Francisco De Jesùs.
Companies to demonstrate nViso's powerful facial analysis software running on CEVA-MM3101 imaging & vision platform at Mobile World Congress 2014.
CEVA, Inc. the leading licensor of silicon intellectual property (SIP) platform solutions and DSP cores, and nViso (www.nviso.ch), a leading provider of 3D facial imaging technology, today announced that the companies have partnered to develop a solution for mobile devices that includes nViso's unique emotion detection capabilities. The solution combines nViso's facial micro-expression recognition software with the CEVA-MM3101 imaging and vision platform to deliver a broad set of high quality facial analysis functions that utilizes the camera in a smartphone, tablet or any other camera-enabled device. Crucially, the solution consumes a fraction of the power typically required to run these tasks on a CPU, reducing the power consumption by a factor of 50x.
At CEVA's booth (Hall 6, stand A50) at the upcoming Mobile World Congress in Barcelona, CEVA and nViso will demonstrate this solution running on a standard Android device and utilizing CEVA's Android Multimedia Framework (AMF) to offload the computer vision functions to the CEVA-MM3101 platform.
Facial imaging technology is a key component in a new wave of natural user interfaces (NUIs) that can analyze and understand facial movements. A primary use model of the nViso technology is to interpret people's emotions by tracking hundreds of micro-expressions and movements to gain a more accurate and real-time understanding of the user's emotional reactions to any media content, gaming or interactive experience. The nViso facial imaging engine is also able to recognize people's age, gender, eye movements and other factors that can be used to deliver a more personalized experience to users.
The CEVA-MM3101 platform delivers the performance required for the nViso technology to analyze and interpret various facial expressions, with minimal power consumption. Furthermore, by utilizing CEVA's AMF, the solution leverages the performance of the vector DSP directly from the Android environment, seamlessly offloading the CPU and completely abstracting any programming and system complexities for software developers.
"By leveraging the most proven and widely adopted platform for embedded vision applications – the CEVA-MM3101 – we can deliver our unique facial imaging technology to a new class of mobile applications and devices, broadening the use model and benefit of this intelligent user interface," said Tim Llewellynn, CEO of nViso. "Given its high-performance and low-power characteristics, the CEVA-MM3101 is ideal for implementing computer vision applications, particularly in always-on environments. It forms the foundation for a robust and cost-effective 3D facial imaging solution with the flexibility to adapt for more accuracy and more features in the future."
"nViso offers a very unique imaging application that extends the benefit of facial recognition interfaces to new areas such as emotion detection," said Yair Siegel, director of product marketing for multimedia at CEVA. This partnership strengthens the industry's largest ecosystem around an embedded vision platform, reinforcing the CEVA-MM3101's position as the emerging standard for camera-enabled mobile applications."
The CEVA-MM3101 is CEVA's third generation imaging and vision platform, addressing the extreme computational needs of the most sophisticated computational photography and computer vision applications. By offloading these performance-intensive tasks from the CPUs and GPUs, the highly-efficient CEVA-MM3101 dramatically reduces the power consumption of the overall system, while providing complete flexibility. The platform includes a vector DSP developed specifically to deal with the complexities of such applications, an Android Multimedia Framework (AMF) that streamlines software development and integration effort while enabling direct development on the CPU in Android environment while accelerating tasks to the DSP, a set of advanced software development tools and a range of software products and libraries optimized for the DSP. For more information, visit http://www.ceva-dsp.com/CEVA-MM3101.
nViso is a leading provider of emo tion recognition software that interprets human facial micro-expressions and eye movements captured through video. Its solutions use proprietary 3D facial imaging technology with artificial intelligence to track hundreds of different facial points to recognize human emotions. The company uniquely combines the latest advancements in computer science, engineering and behavioral sciences to make automatic emotion recognition a viable reality using any image based device. Its proprietary analytical techniques are based on theoreti cal work by Dr. Paul Ekman, which demonstrates that emotions can be precisely recognized by minor changes in micro-expressions in the face. nViso is based at the Swiss Federal Institute of Technology in Lausanne, Switzer land (EPFL). More information can be found at www.nviso.ch.
About CEVA, Inc.
CEVA is the world's leading licensor of silicon intellectual property (SIP) DSP cores and platform solutions for the mobile, digital home and networking markets. CEVA's IP portfolio includes comprehensive technologies for cellular baseband (2G / 3G / 4G), multimedia (vision, imaging and HD audio), voice processing, Bluetooth, Serial Attached SCSI (SAS) and Serial ATA (SATA). In 2013, CEVA's IP was shipped in over 1 billion devices, powering smartphones from many of the world's leading OEMs, including HTC, Huawei, Lenovo, LG, Nokia, Motorola, Samsung, Sony, TCL and ZTE. Today, more than 40% of handsets shipped worldwide are powered by a CEVA DSP core. For more information, visit www.ceva-dsp.com. Follow CEVA on twitter at www.twitter.com/cevadsp.
SOURCE CEVA, Inc.