About FSI Technologies Inc.

FSI Technologies Inc. has been manufacturing and supporting quality automation products since 1959

Who is the WEAVER?

Adaptive Vision logo

The WEAVER is a new deep learning inference engine that comes with Adaptive Vision Studio 4.12. He is user friendly, cares greatly about performance and reliability. This newsletter will help you to get to know him better.

1- Performance

Deep learning networks are typically created with frameworks like TensorFlow, PyTorch or Caffe. These are great environments for research. However, to achieve the highest possible performance you will also need an inference engine dedicated to your hardware platform. Our experiments have shown that relatively mature and usable choices are: TensorRT (GPU), OpenVINO (CPU), MXNET (GPU), PlaidML (GPU) and ONNX Runtime (CPU). WEAVER is a new option. He works best in machine vision applications and provides state of the art performance on both GPU and CPU.

Below you can see how WEAVER‘s performance looks like on our most popular neural network, Feature Detection (supervised pixelwise labeling, Thread Inspection official example):

Feature Detection: Performance on GPU GTX 2060
Feature Detection: Performance on GPU GTX 1060

On nVidia RTX 2060, it gets even more interesting. TensorRT can go faster when numeric precision is reduced to 16 bits, while WEAVER still works with full 32-bit precision:

Feature Detection: Performance on GPU GTX 2060

On the Intel CPU platform we compare WEAVER against OpenVINO and ONNX:

Feature Detection: Performance on CPU
Feature Detection: Performance on CPU

DISCLAIMER: The WEAVER inference engine was specifically optimized for neural network we use, including Feature Detection. Performance for other neural network architectures may be different.

2. Reliability

The fast pace of development in the field of deep learning is not particularly helpful in developing real-world systems. Most of our customers require long-term support and stable availability of the components they use. WEAVER solves that. He is independent of the open-source frameworks, eliminates Python code and provides long-term support for commercial projects.

3. Ease of use

Most of the other inference engines require you to do the Python programming and tweak many things. WEAVER is different. He only does two things: (1) model optimization, (2) execution. All you need to deliver is your H5 network file (Keras output). Moreover, when you create your solution with Adaptive Vision Studio, WEAVER is already employed in three ready-to-use deep learning tools: Feature Detection, Point Location and Object Classification.

Model Optimization and execution

DISCLAIMER: TensorRT, OpenVINO, MXNET, PlaidML, ONNX, TensorFlow, PyTorch and Coffe are trade marks of third party companies.

Blog by: Adaptive Vision

FSI Advanced Research Exhibiting at SouthTec 2019, Greenville SC

Visit FSI Advanced Research in booth # 2605 at SouthTec 2019 to learn about the latest in machine vision technologies, featuring deep learning and 3D. FSI brings the right technology, engineering expertise and advanced analytics to help clients achieve quality performance and experience greater value. Greenville Convention Center, October 22-24. For more information, click here.

EyeVision supports DALSA cameras – all at once with Multi-Instance

DALSA Genie camera and many more are now supported by EyeVision

The Genie GigE series and others by DALSA are now supported in EyeVision software.

In addition, EyeVision offers a new feature, where with only one instance several cameras or sensors can be operated at the same time. Computers with more than one core can operate more than one camera per instance. The cameras can run different inspection programs but only use one EyeVision license. In short: One EyeVision license, several instances and several cameras per instance. And it does not matter if the cameras have different interfaces (GigE, USB, RS232, etc.), are 2D or 3D cameras, or have color or grey scale sensors.

Multi Instance overviewWith this function the user might consider using EyeMultiView. It can display up to 16 camera views and evaluation images on one screen. With that many instances and cameras running at the same time, the display functionality of EyeMultiView makes monitoring easier for the user.

For example, one camera can run pattern matching for error detection on a label and on the second camera the inspection for closed package. On the third camera the color inspection and the fourth one can read the bar code. EyeVision Parallel ProcessingWith the Multi-Instance you only need one license for all this. All is now possible with DALSA cameras and as always, the inspection programs can be created with the drag-and-drop function and in the graphical user interface where the user can switch between the different projects and programs.

EyeSens Robotic for a Robot Vision solution in only a few clicks!

Smart Vision Sensor with commands for robot control

EyeSens RoboticEVT has now added the new EyeSens Robotic to the Smart Vision Sensor System EyeSens.

It is now possible to directly control a UR “Universal Robot” with the new software add-on with only a few clicks. With the EyeSens smart vision sensors the user can easily create a complex pick and place application. The Robotic add-on in combination with the EyeSens Match allows every user, beginners as well as advanced users, to solve pick and place applications with a UR robot.

The support of other robots with the EyeSens Vision Sensors will be possible in the near future.

The EyeSens Vision Sensors contain the command set based on EyeVision software which contains hundreds of tools including the KeyMatch (pattern matching) and Blob (object detection) commands.

