Shuowen Hu

Learn More
In low light conditions, visible light face identification is infeasible due to the lack of illumination. For nighttime surveillance, thermal imaging is commonly used because of the intrinsic emissivity of thermal radiation from the human body. However, matching thermal images of faces acquired at nighttime to the predominantly visible light face imagery in(More)
Although visible face recognition has been an active area of research for several decades, cross-modal face recognition has only been explored by the biometrics community relatively recently. Thermal-to-visible face recognition is one of the most difficult cross-modal face recognition challenges, because of the difference in phenomenology between the(More)
A confound for functional magnetic resonance imaging (fMRI), especially for auditory studies, is the presence of imaging acoustic noise generated mainly as a byproduct of rapid gradient switching during volume acquisition and, to a lesser extent, the radiofrequency transmit. This work utilized a novel pulse sequence to present actual imaging acoustic noise(More)
Kernel density estimation is an important technique for understanding the distri-butional properties of data. Some investigations have found that the estimation of a global bandwidth can be heavily affected by observations in the tail. We propose to categorize data into low-and high-density regions, to which we assign two different bandwidths called the(More)
Face recognition research has primarily focused on the visible spectrum, due to the prevalence and low cost of visible cameras. However, face recognition in the visible spectrum is sensitive to illumination variations, and is infeasible in low-light or nighttime settings. In contrast, thermal imaging acquires naturally emitted radiation from facial skin(More)
A face recognition system capable of day- and night-time operation is highly desirable for surveillance and reconnaissance. Polarimetric thermal imaging is ideal for such applications, as it acquires emitted radiation from skin tissue. However, polarimetric thermal facial imagery must be matched to visible face images for interoperability with existing(More)
We present a polarimetric thermal face database, the first of its kind, for face recognition research. This database was acquired using a polarimetric longwave infrared imager, specifically a division-of-time spinning achromatic retarder system. A corresponding set of visible spectrum imagery was also collected, to facilitate crossspectrum (also referred to(More)
Recognition rate of face recognition algorithms is dependent on the resolution of the imagery, specifically the number of pixels contained within the face. Using a sequence of frames from low-resolution videos, super-resolution image reconstruction can form a higher resolution image, aiding the face recognition stage for improved performance. In this work,(More)
A method for synthesizing visible spectrum face imagery from polarimetric-thermal face imagery is presented. This work extends recent within-spectrum (i.e., visible-to-visible) reconstruction techniques for image representation understanding using convolutional neural networks. Despite the challenging task, we effectively demonstrate the ability to produce(More)