WELCOME TO THE FUTURE
OF QUALITY CONTROL
Meet the Inspector.
It easily performs operations such as defect detection, defect classification, and absence detection. Inspector is equipped with advanced deep learning algorithms and algorithms that automatically perform the dataflow process.
Inspector is designed to meet the needs of quality control, product sorting, and counting in every production process. It combines advanced Artificial Intelligence and Computer Vision technologies. In this way, it offers an ideal solution for increased productivity in manufacturing. Simplify your operations and achieve excellence with Inspector's user-friendly interface and real-time error detection.
Detection
Object & Defect Detection
Classification
Object & Defect Classification
Counting
Object & Defect Counting
START PERFORMING QUALITY CONTROL WITH COMPUTER VISION IN 4 EASY STEPS.
USER INTERFACE
EVERYTHING YOU NEED
All the Essential Tools for Computer Vision Projects in Inspector.
Dashboard
Manage all your quality control processes from a user-friendly dashboard. Optimize operations with real-time data tracking and analytics.
Built-in IoT Device Connectors
It can communicate with devices that use Siemens S7, Modbus TCP, and MQTT protocols.
Image & Video Acquisition
Capture high-quality images and videos, and analyze real-time data from the production line. Detect defects and improve your processes.
Labeling Tool
Quickly and efficiently label images with the user-friendly labeling tool, accelerating the training of AI models.
Training & Testing Tool
Train and test your AI models with real data. Develop high-accuracy, reliable AI solutions.
Deployment Tool
Deploy trained models quickly and easily. Transfer AI models to your production environment with a single click and start using them immediately.
1- UPLOAD MEDIA
Start your quality control process by uploading image or video files to the system. Analyze the uploaded media to remove unnecessary visual frames and create high-quality datasets.
2- LABEL IMAGES
Label objects or errors to be captured in your uploaded media files. Easily label and annotate your images using the user-friendly labeling tool and move on to the training phase of your model.
3- TRAIN THE AI MODEL
Train and test your AI model with the labeled data. Using real data in the training and testing processes ensures the development of highly accurate and reliable AI solutions.
4- DEPLOY THE PROJECT
Quickly and easily deploy your AI project on your AI computer. Launch your project and optimize your quality control processes.
Features | Standard | Pro | Advanced |
---|---|---|---|
CPU Max Freq. | 1.5 GHz | 2 GHz | 2 GHz |
Dimensions | 110 mm x 130 mm x 60 mm | 110 mm x 130 mm x 60 mm | 160 mm x 110 mm x 95 mm |
Networking | 1x GbE | 1x GbE | 1x GbE |
AI Performance | 40 TOPS | 100 TOPS | 200 TOPS |
Video Encode | 1080p30 supported by 1-2 CPU cores | 1x 4K60 | 3x 4K30 | 6x 1080p60 | 12x 1080p30 (H.265) H.264, AV1 | 4x 4K60 | 8x 4K30 | 16x 1080p60 | 32x 1080p30 (H.265) | 4x 4K60 | 8x 4K30 | 14x 1080p60 | 30x 1080p30 (H.264) |
Power | 7W - 15W | 10W - 25W | 15W - 30W |
Video Decode | 1 x 4K60 (H.265) | 2 x 4K30 (H.265) | 5 x 1080p60 (H.265) | 11 x 1080p30 (H.265) | 1x 8K30 | 2x 4K60 | 4x 4K30 | 9x 1080p60 | 18x 1080p30 (H.265) H.264, VP9, AV1 | 2x 8K30 | 6x 4K60 | 12x 4K30 | 26x 1080p60 | 52x 1080p30 (H.265) | 4x 4K60 | 8x 4K30 | 16x 1080p60 | 32x 1080p30 (H.264) |
Display | 1x 4K30 multi-mode DP 1.2 (+MST) | eDP 1.4 | HDMI 1.4 | 1x 8K30 multi-mode DP 1.4a (+MST) | eDP 1.4a | HDMI 2.1 | 1x 8K30 multi-mode DP 1.4a (+MST) | eDP 1.4a | HDMI 2.1 |
Operating Temp. | '-10 °C / 60 °C | '-10 °C / 60 °C | '-10 °C / 60 °C |
AI Model Concurrent Execution Limit | 1 | Up to 4 | Up to 10 |
GPU | 1024-core NVIDIA Ampere architecture GPU with 32 tensor cores | 1024-core NVIDIA Ampere architecture GPU with 32 tensor cores | 512-core NVIDIA Volta™ GPU with 64 Tensor Cores |
DL Accelerator | 2x NVDLA v1 | 2x NVDLA v1 | 2x NVDLA v1 |
Other I/O | 3x UART, 2x SPI, 2x I2S, 4x I2C, 1x CAN, DMIC & DSPK, PWM, GPIOs | 3x UART, 2x SPI, 2x I2S, 4x I2C, 1x CAN, DMIC & DSPK, PWM, GPIOs | 3x UART, 2x SPI, 2x I2S, 4x I2C, 1x CAN, DMIC & DSPK, PWM, GPIOs |
Max GPU Freq. | 625MHz | 918MHz | 918MHz |
Storage | 2x M.2 Key-M 250GB SSD | 2x M.2 Key-M 250GB SSD | 2x M.2 Key-M 250GB SSD |
Memory | 8GB 128-bit LPDDR5 68GB/s | 16GB 128-bit LPDDR5 102.4GB/s | 32 GB 256-bit LPDDR4x 136.5GB/s |
Integrated Hardware Module | NVIDIA JETSON ORIN NANO 8GB | NVIDIA JETSON ORIN NX 16 GB | NVIDIA JETSON ORIN AGX 32GB |
Vision Accelerator | 2x PVA v1 | 2x PVA v1 | 2x PVA v1 |
Weight | 760 g | 760 g | 1340 g |
USB | 3x USB 3.2 Gen2 (10Gbps) | 3x USB 2.0 | 3x USB 3.2 Gen2 | 3x USB 3.1 | 4x USB 2.0 |
CPU | 6-core Arm Cortex-A78AE v8.2 64-bit CPU 1.5MB L2 + 4MB L3 | 8-core Arm® Cortex®-A78AE v8.2 64-bit CPU 2MB L2 + 4MB L3 | 8-core NVIDIA Carmel Arm®v8.2 64-bit CPU 8MB L2 + 4MB L3 |
PCIe | 1 x4 + 3 x1 (PCIe Gen3, Root Port and Endpoint) | 3 x1 + 1 x4 PCIe Gen 4 | 1 x8 + 1 x4 + 1 x2 + 2 x1 (PCIe Gen4, Root Port & Endpoint) |
FEATURES & DETAILS
ARTIFICIAL INSPECTOR
Easy Image Acquisition
Import images from cameras or upload existing images into Inspector with a single click to train AI models.
Just Label It
Quickly label images and create datasets with the labeling tool.
Pre-Optimised Settings
Train and test dozens of different AI models.
Deploy to Edge or Cloud
Install your trained AI models on any industrial Edge AI computer or in the cloud.
Integrate with OT&IT Systems
Inspector can be connected to OT systems such as IoT devices, PLC, remote IO, etc., and integrated with IT systems such as ERP, EMS, QMS, etc.
Package Contents
Check out and compare the details of all-in-one packages in the table below.