スカイロジック List of Products and Services

NumberVision utilizes AI technology to instantly recognize and digitize vehicle license plates. This enables various applications such as parking management, enhanced facility security, customer management, and traffic statistics. It can recognize plates with 99.9% accuracy even in low light or bad weather, and since it is a one-time purchase model, there are no ongoing costs. It can be flexibly utilized according to the customer's environment, allowing for license plate recognition in diverse scenarios. 1) Capture vehicles with your existing network camera. 2) NumberVision recognizes the vehicle license plate → digitizes and records the data. 3) Management can be tailored to your needs. ■Features 【Catering to Various Needs】 Can be utilized in various settings, including parking lots, factories, commercial facilities, hospitals, and gas stations, both indoors and outdoors. 【Easy and Quick Implementation】 All necessary software, PC, and cameras are provided, allowing for immediate operation after purchase, and it is a one-time purchase model that eliminates troublesome operational costs. 【Overwhelming Recognition Accuracy】 Recognizes license plates with 99.9% accuracy regardless of day or night, even in low light or at dusk.

• Image Processing Software

The AI general-purpose appearance inspection software "EasyInspector2" has newly added the "AI Segmentation" feature. The "AI Segmentation" feature performs segmentation (region division and labeling of each pixel in the image) using deep learning within the image. It calculates the ratio of pixels detected by segmentation within a specified polygonal area and makes pass/fail judgments. This feature can mainly be used for the following applications: - Tank water level - Area of metal processing surfaces and coating area - Measurement of crop growth (size) - Detection of lesions in photos and measurement of their area - Checking for coating gaps in sealants and adhesives - Monitoring the amount of smoke emitted By using the AI Segmentation feature for judgment, it achieves: - Improved work efficiency: Significant time savings compared to visual inspection - Enhanced accuracy in quality control: Reducing human errors and stabilizing quality - Cost reduction: Lower labor costs and reduced costs due to suppression of defective products.

• Image Processing Software

During the inspection stage of wood cutting, you were considering cutting a board measuring 2m in length and a certain width from 5mm to 160mm while avoiding defective parts and cutting at the right timing. 【Inspection Settings and Results】 For knots, we used the "Color Comparison Inspection / Presence or Absence of Specified Color" function of EasyInspector. The specified color was set to the color of the knots. An inspection frame the size of one kamaboko board was set from the edge of the board, and this area was divided into four parts for the presence or absence color inspection. To capture the roughness of the board, we dimmed the indoor lighting and illuminated it from an angle, which allowed us to detect the roughness. The inspection item was "Scratch Inspection." No alignment correction was applied for the inspection of the flowing boards.

• Image Processing Software

This was an inquiry from a trading company interested in our software EasyInspector, asking whether standard features could accommodate their needs, and if not, whether customization would be possible. 【Inspection Settings and Results】 By using the "Dimension Angle Inspection" feature of EasyInspector, we measured two dimensions and made a judgment in less than one second. Inspection frame 001 measured the inner diameter of a circle (251.50 pixels), and inspection frame 002 measured the black width (59.50 pixels). In this verification, measurements were possible with standard features, and while customization can be accommodated according to customer requests, it will incur additional costs. 【Software Used】 Software Used: EasyInspector200 Number of Inspection Points: 2

• Image Processing Software

The packaging design of food products often changes in small parts or colors during campaigns, and there have been instances of mistakenly shipping packaging due to similar designs, which has caused some trouble. This time, we determined the differences in design and the differences in the same design materials. 【Inspection Settings and Results】 By using the "Comparison with Master Image" feature of EasyInspector, we detected design differences in the entire imaging screen frame and were able to identify visually similar products (different items) in under 50 seconds. 【Software and Equipment Used】 Software Used: EasyInspector710 Field of View: A4 Size Minimum Size of Inspection Target: 5mm Number of Inspection Points: 1 Camera Resolution: Our Company Scanner Current 'EasyInspector2' color package can be inspected using the "Comparison with Master Image" feature.

• Image Processing Software

It seems that the inspection involving a mix of letters and numbers was difficult to determine at the time. With improvements in lighting and settings, we were able to read with higher accuracy. This request was made in 2015, but the OCR reading function in the current EasyInspector has been enhanced, increasing its accuracy, allowing us to retain images and record content in a CSV file. 【Inspection Settings and Results】 By using EasyInspector's "Character Recognition (OCR)" function, we detected readings from 16 printed locations, achieving a probability accuracy of about 90%, and we were able to make determinations in under 3.41 seconds. A 3-megapixel camera provided the most stable inspections. It is indeed easier to misdetect when letters and numbers are mixed; for example, "8" and "B" are characters that are prone to misdetection. However, when "8" is among the numbers and "B" is among the letters, we were able to read them relatively accurately and stably. Although the number of inspection frames increases, we believe that separating letters and numbers and setting inspection frames accordingly will enable stable inspections.

