside the inner contour line is defined as the outer contour line.
The contour line is extracted, for example, from the outside to the inside of the sheet material. For example, the closed contour line extracted first is set as the outer contour line, and the inner side is searched by searching for the inner contour line. The contour line may be extracted. However, in this case, it is necessary to extract a contour line, for example, on the entire table surface where the sheet material is developed, regardless of whether the sheet material is inside or outside.

  On the other hand, when the contour line is extracted from the inside of the sheet material, the first extracted contour line is the inner contour line, and whether there is an outer contour line outside or whether the outer contour line is extracted from the beginning. , Either. Next, in the inner contour line corresponding to the wrinkle, the change in brightness is large, but the difference in chromaticity such as hue is small. On the other hand, since the outer contour line corresponding to the outer shape of the sheet material moves from the inside of the sheet material to the outside, the difference in chromaticity is also large. Therefore, a contour line whose chromaticity difference between the inside and outside is equal to or less than a predetermined condition is set as a candidate for the inside contour line. And if you search the outside and extract the outer contour line, you can limit the search range of the contour line and predict whether the inner contour line or the outer contour line before extracting the outer contour line, The contour lines inside and outside can be extracted efficiently.

More preferably, a plurality of polygons are generated based on the contour points by generating a plurality of polygons having a small size in a region having a high density of contour points and a large size in a region having a low density. And further providing a space dividing means for
In the contour extraction means, the polygon image is searched from the point inside the sheet material toward the side of the polygon, and when the side touches a side having a length less than a predetermined length, the side is exceeded. When the search is stopped and the side is stored and a side having a predetermined length or longer is touched, the search is continued beyond the side having a predetermined length or longer.

  Simply, contour points extracted by filtering may be connected to generate a contour line. However, when the contour line is ambiguous, there is no guarantee that an accurate contour line will be extracted. For example, in FIG. 10, R1 is leather, R2 is table background, L1 and L2 are contours, and because of the thickness of leather R1, the top edge of the leather constitutes contour L1, and the bottom edge constitutes contour L2. ing. Here, it is easy for the human eye to distinguish between the contour L1 and the contour L2 and select the contour L1, but it is not easy to automatically execute the image recognition using a computer.

  Therefore, it is preferable to start from the inside of the object and search toward the sides of the polygon generated based on the contour points. Since the contour points are densely distributed around the contour line, the size of the polygon is small, and if it collides with an edge with a length less than the predetermined length, the search beyond that edge is stopped, and the length of the polygon less than the predetermined length is stopped. Memorize the edges. When an edge longer than a predetermined length is reached, the search is continued beyond that edge. For this reason, the search is stopped when searching for many small polygon sides distributed in the contour, and the first contour of the object is obtained when the extracted sides are connected. This contour line is either the outer contour line or the inner contour line. Then, as described above, if the contour line having a chromaticity difference equal to or less than a predetermined condition is set as a candidate for the inner contour line and the outside is searched, the outer contour line can be extracted.

Preferably, a wrinkle tolerance is assigned to the part or an area within the part, and the assigning unit assigns the part to the wrinkle according to the ranking and the tolerance.
There are parts that are important in design and parts that are not important in design, and the tolerance for the shape accuracy, that is, the tolerance for wrinkles also varies depending on the part. Therefore, when wrinkles are ranked and tolerances for wrinkles are assigned to the parts, wrinkles can be used for the parts within the tolerance range, and the sheet material can be used effectively.
When a part has a seam allowance or the like, the shape accuracy and quality requirements of the part differ depending on the area in the part. If wrinkle tolerance is specified according to the area in the part, the wrinkle portion can be used more effectively.

  In the following, an optimum embodiment for carrying out the present invention will be shown. In the embodiment, the contour line is simply referred to as a contour.

  1 to 17 show an embodiment of a contour extracting device 18, a contour extracting program, and a contour extracting method, taking the cutting device 2 as an example. In FIG. 1, 4 is a cutting table, and 6 is a cutting head. The color camera 8 captures a color image of the leather 15, and the leather 15 is cut by rotating, for example, a circular blade 10. The cutting head 6 is moved on the cutting table 4 in both directions XY by the X-axis drive 12 and the Y-axis drive 14. The color camera 8 scans the leather 15 with the cutting head 6 and divides the image of the leather 15 into a plurality of images.

