TWI769485B - Optical detection system and detection method thereof - Google Patents

Abstract

The present invention relates to an optical detection system. The optical detection system includes an automatic control device, a light source and a control and detection module, wherein the automatic control device has an image sensor, and the control and detection module includes a path unit, a comparison unit and a display unit. First, the path information is calculated by the path unit as the moving path of the automatic control device, and then the user excludes those with a large detection angle in the moving path according to the path information, so as to generate the best moving path information, and then the user according to the path information. Optimal moving path information, each light source is turned on or off, and then the equipment is automatically controlled to move along the optimal moving path, image information is generated by the light sensor, and finally, the defects in the image information are identified by the comparison module. Generate the comparison image information, and display the comparison image information through the display. In this way, the defects existing on the object to be tested are detected, so as to achieve the purpose of detecting the defects and reducing the detection time.

Description

Optical detection system and detection method thereof

The present invention relates to a detection system, in particular to an optical detection system and a detection method thereof.

In recent years, in order to conform to the popular trend of vehicle styling design, the size of the rims has gradually increased. The standard rims equipped on commercial vehicles have changed from the previous 15 inches to 16 inches, and have a trend of developing towards 17 inches. The larger the rim, the heavier it will be. In the era of high oil prices that emphasizes energy saving and low fuel consumption, light alloy rims made of alloys such as aluminum or magnesium have gradually become the mainstream in the market.

Light alloy rims have many advantages. Taking a 13-inch diameter as an example, an aluminum alloy rim is about 11% lighter than a steel rim, and a 14-inch rim is about 22% lighter. The larger the wheel diameter, the greater the weight difference between the two. The rim is light in weight, and the inertial resistance driving the rotation of the rim is relatively small, which will greatly improve the user's control sensitivity and save a little fuel consumption. In addition, taking the aluminum alloy rim as an example, its heat transfer performance is good, which helps to ventilate and dissipate heat, which can improve the life of the tire and reduce the risk of tire blowout.

However, the disadvantage of using light alloy rims is that the elongation of the alloy material is usually lower than that of steel, resulting in a poor ability to allow deformation of the light alloy rim, and the poor quality of the light alloy rim is prone to the risk of fracture. On the other hand, due to the complex manufacturing process, including material composition, casting technology, mold design, heat treatment process, cutting and painting, etc., it is easier to cause problems due to human negligence. Therefore, how to accurately identify and detect defects on light alloy rims is one of the problems that R&D personnel should solve.

Therefore, the inventors of the present invention came to the present invention after observing the above-mentioned defects.

The object of the present invention is to provide an optical inspection system, which can generate the corresponding optimal moving path information according to the structure of the object to be tested, and can adjust the light source according to the optimal moving path to detect defects on the surface of the object to be tested, and Significantly reduces detection time.

In order to achieve the above object, the present invention provides an optical detection system, which includes: an automatic control device, which is arranged around an object to be measured, the automatic control module has an image sensor, the image sensor photographing the object to be tested and generating a plurality of image information; a plurality of light sources, which surround the object to be tested, each of the light sources is activated or deactivated according to an optimal moving path information of the automatic control device; and a control detection A module, which is electrically connected with the automatic control device and the light sources, the control and detection module includes a path unit, a comparison unit and a display unit; wherein, the path unit is directed to the object to be tested. The structure is to calculate a path information, and the path information is used as the moving path of the automatic control device; the comparison unit is electrically connected with the path unit, and the comparison unit stores a plurality of defect image information, the comparison unit The pair unit receives the image information generated by the image sensor, and identifies the defects existing in the image information by the defect image information, so as to generate a plurality of comparison image information; and the display unit, which is Electrically connected with the comparison unit, the comparison unit transmits the comparison image information to the display unit, and the display unit displays the comparison image information or the image information.

Preferably, according to the optical inspection system of the present invention, the automatic control devices can use one of a three-axis robot arm and a multi-axis robot arm.

Preferably, according to the optical detection system of the present invention, the control detection module can be one of a computer, a server and a smart phone.

Preferably, according to the optical detection system of the present invention, the image sensor can be one of an industrial camera and a high-speed camera.

Preferably, according to the optical detection system of the present invention, the control detection module is one of a computer, a server and a smart phone.

