スカイロジック List of Products and Services

We will introduce a system that detects broken tablets and stops the conveyor. It was found that using a mechanical relay to perform ON/OFF at 100V generates significant electromagnetic noise, so we switched to a solid-state relay for testing. We added a patrol light to the wiring for "ON/OFF of the 100V power supply from DeepSky," which alerts with a red light and buzzer when a broken tablet (defective product) flows through, stopping the conveyor. When good products continue to flow, a green light is illuminated, and the conveyor keeps moving. For more details, please check the related links below. 【Tools and Equipment】 ■ PC: Mouse Computer/G-Tune, Core i9, 16GB RAM, RTX 2070 SUPER ■ Image Processing Software: Sky Logic/DeepSky DS100K ■ IO Unit: Sky Logic/EI-ITIO-T01 ■ 1.3 Megapixel Camera: Daheng/MER-133-54u3c ■ 25mm Lens: M2514-MP2 ■ Camera Stand (Aluminum Frame) *For more details, please refer to the PDF document or feel free to contact us.

There are three main categories of inquiries we receive regarding non-woven fabric inspections. - Inspection in a roll-to-roll state - Inspection of non-woven fabric with printed patterns - Inspection of non-woven fabric processed into products like masks The systems used vary depending on each state. For example, inspections in a roll-to-roll state often utilize EasyInspector, while detecting foreign substances on products with printed patterns or processed into masks is a specialty of DeepSky. Processed products have irregularities and overlaps, which can lead to frequent false detections with standard binarization methods. However, deep learning can learn and detect features such as insects, hair, and debris, making it largely unaffected by the variations in product patterns and processing. Here, we will introduce detections made by DeepSky. - Foreign substances such as hair and debris (Images 1 and 2) - Defects such as wrinkles and tears (Images 3 and 4) In roll-to-roll inspections, a method that continuously monitors with a fixed camera while the product is moving is suitable. However, in cases like the masks that have been processed into individual products, considering automatic discharge, the following system can be utilized.

This time, the simple verification was requested by a chemical manufacturer, who sent us photos to consider whether we could perform image inspection for the opening and closing of valves and the monitoring of a 7-segment display. Using the "Presence of Specified Color Inspection" feature of EasyInspector, we were able to inspect one location of the valve opening and closing in 0.38 seconds. The setting is such that if there is a specified number of black pixels within the frame, or if there are none, it is considered OK. In the right image, the handle detected in green is not visible in the right image because the valve is open, so it is displayed as defective with a red frame. For the other 7-segment display, we used the "Meter Reading" feature to read a 5-digit number in 0.35 seconds. Due to the low contrast between the numbers and the background, the reading accuracy was unstable, and we may need to adjust the position of the camera and the meter in the future. 【Software Used】 EasyInspector (formerly EasyInspector) Current version: 'EasyInspector2' CL (color) package [Presence of Specified Color] CP (Control Panel) package [Meter Display Reading] can be used for inspection.

You sent us photo samples of defective conditions that occasionally occur in the silk printing process. Is it possible to introduce inspections for issues like missing characters in silk printing through image inspection? This is a consultation regarding that. We will conduct a simple inspection for "missing" and "fading." By using the "comparison with master image" function of EasyInspector, we were able to conduct the inspection. We performed verification on the sample with the smallest visible defect among the samples we received. As a result, under limited conditions (*), we were able to detect the defect of missing characters. However, outside of those conditions, due to the nature and shape of the product, we mistakenly detected many areas that were not defective. *The limited conditions refer to when the inspection was conducted by focusing on one specific area of the printed part, so if we try to operate under the same conditions, the inspection range will likely be quite limited.

