Deploying Accurate Always-On Face Unlock

Accurate face verification has long been considered a challenge due to the number of variables, ranging from lighting to pose and facial expression. This white paper looks at a new approach — combining classic and modern machine learning (deep learning) techniques — that achieves 98.36% accuracy, running efficiently on Arm ML-optimized platforms, and addressing key security issues such a... » read more

Chasing After Phantom Power

A lot of effort is being invested in power reduction techniques for mobile devices, where battery life is an important buying decision and power can translate into heat that can make a device uncomfortable to use. But are people willing to pay more for a device that consumes less power if it's plugged into a wall? And even if they are concerned about the power drawn during operation, what ab... » read more

CEVA Targets Wearables

Coinciding with the announcement of an integrated platform based on a single TeakLite-4 DSP, handling Audio/Voice, Sensor Fusion, always-on UI and Connectivity- Linley Group Mobile Chip Report, By Linley Gwennap (May 5, 2014) describes how CEVA’s new and ground breaking platform is a starter kit of hardware and software blocks that a company can use to build a processor for its wearable produ... » read more

Sensory Overload

There are two new buzzwords—always on and context-aware—that have the potential to transform devices and the way in which we use them. Both are related to smartphones at the moment, but this just the initial place where their impact is being felt. Both concepts add the potential for smartphones to become part of the Internet of Things (IoT) because they enable meaningful interactions bet... » read more