スカイロジック List of Products and Services

The electronic components manufacturer has considered our character recognition for product management. Sample images have been sent. The inspection software called EasyInspector, which you inquired about, is used by customers in the automotive parts and electronic circuit board sectors, making up half of our clientele, and it is also utilized by a wide range of industries for tasks such as assembly verification and inspection of minute dirt on products. 【Inspection Settings and Results】 As shown in the red box in the left image, reading was possible with the EasyInspector "OCR" function in a well-lit environment. If the lighting conditions are improved to uniformly illuminate the entire area, it may be possible to read everything at once. In the current lighting environment, there were misreads with the standard OCR function, such as reading S as 3. However, it was possible to read using the OCR Pro function. 【Software Used】 Software used: EasyInspector710 (formerly EasyInspector) The current 'EasyInspector2' RD (ReaDing) package can perform inspections with 【OCR (character recognition)】 and 【machine learning OCR】.

This is an inquiry from an electronic component manufacturer primarily engaged in the production of printed circuit boards. They have requested a simple verification of metal etching processing. Inspection of fine defects can be conducted meticulously using enlarged images. Our company has contracts with agents in Malaysia and China, and sales are also possible. We have also received inquiries from Japanese manufacturers whose products are manufactured at overseas offices. 【Inspection Settings and Results】 Using EasyInspector's "Comparison with Master Image" function, we focused on the smallest defect among the 12 workpieces you sent. We divided the inspection frame into multiple sections and performed shift correction for each to minimize the detection of noise. However, the inspection time takes about 15 seconds. To shorten the inspection cycle, we suggest using multiple cameras or lowering the resolution. However, reducing the resolution may affect the detection capability (stability) of extremely small defects.

This time, we have a verification project from a trading company we have been dealing with for some time. It involves measuring the connector's opening. The end user has requested a stricter tolerance judgment this time. The accuracy of the inspection is determined by how well we can capture the defective parts in the image inspection. 【Inspection Settings and Results】 By using EasyInspector's "Dimension and Angle Inspection" feature, we were able to measure the dimensions of eight holes. The left image shows an enlarged view of the master screen, while the right image displays an enlarged view of the measured judgment frame. We used a 20-megapixel camera available in our company to measure the dimensions of several cross-sections. The field of view is 43mm wide, and with a width of 5496 pixels, the size of one pixel is 0.0078mm. To conduct a more stable inspection, a factor of 3 to 5 times this is necessary. Since the inspection may be somewhat rough, we reported that the feasibility of operation would depend on how much the end user can tolerate.

We received an inquiry via email from an electronic component manufacturer considering automated visual inspection. They were experiencing issues with a workpiece that has a grommet inside the connector, making it difficult to determine by hand whether it has been inserted all the way to the back of the connector, leading to incidents of insufficiently inserted items being shipped to customers. We conducted a simple verification after receiving photos. 【Inspection Settings and Results】 By using the "Presence or Absence of Specified Color" function of EasyInspector, we were able to determine the presence or absence of the grommet in four locations. While it may also be possible to detect the plastic lock part and provide pass/fail judgment, detecting the crimp terminal (the silver part) would likely result in more stable inspection. As for the operational method, it is also possible to take photos from an angle for inspection; the inspection cycle time was 0.16 seconds. 【Software Used】 Software used: EasyInspector710 (formerly EasyInspector) The current 'EasyInspector2' color package can perform inspections with the "Presence or Absence of Specified Color" feature.

This is an inquiry about the implementation of circuit boards. Inspections related to circuit boards can be said to be the most common inquiries we receive. Our inspection software is already being used in various locations for image inspections of circuit boards. We have received samples shipped from an electronic component manufacturer. 【Inspection Settings and Results】 By using the "Comparison with Master Image" feature of EasyInspector, we were able to detect the presence or absence of 17 connector insertion points and differences, and we could determine visually similar items (different products) in 0.24 seconds. The areas indicated by the blue circles were detected due to color differences in the components. The areas indicated by the yellow arrows represent false detections that could not be completely eliminated through settings, but they are clearly smaller than the amount detected due to color differences, so they do not affect the inspection.

There was an inquiry about wanting to detect the parts that appear to protrude due to insufficient insertion as differences. This is from a customer in the plastic processing industry. 【Inspection Settings and Results】 Inspection was possible by using the "Comparison with Master Image" feature of EasyInspector. However, since the comparison with the master image detects differences as discrepancies if there are any "differences from the master image," there is a possibility of false detection if there are variations in the insertion quality among good products. Additionally, positioning is relatively strict for inspection purposes. The software called DeepSky, which utilizes deep learning, seems to be more suitable for this inspection. In this case, the software determines pass or fail by training on good and defective products. Compared to conventional procedural inspection software, it is more resilient to variations among good products, so the strict positioning required by EasyInspector may not be necessary, and it can distinguish between good and defective products even from images with subtle differences in insertion quality or the way cables are captured.