Until now, the focus has primarily been on the utilization of equipment within factories and manufacturing sites, but with AI capabilities, it has become possible to detect humans and animals, allowing for applications in various industries such as agriculture. This contributes to reducing time and effort through verification. ■ Management of control panels in greenhouses Automates visual patrol checks using cameras and image processing. ■ Measures against wildlife damage Ignores humans and vehicles, detecting only birds and animals. ▼ Image collection possible in areas without power In forested areas and farmland without power, it is possible to supply power using solar batteries and collect images via mobile phone lines. Real-time notifications can be sent regarding damage from wild boars and deer, as well as illegal dumping. 【Functionality and monitoring examples】 Analog meter reading Reading flow meters, float meters, etc. Digital display (7-segment) numerical reading Lamp status (such as in control panels) Dot matrix numerical reading Reading values and displays from centralized management PC monitors Reading vertical rotation power meters and difficult-to-read characters Monitoring absence of people and entry into restricted areas Detection of insect contamination and animal intrusion Condition of liquids

We received an inquiry from a company that produces labels and POP materials, and we will verify the printing defects. First, we asked them to visit our company for an explanation of our inspection software, leading to a simplified verification process. Our company also accommodates web meetings for those who cannot visit in person. To prevent the work's backing from lifting and affecting the inspection, we pressed down on it with a transparent glass plate while taking photos. If we took photos with the backing still lifted, we detected many discrepancies compared to the master. We covered the "comma" in the print with black to eliminate it and used the "comparison with master" feature of EasyInspector when it reappeared for verification. As a result, we were able to detect the comma. Since the detected value was less than 10 pixels, which is very small, if we want to detect such defects, we need to be careful about the position of the sample when placing it (to minimize misalignment) and avoid detecting discrepancies due to changes in lighting.

We received an inquiry from an industrial machinery manufacturer regarding wastewater treatment. We will inspect whether the treatment has been sufficiently completed. At SkyLogic, we research the latest technologies such as AI and IoT, transforming them into user-friendly products for our customers. For example, in the AI field, we offer DeepSky, which enables flexible recognition through deep learning, and in the IoT field, we have EasyMonitoring, which processes images from dozens of network cameras. By using the "Defect Inspection" feature of EasyInspector, we detect the processing status of the entire image at one location. When inspecting with EasyInspector, it is necessary to stabilize the imaging environment. Although we were able to detect it this time, we recommend using inspection software that employs AI (deep learning) for operational purposes. [Software Used] Software: EasyInspector310 (formerly EasyInspector) Current 'EasyInspector2' color package [Defect Detection] Inspections can be conducted with 'EasyMonitoring2'.

This is an inquiry from a company that sells lighting fixtures. It is a simple verification to determine whether the LED chips, which are the source of the lighting, are of good quality (i.e., whether there are any defects). There is growing expectation for tools that promote automation and labor-saving in manufacturing lines by combining various inspection systems. We hope to be of assistance to our customers by applying our inspection software. 【Inspection Settings and Results】 The inspection item was positioned within the screen, and settings were made using the EasyInspector "Presence of Specified Color" inspection function. Additionally, the number of lit locations was set in "Counting Mode." The left image is an enlargement of the inspection results, where the green areas indicate the detected parts of the specified color, and the numbers represent the detected pixel count. The right image shows the imaging environment for this inspection.

We received an inquiry about wanting to determine the size of caries (cavities) using a model that mimics external caries on the appearance of teeth. The processing of caries involves marking the position and size on the tooth using a gauge, then using a motor (grinding machine) to freehand grind and shape it. The inspection defines the center value of the height and width of the caries, with items exceeding the maximum value or below the minimum value being deemed unacceptable. 【Inspection Settings and Results】 By using the "Presence of Specified Color Inspection" function of EasyInspector, we were able to determine the presence and size of a caries hole in 0.11 seconds. The settings included a color judgment tolerance range set to "90," with the specified color being "black" and all RGB values set to 0. The light blue pixels "136" at the bottom of the image on the right represent the number of fluorescent pixels (caries detection pixels) within the blue frame on the left. 【Software Used】 Software Used: EasyInspector710 (formerly EasyInspector) The current 'EasyInspector2' color package can perform inspections for the "Presence of Specified Color."

The manufacturer of FA machine automatic systems was considering inspection software for film defects. Our company has over 2,000 implementations in inspection lines and is utilized in various fields such as electrical, electronic, mechanical, and assembly. By replacing visual inspections with image processing, automatic appearance inspection that prevents the outflow of defects can be realized. 【Inspection Settings and Results】 Using the "Comparison with Master Image" function of EasyInspector, we conducted inspections for tape defects in two locations and foreign substances on the tape. While detection was possible, the inspection cycle took more than "1 sec per piece." - There is a shift for each image, which takes time for shift correction. - The images you provided this time have a high resolution of 40 million pixels. → It may be necessary to reduce it to around 300,000 pixels. Due to the time required for shift correction as mentioned above, we recommend using image inspection software with AI (deep learning) for verification in cases where shifts occur in operation, as shown in the sample images.

