Search
Now showing items 1-10 of 25
Beyond stream processing??? A distributed vision architecture for the Internet of Things
(IEEE, 2016)
An ‘edge-based’ image processing architecture for
the internet of things (IoT) is devised, drawing on the existing
image processing pipelines that are implemented in today’s
imaging modules in digital cameras and ...
A crash course on patents for engineers
(2013)
Most engineers are aware of the existence of patents. Indeed the preparation of patent disclosures is an important aspect of most research engineering job functions. Yet for many engineers the world of patents remains ...
Detection and repair of flash-eye in handheld devices
(IEEE, 2014)
Red-eye and flash-eye defects in still photography continue to cause problems for digital imaging devices. New variants of flash-eye defects have appeared as cameras and cameras sub-systems get smaller in size. This paper ...
Wide field of view (WFoV) imaging for consumer devices
(2014)
The concepts of wide field of view (WFoV) imaging for consumer devices are explained. Some current examples and enabling technologies are provided. The need for real-time distortion correction is outlined. Several new ...
An FPGA-based stereoscopic camera - electronic design tools and techniques
(IEEE, 2010-08-05)
Electronic design tools and techniques for the implementation of a stereoscopic camera based on an FPGA (Field Programmable Gate Array) are presented. The stages of an IPP (Image Processing Pipeline) are presented together ...
Hardware implementation of a real-time 3D video acquisition system
(IEEE, 2010-07-15)
An implementation of a real-time 3D video acquisition system on a single FPGA is presented. Our approach is based on the use of stereo image sensors and can display real-time 3D video when combined with shutter glasses. ...
A crash course on patents for engineers
(IEEE, 2013-01-12)
Most engineers are aware of the existence of patents. Indeed the preparation of patent disclosures is an important aspect of most research engineering job functions. Yet for many engineers the world of patents remains ...
Getting more from your datasets: Data augmentation, annotation and generative techniques
(XPERI Inc., 2018-05-18)
Deep Learning for embedded vision requires large datasets. Indeed the more varied training data is, the more accurate the trained network. But, acquiring and accurately annotating datasets costs time and money. This talk ...
Hybrid Semi-Parallel Deep Neural Networks (SPDNN) – example methodologies and use cases
(XPERI Inc., 2018-05-23)
Deep neural networks (DNNs) are typically trained on specific datasets, optimized with particular discriminating capabilities. Often several different DNN topologies are developed solving closely related aspects of a ...
A practical challenge for iris authentication on handheld imaging devices
(IEEE, 2015)
Following on the introduction of fingerprint
biometrics, iris authentication for handheld imaging devices has
become a hot research topic. However widespread adoption of
this technology faces a significant challenge as ...