JP2872553B2 - Image recognition positioning method and apparatus - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image recognition positioning apparatus for positioning a substrate based on image processing of the surface of the substrate.

[0002]

2. Description of the Related Art Solder is printed on a desired area on a printed circuit board through a screen mask, electronic components such as semiconductor devices, resistors and capacitors are mounted or mounted, and a photomask is placed on a semiconductor wafer (semiconductor substrate). For example, when performing photolithography, it is necessary to accurately align these substrates.

Conventionally, positioning has been performed by the following method. That is, an isolated mark is provided in a specific region of the substrate for alignment. On the other hand, information on the position of the specific area and information on the mark shape are stored and set in the image processing unit as reference information. The substrate is transported to a position facing an image reading unit such as a camera, and the read image of the substrate surface is binarized. Then, image processing is performed to detect a mark, and a center position, a center of gravity, and the like are obtained. The position information is compared with the reference information to determine a position deviation, and the position of the substrate is corrected based on the deviation. Thus, accurate positioning of the substrate has been performed.

In the above-described method, in order to arrange an isolated mark, an area around the isolated mark is required to be free of a pattern that can be mistaken for the mark. However, with the high definition of printed circuit boards and semiconductor wafers, a situation often occurs in which there is no space for providing an isolated mark.

Therefore, a method has been proposed in which positioning is performed using an arbitrary pattern on the substrate surface without providing a special positioning mark. In this method, a pattern to be used as a reference for performing positioning is extracted in advance, and a predetermined area including the pattern is determined.

The above area of the member to be aligned with the substrate to be processed is read, and the image is stored in the image processing section as a dictionary area (also referred to as a reference model). The substrate to be processed is transported to the image reading area, a binarized image is created,
By performing the image processing, the ratio of the area of the bright area in the processing area to the area of the processing area on the surface of the substrate to be processed (area ratio of the bright area) is compared with the area ratio of the bright area of the dictionary area. A region having the same area ratio is searched for, and the matching region is aligned.

A method of searching for a region in which the area ratio of the dictionary region and the bright portion matches is called gray-scale pattern matching, gray-scale pattern matching or auto-correlation function method.
Image Processing Apparatus and Its Applications "(by Eiji Mizutani) (New Technology Communications Inc." O plus E ")
August 1991 No. 141 pp 141-15
2) etc.

In gray-scale pattern matching, a normalized correlation coefficient (match rate) is used as the degree of coincidence between two images. The match rate takes a value of +1 to −1, and when +1, it indicates that the two images are completely matched.

[0009]

In the case of performing the alignment by shading pattern matching, the alignment is performed by matching the pattern of the dictionary area with the pattern of the area (corresponding area) corresponding to the dictionary area on the surface of the substrate to be processed. It can be carried out. However, when the pattern of the dictionary area and the imaged pattern of the corresponding area on the surface of the substrate to be processed are in a relationship where the brightness is reversed, the match rates hardly match.

For example, if the area ratio of the bright part of the dictionary area is 0.7
When the area ratio of the bright part of the inverted image pattern is 0.3, the match rate cannot be calculated as it is. This occurs, for example, in a screen printing machine. That is, when the screen mask is read by a camera, the image is dark because the light passes through the aperture, and the image is bright because the light is reflected outside the aperture. On the other hand, on a printed circuit board, light is strongly reflected at the land of the wiring where the solder is printed, so the image is bright at this part,
It becomes dark at other insulating plates.

In such a case, first, a dictionary area of the screen mask is determined, and its representative point is set. Here, the representative point may be any point in the area, and is used for position designation. Next, in determining the dictionary area of the printed board, the operator moves the printed board so that the camera can read the area while watching the monitor screen on which the image of the processing target printed board is projected.
When the pattern of the dictionary area matches the pattern of the area, the cursor on the monitor screen is visually adjusted to a position corresponding to the representative point of the dictionary area of the previously set screen mask.

The corresponding area of the printed circuit board and its representative point are stored as reference information in the RAM of the image processing unit. In printing the solder, using the reference information, the surface of each substrate that is sequentially conveyed is read by a camera, and alignment is performed using a representative point. In other words, instead of using the dictionary area in the screen mask as it is for alignment,
The corresponding area of the printed circuit board is replaced with a dictionary area to perform indirect alignment.