  The contour extracting device 18 is provided integrally with the cutting device 2 or separately from the cutting device 2. 20 is a bus, 21 is a color monitor, 22 is a manual input, and includes a keyboard, stylus, mouse, trackball, joystick, and the like. The disk drive 23 performs input / output with a disk such as a CD-ROM, and the network interface 24 is an interface with a LAN or the Internet. The contour extraction program for controlling the contour extraction device 18 is stored in a storage medium such as a CD-ROM and stored in the program memory 32 from the disk drive 23. Alternatively, the contour extraction program may be input from the network interface 24 using a carrier wave. An input / output 26 exchanges data with the cutting table 4. Data supplied to the cutting table 4 side includes movement of the cutting head 6 in the X and Y directions, control of the blade 10, and imaging control of the camera 8. It is data such as. On the other hand, the color image of the leather 15 captured by the camera 8 is supplied to the input / output 26 from the cutting table 4 side.

  28 is a processor, 30 is a general-purpose memory, and 32 is a program memory, which stores a control program for the cutting apparatus 2 such as a contour extraction program. The contour extracting device 18 functions as shown in FIG. 2 by the processor 28 and the memories 30 and 32. The camera image calibration unit 34 corrects image distortion from the camera 8. Raster images such as camera images are stored in the image memory 36, and the filter 38 applies filtering to the entire leather image obtained by synthesizing a single camera image or a plurality of camera images, and contour points are obtained. Extract. The file memory 40 stores the extracted contour points, and the data content is the coordinates of the contour points. For example, the merge processing unit 42 merges the contour points extracted for each individual camera image by the filter 38 to obtain contour point data for one piece of leather.

  The polygon dividing unit 44 divides the sheet material image into polygons using contour points. The polygon division method is, for example, Delaunay division, and the type of polygon is a triangle with three contour points. The inner contour extraction unit 46 extracts the inner contour of the sheet material such as leather 15 using the image divided by the polygon, and connects the extracted polygon sides to generate a closed contour of the sheet material. Let If the edge extraction is incomplete, the closed edges are extracted by connecting the closest edges to each other.

  The outer contour extraction unit 48 extracts a contour outside the inner contour. An external contour extraction unit that determines whether the chromaticity, for example, hue and saturation, or the Cb signal and the Cr signal in the Y, Cb, and Cr video signals are different from each other by a predetermined condition. Evaluate at 48. As the predetermined condition, for example, the sum of the absolute value of the difference between the Cb signals and the absolute value of the difference between the Cr signals, or the larger value of the absolute values of these differences, or the like is used. Instead of the Cb signal and the Cr signal, the H signal and the S signal in the HLS signal may be used. Further, instead of the chromaticity difference between the Cb signal and the Cr signal, a color difference in the RGB space or the like, that is, a distance in the RGB space may be used. If the change in chromaticity inside or outside the inner contour is equal to or less than a predetermined condition, it is estimated that the wrinkle contour has been extracted, and the outer contour is searched. When the change in chromaticity is equal to or greater than a predetermined condition, for example, no further outward search is performed assuming that the outer contour is extracted. The contour extraction units 46 and 48 connect, for example, the vectors of the sides that are the contours of the extracted sheet material, and store a vector data row as inner and outer contours.

  The wrinkle ranking unit 50 ranks and stores the wrinkle shape, particularly the wrinkle degree based on the aspect ratio (aspect ratio) of the wrinkles. The parts storage unit 52 stores the shape of the parts to be taken out from the leather 15 by cutting and the tolerance to wrinkles. Even if the tolerance to wrinkles is stored in units of parts, the parts are stored for each divided area. Also good. The part matching unit 54 generates an optimum cutting pattern by comparing the shape determined by the inner and outer contours of the sheet material and the ranking of the wrinkle portion with the shape of the part to be taken out and the tolerance to the wrinkle. The head data generator 56 generates control data for the cutting head according to the cutting pattern generated by the parts matching unit 54.

  FIG. 3 shows an example of the filter 38. Reference numeral 60 denotes a Laplacian filter that extracts pixels having different data from surrounding pixels, and 61 and 62 denote differential filters, which are suitable for extracting the direction in which the image changes. Further, when the noise of the camera image is significant, the noise may be removed by processing with a median filter or the like before processing with the filters 60 to 62. The type of filter to be used is arbitrary, and the camera image is filtered and binarized to extract contour points. In the extraction of the contour point, the pixel whose brightness or chromaticity changes suddenly is used as the contour point, but only the pixel whose brightness changes suddenly may be extracted.