This is an inquiry from a manufacturer that has been using our services for some time, regarding the settings for character recognition. Our company offers a "Simple Evaluation Service" provided by technical staff free of charge. If detection and judgment are successful during the simple evaluation, we recommend conducting a "Feasibility Verification" test, which simulates actual operations to evaluate processing time and judgment accuracy. Additionally, we offer demo units for free, allowing customers to physically interact with the inspection software and experience it firsthand. We also provide daily support for inquiries regarding challenging imaging environments that directly affect accuracy, such as "fine defects," "glossy workpieces," and "black parts on a black background." [Inspection Settings and Results] The reason the third frame number of EasyInspector was not being read correctly was due to the position of the frame. I provided guidance via email to adjust the reading frame based on the reference image. Additionally, due to the image being somewhat dark, when the decimal point digit count was set to "automatic," it sometimes detected a decimal point from an empty area. In this case, I explained that unchecking "automatic" and setting the digit count to 0 would resolve the issue.

The electronic component manufacturer that inquired this time was considering automating product management by recording the reading of characters printed on electronic components. Our inspection software includes basic functions for saving inspection results in CSV or image formats, which have been useful for product management across various industries. 【Inspection Settings and Results】 By using the "OCR Reading" feature of EasyInspector, it was possible to read 12 characters at one location. If you want to add the serial value to the file name of the recorded image, you need to create software that automatically renames the files or specify the file name using external control commands for image saving. 【Software Used】 Software Used: EasyInspector710 (formerly EasyInspector) The current 'EasyInspector2' RD (ReaDing) package can perform inspections with [OCR (Optical Character Recognition)] and [Machine Learning OCR].

This is a request for jumper checks through soldering work on the substrate. A sample implementation board measuring 80mm x 40mm has been provided, along with specified camera and lens. The flow meter manufacturer has contacted us through our website to discuss standardization of the work. 【Inspection Settings and Results】 Five inspection frames were set up for each inspection location. Of the five inspection frames, three were configured using EasyInspector's "Comparison with Master Image" inspection function to detect whether chips are mounted, among other things. Two of the five inspection frames were set up using the "Presence/Absence of Specified Color" function to detect only when there are no chips or solder. If defective parts exceeding the reference value are detected, the result will be deemed "Fail."

This is an inquiry from a manufacturer of electromagnetic devices and control design equipment. It involves reading the characters printed on the cable. Our company accepts verification and support from technical staff on a daily basis. If you have any issues, questions, or uncertainties during operation, please feel free to contact us at any time. 【Inspection Settings and Results】 We conducted verification on the sample we received regarding the reading of characters on the tube and the color inspection of the cable. As a result, we were able to detect errors in the characters on the tube and make a pass/fail judgment. We set up a total of six inspection frames, with three frames for the tube section configured with the "OCR pro" function. By setting the "Presence/Absence Inspection of Specified Color" function in the three frames for the cable section, we were able to make judgments on six locations in 0.42 seconds. The inspection frames were set larger to ensure that the inspection parts fit within the frames even with slight misalignments. The inspection settings are based on the premise that the positions and orientations of the cable and tube are fixed in predetermined locations.

This is an inquiry about inspecting images to ensure there are no mistakes in the insertion of film capacitors. We received a request to conduct a simple test to determine whether it is possible to assess based on the thickness of the film capacitors. It seems that due to the capacitors being inserted at an angle, it is currently not possible to distinguish them through dimensional angle inspection. If the thickness cannot be determined, we will verify it using our image inspection software from the side. 【Inspection Settings and Results】 By using the "Comparison with Master Image" feature of EasyInspector, we were able to detect the presence and positional differences of eight holes, allowing us to identify visually similar items (different products) in less than one second. I believe that by capturing images from the side, we can determine the type of capacitor based on the differences in color detection values. During verification, we are inspecting by capturing images from the side with the camera, but another effective method is to use a "mirror" to reflect the side view and detect it from the reflected surface.