The work of replacing the corresponding area of the printed circuit board with the dictionary area is performed manually, and takes time. Further, errors are likely to occur in the setting of the representative point due to the movement of the cursor, and there is a limit in improving the accuracy of positioning. If there is a big mistake in setting the representative point by moving the cursor,
Everything produced using the dictionary area has low accuracy, and the yield is extremely reduced.

It is an object of the present invention to provide an image recognition alignment technique that does not require much time for preparation for alignment and that can perform alignment with high accuracy.

[0015]

According to the image recognition positioning method of the present invention, image data of a surface of a substrate to be processed and a surface of a reference member serving as a reference to be aligned with the substrate to be processed are acquired. In the image recognition alignment method of comparing the two image data and aligning the processing target substrate, an image of a dictionary area including a pattern that is a part of the surface of the reference member and can be a reference for alignment is obtained. Reading, creating regular image data and storing as temporary dictionary data; reading an image of a corresponding area on the surface of the processing target substrate corresponding to the dictionary area, obtaining image data of the corresponding area; A comparison step of comparing the light-dark relationship between the temporary dictionary data and the image data of the corresponding area. Storing the temporary dictionary data as dictionary area data, and storing image data obtained by inverting the brightness of the temporary dictionary data as dictionary area data when the light-dark relationship is an inversion relation; and To form image data to be processed, and align the image data to be processed with the dictionary area data.

In the comparing step, the comparing step obtains a luminance on a predetermined reference line of the dictionary area from the temporary dictionary data to obtain a normal luminance distribution; Obtaining a luminance on a line corresponding to the reference line, and obtaining a luminance distribution of the corresponding area.

Further, in the comparing step, further, the comparing step obtains an inverted luminance distribution obtained by inverting the brightness relationship of the normal luminance distribution, and adds the normal luminance distribution and the corresponding area luminance distribution. And adding the inverted luminance distribution and the corresponding area luminance distribution.

An image recognition alignment apparatus according to the present invention acquires image data of a surface of a substrate to be processed and a surface of a reference member serving as a reference for performing alignment of the substrate to be processed,
In an image recognition alignment apparatus that performs image processing and aligns a substrate to be processed, image data of a dictionary area including a pattern that is a part of the surface of the reference member and can be used as a reference for alignment or its brightness. A temporary dictionary storage means for storing the image data with the inverted relationship as a temporary dictionary area, and a corresponding area image data storage means for storing an image of a corresponding area on the surface of the processing target substrate corresponding to the dictionary area, Comparing means for comparing the light and dark relationship between the image data stored in the temporary dictionary storage means and the image data stored in the corresponding area image data storage means; and based on the result of the comparison means, the temporary dictionary storage means Setting means for adopting the stored image data or image data obtained by inverting the brightness of the stored image data as dictionary area data; Including the image data of those areas, and an arithmetic means for performing alignment by using the image data employed as the dictionary area.

[0019] Further, it may include a switch means for approving the adoption of the certification means.

[0020]

According to the present invention, a pattern which can be used for alignment is extracted from patterns formed on a reference member serving as a reference for performing alignment of a substrate to be processed, and the pattern is used for alignment, thereby obtaining a substrate surface. There is no need to provide a special pattern for positioning.

The normal image data of the reference member is stored as a temporary dictionary. Even when the light-dark relationship between the substrate to be processed and the reference member is reversed, the light-dark relationship between the image data in the area including the pattern that can be used for the alignment of the reference member is reversed. Can be matched.

The image data of the reference member in which the light-dark relationship is matched is stored as dictionary area data, and thereafter, the image data of the dictionary area and the image data of the substrate to be processed are subjected to light and shade pattern matching, thereby quickly positioning. Can be performed.

By determining the luminance distribution of the image data and comparing the profiles of the luminance distribution, it can be easily determined whether or not the light-dark relationship is the same.

[0024]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described below with reference to one embodiment shown in the drawings. FIG. 1 shows a schematic configuration of a screen printing machine using the image recognition alignment device of the present invention.

A printed board 1 is placed on a table 2. The table 2 vacuum-adsorbs the printed circuit board 1 on the upper surface, and can be slightly moved in parallel in the X-axis direction, which is the horizontal direction in the drawing, and the Y-axis direction, which is perpendicular to the X-axis, which is a direction perpendicular to the plane of the drawing. Furthermore, it is possible to slightly rotate and move in the θ direction which is the rotation direction (the rotation direction in the XY plane) about the Z axis. These minute movements are performed by the servo motor 10b.

