1. ProVision Vision System combines visual measurement and automation to enable large-scale production.
2. The system uses five Dalsa line scan cameras to process an area of up to 21” x 25” with a resolution of 5um/pixel. It can inspect and measure over 60 different electronic components on a PCB board per second.
3. When the image is first acquired, each camera will first locate a reference point and measure the overall grayscale value of the PCB to facilitate subsequent image binarization and size measurement. The image analysis and processing can all be done through the computing power of the Matrox image card to reduce the processing on the PC.

Solomon combines machine vision and artificial intelligence to use the Feature Detection tool of the SolVision AI image platform to define the characteristics of the assembly positions of each component in the PCBA layout, and train the AI model with the defined image samples. Through the trained AI model, it can instantly detect abnormal conditions and locations such as missing components or assembly errors.

Cognex Deep Learning handles a wide variety of defects, making it the optimal solution for this application. The defect detection tool learns ink printing problems on curved surfaces and reflective surfaces of syringes before recognizing if ink is too heavy, too light, or dirty using pattern matching software paired with High Dynamic Range Plus (HDR+). This technology decreases glare, enhances contrast, and accelerates automaticized print inspection speeds. Distinguishing factors include quick single-exposure collection for moving components via HDR+, whereas Standard HDR demands immobility and multiple image acquisitions for comparable results.

Cognex PatMax technology and color tools can identify designs and stamps, regardless of changes in direction, angle, lighting, and other factors that can affect the appearance of items on the production line. PatMax uses a set of boundary curves to learn the geometric shape of an object and then searches for similar shapes in the image, without relying on specific grayscale values. Damaged or broken products are removed before being packaged or shipped, avoiding costly returns and protecting brand reputation.

When using traditional automatic optical inspection to detect plastic defects, it is difficult to quantify the defects due to the variety and changing positions of the defects. It is easy to encounter the problem of insufficient defect samples, which makes it difficult to quantify the defects. This leads to insufficient detection accuracy. If manual inspection is maintained, the detection speed is relatively slow and the quality is inconsistent. There are still many difficulties in identification.By using SolVision's Segmentation technology, a defect database is established for the shape and color of rubber product defects, and then AI is used to learn the characteristics of the defects. This can identify defects of various types and positions. With the increase of learning images, the ability of AI visual inspection is continuously optimized, which significantly improves the accuracy of rubber defect identification and effectively solves the problem of unstable detection of rubber product defects.

The internal components and circuits of power supplies are diverse and complex. When detecting connections, they are easily affected by background interference, which affects visual judgment. On the other hand, wires are deformable materials and can be arranged and stored in different ways depending on the assembler. These factors make it difficult for both manual and traditional optical inspection to be performed, making it difficult to effectively control product quality on the production line.Using Solomon SolVision's Segmentation technology, the correct and incorrect feature patterns are defined according to the wire color and terminal block assembly conditions in the image, and the AI model is trained. The trained AI model can accurately detect and locate wire misconnection defects and identify defective products in real time.

Cognex's AI tools help minimize defects related to assembly processes in mini LED screen manufacturing, including solder volume and alignment of LED chips on bonding pads. The detection system uses a series of images representing both good and NG (defective) results during its training phase. It learns to tag notable defects while disregarding abnormal situations within acceptable tolerances. These tools are capable of precisely locating and identifying targeted inspection zones (ROIs) along with any potential critical defects present within those regions. Manufacturing managers can use this information to more efficiently manage the quality of displays, thereby reducing costs and increasing profitability.

In the production of fasteners, the most common injection molding defects are mold release agent oil stains, white spots, burrs and debris, of which oil stains are the most difficult to detect. White spots, burrs and debris have obvious features in the image, while products with oil stains are very similar in appearance to general good products, which are difficult to detect.Using the Segmentation and Classification technology of Solomon SolVision AI image platform, deep learning is performed for each type of surface defect. After the AI model is trained, it can immediately detect all types of defects including oil stains.

