Image recognition device and component mounting machine

Abstract

To provide an image recognition device with which it is possible to perform accurate image recognition of a subject, and a component mounting machine that includes this image recognition device.SOLUTION: An image recognition device 4 comprises a polarized image output unit 42, an image identification unit 43, a recognition condition setting unit 44, and an image recognition unit 45. The polarized image output unit 42 acquires a plurality of captured polarized images G1 differentiated in the direction of polarization by receiving the light reflected by a subject, and outputs a plurality of polarized images GA including the plurality of captured polarized images G1. The image identification unit 43 identifies an image GC of interest from the plurality of polarized images GA, the contrast value C of which is highest. The recognition condition setting unit 44 sets the direction of polarization corresponding to the image GC of interest as a recognition condition DS for the image recognition of the subject. The image recognition unit 45 causes a polarized image conforming to the recognition condition DS to be output as an image GD for recognition, from the polarized image output unit 42, and does image recognition of the subject on the basis of the image GD for recognition.SELECTED DRAWING: Figure 5

Description

[Technical field]

[0001] The present invention relates to an image recognition device for performing image recognition of a subject, and a component mounter including the same. [Background technology]

[0002] A component mounter for mounting electronic components on a substrate such as a printed wiring board includes a head unit that holds the electronic components and performs a component mounting operation for mounting the held electronic components on the substrate at predetermined positions. When the head unit performs the component mounting operation, an image of a subject such as an electronic component or a substrate is captured, and image recognition of the subject is performed based on the captured image.

[0003] The electronic component has a component body and electrodes with different light reflection characteristics, and the board has a board body with different light reflection characteristics and a recognition mark. That is, the subject that is the target of image recognition during the component mounting operation by the head unit has multiple areas with different light reflection characteristics. In order to accurately recognize the subject, it is necessary to increase the contrast between each image area corresponding to the multiple areas of the subject in the image captured of the subject.

[0004] Patent Document 1 discloses a technique for image recognition of a substrate as a subject. In this technique, a polarizing filter is placed on the optical path between a light source and the substrate, and a polarizing filter is also placed on the optical path between the substrate and a camera. In this case, each polarizing filter is detachable and rotatable around the optical axis.

[0005] Patent Document 2 discloses a technology for image recognition of an electronic component as a subject. In this technology, a polarizing filter is placed on the optical path between a light source and the electronic component to irradiate the electronic component with polarized light in a specific direction, and a polarizing filter is also placed on the optical path between the electronic component and a camera to transmit the polarized light in the specific direction and receive it at the camera. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Publication No. 5-152799 [Patent Document 2] Special Publication No. 2005-504986 Summary of the Invention [Problem to be solved by the invention]

[0007] In the technology disclosed in Patent Document 1, an image of a subject is acquired while adjusting the attachment / detachment and rotation of each polarizing filter, but precise adjustment is required to acquire an image with the best contrast, and such adjustment may be difficult. In addition, in the technology disclosed in Patent Document 2, each polarizing filter is fixed without being rotated, so an image with the best contrast may not be acquired as an image of the subject. Therefore, the technologies disclosed in Patent Documents 1 and 2 may not be able to accurately recognize the image of the subject.

[0008] An object of the present invention is to provide an image recognition device capable of accurately performing image recognition of a subject, and a component mounter equipped with the same. [Means for solving the problem]

[0009] An image recognition device according to one aspect of the present invention is a device for image recognition of a subject having a plurality of regions with different light reflection characteristics. The image recognition device includes a polarized image output unit that acquires a plurality of polarized captured images with different polarization directions by receiving light reflected by the subject and outputs a plurality of polarized images including the plurality of polarized captured images, an image specifying unit that calculates a contrast value of each of the plurality of polarized images and specifies an image of interest having the highest contrast value, a recognition condition setting unit that sets the polarization direction corresponding to the image of interest as a recognition condition for image recognition of the subject, and an image recognition unit that causes the polarized image output unit to output a polarized image according to the recognition condition as an image for recognition, and performs image recognition of the subject based on the image for recognition.

[0010] According to this image recognition device, the image specification unit specifies the image of interest with the highest contrast value based on the multiple polarized images with different polarization directions output from the polarized image output unit. When the image of interest is specified from the multiple polarized images by the image specification unit, the recognition condition setting unit sets the polarization direction corresponding to the image of interest as the recognition condition for image recognition of the subject. Then, the image recognition unit causes the polarized image according to the recognition condition automatically set by the recognition condition setting unit to be output from the polarized image output unit as an image for recognition. The image for recognition is a polarized image according to the recognition condition, and is an image with a polarization direction corresponding to the image of interest with the highest contrast value among the multiple polarized images that can be output from the polarized image output unit. Therefore, the image for recognition is an image of the subject with good contrast. Therefore, the image recognition unit can accurately recognize the subject based on the image for recognition according to the recognition condition.

[0011] In the above-mentioned image recognition device, the polarized image output unit may be configured to generate a plurality of polarized composite images by combining the plurality of polarized captured images while changing weighting, and output the plurality of polarized composite images as the polarized image.

