This week, researchers at Carnegie Mellon University have released a demonstration video of a new open-source facial recognition program based on Google’s FaceNet research, which has been named OpenFace.
Check out the video below to see it in action recognizing faces in real-time using just 10 reference photos of the person.
Development and Performance
The OpenFace software is still currently under development, but the research team says that the results are promising. They have noted:
Even though the public datasets we trained on have orders of magnitude less data than private industry datasets, the accuracy is remarkably high and outperforms all other open-source face recognition implementations we are aware of on the standard LFW benchmark.
This statement highlights the impressive performance of OpenFace, even when compared to other systems that have access to much larger datasets. The LFW (Labeled Faces in the Wild) benchmark is a widely recognized standard for evaluating the performance of facial recognition systems, and outperforming other open-source implementations on this benchmark is a significant achievement.
Technical Details and Applications
OpenFace is a Python and Torch implementation of the CVPR 2015 paper “FaceNet: A Unified Embedding for Face Recognition and Clustering” by Florian Schroff, Dmitry Kalenichenko, and James Philbin at Google. This implementation utilizes publicly available libraries and datasets, making it accessible for researchers and developers who want to experiment with facial recognition technology.
OpenFace is a Python and Torch implementation of the CVPR 2015 paper FaceNet: A Unified Embedding for Face Recognition and Clustering by Florian Schroff, Dmitry Kalenichenko, and James Philbin at Google using publicly available libraries and datasets. Torch allows the network to be executed on a CPU or with CUDA.
Torch, a scientific computing framework with wide support for machine learning algorithms, allows the network to be executed on a CPU or with CUDA, which is a parallel computing platform and application programming interface model created by Nvidia. This flexibility means that OpenFace can be run on a variety of hardware configurations, from standard desktop computers to high-performance servers equipped with powerful GPUs.
The potential applications of OpenFace are vast. It can be used in security systems to identify individuals in real-time, in social media platforms to tag users in photos automatically, and in various other fields such as retail, healthcare, and law enforcement. For example, in retail, facial recognition can be used to enhance customer experience by recognizing loyal customers and providing personalized services. In healthcare, it can assist in patient identification and streamline administrative processes.
To download a copy of OpenFace, jump over to the GitHub website via the link below.
Latest Geeky Gadgets Deals
Disclosure: Some of our articles include affiliate links. If you buy something through one of these links, Geeky Gadgets may earn an affiliate commission. Learn about our Disclosure Policy.
