TW202018582A - Method for automatically capturing optical images under composite detection conditions using an image capturing device and a light source to improve detection efficiency - Google Patents

Abstract

The present invention discloses a method for automatically capturing optical images under composite detection conditions, wherein an image capturing device and a light source are interactively operated to perform an optical image capturing operation of an object to be tested, so as to effectively obtain detection results of good/inferior products under the irradiation of a light of different wavebands, thereby improving the detection efficiency.

Description

Automatic detection method of optical image with combined detection conditions

The invention relates to a detection method, in particular to a method for automatically capturing optical images through compound detection conditions.

The products completed on the production line were controlled by manual inspection in the early stage. Due to the limitations of the human eye's visual experience, there will be subjective cognitive differences, such as the inability to determine in detail the defects in fast-moving, micron to nanometer-sized fine-size products, or the external inspection environment and the special conditions of the product itself. The limitation of the visible region of the spectrum makes it impossible to present the defects in the product accurately in the human eye. Later, the quality control operation was developed by manually matching the instruments. However, due to the negligence of the inspector's physiological state or improper operation of the instrument, problems of missed inspections often occur.

Nowadays, thanks to the advancement of technology, the era of machine vision inspection methods replacing human eye vision inspection has arrived. The industry in various fields has begun to use automatic inspection methods to replace manual inspections. On the one hand, the automatic detection method can not only reduce a lot of manpower, but also overcome most of the detection conditions, and improve the detection accuracy and detection speed together, thereby improving the defects caused by the conventional use of manpower detection. Quite objective and universal.

For the detection of flat products, such as printed circuit board (PCB), display panel (Display Panel) or glass (Glass), etc., there are those in the industry who use machine vision, non-contact optical technology for inspection . Taking printed circuit boards as an example, in this field, automatic optical detection is a common representative method in the manufacturing process. It is a common practice to illuminate the printed circuit board with light sources with different directions or different light intensities to produce color gradation of the image Then, the image is captured, and then the graphics and parameters of the qualified product in the data database are analyzed and compared with the captured image of the printed circuit board.

To undertake the previous stage, during the inspection of the printed circuit board, after being irradiated with light emitted from different intensities or different directions, only the gradation of the printed circuit board under the light can be obtained, but it cannot be obtained under other optical conditions. The identification information of defects that can be displayed. For example, applying reflected light can detect scratches on the printed circuit board, but cannot detect the presence of holes; applying penetrating light can detect holes on the printed circuit board, and cannot detect whether it has scratches .

For the same reason, the printed circuit boards are irradiated with light sources in different directions one after another, and then the image acquisition is performed. Although the image analysis obtained is sufficient to identify the information of the defect, it takes a lot of time. For example, the reflected light is applied first, and then the scratches of the printed circuit board are scanned, followed by the penetrating light, and then the holes of the printed circuit board are scanned, which makes scanning and testing takes at least twice as long Time.

For this reason, in view of the problems derived from the above, the present inventors started to develop solutions based on the idea of improvement of the invention, and after a long time, the optical image automatic acquisition method with the composite detection conditions of the present invention was generated to Serve the public and promote the development of the industry.

An object of the present invention is to provide an optical image automatic acquisition method with compound detection conditions, which is adapted to capture an image of an object to be measured by an imaging device and a light source, and can be effectively identified by information presented by various color layers in the image data The flaws of the object to be tested further improve the accuracy and efficiency of the inspection results.

An object of the present invention is to provide an optical image automatic acquisition method with composite detection conditions, which is obtained by irradiating a test object with light of different wave bands and interacting with the function of the photosensitive element of the imaging device Image information can be used to clearly determine whether the object to be tested has defects.

In order to achieve the above-mentioned purposes and effects, the present invention discloses a method for automatically capturing an optical image with composite detection conditions, which includes: providing a detection platform; providing an imaging device, and locking an image area relative to the detection platform; Providing at least one light source, including at least two bands of light irradiating at least one side of the image area; an object to be measured enters the image area and is irradiated by the light rays, and the image capturing device performs image capturing to obtain the images including the bands Image data of light and the object to be tested, and the image data and the color separation image information of the flawless part of the object to be tested, or the same color separation image information of the flawless object to be tested of the object to be measured Compare and obtain a test result.

In an embodiment of the invention, it is also disclosed that the light source and the imaging device are disposed on the same side of the detection platform.

