JPH07280747A - Copper-containing scrap distinguishing and separating apparatus - Google Patents

Abstract

PURPOSE:To automatically distinguish and separate copper-containing scraps among iron scrap groups after crushing. CONSTITUTION:A copper-containing scrap distinguishing and separating apparatus is provided with a transporting means 40 to continuously transport iron scrap groups after crushing, an image pick-up means 41 to take color images of the transporting iron scrap groups, and a distinguishing and processing means 42 which receives the color images and the image taken time from the image pick-up means 41 and sends out the position (X, Y) information of all the copper-containing scrap images among the images and image taken time for the former images. The apparatus is also provided with a separating means 44 joined to the transporting means 40 and having a system to separate the copper-containing scraps and iron scraps and a separating apparatus controlling means 43 which receives the position (X, Y) information of the images of all the copper-containing scraps and respective image taken time from the distinguishing and processing means 42, computes the time delay for transportation from the image taken time for each copper-containing scrap to the separating means 44 based on the position (X, Y) information and the respective image taken time, and operates the separating means 44 when each copper-containing scrap reaches the separating means 44.

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 identifying and separating scrap containing copper, which is an impurity element, from a group of iron scraps in the regenerative treatment of iron scraps.

[0002]

2. Description of the Related Art In order to avoid deterioration of quality of iron produced by scrap regeneration, it is necessary to prevent nonferrous impurity elements such as copper, zinc and tin, which are generally called Trump elements, from being mixed. Zinc and tin are mainly present on the surface of the plated steel sheet, whereas copper is mainly present as copper wire in the motor core of automobiles and home appliances, so it is possible to identify and separate at the crushing scrap stage to prevent contamination. Most effective in.

Conventionally, a regenerator has been used to treat wastes such as automobiles and home appliances by first cutting them into shredders called shredders and cutting them into scrap pieces of about several tens of millimeters, which are then clothed by wind-screening. It removes non-metallic pieces such as plastics and powder, separates non-metallic pieces from metal pieces by eddy current sorting, and separates iron and non-ferrous metal pieces by magnetic sorting. The finally separated iron scrap is handed over to the steelmaker as an iron raw material. However, since the copper core and the iron core are mechanically entangled mechanically in the motor core, which is the largest source of copper, the copper and iron cannot be separated even by magnetic separation, so in the end they are conveyed on the belt conveyor. It has been separated by visual identification of workers and manual selection.

[0004] In such manual identification work, it is difficult to process a large amount of scrap, and a large labor cost is required.
There are problems such as difficulty in ensuring uniform quality of scrap after copper removal, and difficulty in improving the work environment. As an automated means for 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').

Further, as an apparatus for selecting the color of waste by utilizing the difference in color, there is, for example, Japanese Unexamined Patent Publication No. 5-96249, "Cullet color-sorting machine". This is for automatically separating the color of the glass cullet. The color of each cullet is identified by the color image of the CCD camera, and the cullet having the air suction port is provided corresponding to the cullet of the color to be selected. It drives the drum.

[0006]

In the above-mentioned identification method using a laser beam, since an expensive pulse laser irradiator is used, it is difficult to reduce the cost of the device, and the laser and the spectroscope must be used in a bad environment. Therefore, the cost and labor for the maintenance of the device are high. Further, in order to reliably irradiate the individual scrap pieces with the laser beam, it is necessary to arrange the individual scrap pieces in one row, which necessitates an aligning device, which causes a problem that large-scale processing is difficult. Further, in the method according to the above-mentioned Japanese Patent Laid-Open No. 5-96249, it is premised that each cullet is a single color such as brown, blue, and green, so that iron and copper are contained in one scrap like a motor core. It cannot be used to distinguish a mixed color from other iron scraps.

The problem to be solved by the present invention is to provide a scrap group containing a mixture of copper-containing scrap, in which iron and copper colors are mixed in one scrap, such as a motor core, and another scrap of iron. By realizing an identification and separation device that automatically performs separation processing, large-scale processing of scrap is facilitated, large labor costs are unnecessary, uniform quality of scrap after copper removal is facilitated, and working environment is improved. Is to make it easier.

