Solve the most challenging vision applications with AI-based automation
The In-Sight® D900 vision system automates complex applications that are too difficult to deploy with traditional, rule-based machine vision and require reliable, fast, and consistent results not possible with human inspection. Embedded with a full suite of both edge learning and deep learning tools, In-Sight D900 solves a range of tasks from defect detection to assembly verification and optical character recognition (OCR). Processing takes place on-device, which eliminates the need for a PC, simplifying application deployment and bringing the power of artificial intelligence (AI) to non-programmers.
Read challenging characters and text in minutes
The In-Sight D900 deciphers badly deformed, skewed, and poorly etched codes using optical character recognition. Equipped with a pre-trained font library, the read tool works right out of the box, drastically reducing development time. Simply define the region of interest and set the character size. In situations where new characters are introduced, the tool can be easily retrained to read application-specific characters.
Perform fast and accurate assembly verification
The In-Sight D900 uses AI to reliably detect complex features and objects and verifies parts and kits are assembled correctly based on their location within a pre-defined layout. The check tool can be trained to recognize an extensive number, and variety, of components, which can be located in the image even if they appear at different angles or vary in size.
Detect and analyze subtle defects
The detect tool embedded within the In-Sight D900 is ideal for finding anomalies on complex parts and surfaces, even in situations where defects can be unpredictable in their appearance.
Precisely classify any defect
The classify tool leverages AI to automatically identify and sort defects into classes. Within the same class of objects, it discerns visually similar, but different defects to determine whether they are true defects or acceptable abnormalities.
Solve simple classification problems quickly and easily
The In-Sight D900 is embedded with powerful edge learning tools that leverage AI technology to learn “on the edge,” in real time, delivering fast, accurate results. The tools are simple to setup, requiring smaller image sets and shorter validation periods than traditional deep learning. They can be trained in minutes using as few as five to ten images per class with no coding required. This makes them an accessible automation solution for a range of users and skill levels.
Quickly setup and deploy applications with In-Sight spreadsheet
With an intuitive interface and a full communications function set, In-Sight spreadsheet simplifies application development and streamlines factory integration. It also allows you to combine rule-based and AI vision tools in the same project, leading to quicker deployments and faster cycle times.
Address your current and future needs with hardware modularity
Highly flexible in design, the In-Sight D900 includes field-changeable lighting, lenses, filters, and covers that can be customized to match your exact application requirements. It also includes an embedded inference engine that solves complex tasks at production line speeds.
Simplify training and deployment with intuitive web-based HMI
The In-Sight D900 vision system offers mobile, platform independent visualization for accessing HMIs (human machine interfaces) through In-Sight software. A simple point-and-click interface allows customers to build highly interactive, web-based HMIs remotely that are accessible via a web browser over the network.
|Imager Type||2/3 inch CMOS (3.45 μm x 3.45 μm pixels)||1/2.3 inch CMOS (3.45 μm x 3.45 μm pixels)|
|Resolution (pixels)||5 MP
2448 x 2048
1920 x 1200
|Acquisition Speed (Max)||26 fps||16 fps||51 fps||34 fps|
|Memory||File storage||16 GB non-volatile flash memory; unlimited storage via remote network device|
|Processing||3 GB SDRAM|
|Additional Storage||8 GB SD card, network drive via FTP over gigabit network|
|Optics||Lenses||C-Mount, S-Mount, Autofocus|
|Indicator LEDs||SD card status, pass/fail LED and 360° viewing indicator ring, network LED, and error LED|
|Lighting||External lights via light control connector|
|I/O||Network||Gigabit Ethernet (10/100/1000 Mbps)|
|Built-in||1 dedicated trigger IN, 1 general purpose IN, 2 general purpose OUT, 2 bi-direction IN/OUT|
|Mechanical||Industrial M12 Connectors||Power/IO; Ethernet; External light power/control|
|Dimensions||53.4 mm (2.10 in) x 60.5 mm (2.38 in) x 121.0 mm (4.77 in)|
|Weight||380 g (13.4 oz.)|
|Protection||IP67 with C-mount lens cover or integrated light connected|
Automatically moves in and out to focus on the target part eliminating manual intervention by the user. Ideal for inspecting parts on the same line that vary in size or distance from the lens, speeding up inspections and simplifying line changeover.
Incorporates Flexible Image Technology™ (FIT™) that optimizes image formation and minimizes the need for expensive external lighting. Field-changeable and user-configurable lighting and optics modules provide users with ultimate flexibility to customize the system for their application. Offers individually controlled diffuse illumination ideal for inspecting parts at varying working distances.
Covers and integrated light module cover options
Standard and extended C-mount lens covers are available for use when no integrated lighting module is required. Additionally, wider diameter C-Mount covers are available for the 5MP 7000 (IS7905). These covers are used for C-Mount lenses only, not with the integrated lighting module or autofocus module. Optional polarizing and clear (without diffuser) covers are available for use with the integrated lighting module.
Manually-adjusted, high-performance lens offers the most flexibility in terms of lens size, aperture and focus. Provides even resolution throughout the entire field of view, making this the most widely-used lens type.
Offers individually controlled diffuse illumination ideal for inspecting parts at varying working distances.
X-coded, power I/O and external light cables available.
In-Sight D900 is a powerful deep learning software platform designed specifically to solve applications that are too difficult, complex, or expensive for traditional machine vision systems. With an easy-to-use interface, In-Sight D900 eliminates complex programming, making deep learning technology accessible for non-vision experts, and automates inline inspections previously only possible with human inspectors.
<3>In-Sight ViDi Read Tool
The In-Sight ViDi Read tool deciphers badly deformed, skewed, and poorly etched codes using optical character recognition (OCR). It works right out of the box, dramatically reducing development time, thanks to the deep learning pretrained font library. Simply define the region of interest and set the character size. In situations where new characters are introduced, without vision expertise, this robust tool can be retrained to read application-specific codes that traditional OCR tools are not able to decode.
In-Sight ViDi Check Tool
The In-Sight ViDi Check tool uses artificial intelligence to reliably detect complex features and objects and verifies parts and kits are assembled correctly based on their location within a pre-defined layout. It can be trained to create an extensive library of components, which can be located in the image even if they appear at different angles or vary in size.
In-Sight ViDi Detect Tool
The In-Sight ViDi Detect tool is ideal for finding anomalies on complex parts and surfaces, even in situations where defects can be unpredictable in their appearance. It learns from images of good parts in order to identify defective parts. This allows the tool to detect a wide range of defects that do not need to be pre-defined at the time of training.
In-Sight ViDi Classify Tool
The ViDi Classify Tool uses deep learning to automatically identify and sort objects into classes. Within the same class of objects, this powerful classifier is capable of discerning visually similar, but different objects while tolerating natural variation. Classifying the type of defect enables better process control and allows developers to take corrective action to minimize scrap and reduce production of bad parts.