スカイロジック List of Products and Services

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

• Image Processing Software

This is a support case for a customer who has actually implemented DeepSky. We provided guidance to increase the detection rate. The "annotation" used to teach the AI where to detect is crucial for inspection accuracy. The image below shows annotations that had a low detection rate. We advised that annotations that are too large or too small decrease the detection rate. Our company offers 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 set the judgment to "fail" after detecting one or more defective areas. (The inspected images were unknown images different from the trained teacher images.) We inspected 32 unknown images (16 good products / 16 defective products) and achieved 30 correct judgments and 2 incorrect judgments (we failed to detect defects, and all good products were correctly judged). *We also inspected the teacher images, but there were 2 false detections. It is likely that increasing the number of training images and the training time will improve detection. 【Software Used】 Software used: DeepSky

• Image Processing Software

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.

• Image Processing Software

This is an inquiry regarding the monitoring of manufacturing machines from manufacturers of drive recorders and car navigation systems installed in vehicles. We have received six images for monitoring, and we are inquiring about the settings tailored to each reading. Our company website offers a free trial of the inspection software. Since the suitability of the inspection software varies depending on the work, please feel free to contact us if you have any questions. 【Inspection Settings and Results】 For three of the images, we are using the "Specified Color Presence Inspection" function to detect the color when illuminated, and we determine pass or fail based on whether it is detected or not. Images D and E utilize the "Meter Reading Function," but we believe there may be variations in lighting between the upper and lower parts of the meter, so illuminating the lower part, which tends to be darker, with bar lighting or similar would likely reduce false detections. Regarding image F, reading is possible with the image you provided. Additionally, some minor adjustment for misalignment is possible, but fixing the camera is essential.

• Image Processing Software

In manufacturers that handle delicate parts, defects such as scratches have led to accidents. Ideally, we would conduct a more reliable verification by sending sample products for testing, but our company also accepts numerous verifications using sample images. 【Inspection Settings and Results】 By using the "Scratch Detection" feature of EasyInspector, we were able to detect only the dark black areas from the entire screen at one location. In the left image, there are parts that are not scratches but have been detected. Since this area appears darker compared to other smudges and dirt, if we increase the sensitivity of the settings to the level that can detect the scratches in the right image, it will also incorrectly identify the acceptable areas in the left image as defects. 【Software Used】 Software used: EasyInspector710 The current 'EasyInspector2' color package [Scratch and Object Detection] can be used for inspections.

• Image Processing Software

The manufacturer, which designs various devices such as medical equipment and infrastructure, has been a business partner for some time. This time, we received a request for a simple verification inspection to check the signatures on the production management checklist. 【Inspection Setup and Results】 By using the "Presence of Specified Color Inspection" feature of EasyInspector, we detected the presence or absence of signatures in four locations. The left image shows the master image (inspection frame setup screen). It was set up so that if the color of the detected signature within the installed frame is within the reference value, it is marked as OK; otherwise, it is marked as NG. The right image shows that the blue frame indicates pass, while the red frame indicates fail. The areas with signatures are judged as OK, while the empty areas are judged as NG. By setting up an inspection frame in the areas to be checked, the presence or absence of entries can be inspected. A maximum of 999 inspection frames can be installed. 【Software Used】 Software used: EasyInspector710 The current 'EasyInspector2' color package can perform inspections for the "Presence of Specified Color."

• Image Processing Software

The rollers of the printing manufacturer are rotating at high speed. If a defect occurs, it can continue to appear, and inspection can be performed with our image inspection software. This time, we will conduct a simple verification of the interruption of the liquid film. 【Inspection Settings and Results】 By using the "Scratch and Defect Inspection" feature of EasyInspector, it was possible to detect the interruption of the adhesive liquid film from the entire screen in 0.19 seconds. It can be considered that inspection can be performed with a frame capture every 0.19 seconds, but the inspection cycle may vary depending on the specifications of the computer and the settings of the inspection frame. 【Software Used】 Software used: EasyInspector310 (formerly EasyInspector) The current 'EasyInspector2' color package can be used for inspection【Scratch and Defect Detection】.

