[Video Available] Appearance Inspection AI 'Roxy AI' Major Version Up!

Added features like "Attention Map" that achieve semseg with very simple annotations! Accuracy and speed have further improved!

High-precision and high-speed appearance inspection AI 'Roxy AI' has undergone its first major version upgrade! With this addition of features, we are lowering the barriers to implementing AI inspections more than ever before, achieving stabilization of inspection process quality and cost reduction. ■ Attention Map A representative method for detecting defects is semantic segmentation (hereafter referred to as "semseg"). High-performance models like Yolo have been released and are adopted by many appearance inspection AI products, but the annotation process for semseg is very cumbersome, making it a bottleneck for implementation. When the boundary between normal and defective is ambiguous, it can be difficult to annotate correctly. With the newly added proprietary 'Attention Map' in Roxy AI V2, this issue is dramatically improved. There is no need to be aware of the boundaries between normal and defective; simply clicking on the defective area is sufficient. This achieves semseg in an overwhelmingly efficient manner. ■ Learning Environment - Significantly improved detection capability for small objects in measurement AI - Official support for RTX 50 series - Support for learning on CPU - Various other improvements ■ Runtime Environment - Compatible with Keyence's LJ-S8000 - Added a group of workers to flexibly control inspection results

• Other inspection equipment and devices
• Visual Inspection Equipment
• Other analytical and testing equipment

An AI that has learned inappropriate data is useless. Roxy AI maximizes AI performance by cleaning the data!

*There is an explanatory video, so please take a look.* The AI used for visual inspection prioritizes accuracy above all else. For many of the products mentioned above, the goal is to improve accuracy by adding data or repeatedly tuning parameters until accuracy increases. In 'Roxy AI', we focus on organizing data to achieve high accuracy under the condition of having a limited number of defective samples. In this version upgrade, we have added various features as follows, making it even easier to use and achieving even higher accuracy. ■ Judging the quality of shooting conditions before AI learning Roxy AI detects poor conditions that could negatively impact AI learning before the learning process begins. This minimizes unnecessary trial and error and rework. ■ Automatic data organization The AI can automatically exclude data deemed inappropriate during learning. This eliminates the need for visual checks and reduces the time and labor required for data maintenance. ■ An integrated viewer that allows observation of data from various perspectives, among other features. *For more details, please download the materials or contact us through our website.*

• Visual Inspection Equipment

Thank you very much for your continued support. Donaldson Japan Co., Ltd. will be closed during the following period: From April 25 (Saturday) to May 6 (Wednesday). Inquiries made during the closure will be answered sequentially after May 7 (Thursday). We sincerely apologize for any inconvenience this may cause. Thank you for your understanding and cooperation.

The "Mechanical Stitching Method" by Nichinichisui Road Machinery Co., Ltd. is a new technique that allows for the repair of metal cracks without the application of heat. By using special bolts and reinforcement plates, cracks are physically removed, and repairs are made without causing any thermal impact on the base material. Repairs can be carried out in environments where open flames cannot be used. Since no heat is applied, the disassembly of equipment is minimized. ◎ For more details, please contact us. ◎ If a detailed technical explanation is needed, please contact us.

The "Mechanical Stitch Method" by Nichinichisui Road Machinery Co., Ltd. is a new technique that allows for the repair of metal cracks without the application of heat. By using special bolts and reinforcement plates, cracks are physically removed, and repairs are made without causing any thermal impact to the base material. Repairs can be carried out in environments where open flames cannot be used. Since no heat is applied, the disassembly of equipment is minimized. ◎ For more details, please contact us. ◎ If a detailed technical explanation is needed, please contact us.

Fukuda Co., Ltd. has been pursuing leak detection for 60 years and is committed to advancing the future of leak testing. 【 Supporting Various Leak Tests: Air Leak Test / Gas Leak Test (Hydrogen Gas, Helium Gas) 】 We develop, manufacture, and sell leak testing equipment to inspect airtightness and sealing properties. We will propose the appropriate testers and devices for each inspection target. 【 Target Industries and Examples of Inspection Targets 】 - Automotive Industry: Engines, FC components, valves and piping, various parts - Electronic Components Industry: Smartphones, keyless switches, various small sensors - Pharmaceuticals / Food / Cosmetics Industry: Bottle containers, syringes, vials, eye drop containers, pillow packaging, PTP packaging We will propose the most suitable leak testers for each industry. 【 ISO Certification 】JIS Q 9001:2015 (ISO 9001:2015)

We will introduce the implementation results of the sensor technology developed by the Hotron Group, which has been cultivated over more than half a century, through customer case studies. In addition to automatic door sensors, we also offer a wide range of vehicle detection sensors and nursing/care sensors. Many implementation examples are also presented, so please take a look at the case study page.