Francesco Pittaluga

Learn More
The next wave of micro and nano devices will create a world with trillions of small networked cameras. This will lead to increased concerns about privacy and security. Most privacy preserving algorithms for computer vision are applied after image/video data has been captured. We propose to use privacy preserving optics that filter or block sensitive(More)
In this paper we present a low-cost facial recognition system using a commercial off-the-shelf (COTS) unmanned aerial vehicle (UAV) platform to capture images and video. Our novel approach produces real-time accurate detection and recognition of key features allowing the system to be used in real world security applications. We present recognition(More)
The next wave of micro and nano devices will create a world with trillions of small networked cameras. This will lead to increased concerns about privacy and security. Most privacy preserving algorithms for computer vision are applied after image/video data has been captured. We propose to use privacy preserving optics that filter or block sensitive(More)
As cameras turn ubiquitous, balancing privacy and utility becomes crucial. To achieve both, we enforce privacy at the sensor level, as incident photons are converted into an electrical signal and then digitized into image measurements. We present sensor protocols and accompanying algorithms that degrade facial information for thermal sensors, where there is(More)
Face images from the Feret database [3] were convolved with a Gaussian filter and inputed to the CSU Face Identification Evaluation System (FES) [1]. Both the gallery and probe images were convolved with the Gaussian filter before being inputed to the FES. The probe images were convolved with the Gaussian filter to simulate optical defocus. The gallery(More)
  • 1