Common Vision Blox - Tools



Common Vision Blox - powerful, fast, modular

Common Vision Blox (CVB) is a high-speed and high-end machine vision library, allowing users to develop applications that are fast and powerful. Our modular licensing means that you only pay for what you need.

CVB is the result of over 20 years of machine vision expertise from the experts at STEMMER IMAGING.

Particular highlights include

  • our acquisition capabilities, supporting the latest acquisition technology with maximum performance. As active members of the GenICam committee and a supplier of vision components, we have a unique insight on the requirements of our customers. This is why CVB is also hardware-independent, to allow users to take advantage of the rapid pace of camera development, without re-developing an application.

  • CVB Foundation Package contains a large and growing bundle of image processing tools, from 2D and 3D calibration to OPC UA communication and functionality for getting the best from polarisation cameras.

  • our high-end tools include high accuracy search, accurate barcode reading and grading, fast OCR based on machine learning and a machine learning tool for search and classification that requires significantly smaller training sets than deep learning solutions from competitors.

What is new in Common Vision Blox 2019?

The release of CVB 2019 introduces new APIs to provide a new way of developing machine vision solutions with Common Vision Blox, together with an impressive range of new tools.

These new tools provide functionality for hyperspectral and polarisation imaging, as well as OPC UA machine to machine communication capability for Industry 4.0 requirements. In addition it is now possible to develop machine learning solutions on embedded platforms. Object recognition speeds have been greatly increased, as have video sequence recording speeds.

Download CVB 2019 >

CVB Image Manager 2019

New object-oriented APIs supporting Python, .NET and C++. These greatly simplify application development and are also spreading across the CVB tools. CVB Image Manager 2019 brings support for Ubuntu 18.04 on Intel and ARM platforms. There is also a GenICam Transport Layer for Intel RealSense 3D stereo cameras for easy acquisition and control.

Read more
CVB Foundation Package 2019

Polarization enables easy and powerful processing of images from the polarisation sensors from SONY and Teledyne DALSA. OPC UA gives server and client functionality for factory communication with the vision system. There are also updates to Metric for 3D calibration.

Read more
CVB Spectral

A new tool to allow the acquisition and basic processing of data from hyperspectral cameras and ENVI cubes. This rapidly-growing technology has applications in the food, recycling and pharmaceutical industries in particular, where it allows a chemical analysis of materials. A further area of applications is colorimetry, where wavelength-correct colour images (RGB, Lab) can be created. This tool helps by allowing the data to be ‘sliced’ by wavelength or spatial domains for further processing by other image processing tools. It also allows the creation of real calibrated colour data for applications where accurate colour information is an important part of quality analysis.

Read more
CVB Movie

CVB Movie is a tool to allow users to create recordings of image streams. With CVB 2019 it adds a new layer of functionality with a new proprietary format that allows data to be streamed to disk faster than ever before. The new functionality optimises the data to the disk so that the full performance of the disk can be exploited. Tests have shown that gigabytes per second is possible.

Read more
CVB Polimago

CVB’s top machine learning tool is now available for Linux on Intel and ARM platforms, allowing users to migrate their machine learning applications to embedded platforms.

Read more


  • Solve very innovative machine vision tasks
  • Reduce the time to market without standard programming jobs
  • End customers with the help of skilled programmers or machine vision experts


  • Machine vision specialists
  • OEM customers for vertical applications
  • Universities and research organisations
  • End-users with a requirement for high performance vision tools


CVB provides a highly efficient acquisition basis and a set of image processing tools for a large range of applications. In addition, CVB offers you the opportunity to add your own know-how and interface to other libraries such as OpenCV.

CVB’s hardware-independent philosophy allows a change of acquisition hardware at any phase of a project. This releases users from hardware manufacturers’ obsolescence schedules and allows new users to take advantage of new hardware developments such as higher resolution cameras and higher speed interfaces as they become available.

  • Hardware independent

    • True choice of hardware without loss of control
    • DDK to fully support all specialist hardware
    • Direct image access by pointers and tables
  • Platform independent

    • MultiOS supporting Microsoft Windows 32-bit (XP, 7, 8, 10) / 64-bit (7, 8, 10) and Linux 32-bit / 64-bit (Ubuntu, Mint, Kubuntu), Yocto (OpenEmbedded Linux)
    • Support for ARM Platforms - Odroid SoC e.g. Samsung Exynos5422
    • Programmable with VB.NET, C#, Visual Basic, Visual C++, Delphi, or Intel C++
    • New object-oriented APIs supporting Python, .NET and C++
    • GNU Compiler collection (depending on operating system used)
  • Code independent

    • Combine multiple tools to create the best solution
    • CVB, open source libraries, 3rd party packages and own code can be used together


  • Image acquisition and processing libraries
  • Modular licensing, pay for the tools that you need
  • Free lifetime support
  • Free evaluation software
  • Hundreds of programming examples in multiple programming languages to help you to develop your own application as quickly and efficiently as possible.
  • Opportunities for cross-platform development so that a vertical application can move from Windows to Linux to embedded Linux if required.