• Image Processing Software

It has been reported that there was an incident where products with similar package types were shipped with incorrect labels. In many cases where multiple types are manufactured in a flow production system, visual inspection systems play a crucial role. 【Inspection Settings and Results】 By using the "Comparison with Master Image" feature of EasyInspector, judgments could be made in less than one second. The color judgment tolerance was set to 69. As shown in the image above on the right, differences from the master image are detected in red. 【Software Used】 Software Used: EasyInspector310 Number of Inspection Points: 1 The current 'EasyInspector2' color package can be inspected using the "Comparison with Master Image" feature.

• Image Processing Software

This is an inspection where only the model number differs on the product label. Minor differences are often overlooked during visual checks. Inspections related to labels often involve reading and recording serial numbers using OCR functions, but there are also many operations that check whether certain parts, such as model numbers, are correct. This time, the inspection was to verify that the model number and cautionary notes were not incorrect, based on the images sent via email. 【Inspection Settings and Results】 By using the "Presence of Specified Color Inspection" feature of EasyInspector, we were able to detect differences in two locations and determine whether the visually similar label markings were correct in less than 0.10 seconds. 【Software Used】 Software Used: EasyInspector300 Inspection Locations: 2 The current 'EasyInspector2' color package can perform inspections for the "Presence of Specified Color."

• Image Processing Software

This is a judgment test based on the submitted images. If the inspection target can be captured clearly, it can generally be said that inspection is possible. 【Inspection Settings and Results】 By using the "Dimension Angle Inspection" feature of EasyInspector, we were able to measure the angle at one location and make a judgment in 0.09 seconds. 【Software Used】 Software Used: EasyInspector310

• Image Processing Software

**Inspection Settings and Results** By using EasyInspector's "Comparison with Master Image" feature, inspections for four areas of burrs, chips, and shapes were possible. Backlight illumination was used to enhance the contrast between the product and the background for inspection. **Software and Equipment Used** Software Used: EasyInspector310 Field of View: 200 x 150mm Minimum Size of Inspection Target: 0.5mm Number of Inspection Points: 4 Camera Resolution: 1.3 Megapixels Lens Focal Length: 35mm Distance Between Lens and Product: 130mm Lighting: Backlight Current 'EasyInspector2' color package allows inspection with "Comparison with Master Image."

• Image Processing Software

Currently, cases that are verified with DeepSky were previously verified with EasyInspector before the release of DeepSky. This verification involves inspecting the shape of the base of green onions. It includes sorting those with a bulbous, rounded base and many roots. The customer has specific requirements for the camera and resolution. 【Inspection Settings and Results】 We are inspecting the shape of the base of green onions using EasyInspector's "Dimension and Angle Inspection" function and "Damage Inspection" function. We propose various measurement methods across 14 different items. The inspection content is something that our software DeepSky, released in 2020, excels at. Our company aims to solve customer issues as cost-effectively as possible by utilizing the equipment they currently have, such as cameras.

• Image Processing Software

At the request of an LED lighting manufacturer, we conducted a verification test for dirt detection. This test aims to detect dirt such as film-like dust that is difficult to see with the naked eye. 【Inspection Settings and Results】 We received four types of samples and were able to detect three types of dirt. However, for the sample with a bumpy surface finish, we were unable to detect dirt under the same imaging conditions. How to capture the defective areas becomes a crucial point in the inspection. The inspection frame was set as a single frame for the entire area, with an inspection cycle of 2.03 seconds. 【Software and Equipment Used】 Software used: EasyInspector710 Field of view: 64 x 51 mm Minimum size of inspection target: 0.2 mm Number of inspection points: 1 Camera resolution: 10 million pixels Lens focal length: 25 mm for high pixels Distance between lens and product: 260 mm Lighting: LED lighting (illuminated from both sides)

• Image Processing Software

Sintering with silver paste causes less damage to the materials compared to soldering, and it can be said that this material will be used more widely in the future as a substitute for solder. 【Inspection Settings and Results】 By using the "Scratch and Defect Inspection" feature of EasyInspector, we were able to detect both chipping and smudging in 0.40 seconds by applying one inspection frame to the entire area. The size (resolution) per pixel is approximately 7μm (0.007mm). In actual operation, our "sm＠rtROBO" is used to move the inspection area while being inspected by a single camera. 【Software and Equipment Used】 Software Used: EasyInspector Field of View: 14 mm Minimum Size of Inspection Target: Approximately 7μm (0.007mm) Number of Inspection Points: 1 Camera Resolution: 5 million pixels Lens Focal Length: Not recorded Distance Between Lens and Product: 95mm Lighting: Backlight illumination The current 'EasyInspector2' color package can be used for [Scratch and Defect Detection].