This was the first inquiry from a customer primarily manufacturing lighting fixtures, and they are considering the use of image inspection to verify the quality of assembly. Given the current social situation, we are also accommodating meetings via web conferencing. Unless specified otherwise, we often send invitations using "Microsoft Teams," but we can accommodate any common applications such as Zoom or Skype. After understanding the overview of our systems and software, it is common for us to receive sample submissions. 【Inspection Setup and Results】 We conducted verification of incorrect lead wire connections and the presence of labels using the samples we received. By utilizing EasyInspector's "Color Comparison Inspection Function," it was possible to determine good and defective products. The inspection was completed in 2.49 seconds per inspection frame across 11 inspection frames. After reporting the simple verification, we may receive requests for specific paid verification for operational purposes. Additionally, we can lend demo units to customers free of charge for them to experience the product firsthand.

We have received a request for a simple verification of a new project from an overseas audio equipment manufacturer with whom we have previously done business. Since the release of our inspection software "DeepSky," which utilizes AI (deep learning), we have received various inquiries. Even major companies surprisingly have not fully automated their inspection processes. Automation is being promoted with the goals of pursuing stable inspection accuracy and reducing costs. As the shortage of personnel due to the aging workforce becomes more pronounced, we encourage you to consider improving operational efficiency through image inspection to protect "Made in Japan" manufacturing. 【Inspection Settings and Results】 We tried annotating the entire image you sent, but we were unable to identify it as expected, resulting in similar outcomes to what you verified. Even using a method that only trains on OK samples, nearly 90% of the NG samples were classified as OK. However, by assuming a method of determining based on the number of detections within a designated area, as proposed yesterday, and training on the sheet post and recess (5 teacher images), we found that we could achieve 100% correct detection with the images you provided this time. 【Software Used】 Software used: DeepSky

We received a request for a simple verification from a major general electronics manufacturer that has contacted us before regarding DeepSky. The presence or absence of washers is an area where DeepSky excels. We recommend trying out the web version to experience AI (deep learning) more closely. 【Inspection Settings and Results】 From the images provided, we used 10 OK images and 10 NG images, totaling 20 images, as training data. We then evaluated 5 OK images and 5 NG images, totaling 10 images, from the remaining images as unknown data. In this verification, there were no false detections, and we were able to correctly classify all 30 images. 【Software Used】 Software used: DeepSky

We received a request for a simple evaluation regarding the inspection of cracks in parts from an audio equipment manufacturer we have been working with for some time. We received 16 sample images. Our company accepts verification and support from technical staff on a daily basis. If you have any issues, questions, or uncertainties during operation, please feel free to contact us at any time. 【Inspection Settings and Results】 Out of the 16 images, 10 were used as training images. We inspected a total of 16 images, consisting of 10 training images and 6 untrained images (3 OK and 3 NG). We set the criteria to "pass" when there are 0 cracks detected and "fail" when 1 or more are detected, and we were able to detect all 16 images. Even with unknown images that were not trained, we were able to detect them as cracks. The image on the left shows the number of detected cracks displayed on the screen. 【Software Used】 Software used: DeepSky

We received an inquiry from a manufacturer of automotive and construction machinery harnesses. They would like to conduct inspections using our software based on a request from the client, as they cannot confirm the state of terminal crimping through image inspection. A free preliminary evaluation was conducted. In the free sample evaluation, we first perform a simple verification using the samples or images provided, and we report the verification results. The simple verification assesses whether the desired detection/judgment can be achieved using our internal equipment. If detection or judgment is possible in the simple verification, we recommend conducting a test (feasibility verification) assuming actual operation, and evaluating processing time and judgment accuracy. If feasibility verification is to be conducted, you can choose to continue with our company (for a fee) or use our loaned equipment for verification at your company. 【Inspection Settings and Results】 We conducted verification using our "DeepSky" equipped with deep learning capabilities. As a result, we were able to detect and judge each NG item. The left image shows detection frames indicating two types of abnormalities. The right image displays the number of detections that can be confirmed on the settings screen. However, in this verification, there were some instances of false judgments. Therefore, I believe it will be necessary to increase the number of verifications in the future.

In wire harness manufacturing, there is a process of bundling multiple harnesses together. While traditional "EasyInspector" is often used for inspecting electronic components, combining it with "DeepSky," which utilizes Deep Learning, can sometimes lead to higher quality production. 【Inspection Settings and Results】 Even with harnesses of various colors, we were able to accurately assess the bands regardless of their front or back. In the images provided this time, the large field of view made detection more challenging. We advised that taking close-up shots would improve accuracy. The numbers in the images represent the AI confidence percentage (number of recognition points). 【Software Used】 Software Used: DeepSky The current EasyInspector2 is equipped with AI capabilities and can handle inspections of defects with various colors and shapes. We will suggest software tailored to your inspection targets.