Cognex Deep Learning provides an effective inspection solution that combines the human ability to identify subtle variations with the reliability, consistency, and speed of an automated system. Engineers can use the Cognex Deep Learning software's defect detection tool in supervised mode to train the deep learning-based software on a set of representative "good" and "bad" compression ring images. Technicians can add annotations to "bad" images where there are long scratches, and to "good" images with normal variations and allowable defects such as rust and small cracks. Based on these images, Cognex Deep Learning can learn the natural shape and surface characteristics of pistons, as well as the typical appearance of scratches.

Apacer's pillow-shaped bottle independent machine inspection can replace manual multiple inspections, and its special fixture design has obtained a patent for invention design. The machine is versatile and uses 9 precision optical lenses to simultaneously inspect 3 types of internal and 4 types of external bottle defects and supports 5 types of pillow-shaped plastic bottles with a capacity of 15ml or less. In order to adapt to the space environment of the inspection room, a U-shaped design is adopted to facilitate the reduction of the overall size of the machine. It is equipped with a turntable fixture mechanism, visual judgment software, and human-machine interface information display.

Cognex In-Sight 2800 Series Smart Cameras fit neatly into confined quarters of tobacco manufacturer gear. Mounted above hopper bins, In-Sight 2800 sports embedded high-powered lighting rigs, distinguishing loose tobacco apart from pouches. Surface Flaw Tools match perfectly with Filter Program Tools, highlighting luminosity and contrast discrepancies indicative of perforated states especially handy for similarly colored brown tobaccos. Dependably inspecting vessel contents, In-Sight 2800 removes faulty chewing tobacco packs prior to reaching consumers' hands.

High-precision PIN inspection machine designed specifically for PINs, fine inspection, to ensure product quality

Using SolVision AI image platform's unsupervised learning tool Anomaly Detection, AI deep learning is performed with non-defective image samples (Golden Sample), and data augmentation technology is used to improve the AI model's recognition of standard samples. The trained AI model can identify the differences between the tested object and the standard sample, locate and mark the position of the micro-crack defect inside the packaged chip, and is completely unaffected by the characteristics of the penetrating image.

By using Solomon SolVision's Anomaly Detection Tool unsupervised detection tool, the images of PCBA Golden Sample are learned to train the AI model. It can identify the differences between the PCBA to be inspected and the Golden Sample and mark them as defective, which greatly improves the inspection efficiency.

1. Solder paste inspection: Machine vision can inspect for slump, cleaning, bridging, and spikes. It can also be used to visually inspect solder paste location and shape to close the loop control of PCB screen printing process.
2. Surface mount device inspection: Machine vision can inspect for lead length, width, spacing, bend, lead presence, chip size, and ball location, size, and spacing.
3. Automated optical inspection (AOI): When visually testing assembled circuit boards, AOI inspects component placement and checks for missing, reversed, or incorrect components.

Solomon combines machine vision and artificial intelligence to use the Segmentation technology of the SolVision AI image platform to locate and annotate scratches, dirt and other abnormalities and defects on the aluminum substrate in the image sample. Through AI deep learning, it can automatically and instantly detect and locate various defects on the aluminum substrate, greatly improving the production efficiency of the production line.

SMD capacitors are small in size, and it is not easy to pick and place them. To observe defects, it is necessary to observe them under microscopic tools. And because MLCCs are very fragile, the inspection process must also be very careful, which increases the difficulty of inspection.Using SolVision's Segmentation technology, the shape and location of defects on the protruding part of the electrode are learned, and an AI model is established. After the AI learns the characteristics of the defects, it can quickly detect the defects on the protruding part of the capacitor, which greatly improves the overall yield of the process.

1. Flaw detection for various sizes of polarizing plates, brightness films, light guide plates or color filters
2. Detection of various defects, such as foreign objects, creases, indentations, PVA patterns, etc.
3. Three-part mobile inspection, using multiple angles, different light sources and multi-directional methods for measurement
4. CCD can choose different resolutions according to pixel and pitch size, as a judgment for defect measurement
5. Linear and area cameras can be selected for mixed detection of different defects and different accuracies
6. Integrated and customized design to reduce unnecessary adjustment and development costs
7. Can be integrated with production history, scan barcode to link work orders and serial numbers, and complete traceability system with customized database

Cognex AI technology combined with High Dynamic Range Plus (HDR+) technology offers an ideal solution for particle material detection. The Cognex AI solution trains using diverse microparticle substance types found inside pills and pill containers, accounting for varying shapes and sizes, whether air bubbles are present, and incorporates reflections and refractions seen through glass bottles and container windows. As a result, it effectively detects particles even under complex lighting conditions.