We received an inquiry from a representative of a manufacturer of pneumatic devices and control equipment who is considering changing the current visual inspection standards for the dimensional inspection of parts processed by work machines to data-based standards. They expressed a desire to keep a record of the product dimensions and provided sample images. 【Inspection Settings and Results】 We conducted a simple verification of inspections using both EasyInspector and DeepSky. Both were able to detect the dimensions. Our company can offer both the traditional rule-based inspection software "EasyInspector" (detection results are shown in the left image) and the AI (deep learning) based "DeepSky" (detection results are shown in the right image) as needed. For recording methods, there are options to save as SCV (Excel) and inspection images. 【Software Used】 Software used: EasyInspector, DeepSky

No more searching around! The QR process management system eliminates the hassle of reporting and the wasted time spent searching for materials, as well as the effort required to check combinations of materials and tools. By combining QR codes with a network system, we can connect "things" to "things," "things" to "locations," and "things" to "processes," thereby eliminating the hassle of reporting, the waste of searching for items, and losses due to mistakes with items. For example, if information such as whether materials have been "delivered," "when and where they were delivered," and "which process they are currently in" can be easily and accurately shared within a group, it can reduce the hassle of reporting and the wasted time spent searching for materials, as well as the effort required to check combinations of materials and tools. 【Product Lineup】 ■ QR Mono Doko This is a smartphone-based app that can be easily started on a small scale. By scanning the QR codes of the location and product with a smartphone during delivery, the group can simply share "what is where." ■ QR Fixed Point Monitoring System By installing fixed network cameras, we can continuously capture the state of materials, tools, and pipe connections that are always present, automatically verifying whether they are in the correct condition.

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.

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.

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.

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).

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.

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.

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】.

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."

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.

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.

Manufacturers active in various fields, particularly in medical devices and welfare equipment, are considering our character recognition functionality. Reading the text on labels affixed 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 was conducted using the "OCR Pro" feature of the EasyInspector software. 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 displays the detection frame after binarization. The evaluation was based on the provided photograph, but there are concerns about positioning due to the fact that the labels are applied by hand and the cylindrical shape of the parts. 【Software Used】 Software used: EasyInspector710 The current 'EasyInspector2' RD (ReaDing) package can perform inspections with [OCR (Character Recognition)] and [Machine Learning OCR].

This is an inquiry about inspection functions from a measurement equipment manufacturer. This time, we will explain the features of EasyInspector, which you can try for 60 days from our website. The inspection function can read text across various genres. Text reading can be done without selecting a font, and it is also possible to binarize the text or register it in a dictionary with learning capabilities. 【Inspection Settings and Results】 We have responded via email that inspection is possible using the "OCR Pro" feature of EasyInspector. It seems that "unreadable images" may require the use of lighting fixtures or shading. Our company proposes an all-in-one and simple operation inspection software aimed at "making it easy for field users to operate" to improve operational efficiency. 【Software Used】 Software used: EasyInspector710 The current 'EasyInspector2' RD (ReaDing) package can perform inspections with 【OCR (Optical Character Recognition)】 and 【Machine Learning OCR】.

Manufacturers of chemical products such as ink, like those in other industries, clearly indicate the manufacturing date and other details during delivery packaging. We conducted a simple verification of character reading for shipment management. Our image inspection software has the basic functionality to save inspection results in CSV format and images. This makes product management easier, and it is being utilized by various manufacturers. [Inspection Settings and Inspection Results] By using the "OCR Pro" feature of EasyInspector, it was possible to read 15 characters in two locations in 0.09 seconds. If the inspection is only to check for the presence or absence of printing, it is possible to configure a system for under 100,000 yen by combining the EI100 software with a commercially available web camera. Additionally, for automation, you can use our I/O unit or perform external control via socket communication or RS232C communication. The image on the right shows the detection frame for passing products, while the image on the right displays an enlarged view of the detection frame for failing products.