The table 2 can be moved on the rail 3 in the left-right (X-axis) direction on the rail 3 by the servo motor 10a, and stops on the left side (positioning station S1) to perform positioning of the printed circuit board 1. Stop on the right side (printing station S2) and perform solder printing. At the position of the printing station S2, a screen mask 4 is disposed slightly above the printed circuit board 1 placed on the table 2.

The screen mask 4 is provided with a squeegee 5 which slides on the upper surface thereof in the left-right (X-axis) direction by a servo motor 10d. By sliding the squeegee 5 in the left-right direction, the solder can be printed on the surface of the printed circuit board 1 through the opening of the screen mask 4.
Above the stage 2, cameras 6a and 6b for image reading that can reciprocate between the stations S1 and S2 by a servomotor 10c are arranged.

The operation of the servo motors 10a to 10d is performed via a controller 11 and a driver 12 based on a command from the main control unit 7. Each of the motors 10a to 10d is provided with an encoder (not shown) for feeding back the amount of movement of the table 2 or the like to the controller 11, so that accurate control can be performed.

An image monitor 8 for displaying image signals obtained from the cameras 6a and 6b is provided. A touch panel unit 9 for stopping operation of the apparatus and inputting various operation signals is provided on the box. ing.

The main control unit 7 stores the R in which the program is stored.
OM 7a, RAM 7b for temporarily storing image signals and the like obtained from cameras 6a and 6b, CPU 7c for processing and processing image signals and the like obtained from cameras 6a and 6b in accordance with a program stored in ROM 7a, cameras 6a and 6b
Input / output unit 7e for receiving signals from the controller 11
And an input / output unit 7f for transmitting and receiving data to and from the image monitor 8.

FIGS. 2A, 2B and 2C show a camera 6.
An example of an image obtained by inverting the surface image of the screen mask 4 and the printed circuit board 1 and the surface image of the screen mask read at a or 6b is shown. These images are displayed on the image monitor 8.

Hereinafter, the operation and functions of the screen printing machine shown in FIG. 1 will be described with reference to the flowchart of FIG. When the screen printing machine is started, first, step s1 of temporarily setting a dictionary area of the screen mask is executed. In step s1, the cameras 6a and 6b are moved to the printing station S2 to obtain an image of the screen mask 4. A unique pattern in the image, that is, a pattern having no similar pattern in the periphery and usable as an alignment mark is extracted, and a predetermined area including the pattern is stored in the RAM 7b of the main control unit 7 as a temporary dictionary area. I do.

Next, a temporary printed circuit board 1 of the same kind as the substrate to be processed is vacuum-sucked on the table 2 and placed in the positioning station S1. The cameras 6a and 6b are moved to the positioning station S1, the area of the printed board 1 corresponding to the temporary dictionary area of the screen mask 4 stored in the RAM 7b is read, and the image data is stored in the RAM 7b (step s2).

FIGS. 2A and 2B show examples of image data of the temporary dictionary area of the screen mask 4 and the corresponding area of the printed circuit board 1 stored in the RAM 7b. still,
The cameras 6a and 6b read images in a wider area than the images shown in FIGS. 2A and 2B. FIG.
(A) and FIG. 2 (B) show areas extracted from these as dictionary areas.

Here, an image having many bright areas in the image is called a positive screen, and an image having many dark areas is called a negative screen. In addition, when the surroundings of the screen are viewed, a positive screen may be used if the surroundings are bright, and a negative screen may be used if the surroundings are dark, or vice versa.

FIGS. 2A and 2B show the camera 6a,
6b. The reason why the two cameras 6a and 6b are provided in FIG. 1 is to increase the accuracy of the alignment by viewing two points on the diagonal line of the printed circuit board 1 and the screen mask 4, respectively.

In the alignment step, similar processing is performed on the images read by these two cameras, and FIG. 2 shows only the images obtained by one of the cameras.
The temporary dictionary area C1 of the screen mask 4 which is a positive screen shown in FIG.
The white portion of the screen mask 4 is a region where light is reflected by the screen mask 4, and the hatched dark portion is a portion where light is transmitted through an opening provided in the screen mask 4.

A bright portion of a corresponding area C2 (hereinafter, simply referred to as a corresponding area C2) of the printed circuit board having a negative screen shown in FIG. 2B is a metal wiring portion on which solder is to be printed. The dark part is the insulating resin area where the solder is not printed. There are no apertures, but light and dark are formed due to the relationship of light reflectance.