• Image Processing Software

A manufacturer that produces craft paper bags for brown rice was considering using our image inspection software to evaluate the printed content, such as text, on the craft paper bags at their factory. Currently, multiple factory personnel are inspecting the printed content each time, and there are instances where mistakes, such as typos, go unnoticed, leading to incorrect products being delivered to customers. Therefore, they were thinking of transitioning to machine-based inspection to prevent the outflow of incorrect items and reduce the burden on personnel. [Inspection Settings and Results] By using the "Comparison with Master Image" feature of EasyInspector, we were able to inspect the differences in four areas of text in 0.23 seconds. We set the field of view to capture the entire printed area for verification. In the left image, the parts that differ from the master image (settings screen) are highlighted in red as NG (not good) detections. [Software Used] Software used: EasyInspector The current 'EasyInspector2' color package allows for inspection using the "Comparison with Master Image" feature.

• Image Processing Software

The cellulose fiber resin manufacturer has delicate surface processing technology. This time, we received an inquiry about quantifying the surface roughness of the coating layer through inspection, and we decided to test whether the surface roughness could be determined through image inspection instead of visual confirmation (sensory evaluation). 【Inspection Setup and Results】 By using the "Presence or Absence of Specified Color" function of EasyInspector, we were able to quantify the differences in texture at one location (overall). The results were better when judged using EasyInspector, which allows for detailed settings including stability and color tolerance ranges. The settings for how much to detect as black and what shade to consider as black were done using EasyInspector. 【Software Used】 Software Used: EasyInspector710 The current 'EasyInspector2' color package can be used for inspection with the "Presence or Absence of Specified Color."

• Image Processing Software

Due to the burden of counting small parts at a plastic parts manufacturer, we are requesting verification for automation of the counting process. This falls within the expertise of EasyInspector. A simple verification can be conducted by sending images. 【Inspection Settings and Results】 By using EasyInspector's "Presence of Specified Color Inspection" feature, we were able to inspect parts in 24 trays in 0.93 seconds. The left image shows the inspection settings. The right image indicates a misjudgment of the background color in the detection frame. Although you sent a 5-megapixel image, detection is possible even with a camera of about 1.3 megapixels for this type of inspection; reducing the pixel count will shorten the inspection time. If it is not necessary to identify (record) the locations of missing items, we can enclose the entire set (24 workpieces) within a single inspection frame. If the background of the inspected items is a transparent tray, placing a white paper underneath will enhance the contrast between the workpieces and the background, allowing for more stable and accurate detection in a shorter time. In the inspection settings, the report is configured with "Automatic/Default" for offset correction. If stable positioning can be achieved with jigs or similar tools, setting the offset correction to "None" will further reduce the cycle time.

• Image Processing Software

This is an inquiry from a sports equipment manufacturer. We will conduct surface scratch detection on resin products. 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】 An inspection frame was installed at one location on the inspection surface, and settings were made using EasyInspector's "Scratch Detection" function. Detection was possible in 0.47 seconds. The lighting was set to make scratches appear black on the surface, and each value was adjusted to detect the black areas. Since no scratches exceeding the set values were detected in good products, they were deemed "pass." In defective products, the scratched areas appeared black and exceeded the set values, resulting in a "fail" judgment. The surface of the NG products appeared brighter around the scratches, making the scratched areas stand out more. However, if they had appeared with brightness similar to that of good products, it would have been necessary to adjust the detection sensitivity. In that case, sensitivity would be adjusted to a higher setting, which may increase the likelihood of false judgments. The installation position of the inspection items was set without "shift correction" on the premise that it would be fixed in the same position each time.

• Image Processing Software

This is a request for image assessment to check for holes in a circular rubber flange. It is noted that defective products either have no holes (clear points) or have very few holes, or the holes are small. Additionally, there are concerns about detecting burrs, defects on the outer circumference, and debris (clear points outside the hole positions). A sample has been sent from a company involved in ground investigation and ground improvement. 【Inspection Settings and Results】 We conducted verification of hole presence and position inspection using the sample provided. As a result, we were able to detect the hole areas and determine their positions and presence. However, if the position of the holes is also to be inspected, the following conditions are necessary: the inspection item should be fixed in place using an L-shaped fixture or similar. The orientation of the inspection item should also be set to be approximately the same. Regarding the orientation of the inspection item, please align it roughly based on the areas where numbers or letters are displayed on the surface. Using the "Presence of Specified Color Inspection" function of EasyInspector, we were able to detect the presence or absence of holes and differences at five locations, and we could determine visually similar similar products (different items) in 0.59 seconds.