We received an inquiry from a parts manufacturer considering the automation of various inspections for painted sheet metal and electronic components. In the initial simple inspection we will provide, we ask customers to prioritize their needs, and we will conduct free evaluations starting with the highest priority inspections. 【Inspection Setup and Results】 We conducted a simple evaluation to check for any mistakes in the insertion of the connector cables. As shown in the image, we were able to make a good judgment. Items that can be captured on the same screen can be inspected simultaneously. Depending on the PC specifications, it is generally possible to make judgments with an inspection cycle of about 0.2 to 0.3 seconds. In the free sample evaluation, we will first conduct a simple verification using the samples or images provided and report the verification results. In the simple verification, we will evaluate whether the desired detection/judgment is possible using our in-house equipment. If detection or judgment is possible in the simple verification, we recommend conducting a test (feasibility verification) assuming actual operation, where we will evaluate processing time and judgment accuracy. If you wish to conduct feasibility verification, you can choose to continue with our company (for a fee) or use our loaned equipment for verification at your company.

We received a request for a simple evaluation from a manufacturer specializing in wireless power supply and charging products, which we have previously contacted. Visual inspection is often seen as a simple task, but it requires the skill to determine "OK" or "NG," and it may not be a task that everyone can perform consistently. Factors such as physical condition and prolonged working hours can lead to fatigue, which is one of the causes of unstable inspection results. Our company is also developing inspection software that can identify fine scratches and dirt, enabling judgment similar to that of skilled workers. 【Inspection Settings and Results】 We tested with the 10 images provided. The images were assigned as follows: 1-3 → Test images, 4-6 → OK training data, N7-N10 → NG training data Although we could not secure enough NG test images due to the small number, we conducted training with 7 images and were able to correctly classify the 10 images. 【Software Used】 Software used: DeepSky

We received a contact from a manufacturer that produces hardware and software for printed circuit board manufacturing and assembly. They are considering whether it is possible to perform image diagnostics to assess the quality of soldering after components are mounted on the printed circuit board and soldered. 【Inspection Settings and Results】 Based on the images provided, we were able to identify the NG (not good) areas as NG. In this verification, we used a total of 9 images: 6 images (NG1-3, OK1-3) as training data to create the model, but since we could not detect NG7-8, we added these 3 images to the training set. As a result, we were able to detect correctly, but since the occurrence of NG was fixed at the far right, further verification is needed to determine if detection is possible with other patterns.

Automotive parts and other resin-molded components may have variations in the presence or position of holes due to differences in specifications. However, in the case of similar products, accidents have occurred where similar but different items were shipped because they looked almost identical. [Inspection Settings and Results] By using the "Comparison with Master Image" feature of EasyInspector, we were able to detect the presence or absence of holes and positional differences in eight locations, allowing us to determine similar-looking items (different products) in less than one second. [Software and Equipment Used] Software Used: EasyInspector300 Field of View: 400 x 300mm Minimum Size of Inspection Target: 2mm Number of Inspection Points: 8 Camera Resolution: 1.3 Megapixels (Basler acA1300-75gc) Lens Focal Length: 6mm Distance Between Lens and Product: 300mm Lighting: Backlight The current 'EasyInspector2' color package can perform inspections using the "Comparison with Master Image" feature.

This is an inquiry from a manufacturer of FA control equipment with whom we have previously done business, regarding the evaluation of solder. The combination of AI (deep learning) and image inspection can be beneficial even in high-level solution areas. Our image inspection software, DeepSky, enables efficient inspection. 【Inspection Settings and Results】 We have determined the solder quality positively, as can be confirmed in the images. The numbers represent the AI confidence level percentage (number of recognition points). The inspection was conducted using software called DeepSky, which utilizes AI (deep learning). By training the software on the areas we want to detect, it adjusts its own setting parameters and learns to recognize them. To successfully implement AI image inspection, it is crucial to clarify the characteristics of defects. Please feel free to contact us regarding lighting and camera environments. 【Software Used】 Software used: DeepSky

We received an inquiry from a manufacturer of FA control devices with whom we have had dealings in the past, regarding the determination of solder quantity. The combination of AI (deep learning) and image inspection can be beneficial even in high-level solution areas. Please consider our image inspection software, DeepSky, for efficient inspection. 【Inspection Settings and Results】 We are able to accurately determine insufficient and excessive solder, as can be confirmed through images. With our inspection software "DeepSky," you can easily set up inspections by enclosing the areas you want to evaluate and training the system. There is an increasing movement to automate visual inspections due to advancements in AI-based image evaluation technology. To successfully implement AI image inspection, it is crucial to clearly define the characteristics of defects. Please feel free to contact us regarding lighting and camera environments as well. 【Software Used】 Software Used: DeepSky