FIG. 2C shows an inverted area C3 obtained by inverting the light / dark relationship of the temporary dictionary area C1 on the positive screen. The image processing of the screen inversion is used as a screen inversion function in a word processor or the like, and the following method is an example. That is, the average value of the luminance of the bright region and the average value of the luminance of the dark region are determined. Next, when the brightness of each pixel constituting the screen, that is, the luminance, is subtracted from this average value, the pixel has a minus (negative) value in a bright region and a plus (positive) value in a dark region. Assign positive and negative signs to each pixel,
When the screen is displayed with the positive sign bright and the negative sign dark, the resulting screen is an inverted screen.

Next, in step s3, the temporary dictionary area C1
It is determined whether both and the corresponding area C2 are positive screens. As shown in FIG. 2, since both areas have a positive / negative relationship, the process proceeds to step s4. A step s4 decides whether or not both areas C1 and C2 are negative screens.
Since the determination is no, the process proceeds to step s5.

In step s5, the screen of the temporary dictionary area C1 is inverted, and the inverted screen is stored in the RAM 7b of the main control section 7 as a dictionary area. The reverse screen area C3 is the corresponding area C
This is consistent with the light-dark relationship of 2. An approval (setting) switch may be provided on the touch panel unit 9 and the dictionary area may be stored in the RAM 7b by pressing the approval switch.

On the other hand, step s3 or step s4
If both screens are positive or negative, the temporary dictionary area C1 is set as it is in the RAM 7b of the main controller 7 in step s6. That is, through steps s3 to s6, the dictionary area and the corresponding area C2
The light-dark relationship can be matched. Although the case where the reversed image is created only when the two screens do not match with each other in the positive or the negative has been described, first, the reversed image is created, and it is determined whether to use the normal image or the inverted image based on whether the images match or mismatch. You may.

The details of steps s3 and s4 will be described later. Next, in step s7, the temporary printed circuit board 1 on the table 2 is removed, and the printed circuit board 1 on which solder is to be printed is automatically carried in by a conveyor or the like from a preceding device (not shown) and placed on the table 2. I do. Further, the printed circuit board 1 is minutely moved while being monitored by the cameras 6a and 6b, and set at a predetermined position.

In step s8, the table 2 and the camera 6
a and 6b are moved to the printing station S2, and the screen mask 4 and the printed circuit board 1 are aligned. The screen mask 4 is removed, and the printed circuit board 1 is slightly moved while watching the screen of the monitor 8 so that the inverted area C3 of the dictionary area and the corresponding area C2 of the surface of the printed circuit board 1
Is performed. Positioning is completed when the match rate is maximized.

In step s9, solder printing is performed. First,
The screen mask 4 is placed at a predetermined position, and the squeegee 5
To the left. Thereby, the screen mask 4
The upper solder paste is used for opening the screen mask 4 (see FIG. 2).
Screen printing is performed on the metal wiring portion (the bright portion of the region C2 in FIG. 2) of the printed circuit board 1 through the dark portion of the region C1 in (A).

After the printing is completed, the table 2 is returned to the positioning station S1, and the printed circuit board 1 is carried out to the subsequent device by the conveyor (step s10). When the squeegee 5 or the like is returned to the initial position, it is determined whether there is a subsequent printed circuit board 1 on which the same type of solder printing is to be performed (step s11). If there is, the process returns to step s7, and the solder printing is performed in the same process as described above. Do. If there is no subsequent printed circuit board, all processing operations end.

As described above, first, the image data of the dictionary area is set so that the brightness relationship between the image data of the dictionary area of the screen mask and the image data of the corresponding area of the printed circuit board coincides with each other. The substrate can be quickly positioned without determining the light / dark relationship.

Hereinafter, a method of judging whether the images are positive or negative in steps s3 and s4 will be described. First
In this method, the operator visually compares the temporary dictionary area C1 displayed on the image monitor 8 with the corresponding area C2 or the inverted area C3 to determine whether the screen is a positive screen or a negative screen.
In this case, whether each area is a positive screen or a negative screen can be determined only by looking at the light / dark relationship of the image, so that it is not necessary to utilize the area ratio of light / dark.

Next, the second method will be described with reference to FIG. FIG. 5A shows a temporary dictionary area C1b, and FIG.
Shows an example of a corresponding area C2b, and FIG. 5C shows an example of an inverted area C3b obtained by inverting the light / dark relationship of the temporary dictionary area C1b. FIGS. 5D, 5E, and 5F respectively show the temporary dictionary area C
1b shows a luminance distribution on a line passing substantially through the center of the corresponding area C2b and the inversion area C3b.