• Image Processing Software

We will inspect the cushioning foam attached to the Styrofoam used for packaging the product. This inquiry comes from a manufacturer of woodworking and plastic processing machinery. They consulted us regarding the inspection of the presence or absence of gray and black cushioning foam attached to the front and back surfaces, stating that positional accuracy is not currently necessary. They would like to determine whether the foam is partially present or absent and whether it is applied overall. 【Inspection Setup and Results】 We conducted the inspection of the presence or absence of the cushioning foam using the sample images you provided. By using EasyInspector's "Presence of Specified Color Inspection," we were able to determine the presence of the cushioning foam. Additionally, we could also determine the presence of plastic parts using the same function. Since you provided images of the parts installed (front and back), we created test images in a paint software showing a state where some parts are missing (NG state) for verification. The left image shows the inspection frame, and the right image shows the detection frame.

• Image Processing Software

This is an inquiry from a customer who is contacting us for the first time regarding the detection of irregular shapes such as elongated holes and round holes due to deformation or foreign material adhesion in metal parts with hole diameters ranging from φ2.0 to 6.5mm. The target products are between L70 and 200mm. Upon further discussion, it was revealed that the purpose was to detect burrs in the holes. They have sent us samples for a simple verification. 【Inspection Setup and Results】 We captured images of the surface where burrs occur (the surface marked with a marker) facing the camera. It is desirable to set up the inspection surface parallel to the camera sensor. While the software has a function to correct misalignment, we believe that fixing the workpiece with an L-shaped jig or similar will allow for more accurate inspections.

• Image Processing Software

This is an inquiry from an industrial equipment manufacturer with whom we have previously done business. EasyInspector can be used for various parts and defects, but the accuracy of detection can vary depending on the settings. Although it is a one-time purchase inspection software, we will continue to provide support after implementation. 【Inspection Settings and Results】 Regarding the method of inspection using "color presence inspection," in this case of the reverse image, it is likely that detection was possible because it happened to be slightly elevated. Therefore, we would like to put the inspection method for "color presence inspection" on hold and ask you to consider the inspection method using "dimensional angle inspection." Even in the case of "dimensional angle inspection," if the position of the inspection item is elevated (upward on the screen), it may not detect the correct angle. An effective method is to add another inspection frame, set up color inspection and other settings there, and check whether the inspection item is not elevated too much.

• Image Processing Software

There have been numerous inquiries regarding substrate inspections, and a considerable number of customers are already utilizing our services. This inquiry comes from a harness manufacturer that is active in cutting-edge wiring technology. In visual inspections conducted by workers, there is often variability in the criteria for determining "good" and "defective" products among inspectors. The more ambiguous the judgment criteria are, the more inconsistent the inspection results tend to be. We propose stable and efficient production through image inspection. 【Inspection Settings and Results】 By using EasyInspector's "comparison with master images" feature, we were able to detect differences in the positions of defects and identify similar-looking items (different products) with red eyes. The inspection time was approximately 3 seconds. We believe that inspections are relatively easy if the lighting environment is stable. The rule-based traditional image inspection software used this time and the AI (deep learning) image inspection software each have their own strengths and weaknesses. Please contact us to determine which inspection method is more suitable.

• Image Processing Software

The precision sheet metal processing manufacturer was experiencing issues with short shots and gate cut defects, and they inquired whether it was possible to perform automatic inspection of the defective areas. Our inspection software is easy to integrate into systems and can be operated simply like Windows, which has led to numerous inquiries not only from industrial machinery manufacturers but also directly from users. [Inspection Settings and Results] We have reported the results of the verification conducted on the samples we received. By using EasyInspector's "Color Comparison Inspection," we were able to detect differences from the master image (good product), identifying eight locations of short shots and gate cut defects in 2.79 seconds. The extent of misalignment and the method of frame installation can affect the results, but in this case, we performed separate misalignment corrections for four different workpieces, which took more time, resulting in an inspection time of about 2 seconds per instance. For operation, we will consider a conveyor with backlighting. The red display in the images indicates "Fail," while the blue display indicates "Pass" in the inspection results.

• Image Processing Software

We received samples from customers who attended the exhibition. The aluminum processing manufacturer was struggling with the presence of defects and oil contamination on the workpieces. In light of recent circumstances, such as the aging of skilled workers and the spread of the novel coronavirus, there has been a significant movement towards improving operational efficiency to address the lack of people gathering in factories and to realize work style reforms. Our company has been receiving inquiries from various client companies, and it seems that this trend is accelerating. We hope that our image inspection can contribute to your efficiency. [Inspection Settings and Results] Using "DeepSky," we were able to detect "defects" and "scratches." However, inspecting only one side does not allow for a comprehensive examination of all surfaces, so we reported a method for conducting inspections while moving the inspected items (changing the position of the lighting) in an easy-to-understand video. The left image shows the setup work for annotation, which outlines the defects we want to find, and the right image shows the detection frame.