This is an inquiry from a FA control equipment manufacturer. Visual inspection is often seen as a simple task, but it requires the skill to determine "OK" or "NG," and it may not be a task that everyone can perform consistently. Factors such as physical condition and prolonged working hours can lead to fatigue, which is one of the causes of unstable inspection results. Our company is developing inspection software that can identify fine scratches and dirt, enabling inspection judgments similar to those made by skilled workers. 【Inspection Settings and Results】 The device's claw mounting is being judged as good. The software allows for image data collection, learning, and setting of judgments in a manner similar to operating Windows software. It is an easy-to-integrate inspection software available for a one-time purchase. "DeepSky" offers a trial service online, so please check our website even for inspection cases you may have previously given up on. 【Software Used】 Software used: DeepSky

This is an inquiry from an electronic component manufacturer. Recently, there has been an increase in business locations where sending samples is difficult due to compliance and security concerns. DeepSky will create settings by learning from defective areas. Therefore, depending on the inspection content, if sending samples is difficult, it will be necessary to prepare about 20 to 30 images of good products and defective product data. First, it is essential to understand what kind of inspection content is involved, and it often starts with sending a few images of both acceptable and unacceptable products. [Inspection Settings and Results] As a result of the verification conducted with the images you provided, it was possible to distinguish between good and defective products. Since the images were 8-bit monochrome images, they were converted to 24-bit before verification. This verification was conducted using software called DeepSky, which utilizes AI (Deep Learning). By training the software to recognize the areas to be detected, it adjusts its own setting parameters and learns to recognize them. Good and defective products were trained with different labels to enable identification.

In recent years, the decrease in the labor population has become a social issue, and amidst this, the necessity for AI in inspections within the FA industry is increasing to maintain quality. Even among acoustic equipment manufacturers, our image inspection software is being considered. This time, we received a request for evaluation of polarity inspection for circuit board capacitors. 【Inspection Settings and Results】 A total of 23 images were used, including 3 images for NG evaluation, with a total of 11 training images consisting of 5 OK images, 5 NG images, and 1 evaluation image. Only the polarity markers of the capacitors were annotated, and after executing 12,000 steps of learning, judgments were possible. DeepSky is designed to include only the necessary functions for detection and judgment, and we plan to develop external applications for functions that may be required for customer-specific operations. 【Software Used】 Software Used: DeepSky Learning Version Number of Inspection Points: 8

A manufacturer of high-performance precision plastic molds and press molds has contacted us through our website to automate visual inspection. On our website, you can download the 60-day free trial software of EasyInspector and try out DeepSky's web version. Please check it out. 【Inspection Settings and Results】 We submitted the results for both EasyInspector and DeepSky. Considering the variability in the pad suction process and the uncertainty of where defects may appear on the parts, it is likely that DeepSky is more suitable for this situation. The web trial version of DeepSky only allows you to find what you have taught it. If you would like to verify the OK/NG judgment, we can lend you the full version for free. 【Software Used】 Software used: EasyInspector, DeepSky Learning Edition Number of inspection points: 1 location, finding defects from the entire screen.

This is an inquiry from a specialized trading company in automatic control. It involves determining whether crimping is present on harness cables with connectors, assessing the color order of about eight bundled colored wires, and confirming the tightening of screws at four locations on the circuit board. It seems that there are multiple types of cables, and this time we decided to utilize the strengths of both DeepSky and EasyInspector for the evaluation. 【Inspection Settings and Results】 Since the inspection items for insertion errors and defective crimp terminals are different, we verified each with separate software. For the cable insertion errors, we used EasyInspector to check for the presence of specified colors, while the inspection for defective crimp terminals was verified using the software DeepSky. Each software has its strengths and weaknesses. → EasyInspector struggles with inspections that have an infinite number of patterns. → DeepSky is not good at determining when one out of several colors is different. The left image shows the detection frame from DeepSky, and the right image shows the detection results from EasyInspector.

We received a contact from a manufacturer of electronic components and devices regarding an issue where harnesses were slipping out of the binding process after wiring multiple harnesses with cable ties, causing difficulties. We suggested that it might be possible to conduct an inspection by counting the number of cable ties after receiving preliminary images, and subsequently, we actually took a sample for verification. [Inspection Setup and Results] In a simple verification, we were able to determine that the results were satisfactory. Regarding operations, we will consider the details while discussing the conditions in meetings. Given the current social situation, most meetings are held via web conference, but it is also possible for you to visit us directly. Many nearby manufacturers often bring samples, and since Hamamatsu City in Shizuoka Prefecture is an area with a thriving manufacturing industry, we have a track record of providing support to various industrial machinery manufacturers, control equipment manufacturers, and end users. We are also accepting inquiries for inspections that you may have previously given up on. [Software Used] Software Used: DeepSky Learning Edition Number of Inspection Points: 1