Residential equipment and home appliance manufacturers are considering our character recognition functionality. We conducted a simple verification by sending photos. Inspection settings and results: We confirmed that if the image quality is good with EasyInspector's "OCR Pro" feature, it is possible to read the text. We believe that if we can confirm that "there are lighting conditions under which all three workpieces can be read simultaneously," we can determine that inspection is feasible. There are two methods to verify these "conditions for good image quality": (1) Sending sample products for verification, which we will check. (2) Lending equipment for you to verify in your environment. Both methods are essentially free of charge. The left image shows the "Processing 1" screen where settings such as binarization can be configured. The right image is an enlarged view of the detection frame.

We received an inquiry from a manufacturer of infrastructure and medical devices, with whom we have had a business relationship for some time, regarding the reading of "assembly check sheets." The verification of check sheets can be applied across various industries, including situations in banks and government where handwritten input is required. Please consider promoting operational efficiency through image inspection. 【Inspection Settings and Results】 By using the "designated color comparison inspection" feature of EasyInspector, it was possible to determine the presence or absence of 21 checks in 0.5 seconds. The inspection time varies depending on the specifications of the PC used and the number of inspection points. The software used this time (EasyInspector) also has a version equipped with OCR functionality, but it does not support the reading of handwritten characters. (EasyInspector2 does support this.) 【Software Used】 Software: EasyInspector710 The current 'EasyInspector2' color package can inspect for the presence or absence of designated colors.

This is an inquiry from a trading company. We will verify whether it is possible to read the product name, JAN code, expiration date, and lot number printed on the outside of the cardboard using an industrial inkjet printer based on the images provided. This time, we have incorporated the images you provided into our software. Regardless of the industry, I believe labels are displayed at the time of delivery, and this is an example that can be applied across various industries. 【Inspection Settings and Results】 Regarding the reading of the barcode and other prints on the cardboard that you contacted us about, we have confirmed it with the images you provided. As a result, we were able to read QR codes, barcodes, dates, model numbers, etc., from a portion of the images provided, which falls within the scope that we can accept for free as a simple verification. By using EasyInspector's "Bar/QR Reading" function and "OCR function," we were able to make judgments at four locations in 0.54 seconds. The left image shows the inspection frame settings, and the right image shows the detection frame.

This is an inspection of product labels at a packaging materials manufacturer. The demand for inspection automation due to labor shortages has been increasing year by year. I feel that the situation where people cannot gather at factories due to the spread of the new coronavirus is further exacerbating this issue. Please consider automating inspections to facilitate smooth production management. 【Inspection Settings and Results】 By using the "Comparison with Master Image" feature of EasyInspector, we detected differences in position. Even for good products, variations in printing tilt, color intensity, size, etc., were detected, resulting in a "fail" judgment. It will be necessary to change the inspection software for future verification. 【Software Used】 Software used: EasyInspector710 The current 'EasyInspector2' color package can perform inspections using the "Comparison with Master Image" feature.

The manufacturer of the USB memory has the product model number printed in laser, and visual checks were conducted for issues such as fading, misalignment, or absence of printing. There was an inquiry regarding automation. 【Inspection Settings and Results】 By using the "OCRPro" feature of EasyInspector, we were able to successfully read the laser print of 9 characters in one location in 0.43 seconds. The left image shows the binarization settings screen "Process 1". The right image is the dictionary function registration screen. It will be possible to read characters that are not commonly used fonts by utilizing binarization and the dictionary function. 【Software and Equipment Used】 Software Used: EasyInspector710 Field of View: 47 x 37mm Minimum Size of Inspection Target: 20mm Number of Inspection Characters: 9 characters Camera Resolution: 1.3 million pixels Lens Focal Length: 35mm + 5mm close-up ring Distance from Lens to Product: Approximately 275mm Lighting: Linear fluorescent light Distance from Lighting to Inspection Item: Illuminated from above at an angle. Current 'EasyInspector2' RD (ReaDing) package can perform inspections with [OCR (Optical Character Recognition)] and [Machine Learning OCR].