• Image Processing Software

In the label manufacturing industry, such as for product descriptions, productivity is increased by printing multiple labels at once. On the other hand, issues such as missing prints, smudges, and defects due to black spots have also arisen during printing. This problem of defective shipments is one that many label manufacturing companies face, and image processing software has been used as a means of improvement. 【Inspection Settings and Results】 By using the "Comparison with Master Image" feature of EasyInspector, three inspection frames were set for a single label to establish pass/fail criteria for missing prints, smudges, and black spots, detecting multiple defective areas. In the image above, the smudged area (NG) is highlighted in red, while the OK areas remain unchanged. 【Software and Equipment Used】 Software Used: EasyInspector710 Field of View: 60x 70mm Minimum Size of Inspection Target: Approximately 5mm Number of Inspection Locations: 3 Camera Resolution: 1.3 Megapixels Lens Focal Length: 35mm Distance Between Lens and Product: Approximately 360mm Lighting: Indoor Lighting Current inspections can be performed with the 'EasyInspector2' color package using the "Comparison with Master Image" feature.

• Image Processing Software

In the label manufacturing industry for product descriptions, there are many cases where numbers need to be printed. Even if we can detect smudges or black spots, it is meaningless if the printed numbers themselves are incorrect. Therefore, we considered introducing a function to recognize numbers to detect "character discrepancies" and "printing errors." 【Inspection Settings and Results】 By using the "OCR Pro" feature of EasyInspector, we can read multiple lot numbers (corresponding to the number of characters) from a single inspection frame. For characters that are difficult to read, it is also possible to train the system to inspect them one by one. The image on the right above shows that the number "8306" has been successfully read. 【Software and Equipment Used】 Software Used: EasyInspector710 Field of View: 60 x 70 mm Minimum Size of Inspection Target: Approximately 5 mm Number of Inspection Points: 1 Camera Resolution: 1.3 Megapixels Lens Focal Length: 35 mm Distance Between Lens and Product: Approximately 360 mm Lighting: Indoor Lighting The current 'EasyInspector2' RD (ReaDing) package can perform inspections with [OCR (Character Recognition)] and [Machine Learning OCR].

• Image Processing Software

The numbers and alphabetic characters displayed on digital meters used by electronic and electrical equipment manufacturers are mostly in a 7-segment format. There was a need for software that could read those numbers and characters within a PC. 【Inspection Settings and Results】 Using the "OCR Pro" feature of EasyInspector, we trained the three alphabetic characters "C, H, K" one by one. Due to the limited display format, there were instances where similar characters were misrecognized, but by adjusting the sensitivity and retraining, we were able to correctly recognize the characters. 【Software and Equipment Used】 Software Used: EasyInspector710 Field of View: 160mm x 200mm Minimum Size of Inspection Target: Approximately 30mm x 50mm per character Number of Inspection Locations: 3 Camera Resolution: 1.3 Megapixels Lens Focal Length: 6mm Distance Between Lens and Product: Approximately 180mm Lighting: No record The current 'EasyInspector2' RD (ReaDing) package can perform inspections with [OCR (Optical Character Recognition)] and [Machine Learning OCR].

• Image Processing Software

When inspecting automotive parts after painting, there are instances where defects caused by painting errors result in the shipment of defective products. We wanted to enable the detection of these defects through image inspection. In automotive parts manufacturing, post-painting defect inspection is considered crucial for product assembly, leading us to consider the introduction of image processing to ensure accuracy. 【Inspection Setup and Results】 Using the "Scratch and Defect Inspection" feature of EasyInspector, we set up inspection frames to detect bright pixels compared to surrounding pixels and dark pixels at the same position, allowing detection regardless of which type is present. Even in cases where the background has a striped pattern, we were able to detect defects as small as 1mm by modifying the settings.