At the request of a battery charging and discharging equipment manufacturer we have been dealing with for some time, it is important in image inspection to determine whether we can clearly capture the defects such as "scratches" and "scuffs" that we want to identify. 【Inspection Settings and Results】 We rotated the received images by 60 degrees each, resulting in a total of 36 training images. Based on the images we processed, the scratches that were difficult to see were successfully detected using the images taken with the lighting you provided. If we cannot conduct verification with sample products, we cannot determine whether the defects we want to detect can be captured in the image inspection. We will ask you to send images where defects have been captured using various lighting techniques for evaluation. As expected, in the case of free evaluations, due to the fact that detection was performed on specific defective sample images and our imaging environment, we often guide users to actually experience it through the "demo machine trial service." 【Software Used】 Software Used: DeepSky Learning Version Number of Inspection Points: 1 (to find scratches and scuffs from the entire screen)

Until now, we have posted several inspection cases of circuit boards using EasyInspector, but for inspections that determine "NG" if a solder ball is found anywhere on the entire board, we recommend DeepSky. DeepSky excels at inspections that classify a finding as defective if even one is discovered anywhere on the screen. 【Inspection Settings and Results】 By using the inspection function of "DeepSky," we were able to detect solder balls from the entire area and determine the inspection of one screen in 0.39 seconds. The work is displayed across the entire screen, and the task of finding the defective solder balls is referred to as "annotation," which involves surrounding the area with a frame. When the annotation is successful, parameters can be set for good judgment. To allow you to "experience" how much easier it is to set up compared to previous inspection software, the AI-based software DeepSky can be tried out on our company website. 【Software and Equipment Used】 Software used: DeepSky Field of view: 40x 30mm Minimum size of inspection target: 1mm Number of inspection points: 1 location, entire area Camera resolution: 1.3 million pixels Lens focal length: 25mm Distance between lens and product: approximately 200mm

It seems that there are many washers and similar screws used in various industries, making it often cumbersome to distinguish between them. This time, we received an inquiry about how to differentiate washers and screws. Since this is a common issue, we have also created a video to make it easier to visualize. Please take a look for reference. "Discovering the simultaneous omission of two types of parts and stopping the conveyor" https://skylogiq.co.jp/DIY_HowTo/368 【Inspection Settings and Results】 We enclosed the target areas we wanted to detect with a frame and labeled them by type. In this verification, we focused on six types of parts to examine the feasibility of differentiation. We believe that false detections and non-detections occurred due to insufficient training data for the patterns in which the target objects appeared in the images, and we expect that simply increasing the patterns in the training data will improve detection accuracy. However, we cannot determine the final rate of false detections or non-detections until we actually conduct the training.

It seems that among the customers using EasyInspector, the majority are manufacturers who use it for inspecting electronic circuit boards. This time, we are also dealing with the assembly of electronic circuit boards. Due to requests to inspect various parts, we received inquiries about camera environments and settings after downloading the free trial version from our website. 【Inspection Settings and Results】 By using EasyInspector's "Color Comparison Inspection" feature, we were able to detect differences in one location and determine visually similar items (different products) in less than one second. Our website offers a service where you can use EasyInspector's "60-day free trial version" from the download page. There has been an increasing trend in inquiries regarding the inability to lose work due to security and compliance concerns, but many customers are making use of it.

The ferrule made from polyphenylene sulfide (PPS), a thermoplastic resin, is a connector that allows for the high-precision, high-density mass connection of multi-core optical fibers. However, a resolution of 0.01μm in image processing is essential, making it a very challenging situation, and there was a request for hole pitch measurement of the MT ferrule. Additionally, there were multiple inquiries regarding character recognition of semiconductor laser chips and measurement of the amount of adhesive droplets. 【Inspection Settings and Results】 For character recognition of semiconductor laser chips, by using the "OCR Pro" function of EasyInspector, it was possible to read numbers at one location (15 characters) and make a judgment in 0.2 seconds. 【Software Used】 Software Used: EasyInspector Number of Inspection Locations: 1 (15 characters)