Preferably, according to the optical detection system of the present invention, the control detection module further includes a setting unit, and the setting unit is used for setting the structure of the object to be tested.

Preferably, according to the optical detection system of the present invention, the comparison module filters the noise in the image information through Gaussian Blur and Binarization, so as to improve the identification of the image information The accuracy of the existing flaws.

Preferably, according to the optical detection system of the present invention, the comparison module is combined with a convolutional neural network to identify defects existing in the image information.

Preferably, according to the optical inspection system of the present invention, the comparison unit can respectively identify two kinds of defects: dirty particles and paint scratches.

Preferably, according to the optical detection system of the present invention, the comparison image information generated by the comparison unit is marked with a first warning pattern at the dirty particle, and a first warning pattern is marked at the scratch of the paint. The second warning pattern.

Furthermore, in order to achieve the above-mentioned object, the present invention is based on the above-mentioned optical detection system, and further provides a detection method for implementing the above-mentioned optical detection system, which comprises: a simulation step, the optical detection system is based on the structure of the object to be measured. , the path information is calculated by the path unit, and the path information is used as the moving path of the automatic control device; in a correction step, the user eliminates the detection of large amplitudes in the moving path of the automatic control device according to the path information angle, in order to shorten the detection time and generate the optimal movement path information of the automatic control device; in a calibration step, the user activates or deactivates each of the light sources according to the optimal movement path information to obtain The image information is relatively clear; a photographing step, the automatic control device moves according to the optimal moving path information, and uses the image sensor to photograph the object to be tested to generate the image information; a comparison step, comparing The pair unit receives the image information generated by the image sensor, and identifies the defects existing in the image information by the defect image information, so as to generate the comparison image information; and a display step, the The comparison unit transmits the comparison image information to the display unit, and the display unit displays the comparison image information.

Preferably, wherein, the warning method further includes a marking step, the marking step is between the comparing step and the displaying step, and the first warning pattern is marked at the dirty particle through the comparing unit, and The second warning pattern is marked on the scratched part of the paint.

To sum up, the optical detection system and the detection method provided by the present invention mainly utilize the optical detection system of the present invention and the detection method thereof, and can generate the corresponding optimal moving path information according to the structure of the object to be tested, and can The optimal moving path adjusts the light source to detect defects on the surface of the object to be tested, and greatly reduces the detection time. In this way, the present invention will not be affected by the structure of the object to be tested, and can quickly and comprehensively detect the surface of the object to be tested. .

In order for those skilled in the art to understand the purpose, features and effects of the present invention, the present invention is described in detail as follows by means of the following specific embodiments and in conjunction with the accompanying drawings.

The embodiments of the present invention will be described in more detail below with reference to the drawings and component symbols, so that those with ordinary knowledge in the technical field can implement them accordingly after studying the description.

However, the present invention is not limited to the embodiments disclosed herein, but will be implemented in various forms.

The following embodiments are provided only as examples, so that those having ordinary skill in the art can fully understand the disclosure of the present invention and the scope of the disclosure of the present invention.

Accordingly, the present invention should be limited only by the scope of the appended claims.

In the drawings for describing various embodiments of the present invention, the shapes, sizes, ratios, numbers, etc. shown are merely exemplary, and the present invention is not limited thereto.

In this specification, the same reference numerals generally refer to the same elements.

Any reference to the singular may include the plural unless expressly stated otherwise.

Please refer to FIG. 1 to FIG. 4 . FIG. 1 is a schematic diagram of an optical detection system according to a first embodiment of the present invention. As shown in FIG. 1 , the optical detection system 100 according to the present invention includes: an automatic control device 10 , a control detection module 20 , and a light source 30 .

Specifically, in this embodiment, the object to be tested 200 is a wheel rim, and its material can be one or a combination of iron, aluminum and magnesium, but the present invention is not limited thereto.

The automatic control device 10 is disposed around the object to be tested 200 , and the automatic control device 10 has an image sensor 11 . The image sensor 11 captures the object to be tested 200 and generates complex image information 111 .

Specifically, the automatic control device 10 according to the present invention may be one of a three-axis robot arm and a multi-axis robot arm, but the present invention is not limited thereto. The automatic control device 10 is electrically connected with the control and detection module 20 , and receives the command of the control and detection module 20 to control and move, so that the image sensor 11 on the automatic control device 10 can completely photograph the surface of the object to be tested 200 .

