JP3187244B2 - Apparatus for identifying and separating copper-containing scrap - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an apparatus for automatically discriminating and separating scrap containing copper as an impurity element from a group of iron scraps in an iron scrap regeneration process.

[0002]

2. Description of the Related Art In order to avoid the deterioration of the quality of iron produced by scrap regeneration, it is necessary to prevent the incorporation of non-ferrous impurities such as copper, zinc and tin, which are generally called tramp elements. Zinc and tin are mainly present in the surface layer of galvanized steel sheets, whereas copper is mainly present as copper wires in the motor core of automobiles and home appliances, so it is difficult to identify and separate them at the crushing waste stage. The most effective.

Conventionally, the processing performed by regenerators involves first cutting waste such as automobiles and home electric appliances into long pieces of about several tens mm in size using a crusher called a shredder, and selecting the cloth by air screening. , Which removes non-metallic fine particles and powders such as plastics, separates non-metallic pieces from metal pieces by vortex sorting, and separates iron and non-ferrous metal pieces by magnetic sorting. Finally, the separated iron scrap is handed over to steel makers as a raw material for iron. However, the motor core, which is the largest source of copper, cannot separate copper and iron by magnetic selection because the copper wire and iron core are mechanically entangled. It has been separated by visual identification and manual selection of workers.

[0004] In such a manual identification operation, it is difficult to process a large amount of scrap, and it is necessary to invest a large amount of labor.
There are problems such as difficulty in ensuring uniform quality of scrap after copper removal and difficulty in improving the working environment. As means for automating the identification work, for example, a device for performing automatic scrap identification by laser beam irradiation has been proposed (Dr. H. -P
Sattler: VDI BERICHTE NR.934, 1991: 'Scrap sortin
g with Lazer-an automatic process for mixed non-fe
rrous metals from automobile shredders').

[0005] Further, as an apparatus for sorting by utilizing the difference in color of waste, there is, for example, Japanese Patent Application Laid-Open No. 5-96249, "Cullet Color Sorting Machine". This is to automatically sort the color of the glass cullet. The color of each cullet is identified by the color image of the CCD camera, and the cullet of the color to be sorted is selected according to the cullet of the color to be sorted. This is for driving the drum.

[0006]

In the above-described identification method using a laser beam, an expensive pulsed laser irradiator is used, so that it is difficult to reduce the cost of the apparatus, and if the laser and the spectroscope are not used in a bad environment. Therefore, maintenance and maintenance of the apparatus require cost and labor. Further, in order to reliably irradiate the laser beam to each scrap piece, it is necessary to arrange the individual scrap pieces in a line, and therefore, there is a problem that an alignment device is required and mass processing is difficult. Also, in the method disclosed in Japanese Patent Application Laid-Open No. 5-96249, it is assumed that each cullet is a single color such as brown, blue, green, etc., so that iron and copper are contained in one scrap like a motor core. It cannot be used to distinguish a mixture of colors from other steel scrap.

[0007] The problem to be solved by the present invention is that a copper-containing scrap in which iron and copper colors are mixed in one scrap, such as a motor core, and a scrap group in which other iron scraps are mixed. By realizing a discrimination and separation device that automatically performs separation processing, it is easy to process a large amount of scrap, eliminating the need for large labor costs, facilitating uniform quality of scrap after copper removal, and improving the work environment. Is to facilitate.

[0008]

The gist of the present invention is as follows. 1) transport means for continuously transporting the crushed iron scrap group; 2) imaging means for capturing a color image of the iron scrap group being transported; 3) color image from the imaging means. Receiving the imaging time,
From the luminance (I) signal of the color image, individual scraps in the image are individually recognized, and the total area St of each scrap, that is, the total number of pixels is obtained; the hue angle (H) signal and the saturation (S) of the color image are obtained. ) From the signal, determine whether each pixel is copper and determine the copper area in each scrap, that is, the number of pixels determined to be copper; the copper area S of each scrap
From the ratio of Cu to the total area St, R = SCu / St, it is determined whether or not there is a copper-containing scrap; position (X, Y) information in the image of all the copper-containing scraps in the image and the image capturing Identification processing means for outputting time; 4) separation means coupled to the transport means and having a mechanism for separating copper-containing scrap and iron scrap; 5) all of the images in the image from the identification processing means. Receiving the position (X, Y) information in the image of the copper-containing scrap and the image capturing time; from the position (X, Y) information and the image capturing time, the individual copper-containing scrap is conveyed to the separating means. And a separation device control means for driving the separation device when the copper-containing scrap reaches the separation device. Used.