It is common in any industry to manufacture seemingly similar products on a single line. Even in audio equipment manufacturing, there have been incidents where the rear display of Blu-ray recorders of the same shape was mistakenly swapped, or defects occurred where the printing was smudged and unreadable. 【Inspection Settings and Results】 By using EasyInspector's "Comparison with Master Image" function, we were able to detect six printing discrepancies and determine visually similar counterfeit products (different items) in 0.36 seconds. Since a printing deviation of approximately ±1mm is considered acceptable, it would be deemed unacceptable under the current inspection settings, necessitating some adjustments. For example, one could set the verification level to a larger value or set the deviation correction for each inspection frame to "automatic" to perform corrections at various points, while conducting separate dimensional angle inspections for positional deviations. 【Software and Equipment Used】 Software Used: EasyInspector310 Field of View: Approximately 200 x 130mm Minimum Size of Inspection Target: 2mm Number of Inspection Points: 6 Camera Resolution: 3 million pixels Lens Focal Length: 12mm Distance from Lens to Product: 280mm Lighting: Indoor fluorescent lights

We received an inquiry regarding the optical character recognition of serial numbers on laser diodes from an electronic component manufacturer. Our inspection software, EasyInspector, enhances processing speed by converting characters into two colors, black and white, to clearly define the boundary between the inspection target and the background (binarization). By using the "OCR Pro" feature of EasyInspector, we were able to detect the presence and positional differences of three holes, allowing us to determine visually similar counterfeit products (different items) in 0.05 seconds. This evaluation was based on the images provided. The image on the right shows the display when inspection results are recorded in a CSV file. In this way, all inspection results can be recorded, and it is also possible to keep a visual record.

The inspection of solder bridges, whether present or absent, is one of the defects we receive numerous inquiries about. Verification is conducted by sending photos. Our affordable inspection software is being utilized across various sectors. We hope to support your company in stable product manufacturing with our inspection software. 【Inspection Settings and Results】 By using the "Luminance Change Inspection" feature of EasyInspector, we were able to determine a solder bridge at one connected solder point in 0.04 seconds. The pink frame in the right image represents the inspection area. The green line in the left image indicates luminance. The pass or fail is determined by how many low luminance areas (black parts) between the solders are detected, and the settings ensure that the solder bridge does not form a clean green wavy line, resulting in a failure. In this case, a count of 6 was measured, which is a pass. Additionally, we were able to simultaneously assess the presence or absence of other components such as chips and capacitors, as well as their polarity, for a total of 10 inspection points. 【Software Used】 Software Used: EasyInspector710 Number of Inspection Points: 10

We received an inquiry from a camera control equipment manufacturer regarding the customer's request to create a system for air conditioning implementation inspection. 【Inspection Settings and Results】 By using the "Comparison with Master Image and Presence of Specified Color Inspection" feature of EasyInspector, we were able to detect the presence and positional differences in three locations and make a judgment in 0.34 seconds. For each of the three inspection locations, we propose two types of inspection methods: "Comparison with Master Image" and "Presence of Specified Color Inspection." The inspection is conducted using the images provided. 【Software Used】 Software Used: EasyInspector710 Number of Inspection Locations: 3 The current 'EasyInspector2' color package can perform inspections with [Presence of Specified Color] and [Comparison with Master Image].

The OCR reading printed on the chip capacitors of electronic component mounting boards is a feature of our inspection software that many companies utilize. Additionally, it is often capable of detecting damage to components, solder debris, and the presence of dirt. 【Inspection Settings and Results】 By using the "OCR" function of EasyInspector, there were parts of the IC chip's serial number that could be read by OCR and parts that could not. This verification was conducted in 2015, and it has since been upgraded to the "PCRPro" function, allowing for more accurate readings. As shown in the left image, readings can be performed by registering a dictionary and setting binarization, but it can be challenging if the characters are connected, lines are interrupted, or they appear as dots. Please try our EasyInspector to see how well it can perform binarization. 【Software Used】 Software Used: EasyInspector710 Field of View: No records Number of Inspection Points: 3 The current 'EasyInspector2' RD (ReaDing) package can inspect using 【OCR (Character Recognition)】【Machine Learning OCR】.

If there are chips on the substrate, they are treated as defective products. Electronic component manufacturers pay close attention to the handling of parts, but inevitably, a few defective items do occur. The defect in this case was a chip on the side of the substrate. During visual inspection, it was difficult to distinguish between the chipped area and the substrate pattern, making the inspection challenging. The goal was to supplement this difficulty with image recognition to inspect efficiently and accurately. 【Inspection Settings and Results】 Using the "Scratch Inspection" feature of EasyInspector, we inspected the chips on the side of the substrate. By tilting the substrate slightly, the chips became easier to see. When we set the detection sensitivity (luminance difference) to a strict level (10), we were able to detect the chipped area, but the substrate pattern was also detected. After further inspection, we loosened the detection sensitivity (to 20), which successfully allowed us to detect only the chips without detecting the substrate pattern. 【Software and Equipment Used】 Software Used: EasyInspector310 Minimum Size of Inspection Target: Approximately 3-5mm Number of Inspection Points: 4 Camera Resolution: EI-Scan Current inspections can be performed with the 'EasyInspector2' color package [Scratch and Object Detection].