[0012] In this aspect, the polarized image output unit generates a plurality of polarized composite images by synthesizing a plurality of polarized captured images with different polarization directions while changing the weighting. In this case, the polarized image output unit generates a plurality of polarized composite images with different polarization directions that are subdivided according to the weighting. The polarized image output unit outputs a plurality of polarized composite images with different polarization directions that are subdivided by outputting a plurality of polarized composite images as polarized images. In this case, the image specification unit can specify the target image with the highest contrast value based on the plurality of polarized images with different polarization directions that are subdivided. As a result, the recognition image, which is a polarized image according to the recognition condition indicated by the polarization direction corresponding to the target image, becomes an image of the subject with good contrast more reliably. Therefore, the image recognition unit can more accurately recognize the subject based on the recognition image according to the recognition condition.

[0013] In the above-mentioned image recognition device, the polarization image output unit may be configured to generate a polarization angle image expressed in grayscale for each angle of the polarization direction based on the plurality of polarized captured images, and output the polarization angle image as the polarization image.

[0014] In this aspect, the polarization image output unit outputs the polarization angle image as a polarization image. The polarization angle image is an image based on a plurality of polarization captured images with different polarization directions, and is an image expressed in grayscale for each angle of the polarization direction. Therefore, when the image specification unit specifies the polarization angle image as an image of interest, the recognition condition setting unit can set the polarization direction with the highest contrast value as the recognition condition based on the polarization angle image specified as the image of interest.

[0015] In the above image recognition device, the polarized image output unit may be configured to calculate a degree of linear polarization for each pixel based on the plurality of polarized captured images, generate a linear polarization degree image consisting of a pixel group having a luminance value according to the linear polarization degree, and output the generated image as the polarized image. In this case, the recognition condition setting unit sets, as the recognition condition, that the polarized image output unit generates and outputs the linear polarization degree image when the image specifying unit specifies the linear polarization degree image as the target image.

[0016] In this aspect, the polarized image output unit outputs the linear polarization degree image as a polarized image. The linear polarization degree image is an image based on a plurality of polarized captured images with different polarization directions, and is an image made up of a group of pixels having a luminance value according to the linear polarization degree. When the image specification unit specifies the linear polarization degree image as the image of interest, the recognition condition setting unit sets, as a recognition condition, that the polarized image output unit generates and outputs a linear polarization degree image. In this case, the image recognition unit causes the polarized image output unit to output the linear polarization degree image as an image for recognition in accordance with the recognition condition. The image recognition unit can accurately recognize the subject based on the image for recognition shown by the linear polarization degree image in accordance with the recognition condition.

[0017] In the above-mentioned image recognition device, the image specification unit may be configured to generate a brightness histogram indicating the number of pixels for each brightness value for each of the plurality of polarization images, and calculate a contrast value for each of the plurality of polarization images based on the brightness histogram.

[0018] In this aspect, the image specifying section can accurately calculate the contrast value of each of the plurality of polarized images based on the brightness histogram, thereby enabling the image specifying section to more accurately specify the image of interest with the highest contrast value from among the plurality of polarized images output by the polarized image output section.

[0019] A component mounter according to another aspect of the present invention includes a substrate transport unit which transports a substrate having a predetermined mark to a predetermined position, a head unit which holds an electronic component having electrodes and performs a component mounting operation to mount the held electronic component on the substrate at the predetermined position, and an image recognition device as described above which performs image recognition of the electronic component held by the head unit or the substrate on which the electronic component is to be mounted as the subject, and a head control unit which controls the component mounting operation of the head unit based on the recognition result by the image recognition unit of the image recognition device.

[0020] According to this component mounter, the image recognition unit performs image recognition of the electronic component or the board based on a recognition image having as a subject the electronic component held by the head unit or the board on which the electronic component is to be mounted. The head control unit controls the component mounting operation of the head unit based on the recognition result by the image recognition unit. The component mounting operation of the head unit controlled based on the recognition result by the image recognition unit improves the mounting accuracy of the electronic component on the board.

[0021] The component mounter further includes a management data storage unit that stores management data to be referenced when the head control unit controls the head unit, the management data including target holding position information indicating a target holding position when the head unit holds the electronic component and target mounting position information indicating a target mounting position of the electronic component set on the board. The management data storage unit stores the management data in association with the recognition conditions set by the recognition condition setting unit.

[0022] In this aspect, the image recognition unit can refer to the recognition conditions associated with the management data stored in the management data storage unit when performing image recognition of the electronic component or board based on the recognition image. In this case, the image recognition unit causes the polarized image output unit to output a polarized image conforming to the recognition conditions associated with the management data as the recognition image.

[0023] In the above-mentioned component mounting machine, the recognition conditions set by the recognition condition setting unit are stored in association with the component data or the board data in a predetermined accumulation memory unit that accumulates and stores component data including parameter data related to the characteristics of the electronic components, and board data including data related to the marks affixed to the board.

[0024] In this aspect, the recognition conditions set by the recognition condition setting unit are stored in the predetermined accumulation storage unit in association with the component data or the board data. In this case, the image recognition unit can read out and use the recognition conditions from the accumulation storage unit each time it causes the polarized image output unit to output a polarized image conforming to the recognition conditions as an image for recognition.

[0025] In the above-mentioned component mounting machine, the image identification unit sets, for each of the multiple polarized images, a predetermined range of area including an electrode image area corresponding to the electrode in the electronic component, or a mark image area corresponding to the mark on the board, as a target area for calculating the contrast value.