[0009]

As shown in FIG. 1, shredder chips such as automobiles and home appliances are subjected to appropriate pretreatment such as wind and vortex sorting to separate metal chips, and then subjected to magnetic separation to have magnetic properties. The iron scrap group 1 including the motor core, which is separated as a scrap group, is put into a conveying means 40 such as a belt conveyor. However, various means such as a belt conveyor from a pretreatment process, a vibration feeder, and the like can be used as the charging means (not shown).

The image signal taken by the image pickup means 41 for picking up a color image of the scrap group 1 on the transport means 40 is transmitted to the identification processing means 42 and is transmitted to all the copper-containing scraps in the image. Position (X, Y) information is obtained, and together with the image capturing time, the separation device control means 4
3 is transmitted. The separation device control means 43 detects the position (X,
Y) Based on the information and the image capturing time, a time delay in which each copper-containing scrap is transported to the separating means 44 is calculated, and a control signal for driving the separating means 44 when the copper-containing scrap has arrived is output. As a result, the iron scrap 45 and the copper-containing scrap 46 are separated by the separating means 44.

The identification of the copper-containing scrap in the iron scrap group 1 is realized as described below. That is, FIG.
As shown in (1), in a state where the iron scrap group 1 is illuminated by the light source 2, the color television camera is imaged as an image pickup means 41 in a range where copper identification in the iron scrap group 1 is required. However, a light source is not always necessary when an image can be captured by a color television camera without a light source.

Inside the identification processing means 42, the imaging means 4
The HSI converter 5 converts the RGB signal 4 of the color television camera transmitted from 1 into a hue angle H (6) and a saturation S
(7), and converted into a luminance I (8) signal and transmitted to the identification processing unit 9. The identification processing unit 9 will be described later,
And outputs a signal (X, Y) of the center of gravity (X, Y) 10 of the scrap identified as containing copper.

The separating device control means 43 of the separating means 44 provided at the rear of the conveying means 40 in the conveying direction receives the centroid position (X, Y) signal 10 of the copper-containing scrap and corrects the conveying time delay of the scrap. Then, a so-called tracking process is performed, and an appropriate separating process is executed at the time when the scrap reaches the separating device.

In some cases, real-time processing cannot be performed because the processing in the identification processing unit 9 includes complicated image processing. In this case, as shown in FIG. If transmitted to the control means 43, appropriate tracking processing can be performed. If the identification processing unit 9 can perform real-time processing, the imaging time signal 1
Needless to say, appropriate tracking processing can be performed only by correcting the transport time delay without transmitting 1 to the control device of the separation device.

The identification processing section 9 identifies the copper-containing scrap by performing the following processing on the photographed image. It is determined whether or not the saturation value of each pixel is equal to or greater than a preset threshold value. If the saturation value is equal to or greater than the threshold value, the hue angle value of the pixel is determined, and the value is determined in advance. Compare and refer to the corresponding relationship of the set copper hue angle value range,
If the hue angle is within the range, the pixel is determined to be copper; if not, it is determined not to be copper; if the saturation value is less than the threshold, the pixel is determined to be copper. It is determined that it is not.

A labeling process is performed on the entire image using the luminance value I to perform individual recognition of scrap.
The total area St of each scrap, that is, the number of pixels occupied by the scrap is obtained; the copper area SCu in the image area occupied by the scrap, that is, the total number of pixels determined to be copper by the processing is obtained; SCu to St ratio R = S
To obtain Cu / St, the ratio R is set to a predetermined threshold R
If it is not less than min, the scrap is identified as a copper-containing scrap, and the center of gravity (X, Y), that is, the total area S
The pixel address of the center of gravity of t is obtained.

The separating means 44 performs an operation for receiving a driving command from the separating device controlling means 43, for example, a pulse signal to separate the corresponding scrap piece as copper-containing scrap. An operation for separating the scrap pieces that have been made as iron scrap is performed.

[0018]

FIG. 3 shows an example of the configuration of an identification / separation apparatus according to the present invention. The conveying means 40 uses a belt conveyor, and scraps are two-dimensionally randomly arranged on the belt conveyor. A color CCD camera is used as the imaging means 41, and an image signal is transmitted to an identification processing means 42 (not shown). In this example, a high-speed image processing device connected to a workstation was used as the identification processing means.