• Image Processing Software

There are two requests: to detect and identify burrs in a hole (with a hole diameter of 2mm) and to determine the misalignment of a part with text centered on a 50mm square plate. This inquiry came from a manufacturer of air conditioning equipment considering an automatic inspection system. 【Inspection Settings and Results】 By using the EasyInspector "Presence of Specified Color Inspection" function, we were able to detect the differences in the two holes and determine the misalignment in 1.49 seconds. We introduced a 30-day trial service available for download from our website, allowing them to try it out and provided guidance on the setup method. We suggested changing the "Correction Position" (red frame and light blue frame), the values for "Color Judgment Tolerance Range," and the "Pass/Fail Criteria Value" to "Both." Additionally, we noted that there are areas where misjudgment may occur due to uneven brightness (the edges appear darker). We advised them to reconsider the position and brightness of the lighting.

• Image Processing Software

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.

• Image Processing Software

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.

• Image Processing Software

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."

• Image Processing Software

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].

• Image Processing Software

This is a request for a simple verification from China. Our company has contracts with agents in China and Malaysia, and we are expanding sales locally. We may also introduce agents for inquiries related to the operations of Japanese companies' overseas manufacturing departments. This time, we will conduct a simple verification of the wear and tilt of the labels affixed to the products. 【Inspection Settings and Results】 Inspection was possible with EasyInspector. The left image shows the wear on the label and the settings for comparison inspection with the master image. The right image shows the angle of the label and the settings for the dimensional angle inspection function. By using this function, we were able to determine the wear and angle of the labels at three locations in 0.07 seconds. 【Software Used】 Software used: EasyInspector Current 'EasyInspector2' color package [comparison with master image] MS (MeaSure) package [position and width measurement] [angle measurement] can be used for inspection.

• Image Processing Software

This inquiry is from a manufacturer of containers and packaging materials. They are a valued customer with whom we have had multiple transactions in the past. Our technical staff receives various inquiries daily and provides careful support regarding inspection setup methods and imaging environments. This time, the inquiry is about the setup method for detecting white objects and white spots in packaging materials. **[Inspection Setup and Results]** The inspection setup was changed from "comparison with the master image" to "presence or absence of specified color." The image is an enlarged version. In the case of "comparison with the master image," subtle differences for each inspected item (such as the reflection of light due to surface irregularities) may also be detected, leading to a higher risk of misjudgment. However, with "presence or absence of specified color," only white spots will be detected, reducing the likelihood of misjudgment. The specified color was registered as "white" (RGB all 255), and the "color judgment tolerance range" was set to "140." By setting the "detection size judgment" to "count mode" and using "count mode," we can determine whether each individual white spot is classified as NG or OK based on its size (perimeter).

• Image Processing Software

Our company provides daily support for inquiries regarding imaging environments that are difficult to capture characteristics such as "glossy work" or "black parts on a black background," which are directly related to accuracy. 【Inspection Settings and Results】 By using EasyInspector's "Dimension and Angle Inspection" feature, we were able to inspect one location in 1.94 seconds using three inspection frames. The field of view displayed on the inspection screen is approximately 255mm wide, and with a 20-megapixel camera, the horizontal pixel count is 5392 pixels. When calculating the actual size, it results in 1 pixel being 25.5÷5392 = 0.004729228. We measure how many pixels high and wide it is, then multiply by 0.004729 to measure the actual length. The images of the three setting screens show the settings for each inspection frame. The fourth image captures the protruding vertex portion of the enlarged inspection result.

• Image Processing Software

This is an inquiry from a manufacturer of industrial robots. We received sample images and conducted a simple verification. They requested to inspect the process of setting 50 non-woven fabric sheets to ensure there are no omissions. 【Inspection Settings and Results】 This time, we set the good product image provided as the master image and were able to conduct an inspection for the presence or absence of non-woven fabric. The right image could not detect the specified black pixels as set, so the left image displays a red detection frame (fail). 【Software Used】 Software used: EasyInspector The current 'EasyInspector2' color package can inspect for the presence or absence of specified colors.