[0026] When an electronic component is accurately recognized, it is desirable to recognize the electronic component based on a recognition image having a high contrast between an electrode image area corresponding to a characteristic electrode in the electronic component and its surrounding image area. Similarly, when a board is accurately recognized, it is desirable to recognize the board based on a recognition image having a high contrast between a mark image area corresponding to a characteristic mark in the board and its surrounding image area. In view of this, it is desirable that the target image referred to by the recognition condition setting unit when setting the recognition conditions corresponding to the recognition image is an image having a high contrast between the electrode image area or mark image area and its surrounding image area.

[0027] For this reason, the image specification unit sets a predetermined range of regions including the electrode image region or the mark image region for each of the multiple polarized images as a target region for calculating the contrast value. In this case, the image specification unit specifies, as the image of interest, the polarized image having the highest contrast value within the predetermined range of regions including the electrode image region or the mark image region among the multiple polarized images output by the polarized image output unit. As a result, the recognition image, which is a polarized image according to the recognition conditions corresponding to the image of interest, is an image with high contrast between the electrode image region or the mark image region and its surrounding image region. Therefore, the image recognition unit can accurately recognize the electronic component or board as the subject based on the recognition image. Effect of the Invention

[0028] As described above, according to the present invention, it is possible to provide an image recognition device capable of accurately performing image recognition of a subject, and a component mounter including the same. [Brief description of the drawings]

[0029] [Figure 1] 1 is a block diagram of a component mounter to which an image recognition device according to an embodiment of the present invention is applied. [Diagram 2] 2 is a plan view showing a configuration of a mounter body in the component mounter. FIG. [Diagram 3]2 is a diagram illustrating a schematic configuration of a light irradiation unit and a polarized image output unit provided in the image recognition device. FIG. [Figure 4] 13A and 13B are diagrams showing polarized images output by a polarized image output section; [Diagram 5] 2 is a diagram for explaining the processes of an image specification unit, a recognition condition setting unit, and an image recognition unit provided in the image recognition device. FIG. [Figure 6] FIG. 13 is a diagram showing a modified example of the polarized image output section. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0030] Hereinafter, an image recognition device and a component mounter including the same according to an embodiment of the present invention will be described with reference to the drawings. Note that, in the following, directional relationships will be described using XY Cartesian coordinates that are mutually orthogonal on a horizontal plane.

[0031] The component mounter 1 shown in FIG. 1 and FIG. 2 is a device that mounts (mounts) electronic components on a substrate PP to produce an electronic circuit board. Examples of electronic components include chip components with electrodes provided at one end and the other end of the component body, and multiple types of components such as SOP (Small Outline Package), QFP (Quad Flat Package), PLCC (Plastic Leaded Chip Carrier), and BGA (Ball Grid Array). The SOP is a component in which multiple electrodes are arranged at one end and the other end of the component body in the X-axis direction. The QFP and PLCC are components in which multiple electrodes are arranged at one end and the other end of the component body in the X-axis direction and multiple electrodes are arranged at one end and the other end of the component body in the Y-axis direction. The BGA is a component in which multiple ball-shaped electrodes are provided on the bottom surface of the component body. Note that there are also electronic components in which the electrodes are not exposed to the bottom surface of the component body.

[0032] The component mounter 1 includes a mounter main body 2, a control device 3, an image recognition device 4, and a storage device 5.

[0033] The mounting machine main body 2 constitutes a structural portion that performs operations such as component mounting, which mounts electronic components on the board PP, during the production of electronic circuit boards. A solder paste pattern is printed on the board PP before the mounting machine main body 2 mounts the electronic components. In other words, the mounting machine main body 2 mounts the electronic components on the board PP on which the solder paste pattern has been printed. The mounting machine main body 2 includes a main body frame 21, a board transport section 22, a component supply device 23, a head unit 25, and a board support device 28.

[0034] The main body frame 21 is a structure in which the various components constituting the mounting machine main body 2 are arranged, and is formed in a substantially rectangular shape in a plan view seen from a direction (vertical direction) perpendicular to both the X-axis direction and the Y-axis direction. The board transport unit 22 is formed of a conveyor, and is arranged on the main body frame 21 so as to extend in the X-axis direction. The board transport unit 22 transports the board PP in the X-axis direction. The board PP transported by the board transport unit 22 is positioned by the board support device 28 at a predetermined work position (a component mounting position where components are mounted on the board PP). The board support device 28 positions the board PP at the component mounting position by supporting the board PP from below.

[0035] The component supply devices 23 are disposed in the respective regions at both ends of the main body frame 21 in the Y-axis direction. The component supply device 23 is not particularly limited in the component supply method as long as it is configured to be able to supply electronic components. For example, the component supply device 23 may be a tape feeder that supplies electronic components using a tape as a carrier, a tray feeder that supplies electronic components by moving a pallet including a tray on which electronic components are placed, or a stick feeder that supplies electronic components stored in a cylindrical stick while pushing the electronic components out of the stick.