• Image Processing Software

The stickers applied during the manufacturing process of automobile manufacturers can lead to delays in shipping if they are forgotten or misapplied. Therefore, it was suggested that image processing might be more efficient than visual inspection, and we received a request from our company. 【Inspection Settings and Results】 This was verified by sending images. Using the "Presence of Specified Color Inspection" feature of EasyInspector's "Color Comparison Inspection," we verified whether the color of the sticker was present within two inspection frames. We specified the inspection frames to ensure that the upper and lower stickers did not overlap, and we were able to detect the specified color within those frames. 【Software Used】 Software Used: EasyInspector310 Minimum Size of Inspection Target: Approximately 30mm x 30mm Number of Inspection Locations: 2

• Image Processing Software

In the automobile manufacturing process, buttons are installed, and when pressed, the operation begins. However, if the installation order is incorrect, the marks and operations may not match, leading to the possibility of shipping defective products. Such defects can result in significant losses for automobile manufacturers, so an image processing system was used to enhance accuracy. 【Inspection Settings and Results】 Using the "Color Comparison Inspection" feature of EasyInspector, specifically the "Comparison with Master Image," inspection frames were designated for the marks of four buttons to check if the mark images matched. The white marks were successfully identified against a black background. 【Software and Equipment Used】 Software Used: EasyInspector310 Field of View: 125mm x 170mm Minimum Size of Inspection Target: Approximately 20mm x 30mm Number of Inspection Points: 4 Camera Resolution: 1.3 Megapixels Lens Focal Length: 6mm Distance Between Lens and Product: Approximately 200mm Lighting: Not used The current 'EasyInspector2' color package allows for inspection using the "Comparison with Master Image" feature.

• Image Processing Software

In the automotive manufacturing industry, the panels to be installed have many holes, and because there are similar panels, if there is any issue with the presence or position of even one hole, the product cannot be deemed acceptable. Therefore, we considered using image recognition technology. [Inspection Settings and Results] We included a panel with two large holes and 27 small holes within the field of view. For the larger holes, we set up the EasyInspector's "Color Comparison Inspection" feature to detect the "pink color" of the holes. For the smaller holes, we used the "Defect Inspection" feature to detect white defects. The holes themselves were clearly captured using backlight illumination, allowing for accurate inspection even if the position of the holes was off by 50mm. The red areas on the right side of the image indicate where the holes were detected.

• Image Processing Software

It is common to use heat-resistant ceramic sheets in situations where products are handled. They come in various thicknesses, ranging from about 60μm for thin sheets to about 200μm for thicker ones. This time, we solved the problem of measuring the number of 200μm ceramic sheets handled by an electronic component manufacturer, which was previously done manually one by one, by using our software that allows for non-contact measurement of the sheets. 【Inspection Settings and Results】 The verification was done using only photographs. By using EasyInspector's "Luminance Change Inspection," we were able to distinguish between light and dark, and we captured images with 23 thick sheets stacked. Shadows were created between the stacked sheets, making the contrast between light and dark clear, and due to the consistency of the bright and dark lines, we were able to conduct the inspection smoothly. 【Software Used】 Software Used: EasyInspector310 Field of View: 10mm x 13mm Minimum Size of Inspection Target: Approximately 0.2mm (200μm) Number of Inspection Points: 23 Measurement of the Number of Ceramic Sheets (Thin) https://skylogiq.co.jp/DIY_HowTo/860

• Image Processing Software

When measuring the number of approximately 60μm thin ceramic sheets handled by an electronics manufacturer, there were disadvantages such as counting errors and the time taken for visual inspection. Therefore, we considered using our image processing software to enable non-contact counting of the sheets. 【Inspection Settings and Results】 Using the "Luminance Change Inspection" function of EasyInspector, we conducted verification by stacking 63 ceramic sheets of 60μm size. If we can clearly show the difference in brightness, inspection is possible. By uniformly illuminating from the front and aligning the product bundle evenly, we were able to count the number of sheets of 60μm size. However, there was a challenge in the stage of setting the inspection frame, as we had to avoid areas with dust and other contaminants. 【Software Used】 Software Used: EasyInspector310 Field of View: 9mm x 12mm Minimum Size of Inspection Target: Approximately 0.06mm (60μm) Number of Inspection Points: 63 Counting of Ceramic Sheets (Thick) https://skylogiq.co.jp/DIY_HowTo/856

• Image Processing Software

There are tasks involving the application of logo marks from various manufacturers. It is a common mistake to accidentally apply rectangular or square logo marks in reverse. Our company supports you with image inspection to ensure that your important logo is shipped with high design quality and beauty. 【Inspection Settings and Results】 By using the "Comparison with Master Image" feature of EasyInspector, we were able to determine a labeling error in less than 3.56 seconds. The "OK" and "NG" images provided had differences in field of view, brightness, and brightness direction, so we adjusted the "Shift Correction" feature and the settings for "Color Judgment Tolerance Range." It is necessary to prepare the inspection environment during actual operation. (Fixing camera position and orientation, fixing lighting position and intensity, fixing inspection item placement, etc.) 【Software Used】 Software Used: EasyInspector710 The current 'EasyInspector2' color package can perform inspections using the "Comparison with Master Image" feature.