Specifically, the image sensor 11 according to the present invention may be one of an industrial camera and a high-speed camera, but the present invention is not limited thereto. It should be further explained that, compared with using a general camera, the advantages of using an industrial camera are high stability, easy installation, stable structure and not easy to be damaged, and a long continuous working time. However, the disadvantage is that the operation cost is greatly increased and the operation time is long.

Please refer to FIG. 2 and FIG. 3 , FIG. 2 is a schematic diagram of the arrangement position of the optical detection system according to the first embodiment of the present invention, and FIG. 3 is a schematic diagram of the structure of the optical detection system according to the first embodiment of the present invention. The control and detection module 20 according to the present invention is electrically connected with the automatic control device 10 and the light source 30 . The control and detection module 20 includes a path unit 21 , a comparison unit 22 and a display unit 23 .

Specifically, the control and detection module 20 according to the present invention may be one of a computer, a server and a smart phone, but the present invention is not limited thereto.

The path unit 21 calculates the path information 211 (not shown) as the moving path of the automatic control device 10 according to the structure of the object to be tested 200 . When the path information 211 is used as the moving path of the automatic control device 10 , it is guaranteed that The image sensor 11 on the automatic control device 10 completely captures the surface of the object to be tested 200 .

It should be further explained that the path information 211 is not the optimal moving path of the automatic control device 10, and some of the movements may include a large detection angle, which will result in a longer detection time. Therefore, the optical system according to the first embodiment of the present invention In the detection system 100, after the path unit 21 calculates the path information 211 as the moving path of the automatic control device 10, the user can obtain the optimal moving path by removing the path information with a large detection angle according to the path information 211. The information 212 is used as the moving path of the automatic control device 10 , which effectively reduces the detection time of the optical detection system 100 .

Please refer to FIG. 2 , in conjunction with FIG. 5 , the comparison unit 22 is electrically connected to the path unit 21 , and the comparison unit 22 stores a plurality of defective image information 221 (not shown), and the comparison unit 22 The image information 111 generated by the image sensor 11 is received, and the defects existing in the image information 111 are identified by the defect image information 221 to generate a plurality of comparison image information 222 .

Specifically, according to the defect image information 221 according to the first embodiment of the present invention, the defects may include impurities, bumps, black spots, cotton wool, shrinkage holes, dents, wear marks, scratch lines, scratches, bumps, and different colors , knife marks, lack of meat, bristle, chipping paint, flowing paint, thin spraying, high-gloss silver difference, etc., all of the above are various manufacturing errors generated in various stages of rim production, but the present invention is not limited to this.

The display unit 23 is electrically connected to the comparison unit 22, the comparison unit 22 transmits the comparison image information 222 to the display unit 23, and the display unit 23 displays the comparison image information 222 or the images Information 111. Specifically, the display unit 23 according to the present invention may be a liquid crystal display, a light emitting diode display or an organic light emitting diode display, but the present invention is not limited thereto.

Please refer to FIG. 4 , in conjunction with FIG. 3 . FIG. 4 is a schematic diagram of the arrangement position of the light source according to the first embodiment of the present invention. In this embodiment, the light sources 30 are arranged around the object to be tested 200, and the specific number of the light sources 30 is 7, however, the present invention is not limited to this, and the user can increase or decrease the number of the light sources 30 according to requirements, and The light source 30 is electrically connected to the control and detection module 20 . Specifically, the light source 30 according to the present invention may use one or a combination of light emitting diodes and organic light emitting diodes, but the present invention is not limited thereto.

It should be further explained that, as mentioned above, according to the optical detection system 100 of the present invention, the optimal moving path information 212 generated according to the structure of the object to be tested 200 is used as the moving path of the automatic control device 10. In this implementation In the example, since the object to be tested 200 is made of metal, its surface is shiny and easy to reflect light, so that when the automatic control device 10 moves and shoots the surface of the object to be tested 200 at different angles, the image sensor 11 cannot take a clear picture. Therefore, it is difficult for the comparison unit 22 to identify defects, resulting in incorrect detection results or an increase in the number of detections.