[0036] The head unit 25 is held by a moving frame 27. On the main body frame 21, a fixed rail 261 extending in the Y-axis direction and a ball screw shaft 262 rotated by a Y-axis servo motor 263 are arranged. The moving frame 27 is arranged on the fixed rail 261, and a nut portion 271 provided on the moving frame 27 is screwed onto the ball screw shaft 262. In addition, a guide member 272 extending in the X-axis direction and a ball screw shaft 273 driven by an X-axis servo motor 274 are arranged on the moving frame 27. The head unit 25 is movably held by the guide member 272, and a nut portion provided on the head unit 25 is screwed onto the ball screw shaft 273. The moving frame 27 moves in the Y-axis direction by the operation of the Y-axis servo motor 263, and the head unit 25 moves in the X-axis direction relative to the moving frame 27 by the operation of the X-axis servo motor 274. That is, head unit 25 is movable in the Y-axis direction in conjunction with the movement of movable frame 27, and is movable in the X-axis direction along movable frame 27. Head unit 25 is movable between component supply device 23 and substrate PP supported by substrate support device 28.

[0037] The head unit 25 includes a plurality of holding nozzles 251. The plurality of holding nozzles 251 are detachably attached to the head unit 25. Each holding nozzle 251 is, for example, a nozzle capable of suction-holding an electronic component supplied by the component supply device 23. In this case, each holding nozzle 251 is capable of communicating with any of a negative pressure generator, a positive pressure generator, and the atmosphere via an electric switching valve. That is, a negative pressure is supplied to each holding nozzle 251, thereby enabling the holding nozzle 251 to suction-hold an electronic component, and then a positive pressure is supplied to release the suction-holding of the electronic component.

[0038] Each holding nozzle 251 can move up and down in a vertical direction (Z-axis direction) perpendicular to both the X-axis direction and the Y-axis direction relative to the frame of the head unit 25, and can rotate around a nozzle axis extending in the Z-axis direction. Each holding nozzle 251 can move up and down along the Z-axis direction between a holdable position where an electronic component supplied by the component supply device 23 can be held and a retreated position above the holdable position. That is, when holding an electronic component supplied by the component supply device 23, each holding nozzle 251 descends from the retreated position to the holdable position and holds the electronic component at the holdable position. On the other hand, after holding the electronic component, each holding nozzle 251 rises from the holdable position to the retreated position. Furthermore, each holding nozzle 251 can move up and down along the Z-axis direction between a mountable position where the held electronic component can be mounted on a predetermined target mounting position on the substrate PP and the retreated position.

[0039] The head unit 25 performs a component mounting operation for mounting the electronic components P (FIG. 3) held by each holding nozzle 251 onto the substrate PP, at each of a plurality of target mounting positions set on the substrate PP.

[0040] 2, the head unit 25 is provided with a first imaging camera 252 and a second imaging camera 253. The first imaging camera 252 and the second imaging camera 253 are cameras equipped with imaging elements such as a complementary metal-oxide-semiconductor (CMOS) or a charged-coupled device (CCD).

[0041] The first imaging camera 252 captures an image of the mark M from above to recognize the mark M on the top surface of the substrate PP transported to the component mounting position by the substrate transport section 22. The amount of positional deviation from the origin coordinates of the substrate PP is detected by image recognition of the mark M on the substrate PP based on the image captured by the first imaging camera 252. Image recognition of the mark M on the substrate PP may be performed by the image recognition device 4 described later.

[0042] The second imaging camera 253 captures an image from obliquely above of the supply position of the electronic component P in the component supply device 23. The image acquired by imaging with the second imaging camera 253 is referred to when recognizing the posture of the electronic component P supplied to the component supply position by the component supply device 23.

[0043] The storage device 5 includes a management data storage unit 51 that stores management data D1 referenced by the control device 3, and an accumulation storage unit 52 that accumulates and stores component data D2 and board data D3 referenced by the image recognition device 4.

[0044] The management data D1 stored in the management data storage unit 51 is data configured by various information necessary for the control of component mounting processing and the like by the control device 3. Examples of information configuring the management data D1 include component information, component supply information, nozzle information, head information, target holding position information, and target mounting position information. The component information is information for identifying the type of electronic component P. The component supply information is information for identifying the component supply device 23. The nozzle information is information for identifying the type of the holding nozzle 251. The head information is information for identifying the head unit 25. The target holding position information is information indicating a target holding position when the holding nozzle 251 holds the electronic component P. The target mounting position information is information indicating a target mounting position of the electronic component P set on the board PP.

[0045] As shown in FIG. 1, the management data storage unit 51 stores management data D1 in association with recognition conditions DS set by a recognition condition setting unit 44 of the image recognition device 4, which will be described later.

[0046] 1, the component data D2 and board data D3 stored in the accumulation storage unit 52 will be described. The component data D2 is composed of data related to the characteristics of the electronic component P. Examples of the data related to the characteristics of the electronic component P include the external dimensions of the electronic component P, the size of the electrodes P2 (FIG. 3) in the electronic component P, the shape of the electrodes P2, and, in the case of an electronic component P in which multiple electrodes P2 are arranged in a predetermined arrangement direction relative to the component body P1 (FIG. 3), the pitch between the electrodes P2. The board data D3 is composed of data related to the characteristics of the board PP. Examples of the data related to the characteristics of the board PP include the shape of the mark M affixed to the board PP, the position of the mark M relative to the board PP, and the like.

[0047] The accumulative storage unit 52 accumulates and stores component data D2 for each type of electronic component P, and accumulates and stores board data D3 for each type of board PP. As shown in Fig. 1, the accumulative storage unit 52 stores the component data D2 or the board data D3 in association with recognition conditions DS set by a recognition condition setting unit 44 of the image recognition device 4 described below. Note that the accumulative storage unit 52 is not limited to being included in the storage device 5 provided in the component mounter 1. For example, the accumulative storage unit 52 may be incorporated in a server device separate and independent from the component mounter 1.