  FIG. 4 shows an inner and outer contour extraction algorithm. A leather 15 is set on the cutting head 6 and, if necessary, a color tape 16 is attached to a ridge on the leather. Then, the cutting head 6 is moved in the XY directions to divide the image of the leather 15 into, for example, several tens of images (S1). The camera image calibration unit 34 corrects distortion of the captured image (S2), and extracts contour points for each of brightness and chromaticity. In the extraction of the contour point, for example, the camera image is processed by the filter of FIG. 3, the processed image is binarized, and a value of a predetermined value or more is set as the contour point (S 3). Contour points are obtained for each of lightness and chromaticity, and both the lightness contour points and the chromaticity contour points are extracted as contour points, but the chromaticity contour points need not be extracted. The above processing is repeated for each captured image (S4).

  Contour points are collected for one piece of leather (S5), and the sheet material image is divided by triangles having the contour points as vertices (S6). The image here is actually data consisting only of contour points. In the generation of a triangle, the sides of the triangle are formed by combining the vertices in the vicinity with priority over the vertices in the distance. It also decides which vertices to connect to avoid triangles with small interior angles. In other words, paying attention to the smallest interior angle among the three interior angles of the triangle, avoid those having a small interior angle, for example, avoid triangles having an interior angle that is less than or equal to a predetermined value.

  The above algorithm can be simplified as follows. Paying attention to one vertex, it is connected to nearby vertices within a predetermined range of surrounding angles. If this process is repeated 360 ° around the focused vertex, the vertex is connected to a plurality of surrounding vertices. When the above process is repeated for each vertex, the image is divided into triangles. The vertex of the triangle is a contour point.

  Next, one point in the leather is designated (S7). This point may be designated by manual input, or a point inside the large triangle may be computer-extracted with a color different from the ground color, that is, the color of the cutting table 4. Searches to propagate from one specified point across the triangle side. When a side having a length longer than a predetermined length is touched, two sides of the triangle that are beyond that side are searched. As described above, the area corresponding to the inside of the sheet material is expanded (S8).

  If it collides with a short side of the triangle, the search beyond that side is aborted. Of course, the search is continued for other sides (S9). The threshold value for continuing or aborting the search is constant in the embodiment, but may be variable. The search is continued until there are no more sides to search (S10). In the above process, if the search is terminated due to collision with a short side, the corresponding side is stored. Since the edge data is vector data, the coordinates of the start and end points of the edge are stored. When the memorized sides are connected, a closed contour of the leather is obtained, which is the inner contour of the leather (S11).

  It is checked whether the change in chromaticity is greater than or equal to a predetermined condition inside and outside the inner contour (S12), and if the change in chromaticity is less than the predetermined condition, An outline is extracted (S13). This process is the same as S9 to S11. When the area surrounded by the outer contour and the inner contour, and the inner contour are closed as such, the inside of the inner contour is wrinkled (S14).

FIG. 7 shows an example of searching with Delaunay triangles. The vertices of the triangle in the figure are contour points, and when viewed with the human eye, there appear to be two contours L1 and L2 and isolated contour points P1 and P2. However, it is difficult to perform such recognition automatically. It is assumed that the search starts from the upper left side in FIG. The double line in the figure indicates a short side where the search is stopped, and if it collides with a short side, the search beyond the side is terminated. Then, by connecting the short sides where the search is terminated, an outline is obtained. To ensure that the contour is extracted,
・ Connect adjacent contour points to each other,
Avoid triangles with small interior angles,
This is very important. Delaunay division is known as an algorithm for dividing a space by triangles while satisfying the above conditions.

  FIG. 8 shows space division by Voronoi polygons. For example, with respect to the contour point P1, a perpendicular bisector for the side connecting to the surrounding contour points is generated, and the perpendicular bisectors are connected to each other to form a polygon. Although a hexagon is displayed in FIG. 8, the number of sides of the Voronoi polygon is indefinite. It can be said that the Voronoi polygon is obtained by dividing an image according to which contour point is closest to an image composed of a set of contour points. In the region where the contour points are densely gathered, the size of the Voronoi polygon is reduced, and in the rough region, the size of the contour point is increased. The same applies to the Delaunay triangle. In order to efficiently search for an edge, it is preferable to store both ends of each edge of a Voronoi polygon or Delaunay triangle and add a bit indicating whether or not the search has been completed.