The copper-containing scrap position and the imaging time are transmitted from the discrimination processing means to the separation device control means 43 using a sequencer (not shown), and a drive signal to the separation means is generated and transmitted by correcting the transport time delay. Is done. In the case of this example, a separating device composed of an air cylinder 47 and a bounce plate 48 is used, and the iron scrap 45 and the copper-containing scrap 46 are each transported to the next step.

In the case of this example, when copper-containing scrap and iron scrap are arranged side by side in the width direction of the belt conveyor, the iron scrap is also separated and processed as copper-containing scrap together with copper-containing scrap. However, there is no particular problem since the original purpose of the copper-containing scrap discrimination / separation is to prevent copper from being mixed into steel obtained by regenerating iron scrap.

In addition, since the amount of copper-containing scrap, such as a motor core, in the shredder waste of automobiles and home appliances is about several percent by weight, the amount of iron scrap separated together with the copper-containing scrap is also relatively large. And there is no concern that iron scrap regeneration efficiency will be reduced. It is also possible to improve the separation efficiency of copper-containing scrap and iron scrap by performing batch separation and separation of the scrap group once separated as copper-containing scrap again. It may be repeated.

In the example shown in FIG. 3, a light-shielding plate (not shown) is provided around the image pickup means 41 in order to reduce the influence of ambient light such as a fluorescent lamp in a factory, and an image is taken therein. Of course, when the influence of ambient light is small, it goes without saying that the light shielding plate need not be used. As a light source, a four-point light source (not shown) for illuminating a scrap conveyed on a belt conveyor from four directions was used. A four-point light source has the effect of reducing shadows on scrap and its belt conveyor as compared to a light source illuminating from one direction. If the occurrence of shadows can be kept within a range that does not hinder the identification processing, a four-point light source is not necessarily required.

Using the discriminating and separating apparatus shown in FIG. 3, an automatic discriminating and separating experiment was conducted between iron scrap in automobile shredder scrap and motor core scrap made of iron and copper. In the shredder sample used in this experiment, waste such as automobiles and home appliances was first cut into long pieces of about 80 mm in size by a shredder, and non-metallic pieces such as cloth, plastics, and powder were cut out by air filtration. It is separated as non-metallic pieces and metal pieces by vortex-type sorting, and then separated from iron and non-ferrous metal pieces by magnetic sorting. It is a mixture of iron scrap consisting of iron only and motor core scrap mixed with copper. In other words, the scrap sample used in this experiment has been conventionally discriminated and separated only by the visual observation and manual operation of the worker.

Prior to the actual discrimination / separation experiment, the following three types of preliminary experiments were performed to determine the set values of this experiment. First, a preliminary experiment was performed to determine a boundary value between a saturation value and a hue angle value for copper identification. Under the same optical conditions as those used for identification (setting conditions such as the light source, operating conditions of the CCD camera, and the distance between devices and target scrap), each of the scrap copper portion, the scrap iron portion, and the belt conveyor portion where the scrap is placed has. The hue angle value distribution was measured. Furthermore, under the same conditions, scrap copper part,
The chroma value distribution of each of the scrap iron and the belt conveyor was measured. From the results of these preliminary experiments,
An appropriate range of the saturation value S for performing the copper determination and a range of the hue angle value H of the copper portion were found.

In FIGS. 4 and 5, R, G and B are red, respectively.
An axis indicating the hues of green and blue, an angle between a straight line connecting arbitrary color coordinates and the origin and the R axis indicates a hue angle, and a distance from the origin indicates saturation. As shown in FIG. 4, the saturation value is (0.3 ≦ S ≦ 1.0) (range of 30), and the phase angle value is (0 ° ≦ H ≦ 52 ° and 3 °) as shown in FIG.
29 ° ≦ H <360 °) (the range of 31). In the discrimination experiment described below, a boundary value between the saturation value and the hue angle value for these discriminations was used.

Second, a so-called labeling processing experiment was performed in which scraps in an image were individually recognized using a luminance signal. Utilizing the fact that the belt conveyor is black and the luminance signal value is extremely low, a certain luminance signal threshold value is set, the image is binarized, and labeling processing is performed using the continuity of pixels in the portion above the threshold value. Went to scrap iron,
The copper-containing motor core scrap and the like were separated from the belt conveyor part, and individual scrap pieces could be easily recognized individually.

Although the threshold value of the luminance signal may be set in advance, the threshold value is automatically set to a value of, for example, 25% of the average luminance of the entire image so as to cope with a variation in the intensity of the illumination light. Needless to say, various labeling processes conventionally proposed, such as setting, can be used.