[0048] The control device 3 is composed of a CPU (Central Processing Unit), a ROM (Read Only Memory) that stores a control program, a RAM (Random Access Memory) used as a working area for the CPU, etc. The control device 3 controls the operation of each component of the mounting machine main body 2 by the CPU executing the control program stored in the ROM. The control device 3 controls the operation of each component in accordance with management data D1 stored in a management data storage unit 51. As shown in Fig. 1, the control device 3 includes, as its main functional components, a board transport control unit 31, a component supply control unit 32, and a head control unit 33.

[0049] The board transport control unit 31 controls the transport operation of the board PP by the board transport unit 22. The component supply control unit 32 controls the supply operation of the electronic components P by the component supply device 23 according to the component information and component supply information in the management data D1. The head control unit 33 controls the holding nozzle 251 by controlling the head unit 25 according to the component information, nozzle information, head information, target holding position information, and target mounting position information in the management data D1. As a result, the head control unit 33 causes the holding nozzle 251 to perform a holding operation to hold the electronic components P by the holding nozzle 251 corresponding to each of the multiple target mounting positions set on the board PP, and also moves the head unit 25 to perform a component mounting operation.

[0050] The image recognition device 4 is a device for performing image recognition of a subject having a plurality of areas with different light reflection characteristics. The image recognition device 4 will be described with reference to FIGS. 3 to 6 in addition to FIGS.

[0051] The subject of image recognition by the image recognition device 4 includes an electronic component P and a substrate PP. The electronic component P has a component body P1 and an electrode P2 with different light reflection characteristics. In the electronic component P, the electrode P2 made of metal has a reflection characteristic of specularly reflecting incident light, and the component body P1 made of nonmetal such as ceramics or resin has a reflection characteristic of diffusely reflecting incident light. The substrate PP has a substrate body with different light reflection characteristics and a mark M for recognition. The image recognition device 4 performs image recognition on the electronic component P held by the holding nozzle 251 of the head unit 25, or the substrate PP on which the electronic component P held by the holding nozzle 251 is to be mounted, as the subject. The image recognition device 4 when the electronic component P is the subject will be described below.

[0052] The image recognition device 4 performs image recognition of the electronic component P held by the holding nozzle 251 of the head unit 25 before the electronic component P held by the holding nozzle 251 is mounted on the substrate PP. The image recognition device 4 includes a light irradiation unit 41, a polarized image output unit 42, an image specification unit 43, a recognition condition setting unit 44, and an image recognition unit 45. The light irradiation unit 41 and the polarized image output unit 42 are disposed on the main body frame 21 (see FIG. 2). Meanwhile, the image specification unit 43, the recognition condition setting unit 44, and the image recognition unit 45 may be configured by a microcomputer separate and independent from the above-mentioned control device 3, or may be integrated into the control device 3.

[0053] 3, the light irradiator 41 irradiates unpolarized light L1 from diagonally below onto the electronic component P held by the holding nozzle 251 of the head unit 25. When the light L1 irradiated from the light irradiator 41 enters the electronic component P, it is diffusely reflected by the component body P1 and specularly reflected by the electrode P2.

[0054] The polarized image output unit 42 is disposed below the electronic component P held by the holding nozzle 251, and receives light L2 reflected from the electronic component P in response to the incidence of light L1 irradiated from the light irradiation unit 41. As a result, the polarized image output unit 42 acquires a plurality of polarized captured images G1 having different polarization directions as shown in Fig. 4. The polarized image output unit 42 outputs a plurality of polarized images GA including the plurality of polarized captured images G1. Each polarized captured image G1, which is an image of the electronic component P, includes a component body image region AR1 corresponding to the component body P1 and an electrode image region AR2 corresponding to the electrode P2.

[0055] In this embodiment, the polarized image output unit 42 is configured as a polarization camera equipped with a polarizer stacked imaging element 421 in which polarizers 4212 with different polarization directions are stacked on each pixel of an imaging element 4211 such as a CMOS or CCD. Each pixel constituting the polarizer stacked imaging element 421 is provided with a polarizer 4212 that functions as an optical filter that transmits only light polarized in a specific direction. An imaging element 4211 that receives light transmitted through the polarizer 4212 is provided below the polarizer 4212.

[0056] The polarizer 4212 set in each pixel constituting the polarizer stacked imaging element 421 is configured such that a plurality of pixels (for example, four pixels) are treated as one unit and these plurality of pixels (four pixels) transmit only light having different polarization directions. In the case of the polarizer stacked imaging element 421 in which the polarizer 4212 is stacked with four pixels as one unit, the polarization directions of the four pixels a, b, c, and d of the polarizer stacked imaging element 421 are set, for example, as follows. That is, the polarization direction of pixel a is the horizontal direction of 0 degrees, and in this case, pixel a receives only light polarized in the direction of 0 degrees. The polarization direction of pixel b is the diagonal direction of 45 degrees to the upper right, and in this case, pixel b receives only light polarized in the direction of 45 degrees. The polarization direction of pixel c is the vertical direction of 90 degrees, and in this case, pixel c receives only light polarized in the direction of 90 degrees. The polarization direction of pixel d is the diagonal direction of 135 degrees to the lower right, and in this case, pixel d receives only light polarized in the direction of 135 degrees.