  9 to 11 show the contour extraction results for leather. FIG. 9 is a binarized image of the entire leather, and four color tapes are pasted inside the image. FIG. 10 shows an image of contour points for a portion of leather, where R1 is the leather region, R2 is the background region, R3 is the soil region, and the leather is thick, so the two parallel contours L1 , L2 seems to be there. For example, it is not always easy for the computer to automatically extract only the contour L1 from here.

  FIG. 11 shows Delaunay division for the entire leather. Select a start point inside a large triangle, either manually or in a different color from the background, and perform a search from here toward the edge of the Delaunay triangle. When a collision occurs with the side, the length is checked. If the length exceeds the predetermined length, the search is continued beyond the side. If the side collides with a side shorter than the predetermined length, the detected side is not stored. When the above processing is performed, a large amount of small Delaunay triangles are present in the leather contour, so that the contour can be extracted. In addition, since there are a large number of fine Delaunay triangles at the boundary between the color tape and leather, the color tape can be extracted. The leather contour in FIG. 9 can be extracted as described above.

Next, the extracted wrinkle process will be described. As shown in FIG. 5, the major axis a and the minor axis b of the wrinkle are obtained, and the ratio a / b is set as the aspect ratio (S21). Instead of a / b, a ratio between the major axis a and the circumference of the wrinkle, or a ratio of a half root of the major axis a and the minor axis b, that is, a / b ^1/2 may be used. Next, the wrinkles are ranked so that the wrinkles are stronger as the aspect ratio is larger and weaker as the aspect ratio is smaller (S22). Then, parts are allocated in the leather so as to fit the wrinkle rank and not to protrude from the outer contour of the leather (S23). Then, the parts are cut (S24).

  FIG. 12 shows processing related to the wrinkle 88. It is assumed that the contour is extracted from the inner side to the outer side of the leather 80 and the contours 81 and 82 are obtained. The contours 81 and 82 are obtained by connecting short vectors, and areas 83 to 87 are generated along these vectors, for example. Here, the areas 83 to 87 are generated in a jumping manner, but may be generated so as to connect them. The widths of the areas 83 to 87 are larger than the interval between the contours L1 and L2 shown in FIG. 10, and specifically, for example, twice or more the interval between the upper surface edge and the lower surface edge of the leather. Then, for the areas 83 to 87, the difference in chromaticity inside and outside the contours 81 and 82 is obtained. The chromaticity is, for example, Cb and Cr signals in the Y, Cb, and Cr systems, and H and S signals in the HLS system. When the change in chromaticity is large, there is no other contour on the outside, and when the change in chromaticity is small, the contour is on the inside. The change in chromaticity around the contour point may be obtained for each contour point at the stage of processing by the filter of FIG.

  In the case of FIG. 12, the contour 82 is an inner contour, and the contour 81 is an outer contour. Therefore, the outer contour 89 is obtained so as to exceed the inner contour 82 by the method shown in FIG. An area surrounded by the inner and outer contours 81 and 89 is a wrinkle 88. The major axis a and the minor axis b can be obtained for the wrinkle 88. For example, the degree of wrinkle can be obtained from this ratio.

  FIG. 13 shows the relationship between the aspect ratio and the wrinkle rank. The larger the aspect ratio, the higher the wrinkle rank. As the aspect ratio, an appropriate value can be used in addition to the ratio between the major axis a and the minor axis b.

  Wrinkles are not limited to those that touch the outer contour of the leather. Such an example is shown in FIG. 90 is leather, 91 is an inner contour, and 92 is an outer contour, which is an example of an isolated wrinkle inside the leather.

  FIG. 15 shows the influence of the wrinkle parts on the cutting accuracy. 102 and 108 are wrinkles shown in FIG. 18, the wrinkles 102 are thin and sharp wrinkles, and the wrinkles 108 are wide and gentle wrinkles. A chain line 110 indicates the contours of the wrinkles 102 and 108, that is, the inner contour. Since the wrinkles 102 and 108 are raised from the cutting table, when the wrinkles are cut, they become parts 112 and 114, which are difficult to cut into an accurate shape. If the ranks of the wrinkles 102 and 108 are known, it is possible to estimate the height at which the wrinkles are lifted from the cutting table, so that it is possible to correct a decrease in shape accuracy due to wrinkles. That is, when a wrinkle area with a high rank is cut, the size of the part increases along the minor axis direction of the wrinkle. The extent to which the size increases depends on the wrinkle rank and the distance that the part enters in the minor axis direction of the wrinkle. Therefore, if the influence of the size of the part is stored as an empirical rule based on the wrinkle rank and the distance, it is possible to compensate for a decrease in shape accuracy due to wrinkles.