Precise Measurement of Holes and EVT Support of Various 3D Sensors

The measurement of holes and the determination of their position is a special challenge. EyeVision 3D software offers precise 3D measurements with more than 40 specialized commands.

In the case of sheet metal components, it is possible to capture the whole component geometry in a high-resolution point cloud by using visual 3D metrology. A precise metrology command set allows correctly defining various measurements in a point cloud and their coordinates in relation to other results with only a few commands.
Typical characteristics such as hole patterns, cut/trimming, and resilience on edge laps of car bodies can also be measured exactly.

For the inspection of weld seams, as well as adhesive beads, EyeVision 3D software uses the ProfileMatch command. Just a simple parametrization allows the evaluation of profiles and issues an analysis of the detected defect. A detailed protocol for all measurement results can be issued with just a few mouse clicks.

With the complete command set of EyeVision software it is possible to configure the application with 2D cameras and 3D sensors. For example, the point cloud can be displayed as 2½D image, and read an embossed or engraved lettering with a 2D OCR module. This is useful when reading DOT code on a tire or stamped numbers in metal.

EVT image processing software supports various 3D sensors of different technologies, including: AT Automation Technology, Gocator from LMI, Basler ToF, Wenglor, QuellTech, ShapeDrive, Zivid, etc (see table below).

3D Technology EyeVision 3D supported Maker
Stereo RealSense
Zivid
Chromasens
Time of Flight Basler ToF
BlueTechnix
Shape-by-Shading ShapeDrive
LMI
Lasertriangulation AT Automation Technology
Wenglor
LMI (Gocator)
VRmagic
QuellTech
3D cameras PhotoFocus

More 3D sensors which will be supported by EyeVision 3D are about to follow.

FSI Advanced Research Exhibiting at SouthTec 2017

Visit FSI Advanced Research in booth # 214 at SouthTec 2017 to learn about the latest in machine vision technologies, including deep learning, 3D, and multispectral and thermographic imaging. FSI brings the right technology, engineering expertise and advanced analytics to help clients achieve quality performance and experience greater value. TD Convention Center, Greenville, SC, October 24-26. For more information, and to register for free, click here.

EyeMeasureEasy

EyeVision software from EVT now offers EyeMeasureEasy (EME), an intuitive image analyzing tool. The user can directly measure and analyze image data with only a few mouse clicks. The tool can be used for applications in microscopy. The features of EME can be extended, so that it can be integrated into a fully automated, industrial inspection process.

With EyeMeasureEasy the user can display live-images, and can save images and load them from memory. There are several different measurement options that can be carried out on those images, such as:

  • Angle including three points or four points
  • Distances between two points
  • Radius of circles including three points or n-points or automatic

The measured results can be shown via a text overlay, list boxes or charts. The measurements can be controlled by the user through “start” and “stop” buttons, or the measurements can be carried out in a free-running measurement.

The camera options can be set directly and the user interface is a design framework for a customized graphic user interface.

01_EyeMeasure-Angle-3-800
02_EyeMeasure-Angle-2-800

03_EyeMeasure-Distance-1-800
04_EyeMeasure-Circle-1-800

EyeVision now supports the Gocator 3D sensor from LMI

EyeScanGo_back_L_EyeVision_support-KopieEyeVision software provides the integrated “brain” of the 3D sensor. EyeVision allows the sensor not only to capture an image but also to use the complete 3D command set of the software to measure, compare and read the 3D point cloud or 2D gray-scale image.

The Gocator is a compact sensor in an industrial housing with a protection class of up to IP67. It has two digital outputs, RS485 Serial and one analogue output (4 – 20 mA). More than one of the Gocator sensor families can be used with effortless configuration and synchronization.
With the EyeVision machine vision software the sensor has various commands available. Starting with the “3D Blob” command which is very versatile and can be used count objects within a point cloud, the software contains commands to measure openings (holes, slots), cylinder, studs (threaded and non-threaded), plane, etc. It has also 3D volumetric tools: volumes, areas, bounding boxes, positions (min, max, centroid), ellipses, orientations, etc.

Additionally, the 3D-software now also has a “RectProbe” command to find edge-points in a certain direction and returning the detected edge. This can be useful for additional measurements on the point cloud. There are also various filter commands such as “Merge”, which merges two point clouds into one, or the filter command “Outlier Removal”, which removes all points that deviate in Z-direction from their neighbors by a certain amount. Also important is the “Voxelgrid” filter, which down-samples a point cloud using a voxel grid and outputs points that are the average of all points inside a voxel. The filter can make unordered point clouds into ordered.

EyeVision software utilizes a graphical user interface. The commands can be drag-and-dropped in a program editor, where the inspection program can be created, even without programming skills.