[0057] In the above explanation, the horizontal direction, upper right diagonal direction, lower right diagonal direction, and vertical direction are directions relative to the polarization camera that constitutes polarization image output unit 42, with the direction perpendicular to the optical axis of the polarization camera being the horizontal direction and the direction parallel to the optical axis of the polarization camera being the vertical direction. Therefore, the polarization direction of each pixel changes depending on the tilt of the polarization camera.

[0058] The polarized image output unit 42, which is configured with a polarization camera equipped with a polarizer stacked imaging element 421 in which polarizers 4212, each of which has four pixels as one unit, receives light L2 reflected by the electronic component P in response to the incidence of light L1 irradiated from the light irradiation unit 41, thereby acquiring polarized captured images G1 with polarization directions of 0 degrees, 45 degrees, 90 degrees, and 135 degrees. By configuring the polarized image output unit 42 with a polarization camera, it is possible to acquire four polarized captured images G1 with different polarization directions in one imaging of the electronic component P held by the holding nozzle 251 from the lower side. This allows the polarized image output unit 42 to shorten the time required to acquire multiple polarized captured images G1.

[0059] 4, the polarized image output unit 42 generates a plurality of polarized composite images G2 by synthesizing a plurality of polarized captured images G1 with different polarization directions while changing the weighting. In this case, the polarized image output unit 42 generates a plurality of polarized composite images G2 with different polarization directions that are subdivided according to the weighting. The polarized image output unit 42 outputs a plurality of polarized composite images GA with different polarization directions that are subdivided by outputting the plurality of polarized composite images G2 as polarized images GA. Note that the polarized composite image G2 includes a component body image area AR1 corresponding to the component body P1 and an electrode image area AR2 corresponding to the electrode P2, similar to the polarized captured image G1.

[0060] The polarized image output unit 42 generates a polarization angle image G3 expressed in grayscale for each angle of the polarization direction based on the multiple polarized captured images G1, and outputs the polarization angle image G3 as a polarized image GA. Note that, like the polarized captured image G1, the polarization angle image G3 includes a component body image region AR1 corresponding to the component body P1 and an electrode image region AR2 corresponding to the electrode P2.

[0061] Furthermore, the polarized image output unit 42 calculates the degree of linear polarization (DoLP) for each pixel based on the multiple polarized captured images G1, and generates a linear polarization degree image G4 consisting of a pixel group having a luminance value according to the linear polarization degree. In this case, the polarized image output unit 42 outputs the linear polarization degree image G4 as a polarized image GA. Note that, like the polarized captured image G1, the linear polarization degree image G4 includes a component body image area AR1 corresponding to the component body P1 and an electrode image area AR2 corresponding to the electrode P2.

[0062] As described above, the polarized image output section 42 outputs the multiple polarized captured images G1, the multiple polarized composite images G2, the polarization angle image G3, and the linear polarization degree image G4 as polarized images GA.

[0063] The polarized image output unit 42 may be configured to generate a non-polarized image GB by synthesizing a plurality of polarized captured images G1 with the same weighting, and output the non-polarized image GB. Like the polarized captured image G1, the non-polarized image GB includes a component body image area AR1 corresponding to the component body P1 and an electrode image area AR2 corresponding to the electrode P2. Note that the non-polarized image GB may be obtained by imaging with a normal imaging camera equipped with an imaging element such as a CMOS or CCD, instead of being generated by the polarized image output unit 42 consisting of a polarization camera.

[0064] As shown in Fig. 5, the multiple polarized images GA and non-polarized images GB output by the polarized image output unit 42 are input to the image specifying unit 43. The image specifying unit 43 calculates a contrast value C for each of the multiple polarized images GA and non-polarized images GB, and specifies an image of interest GC with the highest contrast value C. Specifically, the image specifying unit 43 generates a luminance histogram HG indicating the number of pixels for each luminance value for each of the multiple polarized images GA and non-polarized images GB. Then, the image specifying unit 43 calculates the contrast value C for each of the multiple polarized images GA and non-polarized images GB based on each luminance histogram HG in accordance with the following equation (1): Contrast value C=(max-min) / (max+min) (1)

[0065] In the above formula (1), for the luminance value of each pixel constituting each of polarized image GA and unpolarized image GB, the highest luminance value is indicated as "max" and the lowest luminance value is indicated as "min."

[0066] The image specifying section 43 can accurately calculate the contrast value C of each of the multiple polarized images GA and non-polarized images GB based on the brightness histogram HG. This allows the image specifying section 43 to more accurately specify the image of interest GC with the highest contrast value C from the multiple polarized images GA and non-polarized images GB output by the polarized image output section 42.

[0067] The recognition condition setting unit 44 sets a recognition condition DS for image recognition of the electronic component P based on the image of interest GC specified by the image specifying unit 43. When the image specifying unit 43 specifies the image of interest GC from among the multiple polarized captured images G1, the multiple polarized composite images G2, and the polarization angle image G3, the recognition condition setting unit 44 sets the polarization direction corresponding to the image of interest GC as the recognition condition DS. When the image specifying unit 43 specifies the linear polarization degree image G4 as the image of interest GC, the recognition condition setting unit 44 sets the recognition condition DS to have the polarized image output unit 42 generate and output the linear polarization degree image G4. When the image specifying unit 43 specifies the non-polarized image GB as the image of interest GC, the recognition condition setting unit 44 sets the recognition condition DS to have the polarized image output unit 42 generate and output the non-polarized image GB.