In an electronic component manufacturer, if the terminals do not function properly, the product cannot be established. Issues such as incorrect wiring combinations or deformation of the terminals can be cited as problems. This time, we received an inquiry to inspect whether the terminals are deformed using image processing. 【Inspection Settings and Results】 Using the "Color Comparison Inspection" function of EasyInspector's "Comparison with Master Image," we set inspection frames on four terminal areas to detect differences from the good product master image. The pass/fail criteria were established based on the minimum value when inspecting defective products, allowing us to determine pass or fail. 【Inspection Settings and Results】 Software Used: EasyInspector310 Number of Inspection Points: 4 Camera Resolution: 1.3 million pixels Lens Focal Length: 50mm Distance Between Lens and Product: Approximately 210mm Lighting: Thin Ring Lighting The current 'EasyInspector2' color package can perform inspections using the "Comparison with Master Image."

This is a request for a simple verification from a manufacturer of custom automatic machines, who specializes in high precision and high-speed transport. In the free sample evaluation, we will first conduct a simple verification using the samples or images provided, and report the verification results. After that, we recommend conducting tests (feasibility verification) assuming actual operation, where we will evaluate processing time and judgment accuracy. 【Inspection Settings and Results】 We conducted verification using the "Dimension and Angle Inspection" function of EasyInspector on the samples we received. We measured the vertical dimension of the clip and made pass/fail judgments based on the overall length. It was possible to make pass/fail judgments in 0.89 seconds. The inspection cycle may vary depending on the specifications of the PC. 【Software Used】 Software used: EasyInspector710 The current 'EasyInspector2' MS (MeaSure) package can perform inspections for [Position and Width Measurement] and [Angle Measurement].

We reported on the re-evaluation conducted with DeepSky, which was just released in 2020, using the sample images that you previously inquired about from the comprehensive manufacturer of containers and packaging materials. The inspection was performed using software that employs AI (Deep Learning). By training the software on the areas we want to detect, it can adjust its own setting parameters and recognize them. In actual operations, various patterns of defects (size and characteristics) are expected, so it is necessary to increase the number of training images. [Inspection Settings and Results] "DeepSky" significantly differs from conventional software and detection methods, allowing for the detection of pre-trained feature areas from the screen. I thought that "DeepSky" could be utilized for the inspection of coating amounts of the coating agent that you previously inquired about. Unlike before, it is no longer necessary to increase the number of inspection frames for certain settings. However, it is necessary to prepare multiple images in advance for cases of failure, but since September 2021, it has become possible to augment training images. The function to augment a single defective image into up to 36 images by adjusting brightness, orientation, angle, and noise has been implemented, making it more convenient to use.

We received an inquiry from the engine valve manufacturer through our website. They were using a conventional inspection software but were troubled by excessive false detections. Our company provides verification and support from technical staff on a daily basis. If you have any issues, questions, or uncertainties during operation, please feel free to contact us at any time. 【Inspection Settings and Results】 We conducted the inspection using a software called DeepSky, which utilizes AI (Deep Learning). By training the software on the areas we wanted to detect, it adjusts its own setting parameters and learns to recognize them. In this instance, it was able to determine water droplets and scratches. The image shows a successful assessment of a scratch. Our company is located in Hamamatsu City, Shizuoka Prefecture, and we serve numerous industrial machinery manufacturers and users, primarily in the automotive industry. We develop inspection software that is easy to integrate and sell outright, and we have received many repeat orders. 【Software Used】 Software Used: DeepSky

A customer from a metal processing manufacturer inquired about using inspection software to prevent contamination due to product similarities, differences in plate thickness, and variations in hole diameter. 【Inspection Settings and Results】 By using EasyInspector's "Comparison with Master Image" function and "Color Comparison Inspection" function, we were able to detect the presence or absence and positional differences in four locations, allowing us to determine visually similar products (different items) in 0.25 seconds each. Since it was not possible to capture all inspection areas in a single field of view, we proposed using three cameras. 【Software and Equipment Used】 Software Used: EasyInspector300 Field of View: Approximately 198 x 147mm Minimum Size of Inspection Target: 10mm Number of Inspection Points: 4 Camera Resolution: 1.3 Megapixels Lens Focal Length: 12mm Distance from Lens to Product: 500mm Lighting: Indoor Fluorescent Light The current 'EasyInspector2' color package can perform inspections using the [Comparison with Master Image] and [Color Comparison Extraction + Particle Count] functions.