Therefore, in this embodiment, the user can turn on or off each of the light sources 30 individually according to the optimal movement path information 212 as the movement path of the automatic control device 10 to reduce the reflection of light on the surface of the object to be measured. This ensures that the image sensor 11 captures clear image information 111 for the comparison unit 22 to identify the defects on the image information 111, so as to improve the detection accuracy of the optical inspection system 100 according to the present invention.

Please refer to FIG. 5 , which is a schematic flowchart of a process of identifying image information by the comparison unit according to the first embodiment of the present invention. The comparison unit 22 first performs Gaussian filtering on the image information 111 , and replaces the value of each pixel in the image information 111 with the weighted average value of the pixels in the image information 111 , thereby reducing the drastic change in the gray level of the image information 111 and thereby reducing the However, as shown in FIG. 5 , the edges and contours of the image information 111 are bound to be blurred after Gaussian filtering. Then, the comparison unit 22 binarizes the image information 111, and sets the image information 111 that is larger than a predetermined threshold. The pixel grayscale of the grayscale value is set as the grayscale maximum value, and the pixel grayscale less than the preset critical grayscale value is set as the grayscale minimum value, so as to realize binarization and filter the noise in the image information 111 , so as to improve the accuracy of the comparison unit 22 in identifying the defects existing in the image information 111 .

In order to further understand the structural features of the present invention, the application of technical means and the expected effect, the usage mode of the present invention is described here.

Please refer to FIG. 6 and FIG. 7 , in conjunction with FIG. 3 to FIG. 5 , FIG. 6 is a schematic diagram of the identification result of the optical detection system according to the first embodiment of the present invention, and FIG. 7 is a diagram illustrating the execution of the first embodiment of the present invention. The flow chart of the steps of the detection method of the optical detection system. The present invention is based on the above-mentioned optical detection system 100, and further provides a detection method of the optical detection system 100, which includes the following steps:

In the simulation step S1, the optical detection system 100 calculates the path information 211 through the path unit 21 according to the structure of the object to be tested 200. The path information 211 can be used as the moving path of the automatic control device 10, and then performs the correction step S2.

In the correction step S2, the user removes those with a large detection angle according to the path information 211, thereby obtaining the optimal moving path information 212 as the moving path of the automatic control device 10 to shorten the detection time, and then execute the correction step S3.

In the calibration step S3, the user activates or deactivates each of the plurality of light sources 30 respectively according to the optimal moving path information 212 generated in the calibration step S2, so as to ensure that the image sensor 11 can capture the clear image information 111, and then The photographing step S4 is performed.

In the photographing step S4, the automatic control device 10 moves according to the optimal moving path information 212 generated in the correcting step S2, and uses the image sensor 11 to photograph the surface of the object to be tested 200 to generate clear image information 111, and performs a comparison. to step S5.

In the comparison step S5, the image information 111 generated by the image sensor 11 is received by the comparison unit 22, and the image information 111 is identified by the defective image information 221 stored in the comparison unit 22. Existing flaws are detected, and complex comparison image information 222 is generated, and then the display step S6 is performed.

In the display step S6, the comparison image information 222 is transmitted to the display unit 23 by the comparison unit 22, and the display unit 23 displays the comparison image information 222.

For example, please refer to FIG. 6 , in conjunction with FIG. 3 to FIG. 7 , FIG. 6 is a schematic diagram of the identification result of the optical detection system according to the first embodiment of the present invention. According to the optical detection system 100 of the present invention, firstly, the simulation step S1 is performed, and the path information 211 is calculated by the path unit 21; then, the correction step S2 is performed, and the user removes those with a large detection angle according to the path information 211, thereby The optimal movement path information 212 is obtained as the movement path of the automatic control device 10; then the calibration step S3 is executed, and the user activates or deactivates the light sources 30 according to the optimal movement path information 212 generated in the calibration step S2. Each; then perform the photographing step S4, the automatic control device 10 moves according to the optimal moving path information 212 generated in the correcting step S2, and uses the image sensor 11 to photograph the surface of the object to be tested 200; After the photographing is completed, enter the comparison In step S5, the comparison unit 22 identifies the defects existing in the image information 111, and generates a plurality of comparison image information 222; finally, the display step S6 is performed, and the comparison unit 22 uses the comparison image information 222. It is transmitted to the display unit 23 , and the display unit 23 displays the comparison image information 222 . .