For example, the temporary dictionary area C1b shown in FIG.
Is dark and its periphery is bright, so that the luminance distribution becomes concave as shown in FIG. 5D. Conversely, since the central part of the corresponding area C2b and the inversion area C3b in FIGS. 5B and 5C is bright and the peripheral part is dark, the luminance distribution is as shown in FIGS. 5E and 5F. It becomes convex.

As described above, the profiles of the luminance distribution between the positive screens or between the negative screens match or approximate. Conversely, in the case of a combination of a positive screen and a negative screen, the profiles of the luminance distribution have shapes that are turned upside down. Therefore, by visually comparing the luminance distribution profiles, it is possible to easily determine whether the images are positive or negative or a combination of positive and negative.

Next, the third method will be described. FIG.
FIG. 5G shows an added luminance distribution obtained by adding the luminance distribution of the temporary dictionary area C1b in FIG. 5D and the luminance distribution of the corresponding area C2b in FIG. 5E. FIG. The luminance distribution of the inversion area C3b in (F) and the corresponding area C2b in FIG.
And the luminance distribution of FIG.

As described above, when the positive screens or the negative screens are added together, the profile of the luminance distribution is exaggerated. Conversely, the profile of the added luminance distribution in the case of the combination of the positive screen and the negative screen becomes almost flat. Therefore, by visually observing the profile of the added luminance distribution, it is possible to determine whether the combination is positive or negative, or a combination of positive and negative.

Alternatively, for the luminance of the same portion, the value before the addition may be subtracted from the value after the addition by the CPU 7c so that the determination can be made automatically. That is, the brightness of the bright part is +1 and
Assume that the brightness of the dark part is -1. In the case of positive screens or negative screens, the value before addition of the bright portion is both +1 and the value after addition is +2. Therefore, subtracting the value before addition from the value after addition results in +1.

In the case of a combination of a positive screen and a negative screen, if one is a bright part and the other is a dark part, the values before addition are +1 and −1 and after addition are 0. Therefore, subtracting the value of the bright portion before addition from the value after addition results in -1. Therefore, by determining whether the sign is positive or negative,
The following cases are examples of positives or negatives that can easily determine the relationship between screens.

The screen mask made of stainless steel is half-etched along the boundary between the light and dark portions to prepare a temporary screen mask in which the etch grooves are filled with a substance having a low reflectance.

FIG. 5A shows a temporary dictionary area C1a obtained by reading the temporary screen mask formed in this way with a camera.
Is shown. As described above, the light becomes dark in the etch groove portion and becomes light in other portions. FIG. 5C shows a cross-section of the temporary screen mask along the line AA of the temporary dictionary area C1a.
The etch groove 13 etched so as not to penetrate the screen mask is filled with a substance having a low reflectance. By making the outside of the dark part of the temporary dictionary area C1a dark by image processing, the light-dark relationship can be matched with the corresponding area C2a of the printed board shown in FIG.

When the light-dark relation of the corresponding area of the printed circuit board is reversed, the light-dark relation can be matched by darkening the inside of the dark part by image processing. As described above, by making a desired area dark by image processing, it is possible to produce a positive or negative screen.

Alternatively, there is a case where the light-dark relationship between the temporary dictionary area and the corresponding area remains the same. In these cases, when the determination is made in steps s3 and s4,
Since both screens are positive or negative, the temporary dictionary area can be used as a dictionary area without being inverted.

In the above-described first to third methods, the dictionary area may be set by pressing the switch of the touch panel unit 9 after visual confirmation, but in the third method, the determination processing program is stored in the ROM 7a. For example, the dictionary area can be automatically set based on the above-mentioned determination result.

The present invention has been described in connection with the preferred embodiments.
The present invention is not limited to these. For example, it will be apparent to those skilled in the art that various modifications, improvements, combinations, and the like can be made.

[0062]

As described above, according to the present invention, it is possible to obtain an image recognition positioning apparatus which does not require much time for preparation for positioning and which can perform positioning with high accuracy.

[Brief description of the drawings]

FIG. 1 is a schematic configuration diagram of a screen printer using an image recognition alignment device of the present invention.

FIG. 2 is a plan view showing a screen mask and an image of a surface of a printed circuit board read by a camera of the screen printing machine shown in FIG. 1, and an inverted image of the image of the screen mask.