In one embodiment of the present invention, it is also disclosed that the image data includes image information of a red layer and a green layer respectively, and the image information of the red layer and the green layer and the flawless part of the object to be measured are individually The color separation image information, or the color separation image information of the flawless test object that is the same as the test object is compared, and the test result is obtained.

In one embodiment of the present invention, it also discloses that the light rays of these wave bands are a red wave band and a green wave band.

In one embodiment of the present invention, it is also disclosed that the image data includes image information of a red layer and a blue layer, respectively, and the image information of the red layer and the blue layer and the object to be measured have nothing. The color separation image information of the defective part, or the color separation image information of the non-defective test object that is the same as the test object is compared, and the test result is obtained.

In one embodiment of the present invention, it also discloses that the light rays of these wave bands are a red wave band and a blue wave band.

In an embodiment of the present invention, it is also disclosed that the image data includes image information of a green layer and a blue layer, respectively, and the image information of the green layer and the blue layer and the object to be measured have nothing. The color separation image information of the defective part, or the color separation image information of the non-defective test object that is the same as the test object is compared, and the test result is obtained.

In one embodiment of the present invention, it also discloses that the light rays of these wave bands are a green wave band and a blue wave band.

In one embodiment of the present invention, it is also disclosed that the image data includes image information of a red layer, a green layer and a blue layer respectively, and the images of the red layer, the green layer and the blue layer are individually The information is compared with the color separation image information of the flawless part of the test object, or the color separation image information of the same flawless test object, and the test result is obtained.

In an embodiment of the present invention, it also discloses that the light rays of these wave bands are a red wave band, a green wave band and a blue wave band.

In an embodiment of the invention, it also discloses that the image capturing device is a camera mechanism or a camera mechanism.

In one embodiment of the present invention, it is also disclosed that the light source is disposed on one side of the detection platform, and the imaging device is disposed on the other side of the detection platform.

In order for your reviewing committee to have a better understanding and understanding of the features and effects of the present invention, only the examples and detailed explanations are as follows:

As mentioned in the prior art, there are conventional methods for performing automatic optical detection on the object to be tested, and there is a problem that the images under different optical conditions cannot be simultaneously captured and compared. Therefore, the present invention proposes a method for automatically capturing optical images with complex detection conditions, which solves the traditional problems to be improved, so as to improve the accuracy and efficiency of detection results, and is described in detail below.

Here, a method for automatically capturing an optical image of a compound detection condition of the present invention is described. Please refer to the first figure, which is a flowchart of a method for automatically capturing an optical image of a compound detection condition of the present invention. As shown in the figure, the steps of the present invention include:

Step S10: Provide a detection platform;

Step S12: Provide an imaging device to lock an image area relative to the detection platform;

Step S14: Provide at least one light source, including light of at least two wavelength bands illuminating at least one side of the image area;

Step S16: an object to be tested enters the image area and is irradiated by the light rays, and the image capturing device performs image capturing to obtain image data including the light rays of the wavelength bands and the object to be tested; and

Step S18: Compare the image data with the color separation image information of the flawless part of the test object, or the color separation image information of the flawless test object that is the same as the test object, and obtain a test result.

The following description refers to the components of the system for achieving the method of the invention. Please refer to FIGS. 2A and 2B, which are schematic diagrams 1 and 2 of the optical image automatic acquisition system of the composite detection conditions of the present invention. As shown in the figure, the optical image automatic capturing system 1 of the present invention with composite detection conditions includes: an image capturing device 10 and at least one light source 12, the image capturing device 10 is disposed on one side of a detection platform 9 and is opposite to the detection platform 9 and lock an image area 100. The light source 12 can be disposed on the same side of the inspection platform 9 as the imaging device 10 (as shown in FIG. 2A), or the light source 12 can be disposed on one side of the inspection platform 9, and the imaging device 10 can be disposed on the other side of the inspection platform 9 (As shown in the second image B), it includes at least two wavelengths of light L1, L2 illuminating at least one side of the image area 100. The image capturing device 10 captures images in the image area 100 to obtain image data 102.

The above-mentioned imaging device 10 is a camera mechanism or camera mechanism.

As shown in the second figure A, the above-mentioned light source 12 can be composed of lamps with a plurality of light bands, and can emit light L1, L2 of more than two wave bands (colors) at a time according to the inspection needs of the inspection personnel One test object 8 in the image area 100. As shown in FIG. 2B, multiple light sources 12 are provided on the other side of the detection platform 9, and each light source 12 emits a band of light L1, L2, L3 to illuminate the object 8 under test; The light in the band can be the visible band that the human eye can receive, or the invisible band that can be read, analyzed, and compared by the detection software.

