Better Machine Vision Solutions through Computational Imaging
Computational Imaging (CI) refers to digital image capture and processing techniques that combine computation and optical encoding. Fundamentally, CI relies on data extracted and computed from a series of input images captured under different lighting or optical conditions. Advances in lighting technology, high-speed CMOS cameras and high-performance computing platforms are making many CI techniques viable for machine vision.
In this presentation, you will learn the basic concepts of computational imaging and the advantages it offers to designers of modern machine vision systems. In many applications, CI outperforms conventional imaging, and results in more reliable vision solutions with less development time and reduced cost.
We will discuss six practical examples of CI solutions for machine vision applications and show how better or previously impossible images can be created with ease. These techniques include photometric stereo (also known as shape from shading), ultra-resolution color, high dynamic range (HDR), extended depth of field (EDOF), bright field/dark field, and multispectral imaging. With the right computational imaging products, system designers can take advantage of simplified hardware, timing, image acquisition and processing to produce superior machine vision solutions.
Presenter: Marc Landman, Vice President, CCS America
Marc M. Landman is the Vice President of CCS America, where he manages the US sales operations and leads the CCS Vision Solutions Center. Marc has over 30 years' experience in the machine vision industry, holding engineering and management roles at various companies including vision system manufacturers, OEMs, and end-users. Prior to joining CCS, Marc was a Principal Machine Vision Engineer at Osram Sylvania. In addition, Marc founded and ran Vision Machines Inc., a system integration and consulting firm specializing in machine vision systems and technology. Marc holds a BS in Physics from SUNY Albany and a MS in Computer Science from Boston University.