• Image Processing Software

This is an inspection to find black spots on the surface of the customer's product, requested by the trading company. They wanted to detect black spots across the entire screen, so we received images and conducted a judgment test. They requested information (coordinates) indicating where the foreign substances are located. 【Inspection Settings and Results】 Detection was achieved using the "Scratch and Defect Inspection" feature of EasyInspector. The screen was divided into 30 sections, creating 30 inspection frames. It is possible to keep records of which inspection frame detected defects, along with images and CSV files. The test was conducted with strict detection settings, so the customer will need to set their own criteria for what constitutes a defect. Our company offers affordable sales by having customers set the parameters themselves. 【Software Used】 Software used: EasyInspector710 The current 'EasyInspector2' color package can be used for inspection with the [Scratch and Defect Detection] feature.

• Image Processing Software

At the exhibition, we conducted sample verification of precise measurements of CDs at the request of a trading company that actually tried our inspection software. 【Inspection Settings and Results】 By using the "Dimension and Angle Inspection" feature of EasyInspector, measurements of approximately 62 to 73 microns were achieved. This time, a high-resolution camera with a wide field of view was used. The inspection time was about 0.8 seconds. By narrowing the field of view and reducing the resolution, the inspection time can be shortened. The green thin line in the left image indicates the measured part that was detected. In the right image, we have submitted the evaluation of repeatability accuracy for five repetitions at one location. 【Software and Equipment Used】 Software Used: EasyInspector710 Field of View: Not recorded Minimum Size of Inspection Target: 0.01mm (10 micrometers) Number of Inspection Points: 2 Camera Resolution: 5 million pixels Lens Focal Length: Magnification x0.7-x4.5, Working Distance 52mm, Lens Holder Diameter φ50mm, Total Lens Length 190mm Distance Between Lens and Product: 300mm Lighting: Indoor light The current 'EasyInspector2' MS (MeaSure) package can perform inspections for [Position and Width Measurement] and [Angle Measurement].

• Image Processing Software

The instrument manufacturer was experiencing issues with incorrect placement of knobs and dials in their audio products. It is conceivable that human error could occur during visual inspections. They were considering software that could simultaneously inspect multiple factors, such as color differences and incorrect orientations of the knobs. 【Inspection Settings and Results】 Using seven types of image data provided, we were able to detect insertion errors, etc., within our company using the "Master Image Comparison" and "Presence of Specified Color Inspection" functions of "EasyInspector." The inspection time for each part ranged from 0.90 seconds to 0.58 seconds. 【Software Used】 Software Used: EasyInspector310 Number of Inspection Points: 2 to 10 points for each of the 7 images The current 'EasyInspector2' color package can perform inspections using the [Presence of Specified Color] and [Master Image Comparison] features.

• Image Processing Software

Some production technology personnel believe that it is difficult to inspect work with high visibility, such as glass, due to halation. Our company also proposes inspection methods using cameras, lenses, and lighting that can be used for photography. 【Inspection Settings and Results】 By using the "Luminance Change Inspection" function of EasyInspector, we were able to verify the number of stacked glass sheets and make a judgment in 0.04 seconds. We detected the black areas and accurately counted the number of sheets. However, we could not make accurate judgments (detect differences in brightness) in areas where light was not clearly shining, making lighting an important factor in this case as well. 【Software Used】 Software Used: EasyInspector300 Number of Inspection Points: 1

• Image Processing Software

Children have loved card games both now and in the past. Many of you may have collected cards when you were young. Some printing manufacturers produce cards specifically for card games. Once packaged, it becomes impossible to know which cards are inside. Therefore, we utilize our EasyInspector to keep a record of the issued cards before packaging. Inspection settings and results By using the "OCR Pro" feature of EasyInspector, we were able to read a single location with a 7-character format (card number) in 0.19 seconds. The OCR Pro feature includes binarization and dictionary learning functions. It can read not only existing fonts but also other types, although it may become difficult to read if the lines of the characters are broken or if adjacent characters are connected. Please contact us for inquiries about the extent of readability.

• Image Processing Software

There was a request for evaluation of image inspection in multiple areas to reduce personnel and improve operational efficiency in the cabinet manufacturing process. 【Inspection Settings and Results】 By using EasyInspector's "Scratch Detection" function and "Presence of Specified Color Inspection" function, we were able to detect 20 differences and determine visually similar items (different products) for each category in less than one second. 【Software and Equipment Used】 Software Used: EasyInspector710 Field of View: Various field of views Minimum Size of Inspection Target: 2mm Number of Inspection Points: 20 Camera Resolution: 5 Megapixels GigE Lens Focal Length: 25mm Distance from Lens to Product: 1200mm Lighting: Linear fluorescent lights, etc. Distance from Lighting to Inspection Item: Not recorded The current 'EasyInspector2' color package can inspect for the presence of specified colors.