This is an inquiry from a company we have been doing business with even before we started working on infrastructure systems. We sent samples for testing the reading of QR codes to verify the size at which they can be read. QR codes are commonly seen everywhere as highly practical codes. Our inspection software includes basic functions for saving inspection results in CSV and image formats. Our code reading functionality is utilized in various management tasks by manufacturers. 【Inspection Settings and Results】 By using the "Bar/QR Code Reading" feature of EasyInspector, we were able to read codes at two locations. The failure indicated in the left image shows that "QR width: approximately 33 pixels is unreadable," while "QR width: approximately 40 pixels is unstable." The pass shown in the right image indicates that "QR width: approximately 47 pixels is stable." We conducted several reading tests with a combination of a 14-megapixel camera and an 8mm lens. By setting the environment so that the width of one QR code is around 50 pixels, it was possible to read the code.

Samples have arrived from a customer who plans to incorporate the following inspections into the current line: inspection for the presence or absence of bottle cap shrink, inspection for the presence or absence of printing on the bottom of the bottle, complete inspection of labels' barcodes (two-dimensional transparent) within the inline labeler, complete inspection of barcodes on inner packaging boxes (black two-dimensional on coated cardboard), and complete inspection of barcodes on outer packaging boxes (two-dimensional black on cardboard). 【Inspection Settings and Results】 All three types of inspections were determined to be satisfactory. For verifying the presence or absence of text on the bottom of the bottle and the presence or absence of shrink, we used EasyInspector's "Specified Color Presence Inspection" feature. An inspection frame was set up for the bottom text, and it is configured to pass if white is detected within that frame. The inspection frame can also be set to a ring shape as an optional feature. The presence or absence of shrink is determined by the amount of direct reflection (white) from ring lighting. For reading the label barcodes, we utilized EasyInspector's "Bar/QR Code Reading" feature, which allows for reading barcodes with black on a white background or white on a black background, and the barcode can be rotated during processing for reading.

The industrial equipment and machinery manufacturer you inquired about has requested multiple simple verifications in the past. This time, the contact is regarding consultation on inspection methods for scratches that occur on the side walls. However, detecting "scratches" is not a must for the ongoing inspection, and they are looking for technical cooperation on how the inspection can be conducted. 【Inspection Setup and Results】 By using the "Scratch Detection" feature of EasyInspector, we were able to determine a scratch in less than one second at a single location. If the scratch is captured well from the top view, there is a possibility of detection using the scratch detection feature. We receive numerous inquiries from industrial equipment manufacturers, and we offer explanations on usage and demonstrations during web meetings or visits involving end users at no charge. 【Software Used】 Software Used: EasyInspector710 The current 'EasyInspector2' color package can be used for scratch and defect detection.

The fact that 'there are inevitably oversights by operators during visual inspections' can occur not only in factory production processes but also in other areas. This inquiry comes from an industrial machinery manufacturer, but the verification of check sheets filled out by humans is a common issue across all industries. [Inspection Settings and Results] We printed the data from the check sheet you sent and conducted tests. We verified the presence or absence of checks on paper. By using EasyInspector's 'OCR Pro' feature, we were able to read five holes or symbols in just 0.62 seconds. After a simple verification, we will conduct an in-house demonstration. Additionally, we offer a web video demonstration on our website, a 60-day trial software download, and a free evaluation service for inspection items, all aimed at providing information and support to help customers easily implement the inspection system. We look forward to your inquiries and hope you take advantage of the above services. If you have any requests or questions, please feel free to contact us anytime.

We received an inquiry from a battery manufacturer stating, "There is a white + mark on the cover, and we want to determine if there is any mistake in orientation based on its position." They also expressed a desire to take photos while holding a tablet and camera by hand. 【Inspection Settings and Results】 By using the "Presence of Specified Color Inspection" feature of EasyInspector, we were able to determine the orientation of the parts. We reported on a simple verification. Inspection frames were set up in multiple locations (this time at six locations: including two NG locations). We set "white" as the specified color and conducted the inspection based on the extent to which the specified color was detected within the inspection frame. When using EasyInspector, it is essential to fix the camera. While it is possible to take photos with a tablet, it needs to be secured. 【Software Used】 Software used: EasyInspector710 The current 'EasyInspector2' color package can perform inspections for the "Presence of Specified Color."