[0008]

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

[0009]

As shown in FIG. 1, shredder scraps of automobiles, home electric appliances, etc. are subjected to appropriate pretreatment such as wind separation, vortex separation, etc. to separate the metal scraps, and then magnetic separation is applied to obtain magnetism. The iron scrap group 1 including a motor core, which is separated as a scrap group, is put into a conveyor 40 such as a belt conveyor. However, various means such as a belt conveyor from the pretreatment process or a vibrating feeder can be used as the charging means (not shown).

The image signal picked up by the image pickup means 41 for picking up the color image of the scrap group 1 on the conveying means 40 is transmitted to the identification processing means 42, and all the copper-containing scraps in the image are included in the image. Position information (X, Y) of the separation device control means 4 together with the image capturing time.
3 is transmitted. The separation device control means 43 controls the position (X,
Y) The time delay in which the individual copper-containing scrap is conveyed to the separating means 44 is calculated from the information and the image capturing time, and a control signal for driving the separating means 44 is output when the copper-containing scrap arrives. As a result, the separating means 44 separates the iron scrap 45 and the copper-containing scrap 46.

Identification of copper-containing scrap within the iron scrap group 1 is accomplished as described below. That is, FIG.
As shown in FIG. 3, the iron scrap group 1 is illuminated by the light source 2 and, for example, a color television camera is imaged as the imaging unit 41 in the area in the iron scrap group 1 that requires copper identification. However, the light source is not always necessary if the image can be taken by the color television camera without the light source.

Inside the identification processing means 42, the image pickup means 4 is provided.
The RGB signal 4 of the color TV camera transmitted from the H.I.
(7) and the luminance I (8) signal are converted and transmitted to the identification processing unit 9. The identification processing unit 9 will be described later,
Image processing is performed to output a center-of-gravity position (X, Y) signal 10 of the scrap identified as containing copper.

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

Since the processing in the identification processing unit 9 includes complicated image processing, real-time processing may not be possible in some cases, but at that time, as shown in FIG. 2, the image pickup time signal 11 of the image is separated by the separation device. If it is transmitted to the control means 43, it is possible to perform an appropriate tracking process. When the identification processing unit 9 can perform real-time processing, the image pickup time signal 1 of the image
Needless to say, even if 1 is not transmitted to the control device of the separation device, appropriate tracking processing can be performed only by correcting the transport time delay.

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

Labeling processing is performed on the entire image using the brightness value I to identify individual scraps.
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; Ratio of SCu and St R = S
Calculating Cu / St, the ratio R is a preset threshold value R
When it is more than min, the scrap is identified as a copper-containing scrap, and its center of gravity (X, Y), that is, the total area S
Find the pixel address of the center of gravity of t.

The separating means 44 receives a drive command from the separating device control means 43, for example, a pulse signal, and performs an operation for separating the corresponding scrap pieces into copper-containing scraps. Performs an operation to separate the scrap pieces that are received as iron scrap.

[0018]

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

From the identification processing means, the copper containing scrap position and the imaging time are transmitted to the separation device control means 43 which also uses a sequencer (not shown), and the transport time delay is corrected to generate and transmit a drive signal to the separation means. To be done. In the case of this example, the separation means composed of the air cylinder 47 and the bounce plate 48 is used to transport the iron scrap 45 and the copper-containing scrap 46 to the next process.

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

Moreover, since the amount of copper-containing scrap, such as motor cores, in shredder waste of automobiles and home appliances is originally about several percent by weight, the amount of iron scrap separated together with the copper-containing scrap is relatively large. There is no concern that it will become smaller and the efficiency of regenerating iron scrap will be reduced. It is also possible to improve the separation efficiency of the copper-containing scrap and the iron scrap by subjecting the scrap group once separated as the copper-containing scrap to batch separation and separation treatment again. You can repeat it.