• Image Processing Software

In the food industry, foreign object contamination can lead to significant accidents. As of 2017, verification was conducted using the conventional inspection software EasyInspector, but now such cases can be easily configured and inspected with DeepSky. Please refer to the article "Stopping the Conveyor After Discovering Insects on Cabbage." 【Inspection Settings and Results】 By using EasyInspector's "Presence of Specified Color Inspection" feature, it was possible to detect different colors from one location (the entire field of view). However, since the inspection was based on submitted images, there were instances where the background gray was similar to the different color, leading to noticeable false detections. While it is possible to set a strict "color judgment tolerance range," it has been suggested that adjustments to background color and lighting are necessary. 【Software and Equipment Used】 Software Used: EasyInspector710 Number of Inspection Points: 1 (entirety) Current 'EasyInspector2' color package allows inspection for the "Presence of Specified Color."

• Image Processing Software

This is an inquiry from overseas. We have partnered retailers in China and Malaysia. 【Inspection Settings and Results】 By using the "Scratch Inspection" feature of EasyInspector, we were able to determine one location (with a total of two inspection frames) in 0.07 seconds. We applied two types of inspection frames for black and white spots. For detecting even finer fraying, it may be possible to improve detection by increasing the camera resolution or adjusting the lighting. 【Software Used】 Software used: EasyInspector710 Number of inspection locations: 1 (overall)

• Image Processing Software

In convenience stores and dessert shops, it has become common practice to sell items with cutlery included. This time, we will inspect small transparent spoons that are packaged in transparent film on top of bubble wrap. Our company is committed to creating an environment tailored to our customers' inspection situations, providing free evaluations and reports. 【Inspection Settings and Results】 By using DeepSky's inspection features, we easily set up a configuration where if one spoon is present in the screen area, it displays "OK." On the left is the annotation image (the specified image used to teach what to detect), and on the right is the image detecting the spoon. DeepSky can make judgments without fixed positioning, even in situations where it is difficult for a person to distinguish by visual confirmation. 【Software and Equipment Used】 Software Used: DeepSky Field of View: 150 x 120mm Minimum Size of Inspection Target: 70mm Number of Inspection Points: 1 (configured to display "OK" when one spoon is detected and "NG" when no spoon is detected; one label) Camera Resolution: 1.3 million pixels Lens Focal Length: 8mm Distance Between Lens and Product: 430mm Lighting: Indoor fluorescent lights

• Image Processing Software

The seat designs of automobiles, buses, airplanes, and other vehicles may vary in design and size due to different specifications, and the internal components also change depending on the grade. In the case of similar products, accidents occurred where similar but different items were shipped because they looked almost identical. 【Inspection Settings and Results】 An evaluation was conducted using DeepSky. On the left is the annotation image (the teacher image that teaches the part to be detected), and on the right is the inspection result image. This time, since it was a work that could not be externally leaked, our company used a model and proposed an annotation method. Currently, for consideration of implementation, we are offering a free rental service for demo units. The number of demo units is limited, so depending on the reservation status, there may be delays. We kindly ask you to make your reservations as early as possible. 【Software and Equipment Used】 Software used: DeepSky Field of view: 100 x 80mm Minimum size of inspection target: 5mm Number of inspection points: 4 (Label 8) Camera resolution: 1.3 million pixels Lens focal length: 12mm Distance between lens and product: 450mm Lighting: Indoor fluorescent lights

• Image Processing Software

In the pharmaceutical industry, similar to other sectors, products were packed in paper boxes with a specified number and sealed with stickers for shipment. However, incidents of forgetting to apply the seals occurred. We verified this using DeepSky, which can detect the absence of seals regardless of various orientations and angles during the operation. DeepSky is a software that excels in such inspections and is utilized across various industries. 【Inspection Settings and Results】 By using DeepSky's inspection function, we were able to detect the presence or absence of a seal in one location, achieving a judgment time of 0.23 seconds. The inspection time may vary depending on the specifications of the computer. The images were extracted from the report. In the left image, we set it to detect one seal with one type of label as OK, while in the right image, the inspection judgments of "OK" and "NG" were made without false detections. The inspection was conducted with the images provided, but this time we are also considering the environment, such as cameras. The camera and lens will vary depending on the acceptable working distance and field of view.