Third, the copper areas SCu and St required to identify whether or not the scrap contains copper are determined.
An experiment was conducted to determine the threshold Rmin of the ratio R = SCu / St. That is, R values of all samples were actually measured using 100 samples of copper-containing motor core scrap and 100 samples of iron scrap. As a result, in this experiment, it was found that if Rmin = 0.1, the motor core scrap and the iron scrap could be almost completely distinguished.

That is, only two samples erroneously identified the motor core sample as the iron sample, and three identified the iron sample erroneously as the motor core sample.
It was just a sample. However, it goes without saying that the set value of Rmin may vary depending on the extent to which copper-containing scrap is allowed to be mixed into iron scrap in the actual discrimination / separation processing. Further, the position of the center of gravity (X, Y) of a scrap identified as a copper-containing scrap can be easily calculated by simply averaging the pixel positions of each scrap using a binarized image by a labeling process.

Identification processing means 42 used in an actual identification experiment
FIG. 6 is a flowchart showing a specific procedure of the identification processing performed by the CPU. In the discrimination experiment, the motor core scrap 100
Pieces, 2,400 pieces of iron scrap mixed randomly, 60
(M / min), and a discrimination experiment was performed by feeding the belt conveyor on a belt conveyor. Since the discrimination processing means 42 used was capable of performing high-speed image processing in real time, tracking could be easily performed only by correcting a delay in transport time to the separation device.

Analysis of the copper-containing scrap and the scrap separated into iron scraps revealed that 17 iron scraps which were erroneously identified and separated in the copper-containing scrap were found.
There were four copper-containing scraps that were erroneously identified and separated in the iron scrap, and were evaluated to have practically sufficient identification and separation performance.

FIG. 7 is an example showing the result of individual recognition of scrap on a belt conveyor using the luminance (I) signal of a certain image taken. In this case, since the belt conveyor is black and has extremely low brightness, it is possible to easily recognize five scrap pieces individually by judging the continuity of a portion equal to or greater than a preset threshold value. The regions shown in white are recognized as individual scraps, and the total area St is obtained.

FIG. 8 shows white pixels that are determined to be copper from the hue angle (H) signal and the saturation (S) signal of the image. The area SCu of the region determined to be copper is determined for each scrap piece. As a result, for each scrap piece, the ratio of the area of the region determined to be copper to the total area R = SCu
/ St was calculated and the scrap pieces labeled 2 and 5 in the figure with an R value greater than the threshold Rmin = 0.1 for discriminating from copper-containing scrap were identified as copper-containing scrap.

When the material of each scrap piece was confirmed from the corresponding color original image, it was found that 2 and 5 were crushed motor cores and the rest were iron scraps composed of only iron. As shown in FIG. 8, even in the iron scraps of 1, 3, and 4, there were some areas that were determined to be copper, but this was due to the scrap surface coated with a red paint close to the color tone of copper and the red rust. It was considered that the hue angle and saturation were within the copper range due to the surface to which it was attached or the relationship between the illumination and the reflection angle. However, even if there is such a small erroneous discrimination portion, erroneous discrimination between iron scrap and copper-containing scrap can be easily prevented by appropriately setting the threshold value Rmin of the ratio R.

The discrimination / separation apparatus according to the present invention includes a scrap arrangement state on a transport means, imaging and discrimination processing,
As shown in Table 1, an implementation that can be mainly classified into four types is possible by the separation process. Table 1 shows a summary of examples in each implementation.

[0036]

[Table 1]

The first classification is a case where scrap pieces are randomly arranged two-dimensionally on the transport means. The image capturing means basically captures an image for each image dimension unit in the transport direction in order to prevent the scrap from being overlooked. And collectively process the collected images to identify the location of the copper-containing scrap. The separating means collectively separates scrap pieces arranged side by side in the width direction of the transport means at the time when the copper-containing scrap arrives. That is, for example, the embodiment is realized as in the embodiment of the identification and separation apparatus shown in FIG.

In the second category, there is a mechanism capable of being divided in the carrying direction on the carrying means, and a plurality of scrap pieces can be put into each dividing unit. An image is taken and the presence or absence of copper-containing scrap is identified for each division unit. When the division unit including the copper-containing scrap arrives, the separation unit considers all the scrap pieces in the division unit as the copper-containing scrap and collectively separates the scrap pieces.

FIG. 9 shows an embodiment in which a tray conveyor conveyed in one line is used as a conveying means. Scraps are continuously fed by the feeding means 49, but a plurality of scrap pieces enter each tray by a tray conveyor 50 having trays having a structure divided in the transport direction.