[0068] The recognition conditions DS set by the recognition condition setting unit 44 are stored in the management data storage unit 51 in association with the management data D1, and are also stored in the accumulation storage unit 52 in association with the component data D2. When the image recognition device 4 performs image recognition of the board PP as the subject, the recognition conditions DS are stored in the accumulation storage unit 52 in association with the board data D3.

[0069] The image recognition unit 45 outputs the polarized image GA or the non-polarized image GB according to the recognition conditions DS automatically set by the recognition condition setting unit 44 from the polarized image output unit 42 as the recognition image GD. When the recognition conditions DS indicate a polarization direction, the image recognition unit 45 outputs the polarized image GA having the polarization direction indicated by the recognition conditions DS as the recognition image GD from the polarized image output unit 42. When the recognition conditions DS indicate that a linear polarization degree image G4 is to be generated and output, the image recognition unit 45 outputs the linear polarization degree image G4 from the polarized image output unit 42 as the recognition image GD. When the recognition conditions DS indicate that a non-polarized image GB is to be output, the image recognition unit 45 outputs the non-polarized image GB from the polarized image output unit 42 as the recognition image GD.

[0070] The recognition image GD is a polarized image GA or a non-polarized image GB according to the recognition conditions DS, and is an image corresponding to the target image GC having the highest contrast value C among the multiple polarized images GA and non-polarized images GB that can be output from the polarized image output unit 42. Therefore, the recognition image GD is an image of the electronic component P having good contrast. Therefore, the image recognition unit 45 can accurately recognize the electronic component P based on the recognition image GD according to the recognition conditions DS.

[0071] When performing image recognition of electronic component P based on recognition image GD, image recognition unit 45 can refer to recognition conditions DS associated with management data D1 stored in management data storage unit 51. In this case, image recognition unit 45 causes polarized image GA or non-polarized image GB in accordance with the recognition conditions DS associated with management data D1 to be output from polarized image output unit 42 as recognition image GD.

[0072] In addition, since the recognition conditions DS are associated with the part data D2 and stored in the accumulation memory unit 52, the image recognition unit 45 can read out and use the recognition conditions DS from the accumulation memory unit 52 each time it causes the polarized image GA or non-polarized image GB in accordance with the recognition conditions DS to be output from the polarized image output unit 42 as an image for recognition GD.

[0073] The image recognition unit 45 causes the polarized image GA or the non-polarized image GB according to the recognition conditions DS set by the recognition condition setting unit 44 to be output from the polarized image output unit 42 as a recognition image GD for image-recognizing the electronic component P. Then, the image recognition unit 45 performs image-recognition of the electronic component P held by the holding nozzle 251 based on the component data D2 stored in the accumulation storage unit 52 and the recognition image GD output from the polarized image output unit 42. Specifically, the image recognition unit 45 recognizes the position of the electronic component P relative to the holding nozzle 251 as the holding state of the electronic component P relative to the holding nozzle 251, and recognizes the posture of the electronic component P held by the holding nozzle 251, based on the recognition image GD while referring to the component data D2.

[0074] Recognition result information DSS indicating the recognition result by the image recognition unit 45 is input to the head control unit 33. Based on the recognition result information DSS, the head control unit 33 controls the component mounting operation by the head unit 25. The component mounting operation of the head unit 25 controlled based on the recognition result information DSS by the image recognition unit 45 improves the mounting accuracy of the electronic components P on the board PP.

[0075] When accurately recognizing an electronic component P, it is desirable to perform image recognition of the electronic component P based on a recognition image GD that has high contrast between the electrode image area AR2 corresponding to the characteristic electrode P2 in the electronic component P and the surrounding component body image area AR1.

[0076] For this reason, as shown in FIG. 5, the image specifying unit 43 sets a predetermined range of regions including the electrode image region AR2 for each of the multiple polarized images GA and non-polarized images GB as a target region AR3 for calculating the contrast value C. In this case, the image specifying unit 43 specifies, as the image of interest GC, the polarized image GA or non-polarized image GB having the highest contrast value C in the predetermined range of region AR3 including the electrode image region AR2 among the multiple polarized images GA and non-polarized images GB output by the polarized image output unit 42. As a result, the recognition image GD, which is the polarized image GA or non-polarized image GB according to the recognition condition DS corresponding to the image of interest GC, becomes an image with high contrast between the electrode image region AR2 and the surrounding component body image region AR1. Therefore, the image recognition unit 45 can accurately recognize the electronic component P as the subject based on the recognition image GD.

[0077] When the image recognition device 4 performs image recognition of the substrate PP as a subject, the image specification unit 43 sets a predetermined range of area including a mark image area corresponding to the mark M affixed to the substrate PP as a target area for calculating the contrast value C. In this case, the image specification unit 43 specifies the polarized image GA or non-polarized image GB having the highest contrast value C in the predetermined range of area including the mark image area as the image of interest GC. As a result, the recognition image GD, which is the polarized image GA or non-polarized image GB according to the recognition condition DS corresponding to the image of interest GC, becomes an image with high contrast between the mark image area and its surrounding area. Therefore, the image recognition unit 45 can accurately perform image recognition of the substrate PP as a subject based on the recognition image GD.