• Image Processing Software

We received 100 sample images from a manufacturer that produces high-quality films for verification. For the free evaluation of DeepSky, it is necessary to send photos of various defective shapes of the work. 【Inspection Settings and Results】 By using DeepSky's inspection function, we were able to detect the presence of various shapes of defects with an inspection cycle of 0.28 seconds per instance. The left image shows the settings, while the right image outlines the areas we want to identify and labels them for learning purposes. - We created a setting where if any NG (defective) item is detected, it is marked as a failure; if only OK items are detected or nothing is detected, it is marked as a pass. By training the software with OK and NG, we have been able to conduct inspections that meet our customers' requirements. Our website offers a trial service for DeepSky. Please take advantage of it. 【Software Used】 Software Used: DeepSky Learning Version

• Image Processing Software

Out of the 84 sample images you sent (39 NG / 45 OK), 50 images (25 each) were used for training as teacher images. The remaining untrained images were used as test images. 【Inspection Settings and Results】 By using DeepSky's inspection function, we were able to determine the Ito-biki in 0.23 seconds. The results of inspecting the teacher images and the remaining 34 test images showed a correct answer rate of 100%. The number at the top of the image detection frame indicates the AI's confidence level in percentage (number of recognition points). 【Software Used】 Software used: DeepSky Learning Edition

• Image Processing Software

The use of dedicated trays to place workpieces in each grid during manufacturing and shipping is commonly seen in various situations. While it can be challenging to position workpieces that move within the tray, our inspection software, DeepSk, can assist with such inspections. In the verification with the images you provided, we set up an inspection using AI with DeepSky to distinguish between five types of trays. We trained the model with 70 images (14 images for each of the 5 types) out of a total of 277 images. 【Inspection Settings and Results】 We inspected a total of 277 images, consisting of 70 training images and 207 untrained images. The red box in the right image shows how many of each tray were detected. In this setup, if Tray 1 is detected once, it is set to "pass." The results showed 4 false detections among the untrained images, while the remaining 273 images were successfully detected. By retraining on the falsely detected images, the inspection accuracy can be further improved. The ability to retrain is a strength of inspection software that uses AI. The initial evaluation report on detection capability is kept simple. 【Software Used】 Software used: DeepSky Learning Edition

• Image Processing Software

We have received inquiries about counting numbers in various industries. This time, the inquiry comes from a manufacturer that produces tools and machine tools. They would like to determine if a set number of three types of parts is present, considering various orientations and overlaps. 【Inspection Settings and Results】 Using DeepSky's inspection capabilities, we have made it possible to make determinations even in cases of various "orientations," "overlaps," and "mixing of different items." However, there were instances of misjudgment depending on the degree of overlap, indicating that improvements and considerations are needed regarding the annotation methods for training the system. As an initial free evaluation, we will provide a simple report on whether inspection is possible. After that, we conduct detailed verification and proposals based on specific operational methods. Recently, we completed software for counting while operating a conveyor in conjunction with DeepSky inspection. It is evolving to be more user-friendly daily based on customer requests.

• Image Processing Software

It is common to see transparent film used in the packaging of supplements, medicines, and food in everyday life. 【Inspection Settings and Results】 (1) Inspection of the number of films → Determination possible I was able to determine up to 5 layers with high accuracy. If a camera is positioned to capture the entire view of 10 layers, it will also be possible to make a determination. (2) Inspection of content volume → Determination not possible In indoor lighting, the reflection from the film made it impossible to confirm the contents. I conducted the inspection by placing a black board next to the sample for photography, but due to overlapping and uneven distribution of the contents, I was unable to distinguish the volume. Adjustments and innovations in lighting and content distribution are necessary for inspection. (3) Inspection of film overlap → Determination errors present Detection was achieved with an accuracy of 80% (10 errors out of 50). Since there are countless patterns of overlap, I trained with 40 images this time, but I felt that increasing the number of training images would improve accuracy. In cases of complete overlap, it tends to be determined as a single layer.

• Image Processing Software

The label sealed on the cardboard box containing the product is prone to accidents where it is shipped inverted, and this is one of the cases that has received numerous inquiries. This time, we assume the inspection will take place on a free roller after assembling the cardboard. 【Inspection Settings and Results】 We conducted a free evaluation using the software DeepSky, which utilizes AI (Deep Learning). We used a total of 40 images as training data, capturing the orientation and angle of the sample labels from varying distances with the camera. In the left diagram, the settings are divided into two categories: "OK" and "NG," where if there is even one "NG," it is considered a failure, and up to three "OK" labels are considered a pass. As shown in the right diagram, there were no misjudgments, and the determinations were made with high accuracy. When the judgments were favorable, many proceeded to try the demo unit on a free rental basis. 【Software and Equipment Used】 Software Used: DeepSky Field of View: 400 x 300mm Minimum Size of Inspection Target: 150mm Number of Inspection Points: 1 (label inversion) Camera Resolution: 1.3 million pixels Lens Focal Length: 6mm Distance Between Lens and Product: 900mm Lighting: Indoor fluorescent lights