The image pickup means (not shown) picks up an image of one or a plurality of trays, and the identification processing means separates whether or not each tray contains copper-containing scrap from the position information of the copper-containing scrap. The scraps are transmitted to the apparatus control means, and the scrap pieces contained in each tray are collectively separated as copper-containing scrap or iron scrap in response to a drive signal from the apparatus. Batch separation of scrap pieces in each tray can be easily performed by inclining the tray to a shooter for copper-containing scrap or iron scrap, for example.

In the third category, there is a mechanism on the conveying means which can be divided in the width direction.
In order to prevent a scrap from being overlooked, images are basically taken for each image size unit in the transport direction, and the entire collected image is collectively processed.
, The division unit to which the scrap belongs is obtained, and the information and the position X of the scrap in the transport direction are transmitted to the separation device control means. The separating means has a mechanism capable of separating each of the divided units, and receives a drive signal from the separating device control means to separate the copper-containing scrap for each of the divided units.

That is, each division unit basically operates in the same manner as the apparatus shown in the first category, but the transport means, the image pickup means, the identification processing means, and the separation device control means are divided by each division unit. Therefore, a large amount of scrap can be identified and separated at low cost.

FIG. 10 shows an example in which a separating plate is provided and a belt conveyor is divided into two parts in the width direction and used as a conveying means 40 to constitute an identification and separation device. Separation is performed using a bounce plate 48 separately for each division. The discriminating processing means determines which division unit the scrap belongs to from the width position Y of the copper-containing scrap, and determines which bounce plate should be driven by the separation device control means.

In the fourth category, there is a mechanism on the conveying means which can be divided in both the width and the conveying direction, and a plurality of scrap pieces can be put into each division unit. An image is taken for each division unit, and the presence or absence of a copper-containing scrap is identified for each division unit. When the division unit including the copper-containing scrap arrives, the separation unit considers all the scrap pieces in the division unit as the copper-containing scrap and collectively separates the scrap pieces.

FIG. 11 shows an embodiment in which tray conveyors conveyed in two rows are used as conveying means. Scraps are continuously fed by the feeding means 49, and a plurality of scrap pieces enter each tray by a tray conveyor 50 having a tray having a structure divided in the transport direction and the width direction.

The image pickup means (not shown) picks up images on two trays in this case, as indicated by an image pickup area 51,
The identification processing means transmits to the separation apparatus control means whether or not each tray contains copper-containing scrap from the position information of the copper-containing scrap. After receiving the drive signal,
Separation means (not shown) for tilting the trays collectively drops scrap pieces contained in each tray into a belt conveyor 53 for copper-containing scrap or a belt conveyor 52 for iron scrap.

In any of the above classifications, copper-containing scrap and iron scrap are arranged side by side in the width direction of the conveying means such as a belt conveyor, or copper-containing scrap and iron scrap are mixed in the same tray. In this case, iron scrap is also separated and treated as copper-containing scrap together with copper-containing scrap, but the original purpose of copper-containing scrap identification and separation is to remove copper into steel obtained by regenerating iron scrap. There is no particular problem because it is for preventing contamination.

In addition, since the amount of copper-containing scraps such as motor cores in the shredder scraps of automobiles and home electric appliances is about several percent by weight, the amount of iron scrap separated together with the copper-containing scraps is also relatively large. And there is no concern that iron scrap regeneration efficiency will be reduced. It is also possible to improve the separation efficiency of copper-containing scrap and iron scrap by performing batch separation and separation of the scrap group once separated as copper-containing scrap again. It may be repeated.

Further, when the processing speed of the identification processing means 42 is high, a single identification processing means can process color images from a plurality of image pickup means 41. It is needless to say that the apparatus can be configured to use only one identification processing unit.

That is, in any of the four categories shown in Table 1, the copper-containing scrap identification process is performed on a plurality of color images transmitted from a plurality of image pickup means 41 on a plurality of transport means 40. The position (X, Y) information of all copper-containing scraps in the image and the image capturing time
What is necessary is just to transmit to each corresponding separation device control means 43 and drive the separation means 44.

For example, when a belt conveyor is used as a conveying means and the apparatus is operated at a conveying speed of 1 m / sec, if the image size unit in the conveying direction is 0.4 m, processing of 2.5 images per second is carried out in order to prevent oversight of scrap. That is enough. If an identification processing means having the ability to process a normal color camera image in real time is used, 30 images can be processed per second. In this case, one identification separation device can be used for up to 12 identification separation devices. It is also possible to cope with the identification processing means. In practice, it is necessary to perform processing with some margin in timing processing such as image input and processing result output, so that it is practical to handle about eight discrimination / separation devices. As a result, the cost of the identification processing means per identification and separation device can be significantly reduced.