• Image Processing Software

We have received inquiries about our inspection software from manufacturers of printers and printing equipment. We will send samples and conduct a simple verification of the differences in "missing" and "position" of the printed materials. 【Inspection Settings and Results】 We conducted verification of the white lines within the black area and the misalignment of the printing position using the samples provided. We took photographs from directly above with a 20-megapixel camera. Due to the high resolution of the camera, the inspection time for conducting two types of inspections simultaneously was approximately 4.5 seconds per instance. (The actual time may increase depending on the number and range of inspection frames.) There were no defective samples with misalignment among the provided samples, but we can detect misalignments of about ±3mm.

• Image Processing Software

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 a 60-day free trial of EasyInspector and try out DeepSky's web version. Please check it out. 【Inspection Settings and Results】 We submitted the results of using 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. In the web trial version of DeepSky, you can only test finding what you have been taught. 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 Version Number of inspection points: 1 location, finding defects from the entire screen.

• Image Processing Software

This is a request from a manufacturer of automatic packaging machines and medical device system design. Our company, SkyLogic, has over 2,000 examples of image inspection achievements. We have numerous inspection cases published, including metals, plastics, food, electronic circuit boards, and pharmaceuticals, so please check our website's case search tool to see if there are similar cases to the inspection you are considering. 【Inspection Settings and Results】 By using the "Comparison with Master Image" function of EasyInspector, we were able to detect the presence or absence of holes in two locations and differences in their positions, allowing us to determine visually similar look-alikes (different items) in 0.03 seconds. If inspections are to be conducted in a disorganized orientation, operations with another software called DeepSky can also be considered. This was a simple verification based on the images provided. 【Software Used】 Software used: EasyInspector710 Current 'EasyInspector2' color package can be used for inspections with the "Comparison with Master Image" feature.

• Image Processing Software

The image inspection software "EasyInspector" allows for various inspections. Customers from the automotive parts and electronic circuit board sectors make up half of our clientele, and we serve a wide range of industries, including assembly verification of equipment and inspection of minute dirt on products. 【Inspection Settings and Results】 Based on the verification conducted with the samples we received, it was possible to detect abnormalities by using EasyInspector's "Comparison with Master Image" feature and "BAR/QR/OCR" function, while ensuring that the nameplate was not warped and by setting some masks. Our company is located in Hamamatsu City, Shizuoka Prefecture, where the manufacturing industry, including automotive parts, is thriving. We have a track record of providing support for over 2,000 cases and have developed inspection software that is easy to integrate and sold as a one-time purchase.

• Image Processing Software

Manufacturers active in various fields, particularly in medical and welfare equipment, are considering our character recognition functionality. Reading the characters on labels attached to cylindrical parts is expected to be challenging, as the appearance of the characters may change depending on the angle. 【Inspection Settings and Results】 The inspection software EasyInspector's "OCR Pro" was able to make a determination. Four inspection frames were set, and a total of 32 characters were evaluated in 0.57 seconds. The left image shows the inspection frame, while the right image shows the detection frame after binarization. The determination was based on the provided photos, but there are concerns about positioning due to the fact that they are manually applied by hand and the cylindrical shape. 【Software Used】 Software used: EasyInspector710 (formerly EasyInspector) The current 'EasyInspector2' RD (ReaDing) package can perform inspections with [OCR (character recognition)] and [machine learning OCR].

• Image Processing Software

This is an inquiry about the setup method for measuring the distance between the centers of two circles. The inspection software "EasyInspector" that you inquired about is a user-friendly, general-purpose image inspection/image recognition software that can utilize low-cost USB cameras. You only need to install the software and connect a commercially available webcam. You can easily build an inspection system for under 100,000 yen. With over 1,000 successful implementations, it is used in various fields such as electrical, electronics, machinery, and assembly. 【Inspection Settings and Results】 By using the "Dimension Angle Inspection" function of EasyInspector, we were able to measure the distance between the center of one hole and another. The inspection was possible by setting two inspection frames, left → Inspection Frame 1 and right → Inspection Frame 2, over the holes and measuring the difference. This inspection is also a support for customers who are already operating our inspection software regarding the setup method. 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.

• Image Processing Software

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.

• Image Processing Software

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.

• Image Processing Software

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.

• Image Processing Software

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.

• Image Processing Software

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.