Rule-based visual systems face difficulty adapting to seal variations, opacity, or Tyvek materials. Nevertheless, Cognex Deep Learning Solutions serve as supplementary and alternative options. Deep learning reliably identifies foreign objects, invalid sealing, impurities, improper labels, and paint coating flaws detrimental to package integrity. Implementing 100% visual inspection achieves peak efficiency by minimizing operator error and providing instantaneous highlighting of concerns. Such highlights facilitate clear distinction of issues for personnel or machines, followed by subsequent categorization later.

Cognex Deep Learning can dependably examine medical kits bundled in packaging for potential defects despite the presence of components facing varied angles and construction diversity among tubes. By undergoing comprehensive kit image training, the Part Location Tool discovers and confirms necessary components' existence, regardless of numerous possible appearance modifications that could complicate assessment. Damage sustained during assembly leading to deviation beyond allowed change margins causes kit failure in final examinations.

1. Resolution and defect detection capability range can reach 3um~5um
2. Detection area can cover both the mask area and the frame area at the same time
3. Inspection technology can support mask products with different image designs and any shape
4. Intelligent defect classification function

1. Common appearance defect inspection of optical films: creases, hand sweat, residual glue, water stains, foreign objects, black lines, oil stains, etc.
2. Inspectable materials: upper diffusion film, lower diffusion film, composite film, lamination film and brightening film, etc.

NGI Glass Disc Series is a series of glass disc inspection machines that use the light transmission properties of glass to automatically detect defects on both the top and bottom of the glass disc.

Cognex Deep Learning trains with numerous examples of successfully inserted needled nozzles within an acceptable range, alongside outliers marked as defects characterized by characteristics beyond the scope of acceptability, such as air bubbles, cracks, insufficient adhesion of connecting glue, problematic conical tips, or other inclusions. It flags these defects and eliminates them from the production line. Due to ease of training new needle lengths and measurement values, manufacturers avoid lengthy and complicated programming procedures required in conventional machine vision implementations.

1. Real-time autofocus
2. Real-time image stabilization function
3. Smart measurement function
4. Comprehensive observation of bright field and DIC
5. Ultra-long depth of field synthesis function
6. Ultra-large range puzzle
7. Image target navigation
8. AI defect target detection
9. 3D profile measurement

1. Die Bond / Wire Bond multi-layer Chip stacking measurement and inspection can be used, and the AI inspection system can be used to improve the detection accuracy rate to 99.99%
2. Distance: arc height, gap between arcs, line spacing, etc., any measurement of plane or step distance
3. Abnormality: Wire deviation, ball drop, broken wire and other appearance defects

1. Cognex Deep Learning quickly and reliably solves Printed Circuit Board (PCB) assembly verification challenges by undergoing training with sets of qualified vs unqualified PCB images. Three distinct deep learning tools operate seamlessly together on a single workstation for uniform testing of circuit boards without causing delays in production.
2. Assembly Verification Tools check if all components appear correctly positioned; meanwhile, Defect Detection Tools mark any solder problems, damaged locations on board-mounted components or other flaws. OCR (Optical Character Recognition) Tools read all characters on circuit boards and component surfaces, outputting them as text strings.

1. Cognex has specially developed Coated Optics Inspection (COI) machines dedicated to MLCC testing, featuring tailored lighting modules combined with advanced deep learning visual tools. Firstly, custom illumination modules specifically crafted for MLCC tests significantly reduce irrelevant surface fluctuations on capacitor bodies, making hidden defects apparent.
2. Following MLCC checks via Automated Optical Inspection (AOI) machines, COI machines ensure lower false report rates, fewer removed qualifying components from the production line, reduced manual checks, faster speed, enhanced accuracy, and valuable improvement insights in the processes.

