Conventional machine vision systems can accurately calculate quantities of drugs and vials but lack flexibility and adaptability for certain error scenarios, unlike Cognex Deep Learning. Capabilities extend further than counting, encompassing misaligned, reversed, or color-confused containers, thereby improving Overall Equipment Effectiveness (OEE). Component location tools train with containers orientated towards various directions, resulting in consistent recognition across all possibilities, generating reliable counting methodologies considering peripheral distortions simultaneously.

Implementation of Cognex Deep Learning proves effective in solving applications of this nature. Component positioning tools easily handle complex vaccine assembly tests, e.g., items placed in varied directions, overlapping, missing, or containing different combinations of SKUs. After training a deep learning system from multiple angles to recognize assembled components and discriminate between existing and newly introduced ones (even visually alike counterparts), successful identification becomes effortless.

Cognex Deep Learning presents a highly trustworthy medical patch testing solution, hinging upon measurable medication dosages against specified locations. Training occurs through mounting patches above several accepted droplet sizes and shapes against rejected liquid forms, creating classes outlining permissible drops' shape and magnitude. Ultimately, any remaining inconsistencies fall into the removal category.

Solomon combines machine vision and artificial intelligence to create AI learning modules using the Classification function of SolVision AI image platform to judge the precipitation conditions from the image features in the database. Through deep learning technology, it can identify the precipitation conditions of liquids of different colors and accurately distinguish 7 different precipitation patterns, thereby judging the quality of the contents.

Automatic inspection of external defects and dimensions of Chinese herbal pills, Chinese herbal tablets, health pills, etc., such as shape, damage, cracks, color difference, foreign objects, stains, etc., with high-precision screening requirements

Cognex Deep Learning excels in solving problems associated with mass tablet detection, achieving high precision levels. Through comprehensive training with tablets captured from multiple angles, the defect detection tool can subsequently detect any abnormal tablets omitted from initial training sets. All compliant tablets proceed to primary packaging seamlessly.

1. Full Chinese operation interface
2. Applicable to various shapes of tablets
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)

Tablet and capsule inspection and screening machine can automatically and accurately detect tablets, capsules, hard capsules, soft capsules, etc. With simple settings, you can easily and accurately inspect various shapes, colors, foreign objects, stains and other external defects.

Cognex Deep Learning is equipped with High Dynamic Range Plus (HDR+) technology, offering uniform illumination and deeper depth of field without requiring expensive and elaborate lighting systems, making low contrast defects on actuators clearer and more visible. The difference between HDR+ and standard HDR lies in its ability to quickly capture single shots of moving parts during operation compared to traditional HDR methods, which require objects to remain stationary and collect several images to achieve similar results.

Cognex deep learning's defect detection tools train using a small group of sample images to learn the standard appearance of syringes, allowing them to recognize slight deviations indicating needle protrusion situations while accepting changes in the surface appearance of syringes.

Cognex Deep Learning can detect many subtle microscopic slanted needle tip defects using a small dataset of sample images to train the defect detection tool. When magnified significantly, any variation presented in the light path reveals the structure of the needlehead surface. A highly reflective appearance indicates smoothness, whereas dimmed opacity suggests possible defects. This same process also highlights the internal and external diameters of needles for size checks.

1. Syringe Bevel Inspection Suitable for Cognex Deep Learning due to Training Using Multiple Angles; Despite numerous and intricate changes, transparency, and complicated geometry—including minuscule defects overlooked by human inspectors—these differences can still discern acceptable versus unacceptable curvatures.
2. Cognex Deep Learning Defect Detection Tools Easily Adapt to Subtle Shape Variations Arising from Supplier Changes, Resulting in Minimal False Rejections Compared to Traditional Machine Vision Requiring Major Programming Redesigns

Solomon combines machine vision and artificial intelligence to use SolVision's Segmentation technology to train AI models for the various textures and shapes of white and transparent plastic parts. This can effectively detect assembly errors of plastic parts, improve the efficiency of defect detection, and make the overall process more perfect.

Utilizing the powerful yet compact In-Sight 8505P Imaging System, perform measurements for all dimensions of syringes. Equipped with High Dynamic Range Plus (HDR+) technology, In-Sight 8505P addresses complications stemming from glass reflection and refraction, as well as plunger stoppers and liquids. This imaging technique reduces lens flare and image noise, improves edge contrast, increases dimensional precision, and maintains short exposure times. The key distinction between HDR+ and standard HDR involves capturing single exposures of moving components at speed, whereas standard HDR requires static components and collecting multiple images for comparable results.

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.

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 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.

Deep learning streamlines tasks involving automatic positioning, identification, and classification within a single image's multiple characteristics. Depending on various item dimensions, shapes, and surface attributes, the system discerns and groups distinctive features accordingly. Users can train assembly positioning and verification tools to find desired items. Afterward, the picture gets segmented into separate sections, allowing the tool to assess the presence of the required item and validate its kind, regardless of orientation and lighting settings. Furthermore, deep learning finds and identifies flyers inside boxes, averting recalls and assuring patient safety.

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.

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.

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.

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.

This vision system can be connected to the factory's main PC system via a local area network, which facilitates the management of user login, real-time images, defect images, and system settings. Images can also be automatically stored on the main PC, providing quality assurance and other departments with an intuitive user interface with a touch screen. It can be used to monitor and control production data and inspection conditions, and to obtain information such as inspection results and error reports.

Cognex Deep Learning performs exceptionally well in conducting X-ray inspection and verifications for assembled devices and packages. After training with valid device images containing intact components placed correctly, the Assemblies Validation Tool learns about accepted positional shifts across the whole product line and positions of diverse components. Post-training, the instrument promptly recognizes bends, incorrect placements, missing pieces, and drug quantity anomalies among packaged items while accepting completely assembled units meeting requirements.

LEDA Monocle is an AI-enabled Automated Optical Inspection (AI-AOI) software that can be used for contact lens defect detection. Combined with ADLINK's powerful AI machine vision system, it provides a complete AI-AOI solution that allows you to set product defect standards and accurately detect products based on these standards. This solves the problem of high false alarm rates in traditional manual inspection and helps contact lens manufacturers to improve the intelligence of inspection and the accuracy and speed of quality inspection.

PTP packaging is mainly made of transparent PVC blisters combined with aluminum foil backing. However, the blisters are transparent, which makes it easy for light to be reflected in the fast-moving packaging production line, affecting visual judgment and causing the product packaging defect rate to be high.

By using the Segmentation technology of Solomon SolVision AI image platform, the defects in the image samples are labeled and used to train AI models. After deep learning, the quality control department can accurately identify whether there are defects on the mask and eliminate the defective products.

360° intelligent AOI foreign object detection machine with full angle, which contains a new rotating fixture with integrated AOI technology, so that when switching different measurement sizes of bottles, it can be detected in a fully automatic way without changing the fixture and manual intervention; It is also equipped with 360-degree multi-angle shooting to achieve the benefits of precise detection and reducing the overall detection time. In addition, it is equipped with the intelligent optical detection software independently developed by Apacer Smart IoT, which can quickly identify and mark the defective areas of the medicine bottle, and effectively assist the quality control personnel to conduct the next step of verification.