In the example shown in FIG. 3, in order to reduce the influence of ambient light such as a fluorescent lamp in a factory, a light-shielding plate (not shown) is provided around the image pickup means 41, and image pickup is performed therein. Needless to say, the light shielding plate may not be used when the influence of ambient light is small. As a light source, a four-point light source (not shown) that illuminates scrap conveyed on a belt conveyor from four directions was used. A four-point light source has the effect of reducing the shadows that occur on scrap and its belt conveyor, as compared to a light source that illuminates from one direction. The four-point light source is not necessarily required as long as the generation of shadows can be limited to a range that does not interfere with the identification process.

Using the discriminating and separating apparatus shown in FIG. 3, an automatic discriminating and separating experiment was conducted for iron scrap contained in automobile shredder scrap and motor core scrap made of iron and copper. The shredder samples used in this experiment were to cut wastes such as automobiles and home electric appliances into shredders with a long size of about 80mm, and then cloth, non-metallic pieces such as plastics, and powders were selected by wind screening. The non-metal pieces were separated from the non-ferrous metal pieces by eddy-current sorting, and the iron and non-ferrous metal pieces were further separated by magnetic sorting. Is a mixture of iron scrap consisting only of iron and motor core scrap containing copper. That is, the scrap samples used in this experiment have been identified and separated only by the visual inspection of a conventional worker and manual work.

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

4 and 5, R, G and B are red, respectively.
It is an axis showing the hues of green and blue, the angle formed by the straight line connecting arbitrary color coordinates and the origin with the R axis is the hue angle, and the distance from the origin is the 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.
It is an appropriate range to be discriminated as 29 ° ≦ H <360 ° (range of 31). In the discrimination experiment described below, the boundary values of the saturation value and the hue angle value for these discriminations were used.

Secondly, a so-called labeling process experiment was performed in which scraps in an image were individually recognized by using a luminance signal. The belt conveyor is black and the luminance signal value is extremely low. A certain luminance signal threshold value is set to binarize the image, and the labeling process is performed by using the pixel continuity above the threshold value. I went to, scrap iron,
It was possible to separate copper-containing motor core scraps and the like from the belt conveyor and to easily identify individual scrap pieces.

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

Third, the copper areas SCu and St, which are necessary for identifying whether or not the scrap contains copper.
An experiment was conducted to find a threshold value Rmin of the ratio R = SCu / St. That is, the R values of all the samples were measured using 100 samples of motor core scraps containing copper and 100 samples of iron scraps. As a result, in this experiment, it was found that the motor core scrap and the iron scrap can be almost completely discriminated by setting Rmin = 0.1.

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

Identification processing means 42 used in the actual identification experiment
FIG. 6 is a flowchart showing a specific procedure of the identification processing performed by the. Motor core scrap 100 in the identification experiment
Randomly mix 60 pieces of iron scrap and 2,400 pieces of iron scrap
The identification experiment was carried out by sending it out onto a bell conveyor operating at a speed of (m / min). Since the identification processing means 42 has the capability of performing high-speed image processing in real time, the tracking can be easily performed only by correcting the conveyance time delay to the separation device.

When each of the scraps separated into copper-containing scrap and iron scrap was analyzed, there were 17 iron scraps that were erroneously identified and separated in the copper-containing scrap.
The number of scraps containing copper and the number of scraps containing copper that were erroneously identified and separated in the iron scrap was 4, and it was evaluated that the identification and separation performance was practically sufficient.

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

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

When the materials of each scrap piece were confirmed from the corresponding color original images, 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 1, 3, and 4, there are some areas that are discriminated as copper, but this is due to the scrap surface coated with a red paint close to the color tone of copper and red rust. It was considered that the surface was attached or that the hue angle and saturation were within the range of copper due to the relationship between the illumination and the reflection angle. However, even if there is such a minute misidentification portion, it is possible to easily prevent the misidentification of the iron scrap and the copper-containing scrap by appropriately setting the threshold value Rmin of the ratio R.

The identification / separation device according to the present invention is provided with a scrap arrangement state on a conveying means, imaging and identification processing,
As a result of the separation process, as shown in Table 1, there are possible implementation modes that can be mainly classified into four. Table 1 shows a summary of examples in each implementation.