FIG. 3 is a flowchart for explaining image processing and solder printing processing of the screen printing machine shown in FIG. 1;

FIG. 4 is a plan view illustrating a surface image of a screen mask and a printed board subjected to half etching, and a cross-sectional view of the screen mask.

FIG. 5 is a plan view illustrating a surface image of a temporary dictionary area, a corresponding area, and an inverted area, and a graph illustrating a luminance distribution.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Printed circuit board 2 Table 3 Rail 4 Screen mask 5 Squeegee 6a, 6b Camera 7 Main control part 7a ROM 7b RAM 7c CPU 7d-7f Input / output part 8 Image monitor 9 Touch panel part 10a-10d Servo motor 11 Controller 12 Driver S1 Positioning Station S2 Printing station C1 Temporary dictionary area C2 Corresponding area C3 Inversion area

──────────────────────────────────────────────────続 き Continuing on the front page (72) Inventor Masashi Hirosawa 5-2-2 Koyodai, Ryugasaki-city, Ibaraki Pref. Hitachi Techno Engineering Co., Ltd. (72) Inventor Isao Abe 5-2-2 Koyodai, Ryugasaki-shi, Ibaraki Hitachi Techno Engineering Co., Ltd. Ryugasaki Plant (58) Field surveyed (Int.Cl. ⁶ , DB name) B41F 15/08 303 B41F 15/26 B41F 15/34-15/36 H05K 3/12 610 H05K 3/34 505 H05K 13/04 H05K 13/08 G01B 11/24

Claims (5)

(57) [Claims] An image data of a surface of a substrate to be processed and a surface of a reference member serving as a reference to be aligned with the substrate to be processed are obtained, and the two image data are compared to obtain image data of the substrate to be processed. In the image recognition alignment method for performing alignment, reading an image of a dictionary area that is a part of the surface of the reference member and includes a pattern that can be a reference for alignment, creates regular image data, and stores it as temporary dictionary data Reading an image of a corresponding area on the surface of the processing target substrate corresponding to the dictionary area, and obtaining image data of the corresponding area; and comparing the light-dark relationship between the temporary dictionary data and the image data of the corresponding area. A comparing step, when the lightness / darkness relationship between the temporary dictionary data and the image data of the corresponding area matches, the temporary dictionary data is regarded as dictionary area data; When the relationship is an inversion relationship, storing image data obtained by inverting the brightness of the temporary dictionary data as dictionary area data; and reading an image of the corresponding area of the processing target substrate to form processing target image data; Aligning the processing target image data with the dictionary area data. 2. The method according to claim 1, wherein the comparing step obtains a luminance on a predetermined reference line of the dictionary area from the temporary dictionary data to obtain a normal luminance distribution. 2. A method according to claim 1, further comprising: obtaining luminance on a line corresponding to the line to obtain a luminance distribution of the corresponding area. 3. The comparing step of obtaining an inverted luminance distribution obtained by inverting the light-dark relationship of the normal luminance distribution; a step of adding the normal luminance distribution and the corresponding area luminance distribution; 3. The image recognition positioning method according to claim 2, further comprising a step of adding a luminance distribution and the corresponding area luminance distribution. 4. Obtaining image data of a surface of a substrate to be processed and a surface of a reference member serving as a reference for performing alignment of the substrate to be processed, performing image processing, and performing alignment of the substrate to be processed. In the image recognition positioning apparatus to be performed, image data of a dictionary area that is a part of the surface of the reference member and includes a pattern that can be a reference for alignment or image data obtained by inverting the light / dark relationship thereof is stored as a temporary dictionary area. Temporary dictionary storage means for storing, a corresponding area image data storage means for storing an image of a corresponding area on the surface of the processing target substrate corresponding to the dictionary area, and image data stored in the temporary dictionary storage means and Comparing means for comparing the light and dark relationship with the image data stored in the area image data storing means; and the temporary dictionary storing means based on a result of the comparing means. Setting means for using the stored image data or image data obtained by inverting the brightness of the stored image data as dictionary area data, using image data of the corresponding area of the substrate to be processed, and image data adopted as the dictionary area. An image recognition position adjusting device including a calculating means for performing position adjustment. 5. The image recognition positioning apparatus according to claim 4, wherein said recognition means includes a switch for approving the use of the image data stored in the temporary dictionary storage as dictionary area data.