Tự động hóa IoT
Nhà cung cấp thiết bị truyền thông, viễn thông, tự động hóa IoT chuyên nghiệp, liên hệ: Tel/Zalo +84 904 251 826, sales@mctt.com.vn

Ứng dụng AI Vision trong kiểm tra quang học (AI Vision in Automated Optical Inspection)

Lượt xem: 208

Ứng dụng AI Vision trong kiểm tra quang học.

Today‘s printed circuit boards (PCBs) are becoming more complex with smaller and more densely compact components. By integrating artificial intelligence (AI), automated optical inspection (AOI) is able to expand its inspection capabilities through machine learning which facilitates increased yield, improves fabrication operations and processes, and reduces manual operations. Compared with traditional AOI inspection, it has higher efficiency and greater accuracy.

To process images and signals quickly and accurately, the embedded vision system with high-performance Intel® Core™ processor and support of Intel® OpenVINO™ toolkit is required. In addition, it must integrate real-time vision I/O to connect triggers, optical sensors and LED lighting control and support GigE Vision interfaces to complete the online inspection.

Main Requirements

  • High-performance Intel® Core™ processors
  • Supports Intel® OpenVINO™ toolkit
  • Integrated real-time vision I/O
  • Supports GigE Vision interfaces

Axiomtek’s Intelligent Machine Vision System with Intel® Distribution of OpenVINO™ toolkit

Axiomtek has proposed its MVS900-511-FL, an all-in-one AI-enabled vision system that addresses the needs and requirements of most automated visual inspection. It features excellent computing performance, real-time vision I/O control, camera communication interfaces and support of Intel® OpenVINO™ toolkit. Its vision-specific I/O can connect to multiple cameras and interoperate seamlessly with all the vision devices. By adding the support of the Intel® OpenVINO™ toolkit, the MVS900-511-FL is capable for AI application development. This powerful vision controller can be trained and perform inference to catch defects, flawed parts, and other abnormities, making sure every product leaving a production line meet s all quality criteria.


  • Seamless interoperability between cameras and vision devices through the integrated real-time vision I/O and GigE Vision interfaces
  • Achieving high precision and real-time control
  • Operating simultaneously under the sequential control
  • Reducing the CPU loading with CPLD design
  • Reducing the costs with the integrated lighting controller


  • Improving quality and increasing productivity
  • Reducing manufacturing costs

Intel® Distribution of OpenVINO™ toolkit

The Intel® Distribution of OpenVINO™ toolkit is a comprehensive toolkit for quickly developing applications and solutions that emulate human vision. Based on Convolutional Neural Networks (CNNs), the toolkit extends CV workloads across Intel® hardware, maximizing performance. It accelerates applications with high-performance, AI and deep learning inference deployed from edge to cloud.

The Intel® Distribution of OpenVINO™ toolkit:

  • Enables deep learning inference from the edge to cloud.
  • Supports heterogeneous execution across Intel accelerators, using a common API for the Intel® CPU, Intel® Integrated Graphics, Intel® Gaussian & Neural Accelerator, Intel® Movidius™ Neural Compute Stick (NCS), Intel® Neural Compute Stick 2, Intel® Vision Accelerator Design with Intel® Movidius™ VPUs, Intel® Vision Accelerator Design with Intel® Arria® 10 FPGA Speed Grade 1 and Speed Grade 2, and Intel® Programmable Acceleration Card with Intel® Arria® 10 GX FPGA.
  • Speeds time-to-market through an easy-to-use library of CV functions and preoptimized kernels.
  • Includes optimized calls for CV standards, including OpenCV* and OpenCL™.
Bình luận