The above detection software does not limit what kind of software it is, as long as it can analyze the various color layers of the image data 102, for example: Adobe Photoshop CC.

The above-mentioned object to be measured 8 may be a printed circuit board, a display panel or glass.

Referring back to the first figure and the second figure A, the following describes the flow of the method for automatically capturing the optical image of the compound detection condition of the present invention. When performing the automatic optical detection operation on the object 8 to be tested, steps S10 to S18 will be performed. First, the detection platform 9, the imaging device 10, and the light source 12 have been positioned at the working position described in the second Figure A above. When the test object 8 enters the detection platform 9 via a conveyor belt (not shown) or a robot arm (not shown), the light L1 and L2 emitted by the light source 12 illuminate the test object 8 located in the image area 100 to take an image The device 10 takes an image of the object to be measured 8 in the image area 100 which is irradiated with light L1 and L2 and produces an image change. After that, the imaging device 10 captures the image data 102, and then the image data 102 and the color-separated image information of the flawless part of the object 8 or the color-separated image information of the flawless object to be tested 8 Compare. Thereafter, the test result is obtained, and it is known that the test object 8 that has been properly tested is a good product or a defective product with defects.

Please refer to the third figure, the fourth figure A and the fourth figure B together, which are the image data reference picture, the color separation image information reference picture 1 and the color separation image of the optical image automatic acquisition method of the composite detection condition of the present invention Refer to Figure 2 for information. Specifically, if the light source 12 emits a green band of light L1 and a blue band of light L2, as shown in the third figure, it is the image change appearance of the object 8 to be illuminated by the light source 12 and is also The image data 102 obtained by the image capturing device 10 in the image area 100. As shown in Figures 4A and 4B, the image data 102 is processed by the detection software to generate image information with a green layer (Figure 4A) and image information with a blue layer (Fourth) Figure B). Because the light L1 in the green band and the light L2 in the blue band illuminate the object 8, the photosensitive element (not shown) of the imaging device 10 has a difference in sensitivity to different light L1 and L2. That is, when the light L1 of the green band illuminates the object 8 to be measured, the green part of the color of the image data 102 has a richer expression; similarly, when the light L2 of the blue band illuminates the object 8 to be tested, the color of the image data 102 The blue part has richer performance. Therefore, after the image data 102 is subjected to color separation processing, the image information of each color layer is obviously different, and it can be the same as the color separation image information of the flawless part of the test object 8 or the same as the flawless treatment of the test object 8 Recognize and compare the color separation image information of the measured object.

Following the previous stage, as shown in Figure 4A, the image information displays the green band layer of the image data 102 with low-brightness grayscale optical conditions, so that it can be clearly discriminated whether the brighter blocks are defective. If the defect marked by the red arrow in the circled selection of the thick line in the four A picture, it can be used to clearly distinguish the defect from the other parts of the test object 8, but the thick in the four A picture The defects marked by the blue arrows in the selection of the line circle are difficult to identify because they are located in dark areas. Similarly, as shown in Fig. 4B, the image information displays the blue band layer of the image data 102 with high-brightness grayscale optical conditions, so that it can clearly distinguish whether the originally darker block in the green band layer exists defective. If the defect marked by the blue arrow in the circle selection of the thick line in the four B picture, it is obvious that the defect is different from the other parts of the object under test 8, but in the four B picture The defect marked by the red arrow in the thick circle circle selection is originally located in the bright block. In the case of increased brightness, it is difficult to distinguish clearly due to light pollution. Therefore, the optical image automatic capturing method of the present invention can simultaneously visualize the defects/flaws of different appearances of the object to be tested, which is convenient for the inspection personnel and the inspection software to identify the quality of the object to be tested.

In order to reflect the color of the object to be measured 8 itself, the light band of the light source 12 can be changed accordingly. For example, the light source 12 may be light L1 emitting green band and light L2 in red band, light L2 in red band and light L3 in blue band, or light L1 in green band, light L2 in red band and light in blue band L3. In addition, the intensity of the three light rays of the green band light L1, the red band light L2, and the blue band light L3 can be arranged and combined in different, partially the same, or the same manners. According to the wavelength and intensity of the light emitted by the light source 12, the corresponding color layer can be divided to facilitate the analysis and comparison of defects by the inspection personnel and the inspection software.