1. Image recognition rate > 95%
2. Model adjustment
3. Intelligent classification
4. Can detect pores, holes, notches, cracks, micro-cracks, material surface indentation, dirt, scratches, foreign body adhesion, material deformation

Cognex's AI technology helps microLED manufacturers identify defective chips on display panels by being trained with a range of images showing both good and NG (defective) outcomes, enabling the software to skip over insignificant variations within tolerance ranges and instead flag major defects. This analysis tool scans specific areas of the panel, locating subtle imperfections in microLED components. Production managers can utilize a classification tool to categorize various defect types, optimizing upstream processes and boosting overall manufacturing efficiency. By detecting and resolving defects early in the process at an economically viable cost, this solution enables manufacturers to supply their customers with higher quality panels.

1. AI real-time detection; detection calculation speed can reach up to 50 FPS or more
2. Detection items: copper pad defects, offset, LED bonding abnormalities (chip position displacement/rotation)
3. Can support different sizes of substrates/panels according to customer needs

NCI Conveyor Belt Series is an entry-level automatic inspection machine that is ideal for budget-conscious buyers who need to inspect products for single-sided defects.

1. Ultra-high-speed AI real-time detection
2. Detection items: Chip defects, damage, dirt, scratches, missing chips
3. Post-mass transfer chip position displacement/rotation measurement
4. Can support “4~8" wafers and different sizes of panels according to customer needs

1. High-speed detection + AI defect classification
2. Detection items: Open/short circuits, foreign objects, dirt, scratches in the display area and peripheral Fan-Out area
3. Can support different sizes of substrates/panels according to customer needs

Metal case scratches are very fine. Under normal light, it is difficult for personnel to detect defects visually because the metal material is easy to reflect light, which can easily lead to poor appearance quality problems.By using SolVision's Segmentation technology, a defect defect database is established for the appearance shape of defects, and specific defects are classified, such as obvious defects, fine defects and extremely fine defects. Deep learning is used to identify obvious defects and ignore acceptable minor defects. , Effectively improve the detection accuracy and speed, and ensure that the finished products on the production line can enter the assembly process without any defects.

Cognex's deep learning design has the ability to distinguish real defects from acceptable coating irregularities, addressing these complex detection challenges. Defect detection tools undergo extensive training involving different classes of glass bottles and multiple angles to thoroughly learn normal component variations, including the acceptable range of coating defects. Then, when analyzing drug bottles, they scan, evaluate, and label features outside the accepted range, all while minimizing false reports caused by coating defects.

Metal stamping parts can have a wide variety of defects in different shapes and sizes, and oil and water stains are even more difficult to observe. On the other hand, the brightness of the workpiece also varies during imaging, which makes it very difficult to perform defect detection.By using the Segmentation technology of SolVision AI image platform, AI models are trained with images of various defects with different brightness. After training, the AI model can easily detect various defects on stamping parts, such as: shallow scratches, oil stains, water stains, burrs, etc., which greatly improves the surface quality of the product.

The proposed solution combines conventional machine vision and deep learning visual systems, checking bottle caps from below and top-down perspectives, ensuring appropriate dimensioning and positioning, and revealing existing issues. Cognex Deep Learning can detect unexpected scrapes, holes, and other flaws while distinguishing simple cosmetic defects from functional shortcomings. Applying these technologies leads to improved quality, diminished unnecessary waste, increased productivity, and elevated yields.

Cognex Deep Learning solutions enable precise part localization, thorough problem analysis, and robust classification abilities, preventing deficient products from entering supply chains. Combining human-like detection skills with computerized automation and repeatability features ensures maximum functionality alongside robot collaboration, guaranteeing optimal performance in tandem with visual instruments. Detecting complex anomalies missed by operators reduces recall events, lowers rework expenses, and fully collects traceable images throughout operations.

Utilizing machine vision and deep learning techniques, mask manufacturers can ensure compliance with ISO standards during production and discover flawed masks before shipping. The Cognex In-Sight 8402 Visual System detects earloop and headband weld points in mask components while measuring mask width to confirm manufactured dimensions meet expectations. Although many defects might prove elusive and hard to predict, traditional machine vision algorithms struggle to account for them. Fortunately, with just fifty sample images, Cognex Deep Learning can effortlessly locate cracks, stains, sewing faults, and other irregularities, subsequently categorizing them.