It should be further noted that, in the present embodiment, in the comparison step S5 , the comparison unit 22 first performs Gaussian filtering on the image information 111 , and replaces the weighted average of the pixels in the image information 111 with the weighted average value of the pixels in the image information 111 . However, as shown in FIG. 5 , after Gaussian filtering, the edges and contours of the image information 111 are bound to be blurred; then the comparison unit 22 aligns the images The information 111 is binarized, and the pixel gray level greater than the preset critical gray value in the image information 111 is set as the gray maximum value, and the pixel gray level smaller than the preset critical gray value is set as the gray minimum value, Therefore, binarization is realized and the noise in the image information 111 is filtered, thereby improving the accuracy of the comparison unit 22 in identifying the defects existing in the image information 111 .

Therefore, it can be known from the above description that the optical detection system 100 provided by the present invention and the detection method thereof can generate the optimal moving path information 212 for the structure of the object to be tested 200 during detection. The optimal moving path information 212 is matched with a suitable configuration of the light source 30 to accurately identify the defects existing on the surface of the object to be tested 200 . In this way, the optical inspection system 100 provided according to the present invention will not be affected by the structure of the object to be tested 200 . , which can quickly and comprehensively detect defects on the surface of the object to be tested 200 .

Please refer to FIG. 8 and FIG. 9 , FIG. 8 is a schematic diagram of the identification result of the optical detection system according to the second embodiment of the present invention, and FIG. 9 is a flowchart illustrating the steps of executing the detection method of the optical detection system according to the second embodiment of the present invention . Compared with the first embodiment, the main difference between the second embodiment and the second embodiment is that the comparison unit 22 is further combined with a convolutional neural network (not shown) and matched with the defective image information 221, thereby improving the ratio The speed and accuracy of identifying defects existing in the image information 111 for the unit 22 . It needs to be further explained that the artificial neural network is a mathematical model or computational model that imitates the structure and function of the biological neural network, and the convolutional neural network further adds the concept of blocks to Locking the data type with regional properties, in this way, the operation performance of the comparison unit 22 can be greatly improved by using the convolutional neural network in combination. In the second embodiment, the comparison unit 22 can further identify two kinds of defects, dirty particles and paint scratches, respectively. Therefore, the comparison unit 22 can mark the first warning pattern 41 at the dirty particles and paint scratches. The second warning pattern 42 is marked there.

In this way, the second embodiment can not only achieve the effect of the first embodiment, but also can further identify and classify the types of defects and mark obvious marks at the defects. The comparison unit 22 can greatly improve the performance of Applicability and convenience of the optical detection system 100 according to the present invention.

Please refer to FIG. 9 in conjunction with FIG. 8 . FIG. 9 is a flow chart illustrating the steps of executing the warning method of the optical detection system according to the second embodiment of the present invention. Based on the optical detection system 100 of the second embodiment, the present invention further provides a detection method of the optical detection system 1, which includes the following steps:

Similar to step S1', the optical detection system 100 calculates the path information 211 through the path unit 21 according to the structure of the object to be tested 200, and the path information 211 can be used as the moving path of the automatic control device 10, and then executes the correction step S2'.

In the correction step S2', the user removes those with a large detection angle according to the path information 211, thereby obtaining the optimal movement path information 212 as the movement path of the automatic control device 10 to shorten the detection time, and then execute the correction step S3.

In the calibration step S3 ′, the user activates or deactivates each of the plurality of light sources 30 respectively according to the optimal moving path information 212 generated in the calibration step S2 ′, so as to ensure that the image sensor 11 can capture the clear image information 111 , and then execute the shooting step S4.

In the photographing step S4 ′, the automatic control device 10 moves according to the optimal moving path information 212 generated in the correction step S2 , and uses the image sensor 11 to photograph the surface of the object to be tested 200 to generate clear image information 111 , and execute Compare step S5'.

In the comparison step S5 ′, the image information 111 generated by the image sensor 11 is received by the comparison unit 22 , and the defective image information 221 stored in the comparison unit 22 is identified and matched with a convolutional neural network, In order to identify the defects existing in the image information 111, a plurality of comparison image information 222 is generated, and then the marking step S7' is performed.