[0052]

The use of the apparatus for identifying and separating copper-containing scraps according to the present invention makes it possible to automate and improve the accuracy of the task of identifying and separating copper-containing scraps in iron scrap groups, which has been conventionally performed visually by an operator. As a result, it is easy to process a large amount of scrap, it is not necessary to invest a lot of labor costs, it is easy to ensure uniform quality of scrap after copper removal,
Conventional problems such as easy improvement of the working environment can be solved.

[Brief description of the drawings]

FIG. 1 is an explanatory diagram of a configuration of an identification / separation device based on the present invention.

FIG. 2 is an explanatory diagram of a configuration example of an imaging unit and an identification processing unit based on the present invention.

FIG. 3 is an explanatory diagram of an embodiment of an identification / separation device.

FIG. 4 is a distribution diagram of a chroma value range of copper in an example.

FIG. 5 is a distribution diagram of a hue angle value range of copper in an example.

FIG. 6 is a flowchart of an identification process used in the embodiment.

FIG. 7 is an identification diagram of an example of a labeling result using a luminance (I) signal.

FIG. 8 is an identification diagram of an example of a determination result of a copper portion based on a hue angle (H) signal and a saturation (S) signal.

FIG. 9 is an explanatory diagram of an embodiment in which a single-row tray conveyor is used as a transport unit.

FIG. 10 is an explanatory view of an embodiment in which a belt conveyor divided into two in the width direction is used as a conveying unit.

FIG. 11 is an explanatory view of an embodiment in which a two-row tray conveyor is used as a conveying means.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Iron scrap group 2 Light source 3 Color television camera 4 RGB signal 5 HSI conversion device 6 Hue angle H signal 7 Saturation S signal 8 Luminance I signal 9 Discrimination processing part 10 Center of gravity position (X, Y) signal of copper containing scrap 11 Imaging Time signal 22 Dark room 23 CCD camera 24 Four-point light source 25 Monitor television 26 RGB signal 27 Image capture device 28 HSI signal 30 Copper saturation range 31 Copper hue angle range 40 Transport means 41 Imaging means 42 Identification processing means 43 Separation Device control means 44 Separation means 45 Iron scrap 46 Copper-containing scrap 47 Air cylinder 48 Bounce plate 49 Input means 50 Tray conveyor 51 Imaging range 52 Belt conveyor for iron scrap 53 Belt conveyor for copper-containing scrap 54 Partition plate

──────────────────────────────────────────────────続 き Continued on the front page (72) Inventor Shuji Naito 20-1 Shintomi, Futtsu City Nippon Steel Corporation Technology Development Division (72) Inventor Masahiro Ito 20-1 Shintomi, Futtsu City Nippon Steel Corporation Technology (56) References JP-A-5-131175 (JP, A) JP-A-5-223641 (JP, A) (58) Fields investigated (Int. Cl. ⁷ , DB name) G01N 21/00 -21/958 B07C 5/342

Claims (1)

(57) [Claims] The present invention relates to: 1) conveying means for continuously transporting a group of iron scraps after crushing; 2) image capturing means for capturing a color image of the iron scrap group being transported; 3) image capturing means Receiving the color image and the imaging time from
From the luminance (I) signal of the color image, individual scraps in the image are individually recognized, and the total area St of each scrap, that is, the total number of pixels is obtained; the hue angle (H) signal and the saturation (S) of the color image are obtained. ) From the signal, determine whether each pixel is copper or not and obtain the copper area in each scrap, that is, the number of pixels determined to be copper; the copper area S of each scrap
From the ratio of Cu to the total area St, R = SCu / St, it is determined whether or not there is a copper-containing scrap; position (X, Y) information in the image of all the copper-containing scraps in the image and the image capturing Identification processing means for outputting a time; 4) separation means coupled to the transport means and having a mechanism for separating copper-containing scrap and iron scrap; 5) all of the images in the image from the identification processing means. Receiving the position (X, Y) information of the copper-containing scrap in the image and the image capturing time; the individual copper-containing scrap is transported to the separation means from the position (X, Y) information and the image capturing time. A separator control means for calculating a time delay and driving the separating means when the copper-containing scrap reaches the separating means.