Cognex's AI visual system and software assist manufacturers in identifying and classifying genuine LED chip defects through training with a series of images representing good and NG (no-good or defective) results. The software is then able to mark only significant defects within the target inspection area (ROI), which the defect detection tool identifies. Following this, the classification tool categorizes the defects based on the information gathered. With this information, production managers can increase the yield rate of high-quality LED products, address and solve production issues by utilizing classification data, ultimately enhancing profitability.

During the assembly process, there are occasional human errors that can lead to products with screws not fully tightened or with gaps in the accessories. For such repetitive assembly defect detection, the introduction of automation will quickly improve product omission problems and further improve the efficiency of manpower allocation.By applying Solomon SolVision's Segmentation technology, the image of screws and other assembly positions is located, and the preliminary identification and classification of the assembly dovetail degree is performed. The AI model is trained to quickly identify the completeness of the assembly of electronic components. With the increase in the number of image samples learned, its detection efficiency can also be continuously optimized, effectively improving the product quality yield.

Defect Detection Tools excel at detecting a wide array of defects, including but not limited to, soldering voids, bridging solder material, missing parts, misaligned components, and even minute errors invisible to human inspectors. Once detected, these defects are highlighted visually on the image for further processing and examination.

Matrox DA4.0 software uses a flowchart-based user interface, allowing users to easily perform bottle inspection tasks through the built-in software development kit (SDK), including liquid level detection, cap, safety ring, and label height detection.

The In-Sight vision system, combined with feature extraction technology, uses lighting and software algorithms to create high-contrast images that enhance the three-dimensional features of components. It can capture errors and defects such as torn, cracked or deformed labels. Monochrome and color models can identify color errors and inspect the consistency and quality of labels in terms of size, shape, color and material. This quality control measure can reduce errors, help meet label quality standards and ensure customer satisfaction.

1. Full Chinese operation interface
2. Quick adjustment page for product fine-tuning
3. Statistical functions (total inspected/qualified/defective quantities)
4. Defective image storage and classification
5. Ability to adjust settings during inspection
6. Complete rejection mechanism planning (low/medium/high speed, contact/non-contact type)
7. Equipment can process up to 1200 pcs/minute at maximum speed

1. An innovative automatic optical inspection station with two 2D Basler cameras located under the glass screen. When foreign objects in the IV bag fall to the bottom, the lighting system located above the IV bag allows SolVision's complex artificial intelligence algorithm to detect foreign objects.
2. SolVision successfully detected all foreign objects with 100% detection accuracy
3. The inspection cycle is 500 milliseconds per bag, exceeding the customer's target
4. Successfully detected and significantly reduced overall inspection time, exceeding customer expectations

1. AI learning function: You can learn OK samples, automatically analyze defect locations, and greatly improve the defect detection rate.
2. Multi-field detection: By using two light sources, bright field and dark field, the ability to detect color film patterns is improved, so that the software can detect defects that are obscured by patterns.
3. Heat map analysis function: It can analyze the defect location and severity through the heat map, and assist the personnel to analyze and judge the detection result.
4. Defect classification function: It can classify NG photos by training pictures of different defects, which is convenient for production personnel to analyze the production situation.
5. Report function: After each batch is completed, a production report can be automatically generated, including all detection results, production yield, defect ratio and other data.
6. Alarm function: You can set the number of consecutive NGs, automatically stop the machine and alarm the operator to deal with abnormal situations in time.
7. The system can detect the following defects and bad conditions: missing edges, burrs, bubbles, attachments, lint, missing ink, misprinted patterns, cracks, etc.

Cognex Deep Learning provides a simple solution that can identify all anomalous features without even having to train on "defective" images. Instead, engineers can use the defect detection tool in an unsupervised mode, training the software using samples of "good" images. Cognex Deep Learning can learn what normal wire bond and lead appearances and positions should be, and flag any deviating features as defective.