In step S7 ′, the comparison unit 22 and the convolutional neural network are used to identify two kinds of defects, dirty particles and paint scratches, respectively. The comparison unit 22 marks the first place on the dirty particles on the comparison image information 222 . The warning pattern 41 is marked, and the second warning pattern 42 is marked on the scratched part of the paint, and then the display step S6' is performed.

In the display step S6', the comparison unit 22 transmits the comparison image information 222 to the display unit 23, and the display unit 23 displays the comparison image information 222.

For example, please refer to FIG. 8 in conjunction with FIG. 3 , FIG. 4 and FIG. 9 . According to the optical detection system 100 of the present invention, the pseudo-step S1 ′ is first performed, and the path information 211 is calculated by the path unit 21 ; then the correction step S2 ′ is performed, and the user removes the detection angle with a large magnitude according to the path information 211 . , so as to obtain the optimal moving path information 212 as the moving path of the automatic control device 10 ; after that, the calibration step S3 ′ is executed, and the user activates or deactivates the light sources respectively according to the optimal moving path information 212 generated in the modification step S2 . 30; after that, the photographing step S4' is performed, the automatic control device 10 moves according to the optimal movement path information 212 generated in the correcting step S2', and the surface of the object to be tested 200 is photographed by the image sensor 11; photographing After completion, enter the comparison step S5 ′, and use the comparison unit 221 and the convolutional neural network to identify the defects existing in the image information 111 , and generate a complex number of comparison image information 222 ; and then after the identification is completed Carrying out the marking step S7 ′, by combining the convolutional neural network with the comparison unit 22 to identify two kinds of defects, dirty particles and paint scratches, respectively, and the comparison unit 22 marks the dirty particles on the comparison image information 222 The first warning pattern 41 is marked with the second warning pattern 42 at the scratched part of the paint; finally, the displaying step S6 ′ is executed to compare the image information 222 including the first warning pattern 41 and the second warning pattern 42 , The comparison image information 222 is transmitted to the display unit 23 by the comparison unit 22 , and the display unit 23 displays the comparison image information 222 .

It is worth mentioning that although the above description is based on the identification of dirt particles and paint scratches by the comparison unit 22, the present invention is not limited to this, such as impurities, bumps, black spots, cotton wool, shrinkage holes, and concave holes. , wear marks, scratches, scratches, bumps, discoloration, knife marks, lack of flesh, burrs, cracked paint, flowing paint, thin spray, high-brightness silver difference, etc., when the comparison unit 22 stores enough defective images When the information 221 is combined with a convolutional neural network, the comparison unit 22 can further identify the above-mentioned defects or their combination individually, and mark different warning patterns one by one to facilitate the user to identify.

Thereby, the present invention has the following implementation effect and technical effect:

First, based on the optical detection system 100 of the present invention and the detection method provided by the present invention, it can generate the corresponding optimal moving path information 212 according to the structure of the object to be tested 200, and can The optimal moving path 212 adjusts the light sources 30 to detect the defects on the surface of the object to be tested 200 and greatly reduces the detection time.

Second, by combining the comparison unit 22 with the convolutional neural network, the present invention can identify and classify the types of defects and mark the defects with obvious marks, which greatly improves the applicability and convenience of the optical inspection system 100 according to the present invention. sex.

The embodiments of the present invention are described above by means of specific embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification.

Although the present invention has been described with reference to the embodiments depicted in the accompanying drawings, these are merely embodiments and it will be understood by those skilled in the art that various changes and modifications may be made thereto. However, these changes and modifications should not depart from the scope of protection of the present invention. Therefore, the protection scope of the present invention must be limited to the appended claims.