Our company is located in Hamamatsu City, Shizuoka Prefecture, which is known for its thriving automotive parts manufacturing industry. Our main customers are manufacturers of various industrial machinery and control equipment, as well as users. We have a track record of providing support for over 1,000 cases and are developing inspection software that is easy to integrate and sold as a one-time purchase. 【Inspection Settings and Results】 By using the "Specified Color Presence Inspection Function" of EasyInspector, we conducted an inspection at one location. We used a circular frame (optional), but by enclosing the entire workpiece and masking the black background and seam areas, we believe it can also be inspected with a standard frame. In the left image, the masking function allows us to set "non-detection pixels" for areas that should not be inspected, which helps shorten the cycle time and eliminate false detections; it is a highly convenient feature. The right image shows the detection results. 【Software Used】 Software Used: EasyInspector710 The current 'EasyInspector2' color package can perform inspections for "Specified Color Presence."

This time, we received an inquiry from a contract analysis company. Work size: approximately 100mm × 100mm. Seal size: approximately 10mm (width). We created a model and conducted a simple verification. In cases where we receive inquiries, there are many instances where we cannot send sample products or sample images due to compliance and security concerns. [Inspection Settings and Results] Using EasyInpector's "Dimension Angle Inspection," we referred to the materials you provided and measured the tolerances with the seals applied by our company. This time, we measured only one location for each seal, but it is actually possible to measure four points simultaneously. We used a 5-megapixel camera (2592 × 1944) with a field of view of 180mm horizontally, capturing images of a 100mm × 100mm metal plate. We measured by applying two seals, each 10mm wide. There was some slight shaking during imaging, resulting in an error of 3 to 4 pixels, but detection with an accuracy of 0.5 to 0.7mm in tolerance is theoretically possible. Increasing the camera resolution will improve accuracy further.

This is a free simple verification based on the sample images you provided. It is from a manufacturer of industrial control equipment with whom we have had transactions in the past. In image inspection, the imaging environment is a very important point. This time, the accuracy of the inspection varied depending on the captured images. 【Inspection Settings and Results】 We were unable to obtain good results with the images as they were, so we cropped only the areas to be evaluated and conducted the verification. As a result, in the case of the images we verified this time, if we could set the field of view appropriately for the judgment of the paper tube, it was possible to make a judgment. Since there were few OK images, we created mirrored images to use for verification. We used a total of 20 images for training, consisting of 10 OK images and 10 NG images. For the validation of the judgment, we used 2 OK images and 2 NG images that were not used in the training, for a total of 4 images. 【Software Used】 Software used: DeepSky

We received a direct request from a customer who manufactures medical capsules and were conducting a preliminary verification. However, since our company does not sell FA machines, we decided to proceed with the verification through the manufacturer of the control equipment that the customer is dealing with. Our company is located in Hamamatsu City, Shizuoka Prefecture, and we have many industrial machine manufacturers as clients, primarily in the automotive industry. We have developed easy-to-integrate inspection software that is sold outright, and we have received numerous repeat orders from manufacturers of industrial machines and systems. 【Inspection Settings and Results】 As a result of processing the images received, the first image was detected normally. The second image had one false detection and one non-detection. After retraining, it was able to detect normally. After verification, we will conduct a demo at our company to explain the inspection environment and operation methods, and we will lend out demo units so that you can actually check the setup methods and inspection accuracy. 【Software Used】 Software used: DeepSky

At the request of a manufacturer of industrial equipment, we conducted a simple evaluation to determine the harvest timing of strawberries. We used 58 sample images for the inspection. (34 strawberries were classified as OK and 24 as NG) 【Inspection Settings and Results】 As a result, all "harvestable strawberries" were correctly detected. Teacher Images: Correct Judgment 100% (20/20) Incorrect Judgment 0% (0/20) Unlearned Images: 94% (32/38) 6% (2/38) Total: 96% (56/58) 4% (2/58) However, among the strawberries classified as NG, two strawberries that appeared close to OK when viewed by the human eye were mistakenly classified as harvestable. (1) Still pinkish in color, therefore not harvestable... NG1 (Pink) (2) Still white or green, therefore not harvestable... NG2 (White or Green) (3) Strawberries that can be harvested... Harvest OK By creating three types of labels and training the software, it will adjust its own setting parameters and improve recognition. The images are annotated.