In summary, the method for automatically capturing optical images of the composite detection condition of the present invention, through the interaction of the light-sensing element of the image capturing device and the light source to irradiate the test object with different wavelengths, simultaneously obtains the image information of each color layer , You can obviously and efficiently judge whether there is a defect in the test object. Here, the method for automatically capturing optical images of the present invention has effectively improved the defects caused by the traditional automatic optical detection of the test object.

1: Optical image automatic acquisition system 8: object to be measured 9: detection platform 10: imaging device 100: image area 102: image data 12: light source L1: light L2: light L3: light S10: step S12: step S14: Step S16: Step S18: Step

The first picture: it is the flow chart of the method for automatically capturing the optical image of the compound detection condition of the present invention; the second picture A: it is the schematic diagram 1 of the system for automatically detecting the optical image of the compound detection condition of the invention; the second B Figure: It is the second schematic diagram of the optical image automatic acquisition system of the compound detection condition of the present invention; Third Figure: It is the image data reference diagram of the optical image automatic acquisition method of the compound detection condition of the present invention; : It is the color separation image information reference figure 1 of the optical image automatic acquisition method of the composite detection condition of the present invention; and FIG. 4B: it is the color separation image of the optical image automatic acquisition method of the composite detection condition of the present invention Refer to Figure 2 for information.

S10: Step

S12: Step

S14: Step

S16: Step

S18: Step

Claims (12)

A method for automatically capturing an optical image with composite detection conditions, comprising: providing a detection platform; providing an image capturing device that locks an image area relative to the detection platform; providing at least one light source, including at least two wavebands of light illuminating the image At least one side of the area; an object to be tested enters the image area and is irradiated by the light rays, and the image capturing device performs image capturing to obtain image data including the light rays of the wavelength bands and the object to be tested; and the The image data is compared with the color separation image information of the flawless part of the test object, or the color separation image information of the flawless test object that is the same as the test object, and a test result is obtained. The method for automatically capturing an optical image of a composite inspection condition as described in item 1 of the patent application scope, wherein the light source and the imaging device are disposed on the same side of the inspection platform. The optical image automatic acquisition method of composite detection conditions as described in item 1 of the patent scope, wherein the image data respectively includes image information of a red layer and a green layer, and the images of the red layer and the green layer are individually The information is compared with the color separation image information of the flawless part of the test object, or the color separation image information of the same flawless test object, and the test result is obtained. The method for automatically capturing an optical image of a composite detection condition as described in item 1 or 3 of the scope of the patent application, wherein the light of these bands is a red band and a green band. The optical image automatic acquisition method of composite detection conditions as described in item 1 of the patent scope, wherein the image data respectively includes image information of a red layer and a blue layer, and the red layer and the blue layer are individually The image information is compared with the color separation image information of the flawless part of the test object, or the color separation image information of the flawless test object that is the same as the test object, and the test result is obtained. The method for automatically capturing an optical image of a composite detection condition as described in item 1 or 5 of the scope of the patent application, wherein the light rays of these bands are a red band and a blue band. The optical image automatic acquisition method of composite detection conditions as described in item 1 of the patent scope, wherein the image data respectively includes image information of a green layer and a blue layer, and the green layer and the blue layer are individually The image information is compared with the color separation image information of the flawless part of the test object, or the color separation image information of the flawless test object that is the same as the test object, and the test result is obtained. The method for automatically capturing an optical image of a compound detection condition as described in item 1 or 7 of the patent application scope, wherein the light rays of these bands are a green band and a blue band. The method for automatically capturing optical images with composite detection conditions as described in item 1 of the patent scope, wherein the image data includes image information of a red layer, a green layer, and a blue layer, and the red layer, The image information of the green layer and the blue layer is compared with the color separation image information of the flawless part of the test object, or the color separation image information of the flawless test object that is the same as the test object, and obtained The test result. The method for automatically capturing an optical image of a composite detection condition as described in item 1 or 9 of the patent application scope, wherein the light of these bands is a red band, a green band, and a blue band. The method for automatically capturing an optical image of a composite detection condition as described in item 1 of the patent scope, wherein the image capturing device is a photographic mechanism or a photographic mechanism. The method for automatically capturing an optical image of a composite detection condition as described in item 1 of the patent scope, wherein the light source is provided on one side of the detection platform, and the imaging device is provided on the other side of the detection platform.

Images