[0036]

[Table 1]

In the first classification, when scrap pieces are randomly arranged two-dimensionally on the conveying means, the image pickup means basically picks up an image for each image size unit in the conveying direction in order to prevent the scrap from being overlooked. , Collectively process all the collected images to identify the position of copper-containing scrap. The separating means collectively separates scrap pieces existing side by side in the width direction of the conveying means when the copper-containing scrap arrives. That is, for example, it is an implementation mode such as the embodiment of the identification / separation device shown in FIG.

In the second classification, there is a mechanism capable of dividing in the conveying direction on the conveying means, and a plurality of scrap pieces can be put into each dividing unit, and the image pickup means is provided for each single or plural 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 separating means regards all the scrap pieces in the division unit as the copper-containing scrap and separates them all together.

FIG. 9 shows an embodiment in which a tray conveyer conveyed in one line is used as the conveying means. The scrap is continuously charged by the charging means 49, but a plurality of scrap pieces enter each tray by the tray conveyor 50 having a tray 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 scrap pieces transmitted to the apparatus control means and receiving the drive signal therefrom, are separated into scraps containing copper or scraps of iron in a batch. Collective 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 classification, there is a mechanism that can be divided in the width direction on the conveying means, and the image in the entire width direction of the conveying means is
In order to prevent missing of scraps, basically, images are taken for each image size unit in the transport direction, the entire collected images are collectively processed, and the position Y in the width direction is included in the position information of the copper-containing scraps.
From which is determined which division unit the scrap belongs to, and the information and the transfer direction position X of the scrap are transmitted to the separator control means. The separating means has a mechanism capable of separating each division unit, and receives the drive signal from the separation device control means to separate the copper-containing scrap for each division unit.

That is, each division unit basically operates in the same manner as the apparatus shown in the first classification, but the conveyance means, the image pickup means, the identification processing means, and the separation device control means are provided for each division unit. Since it is not necessary to provide it at a low cost, a large amount of scrap can be identified and separated at low cost.

FIG. 10 shows an example in which a partition plate 54 is provided and a belt conveyor is divided into two in the width direction and used as the conveying means 40 to form an identification / separation device. Separation is performed using the bounce plate 48 separately for each division. The identification processing means obtains which division unit the scrap belongs to from the position Y in the width direction of the copper-containing scrap, and the separating device control means determines which splatter plate should be driven.

In the fourth classification, there is a mechanism on the conveying means capable of dividing 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 copper-containing scrap is identified for each division unit. When the division unit including the copper-containing scrap arrives, the separating means regards all the scrap pieces in the division unit as the copper-containing scrap and separates them all together.

FIG. 11 shows an embodiment in which a tray conveyer conveyed in two rows is used as the conveying means. The scrap is continuously charged by the charging means 49, but a plurality of scrap pieces enter each tray by the tray conveyor 50 having a tray having a structure divided in the carrying direction and the width direction.

The image pickup means (not shown) picks up images of two trays in this case, as shown by the image pickup area 51.
The identification processing means transmits to the separator control means whether or not each tray contains copper-containing scrap based on the position information of the copper-containing scrap. Receiving the drive signal from it,
Separation means (not shown) for inclining the tray collectively drops scrap pieces contained in each tray onto the belt conveyor 53 for copper-containing scrap or the belt conveyor 52 for iron scrap.

In any of the above classifications, copper-containing scraps and iron scraps are arranged side by side in the width direction of the conveying means such as a belt conveyor, or copper-containing scraps and iron scraps are mixed in the same tray. If the iron scrap is also treated as a copper-containing scrap together with the copper-containing scrap, the original purpose of the copper-containing scrap identification and separation is to recover the copper in the steel obtained by regenerating the iron scrap. There is no particular problem because it is to prevent mixing.