• Image Processing Software

It has been said that determining the presence or absence of black components in black workpieces through image inspection is difficult. This time, we conducted an implementation inspection of black accordion-style curtains installed on windows of cars, trucks, and buses. In Hamamatsu City, Shizuoka Prefecture, where our company is located, there are many factories producing automotive parts, and our inspection software is utilized by various automotive parts manufacturers. [Inspection Settings and Results] We conducted the inspection using software that employs AI (Deep Learning). By training the software on the areas we want to detect, it adjusts its own setting parameters and becomes capable of recognition. This inspection software can easily inspect "black defects on black workpieces" and "metal (silver gloss) with metal components or defects (silver gloss)" with simple settings. We encourage you to try it out on our website's "DeepSky Learning Service." We verified it using the black curtains for automobiles that you brought. It was possible to detect the number of installation parts and determine the installation positions of the components. The blue detection frame outside the image indicates a pass for the specified area, while the light green and light blue detection frames inside indicate a pass for the types of components.

• Image Processing Software

The curtains installed inside vehicles such as cars, buses, and trucks are folded in an accordion style. If the various components, such as the belts called "hooks" and "tassels," as well as "Velcro," are not attached in the specified positions, the product will not pass inspection. There is a request to automate the current process where workers use jigs to inspect multiple times. 【Inspection Settings and Results】 The inspection was conducted using the inspection software "DeepSky." First, the components to be identified were annotated (left image). To help the software recognize the inspection areas, we annotated 10 good sample images divided into five categories: belts, part A, part B, Velcro, and product tags. Next, the areas where these components should be installed were specified (right image). Since the curtains are accordion-style, a proposal was made to use jigs for fixing in order to capture the workpiece in the correct specified position. It was possible to accurately determine whether the specified components were in the designated locations, marking it as OK if present and NG if not.

• Image Processing Software

A manufacturer that handles fittings for metal products and resin products is currently inspecting for holes caused by bubbles underwater. The appearance of bubbles varies in quantity, size, and continuity, and floating debris underwater can resemble bubbles, leading to many misjudgments. This inquiry is regarding a switch from the current image inspection software. We conducted a free evaluation of the four types of images you sent: "large, medium, small, and very small." 【Inspection Settings and Results】 We were able to make good judgments using a method to inspect for the presence of bubbles floating on the water's surface. The left image is an annotated teacher image for training purposes. The right image shows the detection frame display. The rising speed of bubbles underwater is very fast, and with frame-by-frame shooting every 0.3 seconds, there was a risk of missing captures and inspections. DeepSky allows for continuous shooting settings, and inspections without fixed positions during conveyor or work processes are also possible, but depending on the computer's specifications, it typically results in still image frame-by-frame shooting every 0.2 to 0.3 seconds. 【Software Used】 Software Used: DeepSky (Training Version) Number of Inspection Points: One location at the top of the screen (entire water surface)

• Image Processing Software

The HDD was sent for testing with sample images. 【Inspection Settings and Results】 The left image shows the annotations, while the right image represents the detection frames. By using DeepSky's inspection features, we were able to identify defects in the fabric, such as "discoloration," "thread pulling," and "holes." The overall shooting environment of the images provided was somewhat dark, and as a result, the judgments were generally correct, but there were two misjudgments regarding the floral patterns. If the images could be captured more clearly with better lighting conditions, it would lead to higher accuracy in the assessments. 【Software Used】 Software Used: DeepSky Number of Inspection Points: Entire screen (discoloration, thread pulling, holes)

• Image Processing Software

Seafood and fruits have a rough similarity in shape, but in image inspection, their shapes are not stable, and variations in size and ripeness can change their color and bulge, making them difficult to assess. Our inspection software, DeepSky, excels in inspecting items with slightly different shapes. This time, we evaluated the defect detection of shucked oysters based on an inquiry from a manufacturer that produces automation robots used in food factories. Since it is not the shipping season for oysters, the inspection was conducted using the images provided. 【Inspection Settings and Results】 Upon verifying the sample images you sent, we were able to detect eggs and black spots. The inspection was performed using software that employs 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. Our software does not only detect based on color; it also incorporates texture (surface quality) into its judgment. Additionally, there is no need for fixed positioning, allowing for detection even if multiple oysters flow on a conveyor in various positions and orientations.

• Image Processing Software