  Corresponding to the ranking of wrinkles, the tolerance of wrinkles is determined for parts or parts areas, and which parts can be placed for which wrinkles, or which part of which parts To be able to determine whether or not The part 120 in FIG. 16 has a seam allowance area around it and two areas inside it, and the symbol IA allows no wrinkles at all, and the symbol IB allows only a moderate wrinkle. The symbol II means that up to, for example, a wrinkle of rank 2 in FIG. 13 is allowed.

  FIG. 6 shows a part design, which may be designed by the cutting device 2 or by another device. The shape of the part is designed (S31), the wrinkle tolerance level is designated for the entire part or for each part area (S32), and the required number of parts is input (S33).

  In the examples, contours were extracted from the inside to the outside of the leather. Conversely, the contour may be extracted from the outside to the inside of the leather. Such an example is shown in FIG. 17, where 130 is leather and 132, 133 are wrinkles. When the contour is extracted from the outside of the leather 130, the outer contour 134 is obtained, and when the contour extraction is further continued, the inner contour 136 is obtained. In this case, since the extraction of the contour starts from the outer contour 134 until it collides with another contour, it is necessary to extract the contour substantially for the entire inner and outer sides of the leather 130. For this reason, the contour extraction range is widened.

In the embodiment, the following effects can be obtained.
(1) Can detect wrinkles in leather. For this reason, it can be understood which part of the leather has wrinkles, and the area of the part excluding the wrinkles and the total area of the leather can be obtained.
(2) Since wrinkles can be ranked, parts can be placed in the wrinkles within the allowable range for the parts. Therefore, the utilization efficiency of leather improves.
(3) The contour is extracted from the inside of the leather, and when a contour with a small change in chromaticity is reached, the contour is searched beyond this contour. For this reason, the inner contour and the outer contour can be easily obtained. In addition, the search range can be limited to the inside of leather and around wrinkles.
(4) By ranking wrinkles and setting tolerances for wrinkles for parts or areas within parts, parts can be placed easily.
(5) Using Delaunay division or Voronoi division, the contour can be extracted accurately.

The block diagram which shows the hardware constitutions of the cutting device of an Example The figure which shows the cutting device of FIG. 1 with the functional block regarding outline extraction The figure which shows the example of the filter for outline extraction The figure which shows the outline and wrinkle extraction algorithm in an Example The figure which shows the wrinkle ranking algorithm in the Example The figure which shows the part ranking algorithm in the Example Diagram showing Delaunay division A diagram schematically showing the Voronoi diagram Figure showing a binary image of leather Diagram showing contour point image Diagram showing Delaunay division corresponding to FIG. The figure which shows typically the extraction of wrinkles in an Example The figure which shows typically the relationship between the wrinkle aspect ratio and wrinkle rank in an Example. A diagram schematically showing leather with wrinkles on the inside A diagram that schematically shows that the shape accuracy of a wrinkled part decreases. The figure which shows the ranking for every area in the part typically The figure which shows typically the modification which searches an outline and a wrinkle from the outer side of leather Photo showing wrinkled leather

Explanation of symbols

2 Cutting device 4 Cutting table 6 Cutting head 8 Color camera 10 Blade 12 X-axis drive 14 Y-axis drive 15 Leather 16 Color tape 18 Contour extraction device 20 Bus 21 Color monitor 22 Manual input 23 Disk drive 24 Network interface 26 Input / output 28 Processor 30 Memory 32 Program Memory 34 Camera Image Calibration Unit 36 Image Memory 38 Filter 40 File Memory 42 Merge Processing Unit 44 Polygon Dividing Unit 46 Internal Contour Extracting Unit 48 External Contour Extracting Unit 50 Wrinkle Ranking Unit 52 Parts Storage Unit 54 Parts Matching Unit 56 Head data generator 60 Laplacian filter 61, 62 Differential filter 80, 90 Leather 81 Contour 82, 91 Inner contour 83-87 Area 88 Wrinkle
89,92 outer contour 110 inner contour 112,114 parts 120 parts 130 leather 132,133 wrinkle 134 outer contour 136 inner contour

L1, L2 contour
P1 ~ P6 Vertex R1 Leather R2 Background R3 Dirt a Major axis b Minor axis