[0078] The above describes the image recognition device 4 and the component mounter 1 equipped with the same according to an embodiment of the present invention. However, the present invention is not limited to this, and for example, the following modified embodiments can be adopted.

[0079] In the above embodiment, the polarized image output section 42 of the image recognition device 4 is configured by a polarized camera equipped with a polarizer stack imaging element 421, but the present invention is not limited to such a configuration.

[0080] In a modified embodiment, the polarized image output section 42 may be a camera having a structure shown in FIG. 6. In the example shown in FIG. 6, the polarized image output section 42 is configured by a camera in which a polarizing filter 423 rotatable around an axis 4231 parallel to the optical axis and an image sensor 422 such as a CMOS or CCD are arranged side by side on the optical axis at a predetermined interval. In this case, the polarizing filter 423 is partitioned into a plurality of regions (for example, four regions) that pass light of different polarization directions. For example, the polarizing filter 423 is partitioned into four regions that pass light of polarization directions of 0 degrees, 45 degrees, 90 degrees, and 135 degrees. In the polarized image output section 42 configured in this way, the polarizing filter 423 is rotated by a rotation angle of 45 degrees for each image capture by the image sensor 422. In this case, four polarized captured images G1 with different polarization directions can be obtained by four images capture by the image sensor 422. As a result, the polarization image output unit 42 takes longer to acquire multiple polarization images G1 than when it is configured using the above-mentioned polarization camera, but it can acquire polarization images G1 with higher resolution. [Explanation of symbols]

[0081] 1. Component Mounting Machine 2 Mounting machine body 25 Head Unit 3. Control device 33 Head control section 4. Image Recognition Device 41 Light irradiation unit 42 Polarized image output section 43 Image Identification Section 44 Recognition condition setting section 45 Image Recognition Unit 5 Storage device 51 Management data storage unit 52 Accumulation memory unit

Claims

1. An image recognition device for performing image recognition on a subject having a plurality of regions with different light reflection characteristics, comprising: a polarized image output unit that receives light reflected from the subject to obtain a plurality of polarized captured images having different polarization directions, and outputs a plurality of polarized images including the plurality of polarized captured images; an image specifying unit that calculates a contrast value of each of the plurality of polarization images and specifies an image of interest having the highest contrast value; a recognition condition setting unit that sets a polarization direction corresponding to the image of interest as a recognition condition for image recognition of the subject; an image recognition unit that outputs a polarized image conforming to the recognition conditions from the polarized image output unit as an image for recognition, and performs image recognition of the subject based on the image for recognition.

2. The image recognition device according to claim 1 , wherein the polarized image output section generates a plurality of polarized composite images by combining the plurality of polarized captured images while changing weighting, and outputs the plurality of polarized composite images as the polarized image.

3. 3. The image recognition device according to claim 1, wherein the polarization image output unit generates a polarization angle image expressed in grayscale for each angle of the polarization direction based on the plurality of polarized captured images, and outputs the polarization angle image as the polarization image.

4. the polarization image output unit calculates a degree of linear polarization for each pixel based on the plurality of polarization captured images, generates a linear polarization degree image composed of a pixel group having a luminance value according to the degree of linear polarization, and outputs the linear polarization degree image as the polarization image; The image recognition device according to any one of claims 1 to 3, wherein the recognition condition setting unit sets as the recognition condition that, when the image identification unit identifies the linear polarization degree image as the image of interest, the polarized image output unit generates and outputs the linear polarization degree image.

5. 5. The image recognition device according to claim 1, wherein the image specification unit generates a brightness histogram indicating the number of pixels for each brightness value for each of the plurality of polarization images, and calculates contrast values ​​for each of the plurality of polarization images based on the brightness histogram.

6. a substrate transport unit that transports the substrate having the predetermined mark to a predetermined position; a head unit that holds an electronic component having an electrode and performs a component mounting operation of mounting the held electronic component on the substrate at the predetermined position; 6. The image recognition device according to claim 1, wherein the image recognition device performs image recognition of the electronic component held by the head unit or the substrate on which the electronic component is to be mounted as the subject; a head control unit that controls the component mounting operation of the head unit based on a recognition result by the image recognition unit of the image recognition device.

7. a management data storage unit that stores management data to be referenced when the head control unit controls the head unit, the management data including target holding position information indicating a target holding position when the head unit holds the electronic component and target mounting position information indicating a target mounting position of the electronic component set on the board; 7. The component mounter according to claim 6, wherein the management data storage unit stores the management data in association with the recognition conditions set by the recognition condition setting unit.

8. 8. The component mounter according to claim 6 or 7, wherein the recognition conditions set by the recognition condition setting unit are stored in association with the component data or the board data in a predetermined accumulation memory unit that accumulates and stores component data including parameter data related to characteristics of the electronic components and board data including data related to the marks affixed to the board.

9. The component mounter according to any one of claims 6 to 8, wherein the image specifying unit sets, for each of the plurality of polarized images, an area of ​​a predetermined range including an electrode image area corresponding to the electrode in the electronic component or a mark image area corresponding to the mark on the board as a target area for calculating the contrast value.

Images