100: Optical Inspection System 10: Automatic control equipment 11: Image sensor 111: Video Information 20: Control detection module 21: Path unit 211: Path information 212: Best moving path information 22: Comparison unit 221: Flawed image information 222: Compare image information 23: Display unit 30: Light source 41: The first warning pattern 42: Second warning pattern 200: Object to be tested S1: Simulation step S2: Correction steps S3: Calibration step S4: Shooting steps S5: comparison step S6: Display steps S1': Simulation step S2': Correction step S3': Calibration step S4': Shooting steps S5': comparison step S6': Display steps S7': marking step

1 is a schematic diagram of an optical detection system according to a first embodiment of the present invention; FIG. 2 is a schematic diagram of the setting position of the optical detection system according to the first embodiment of the present invention; FIG. 3 is a schematic diagram of the structure of the optical detection system according to the first embodiment of the present invention; FIG. 4 is a schematic diagram of the arrangement position of the light source according to the first embodiment of the present invention; 5 is a schematic flowchart of a process of identifying image information by the comparison unit according to the first embodiment of the present invention; 6 is a schematic diagram of the identification result of the optical detection system according to the first embodiment of the present invention; 7 is a flow chart illustrating the steps of implementing the detection method of the optical detection system according to the first embodiment of the present invention; 8 is a schematic diagram showing the identification result of the optical detection system according to the second embodiment of the present invention; FIG. 9 is a flowchart illustrating the steps of implementing the detection method of the optical detection system according to the second embodiment of the present invention.

100: Optical Inspection System

10: Automatic control equipment

11: Image sensor

20: Control detection module

21: Path unit

22: Comparison unit

23: Display unit

30: Light source

Claims (10)

An optical detection system includes: an automatic control device, which is arranged around an object to be measured, the automatic control module has an image sensor, and the image sensor captures the object to be measured and generates a plurality of image information; a plurality of light sources, the light sources are arranged around the object to be tested, each of the light sources is activated or deactivated according to an optimal moving path information of the automatic control device; and a control detection module, which is Electrically connected with the automatic control device and the light sources, the control and detection module includes a path unit, a comparison unit and a display unit; wherein, the path unit calculates a path information, the path information is used as the moving path of the automatic control device; the comparison unit is electrically connected with the path unit, the comparison unit stores plural defective image information, and the comparison unit receives the image The image information generated by the sensor, and identifying the defects existing in the image information by the defect image information, so as to generate a plurality of comparison image information; and the display unit, which is related to the comparison unit electrically connected, the comparison unit transmits the comparison image information to the display unit, and the display unit displays the comparison image information and one or a combination of the image information; The movement path information is based on the path information to exclude those with a large detection angle in the movement path of the automatic control device, and generate the optimal movement path information of the automatic control device. The optical inspection system according to claim 1, wherein the automatic control device is one of a three-axis robot arm and a multi-axis robot arm. The optical detection system of claim 1, wherein the image sensor is one of an industrial camera and a high-speed camera. The optical detection system according to claim 1, wherein the control detection module is one of a computer, a server and a smart phone. The optical inspection system according to claim 1, wherein the comparison unit filters the noise in the image information through Gaussian filtering and binarization, so as to improve the accuracy of identifying defects existing in the image information. The optical inspection system as claimed in claim 1, wherein the comparison unit is combined with a convolutional neural network to identify defects existing in the image information. The optical inspection system according to claim 6, wherein the object to be tested is a wheel, and the defects existing on the image information include one or a combination of dirty particles and paint scratches. The optical detection system as claimed in claim 7, wherein the comparison image information generated by the comparison unit is a first warning pattern marked on the dirty particles and scratched on the paint. The wound is marked with a second warning pattern. A detection method using the optical detection system described in claim 1, which comprises the following steps: a simulation step, the optical detection system calculates the path information through the path unit according to the structure of the object to be tested, and the The path information is used as the moving path of the automatic control device; in a correction step, the user excludes those with a large detection angle in the moving path of the automatic control device according to the path information, so as to shorten the detection time and generate the automatic control the optimal movement path information of the device; a calibration step, the user activates or turns off each of the light sources according to the optimal movement path information, so as to obtain the clearer image information; a photographing step, the The automatic control device moves according to the optimal moving path information, and generates the image information by photographing the object to be tested by the image sensor; in a comparison step, the comparison unit receives the image sensor generated by the image sensor. and other image information, and identify the defects existing in the image information by the defect image information, so as to generate the comparison image information; and a display step, the comparison unit transmits the comparison image information to the the display unit, and the display unit displays the comparison image information. The detection method as claimed in claim 9, further comprising a marking step between the comparing step and the displaying step, wherein the first warning is marked at the dirty particle through the comparing unit pattern, and the second warning pattern is marked on the scratched part of the paint.

Images