• Image Processing Software

We received inquiries from material manufacturers as well. This is a simple verification based on the images provided. Our inspection software is used by a wide range of customers for inspecting minute dirt on products. 【Inspection Settings and Results】 We conducted the inspection using the EasyInspector "Scratch and Defect Inspection" function, but it also detected some dark black areas from rubbing. If we could illuminate the area we want to detect from a diagonal angle and make it physically easier to see, it is likely that detection would be more stable. If sending sample products is difficult, you can download EasyInspector from our website to experience the scratch detection inspection firsthand. Additionally, we offer a demo unit rental service, so equipment such as cameras and lenses can also be rented. 【Software Used】 Software used: EasyInspector710 (formerly EasyInspector) You can conduct inspections with the current 'EasyInspector2' color package for [Scratch and Defect Detection].

• Image Processing Software

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.

• Image Processing Software

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】.

• Image Processing Software

This is the first inquiry from a specialized trading company dealing with aircraft and space equipment. The content was about searching for simple inspection equipment (including software). They seemed to be interested in our products for conducting shape inspections of relatively flat components, approximately 40 cm square. We are also able to accommodate inspection verification and demo units, and we have sent detailed materials as well. 【Inspection Setup and Results】 We conducted measurements on five types of samples that we received. By imaging the edges of the components with transmitted lighting and using the "Dimension Angle Inspection" function of EasyInspector, we were able to perform the inspections. The dimensions were converted based on the dimensions of the good products. The samples we have are typically discarded after two weeks. If you wish to have them returned, we kindly ask that you contact us by phone or email within one week after the report is sent.

• Image Processing Software

We have received sample products from a metal parts manufacturer with whom we have previously conducted business. This is a request for verification of the product dimensions. 【Inspection Setup and Results】 We would like to report the verification results of the dimensional measurements of the samples you sent. This time, we conducted the verification in two parts, assuming the use of two cameras, measuring one side at a time. By using backlight illumination, we were able to capture images that made edge detection easier, and using the "Dimension Angle Inspection" feature of EasyInspector, we set up 13 inspection frames and completed the inspection in 1.69 seconds. The green frame in the left image is an enlargement of the inspection frame set in the master image. The right image is an enlarged view of the screen displaying the inspection results.

• Image Processing Software

This is an example of circuit board inspection for an electronic component manufacturer. 【Inspection Settings and Results】 As a result of verification conducted with the samples we received, the EasyInspector's "Presence or Absence of Designated Color Inspection" function was able to determine the presence of different types of resistors and capacitors, as well as any missing components. The verification involved judgment at 8 inspection points in 2.98 seconds. The left image shows the inspection frame settings and the master image. The right image shows the area filled in light blue, which indicates the detected designated color. Since this amount falls within the acceptable range, it was judged as passing and is displayed with a blue frame. 【Software and Equipment Used】 Software Used: EasyInspector710 (formerly EasyInspector) Field of View: Approximately 60 x 45 mm Minimum Size of Inspection Target: 2 mm Number of Inspection Points: 8 Camera Resolution: 5 million pixels Lens Focal Length: 25 mm Distance Between Lens and Product: Approximately 290 mm Lighting: Linear fluorescent light Distance Between Lighting and Inspection Item: About 100 mm above the workpiece The current 'EasyInspector2' color package can inspect for the "Presence or Absence of Designated Color."

• Image Processing Software

We received an inquiry from a manufacturer engaged in the design and production of various electronic circuit boards for industrial equipment, expressing a desire to automate the precise inspection of printed circuit boards. 【Inspection Settings and Results】 We were able to inspect the misalignment of the resist and pad defects in the sample provided. We used EasyInspector's "Comparison Inspection with Master Image." The inspection frame is shown in pink and green (left image). In the actual inspection, it is necessary to enclose the pads to be inspected within the frame. In the right image, the defective product within the inspection frame is indicated by a red inspection frame, as it was inspected. Five inspection frames were set, with a cycle time of 3.49 seconds. 【Software Used】 Software Used: EasyInspector710 Field of View: Approximately 131 x 113 mm Minimum Size of Inspection Target: 2 mm Number of Inspection Points: 2 Camera Resolution: 20 million pixels Lens Focal Length: 16 mm Distance from Lens to Product: Approximately 160 mm Lighting: We tested with a dome placed over ring lighting, simulating dome lighting (to evenly reflect the pads). Current inspections can be performed with the 'EasyInspector2' color package using the comparison with the master image.

• Image Processing Software