Claims (9)

In the device that extracts the contour point by filtering from the image of the sheet material imaged by the camera, connects the extracted contour points, and outputs it as the contour line of the sheet material,
Contour extracting means for obtaining an outer contour line representing the outer shape of the sheet material and an inner contour line inside the outer contour line;
Means for determining the wrinkle shape of the sheet material from the outer contour line and the inner contour line;
A wrinkle shape evaluation means for obtaining an amount representing a ratio between a major axis and a minor axis of the obtained wrinkle shape;
Ranking means for ranking the wrinkles so that the amount representing the ratio is a large wrinkle, and the amount representing the ratio is a weak wrinkle;
An outline extracting apparatus comprising: an assigning unit for assigning parts to be cut from a sheet material to the sheet material in accordance with a wrinkle ranking. In the contour extracting means, a contour line is extracted from the inside to the outside of the sheet material, and a contour line whose chromaticity difference between the inside and outside of the contour line is a predetermined condition or less is set as the inside contour line, and the inside The contour extracting apparatus according to claim 1, wherein a contour line further outside the contour line is defined as the outer contour line. A space for generating a plurality of polygon images by generating a plurality of polygons having a small size in a region having a high density of contour points and a large size in a region having a low density based on the contour points. Further providing a dividing means;
In the contour extraction means, the polygon image is searched from the point inside the sheet material toward the side of the polygon, and when the side touches a side having a length less than a predetermined length, the side is exceeded. 3. The contour according to claim 2, wherein the search is stopped and the side is memorized, and when the side touches the side having a length longer than a predetermined length, the search is continued beyond the side having a length longer than the predetermined length. Extraction device. The wrinkle tolerance is assigned to the part or an area within the part, and the assigning unit assigns the part to the wrinkle according to the ranking and the tolerance. Any contour extraction device. In the program for the contour extraction device, which extracts the contour point by filtering from the image of the sheet material captured by the camera, and outputs the contour point by connecting the extracted contour points,
When read into the contour extraction device, the contour extraction device is
Contour extracting means for obtaining an outer contour line representing the outer shape of the sheet material and an inner contour line inside the outer contour line;
Means for determining the wrinkle shape of the sheet material from the outer contour line and the inner contour line;
A wrinkle shape evaluation means for obtaining an amount representing a ratio between a major axis and a minor axis of the obtained wrinkle shape;
Ranking means for ranking the wrinkles so that the amount representing the ratio is a large wrinkle, and the amount representing the ratio is a weak wrinkle;
An outline extraction program for causing a part to be cut from a sheet material to function as an assigning means for assigning a part to a sheet material according to a wrinkle ranking. In the contour extracting means, a contour line is extracted from the inside to the outside of the sheet material, and a contour line whose chromaticity difference between the inside and outside of the contour line is a predetermined condition or less is set as the inside contour line, and the inside The contour extraction program according to claim 5, wherein a contour line further outside the contour line is defined as the outer contour line. A space for generating a plurality of polygon images by generating a plurality of polygons having a small size in a region having a high density of contour points and a large size in a region having a low density based on the contour points. Further providing a dividing means;
In the contour extraction means, the polygon image is searched from the point inside the sheet material toward the side of the polygon, and when the side touches a side having a length less than a predetermined length, the side is exceeded. 7. The contour of claim 6, wherein the search is stopped and the side is memorized, and when the side touches the side having a length longer than a predetermined length, the search is continued beyond the side having a length longer than the predetermined length. Extraction program. The wrinkle tolerance is assigned to the part or an area within the part, and the assigning unit assigns the part to the wrinkle according to the ranking and the tolerance. Any contour extraction program. In the method of extracting the contour point by filtering from the image of the sheet material captured by the camera, connecting the extracted contour points and outputting as the contour line of the sheet material,
By the contour extracting means, an outer contour line representing the outer shape of the sheet material and an inner contour line inside the outer contour line are obtained,
By means for obtaining the wrinkle shape, the wrinkle shape of the sheet material is obtained from the outer contour line and the inner contour line,
By using the wrinkle shape evaluation means, an amount representing the ratio between the major axis and the minor axis of the obtained wrinkle shape is obtained,
The ranking means ranks the wrinkles so that the amount representing the ratio is a large wrinkle and the amount representing the ratio is a weak wrinkle,
A contour extracting method, wherein an allocating unit allocates parts to be cut from a sheet material to the sheet material according to a wrinkle ranking.