Moreover, since the amount of copper-containing scraps such as motor cores originally contained in shredder scraps of automobiles and home electric appliances is about several% by weight, the amount of iron scraps separated together with copper-containing scraps is also relatively large. There is no concern that it will become smaller and the efficiency of regenerating iron scrap will be reduced. It is also possible to improve the separation efficiency of the copper-containing scrap and the iron scrap by subjecting the scrap group once separated as the copper-containing scrap to batch separation and separation treatment again. You can repeat it.

Further, when the processing speed of the identification processing means 42 is high, color images from a plurality of image pickup means 41 can be processed by one identification processing means, so that a plurality of identification separation devices can be processed. It goes without saying that it is possible to have a device configuration in which only one identification processing means is used.

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

For example, when a belt conveyor is used as the conveying means and the conveying speed is 1 m / s, if the image size unit in the conveying direction is 0.4 m, 2.5 images are processed per second in order to prevent overlooking of scrap. That's enough. When an identification processing means capable of processing an ordinary color camera image in real time is used, 30 images can be processed per second. It is also possible to deal with it by the identification processing means. Actually, since it is necessary to perform processing with a slight margin in timing processing such as image input and processing result output, it is realistic to support about eight identification and separation devices. As a result, the cost of the identification processing means per identification / separation device can be significantly reduced.

[0052]

By using the copper-containing scrap identifying and separating apparatus according to the present invention, it is possible to automate and improve the accuracy of the identifying and separating operation of copper-containing scrap in the iron scrap group, which has been conventionally performed by the operator. As a result, large-scale processing of scrap is easy, large labor cost is not required, uniform quality of scrap after copper removal is easily secured,
It is possible to solve conventional problems such as easy improvement of working environment.

[Brief description of drawings]

FIG. 1 is an explanatory diagram of a configuration of an identification separation device according to the present invention.

FIG. 2 is an explanatory diagram of a configuration example of an image pickup unit and an identification processing unit according to 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 saturation value range of copper in the example.

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

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

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

FIG. 8 is an identification diagram of an example of a result of determination of a copper portion by 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 diagram 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 diagram of an embodiment in which a two-row tray conveyor is used as a transport unit.

[Explanation of symbols]

 1 Iron Scrap Group 2 Light Source 3 Color TV Camera 4 RGB Signal 5 HSI Converter 6 Hue Angle H Signal 7 Saturation S Signal 8 Luminance I Signal 9 Discrimination Processing Section 10 Copper's Scrap's Center of Gravity (X, Y) Signal 11 Imaging Time signal 22 Dark room 23 CCD camera 24 Four-point light source 25 Monitor TV 26 RGB signal 27 Image capturing device 28 HSI signal 30 Copper saturation range 31 Copper hue angle range 40 Conveying 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 Iron scrap belt conveyor 53 Copper-containing scrap belt conveyor 54 Partition plate

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor Shuji Naito 20-1 Shintomi, Futtsu-shi Nippon Steel Corporation Technical Development Division (72) Inventor Masahiro Ito 20-1 Shintomi, Futtsu Nippon Steel Co., Ltd. Technology Development Division

Claims (1)

[Claims] 1. A conveying means for continuously conveying a crushed iron scrap group; 2) an image pickup means for picking up a color image of the iron scrap group being fed; 3) the image pickup means. Received the color image and the shooting time from
Individual scraps in the image are individually recognized from the luminance (I) signal of the color image, and the total area St of each scrap, that is, the total number of pixels is calculated; the hue angle (H) signal and the saturation (S) of the color image are obtained. ) From the signal, it is determined whether or not each pixel is copper, and the copper area in each scrap, that is, the number of pixels determined to be copper is determined; the copper area S of each scrap
The ratio R = SCu / St of Cu to the total area St is used to identify whether or not it 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 having a mechanism connected to the transport means for separating copper-containing scrap and iron scrap; 5) all of the images in the image from the identification processing means. The position (X, Y) information of the copper-containing scrap in the image and the image capturing time are received; the individual copper-containing scrap is conveyed from the position (X, Y) information and the image capturing time to the separating means. And a separating device control means for driving the separating means when the copper-containing scrap reaches the separating means, and an identifying and separating apparatus for the copper-containing scrap.