This is a case that we continued to consider after a simple verification. In image inspection, the shooting environment is very important. If we can accurately capture defects, inspection is possible with a high probability. It is necessary to prepare the inspection environment within the operational range of the camera, lens, and lighting. [Inspection Settings and Results] While continuing our discussions, we found that using a backlight allowed us to clearly capture the entrapment (defect), which is expected to improve the detection rate, so we were able to provide a good report. The device used this time is a tracing table that costs several thousand yen, so I believe that sufficient effects can be obtained even with lighting that is not specifically for inspection, as long as it is a surface light source. Our company website offers a free web trial of the inspection software. You can actually experience the inspection software that uses AI (deep learning). [Software Used] Software Used: DeepSky

The photos you provided made it difficult to conduct inspections due to the shooting environment. While I was able to make a judgment as a simple inspection, it is particularly necessary to carefully consider the lighting, camera, and lens setup when dealing with glossy workpieces. [Inspection Settings and Results] You sent a total of 9 images, of which 6 were used as training images. Each of the 6 images was divided into 60 segments using image segmentation software, and 23 segments with scratches were used for training. The remaining 3 images were used for testing, and these were also divided into 60 segments before inspection. I also tried to detect dents, but I was unable to do so. It is thought that the difficulty in visually identifying certain areas may be the reason for the unsuccessful training, and I believe that defective detection can be achieved depending on the imaging environment. [Software Used] Software used: DeepSky

We received an inquiry from a manufacturer of various machine parts regarding bearings. They currently monitor the treatment of waste liquid through visual inspection, and it is said that when aggregation occurs from the state shown in the left four images below to the state in the right four images, it is considered acceptable. Although there is a roof, it is not an indoor environment, and the imaging conditions for inspection change depending on the time and weather. 【Inspection Settings and Results】 We set 24 images, including the ones above, as training images, annotated them all, and were able to make judgments. With the version upgrade in 2021, we were able to incorporate a data augmentation feature for training images. We will continue to develop inspection software that is user-friendly and practical by adding various convenient features. The strength of AI (deep learning) image inspection software compared to traditional rule-based image inspection software is its ability to perform inspections even with differences in brightness and imaging environments. Inspection software can be beneficial in various industries and processes. 【Inspection Software】 Software used: DeepSky

This is a simple evaluation to detect the "black spots" dirt on workpieces, based on inquiries from manufacturers of precision cleaning agents and car chemical products. The priorities are (1) the presence or absence of lot printing, (2) the proper position of lot printing (front and back of the bottle), and (3) the automation of inspection operations for label dirt. Our company generally offers two types of inspection software: the traditional rule-based image inspection "EasyInspector" and the AI-based "DeepSky." This time, we will use DeepSky, which specializes in detecting black spot-like dirt without fixed positioning, assessing the entire screen. 【Inspection Settings and Results】 As a result, we were able to detect the "presence or absence of printing" and "dirt." We registered multiple images (5 images during verification) of the "dirt" area using the inspection software "DeepSky," performed "annotation," and conducted "learning." Since there was only one type of dirt sample, we reproduced dirt in one additional location (by applying transparent tape and recreating black spots on top of it).

This is a request for evaluation from a manufacturer of audio systems such as speakers. Before the inquiry, line workers were conducting visual inspections of about 10,000 units a day. Due to the black resin and dark adhesive, the work had characteristics that made it very difficult to see, both visually and with cameras. 【Inspection Setup and Results】 Since it was difficult to conduct inspections with EasyInspector, we used a product that utilizes deep learning called DeepSky. Initially, we tried training with the existing images, and detection was possible; however, the number of data points was small, and the images were very difficult to inspect, so I believe more detailed verification is needed in terms of accuracy. Nevertheless, detection was achieved to some extent, and I am reporting the above image as documentation of that process. 【Software Used】 Software used: DeepSky