Person recognition at a distance entails recognizing the identity of an individual appearing in images or videos collected by long-range imaging systems such as drones or surveillance cameras.
Our proposed framework is composed of modified networks for extracting the most correlated intermediate representations from off-pose thermal and frontal visible face imagery, a sub-network to jointly bridge domain and pose gaps, and a joint-loss function comprised of cross-spectrum and pose-correction losses.
Automatic Target Recognition (ATR) is a category of computer vision algorithms which attempts to recognize targets on data obtained from different sensors.
Second, for discriminant features selection, DefakeHop uses an unsupervised approach while DefakeHop++ adopts a more effective approach with supervision, called the Discriminant Feature Test (DFT).
A robust fake satellite image detection method, called Geo-DefakeHop, is proposed in this work.
Though thermal cameras are widely used for military applications and increasingly for commercial applications, there is a lack of robust algorithms to robustly exploit the thermal imagery due to the limited availability of labeled thermal data.
We propose a domain agnostic learning-based generative adversarial network (DAL-GAN) which can synthesize frontal views in the visible domain from thermal faces with pose variations.
Existing thermal-to-visible face verification approaches expect the thermal and visible face images to be of similar resolution.
A light-weight high-performance Deepfake detection method, called DefakeHop, is proposed in this work.
no code implementations • 7 Jan 2021 • Domenick Poster, Matthew Thielke, Robert Nguyen, Srinivasan Rajaraman, Xing Di, Cedric Nimpa Fondje, Vishal M. Patel, Nathaniel J. Short, Benjamin S. Riggan, Nasser M. Nasrabadi, Shuowen Hu
Thermal face imagery, which captures the naturally emitted heat from the face, is limited in availability compared to face imagery in the visible spectrum.
A non-parametric low-resolution face recognition model for resource-constrained environments with limited networking and computing is proposed in this work.
Recent advances in domain adaptation, especially those applied to heterogeneous facial recognition, typically rely upon restrictive Euclidean loss functions (e. g., $L_2$ norm) which perform best when images from two different domains (e. g., visible and thermal) are co-registered and temporally synchronized.
For gray-scale face images of resolution $32 \times 32$ in the LFW and the CMU Multi-PIE datasets, FaceHop achieves correct gender classification rates of 94. 63% and 95. 12% with model sizes of 16. 9K and 17. 6K parameters, respectively.
Finally, a pre-trained VGG-Face network is leveraged to extract features from the synthesized image and the input visible image for verification.
Polarimetric thermal to visible face verification entails matching two images that contain significant domain differences.
Previous approaches utilize either a two-step procedure (visible feature estimation and visible image reconstruction) or an input-level fusion technique, where different Stokes images are concatenated and used as a multi-channel input to synthesize the visible image given the corresponding polarimetric signatures.
Synthesis of visible spectrum faces from thermal facial imagery is a promising approach for heterogeneous face recognition; enabling existing face recognition software trained on visible imagery to be leveraged, and allowing human analysts to verify cross-spectrum matches more effectively.
Previous approaches utilize a two-step procedure (visible feature estimation and visible image reconstruction) to synthesize the visible image given the corresponding polarimetric thermal image.