Search

Recently, biometric recognition has become a significant field of research. The concept of cancelable biometrics (CB) has been introduced to address security concerns related to the handling of sensitive data. In this paper, we address unconstrained face verification by proposing a deep cancelable framework called BiometricNet+ that employs random projections (RP) to conceal face images and compressive sensing (CS) to reconstruct measurements in the original domain. Our lightweight design enforces the properties of unlinkability, revocability, and non-invertibility of the templates while preserving face recognition accuracy. We compare facial features by learning a regularized metric: at training time, we jointly learn facial features and the metric such that matching and non-matching pairs are mapped onto latent target distributions; then, for biometric verification, features are randomly projected via random matrices changed at every enrollment and query and reconstructed before the latent space mapping is computed. We assess the face recognition accuracy of our framework on challenging datasets such as LFW, CALFW, CPLFW, AgeDB, YTF, CFP, and RFW, showing notable improvements over state-of-the-art techniques while meeting the criteria for secure cancelable template design. Since our method requires no fine-tuning of the learned features, it can be applied to pre-trained networks to increase sensitive data protection. [ABSTRACT FROM AUTHOR]

Information extraction from synthetic aperture radar (SAR) images is heavily impaired by speckle noise, and hence, despeckling is a crucial preliminary step in scene analysis algorithms. The recent success of deep learning envisions a new generation of despeckling techniques that could outperform classical model-based methods. However, current deep learning approaches to despeckling require supervision for training, whereas clean SAR images are impossible to obtain. In the literature, this issue is tackled by resorting to either synthetically speckled optical images, which exhibit different properties with respect to true SAR images, or multitemporal SAR images, which are difficult to acquire or fuse accurately. In this article, inspired by recent works on blind-spot denoising networks, we propose a self-supervised Bayesian despeckling method. The proposed method is trained by employing only noisy SAR images and can, therefore, learn features of real SAR images rather than synthetic data. Experiments show that the performance of the proposed approach is very close to the supervised training approach on synthetic data and superior on real data in both quantitative and visual assessments. [ABSTRACT FROM AUTHOR]

Recently, convolutional neural networks (CNNs) have been successfully applied to many remote sensing problems. However, deep learning techniques for multi-image super-resolution (SR) from multitemporal unregistered imagery have received little attention so far. This article proposes a novel CNN-based technique that exploits both spatial and temporal correlations to combine multiple images. This novel framework integrates the spatial registration task directly inside the CNN, and allows one to exploit the representation learning capabilities of the network to enhance registration accuracy. The entire SR process relies on a single CNN with three main stages: shared 2-D convolutions to extract high-dimensional features from the input images; a subnetwork proposing registration filters derived from the high-dimensional feature representations; 3-D convolutions for slow fusion of the features from multiple images. The whole network can be trained end-to-end to recover a single high-resolution image from multiple unregistered low-resolution images. The method presented in this article is the winner of the PROBA-V SR challenge issued by the European Space Agency (ESA). [ABSTRACT FROM AUTHOR]

This paper addresses the problem of training a deep neural network for satellite image segmentation so that it can be deployed over images whose statistics differ from those used for training. For example, in postdisaster damage assessment, the tight time constraints make it impractical to train a network from scratch for each image to be segmented. We propose a convolutional encoder–decoder network able to learn visual representations of increasing semantic level as its depth increases, allowing it to generalize over a wider range of satellite images. Then, we propose two additional methods to improve the network performance over each specific image to be segmented. First, we observe that updating the batch normalization layers’ statistics over the target image improves the network performance without human intervention. Second, we show that refining a trained network over a few samples of the image boosts the network performance with minimal human intervention. We evaluate our architecture over three data sets of satellite images, showing the state-of-the-art performance in binary segmentation of previously unseen images and competitive performance with respect to more complex techniques in a multiclass segmentation task. [ABSTRACT FROM AUTHOR]

A cloud screening unit on a satellite platform for Earth observation can play an important role in optimizing communication resources by selecting images with interesting content while skipping those that are highly contaminated by clouds. In this study, we address the cloud screening problem by investigating an encoder–decoder convolutional neural network (CNN). CNNs usually employ millions of parameters to provide high accuracy; on the other hand, the satellite platform imposes hardware constraints on the processing unit. Hence, to allow an onboard implementation, we investigate experimentally several solutions to reduce the resource consumption by CNN while preserving its classification accuracy. We experimentally explore approaches such as halving the computation precision, using fewer spectral bands, reducing the input size, decreasing the number of network filters and also making use of shallower networks, with the constraint that the resulting CNN must have sufficiently small memory footprint to fit the memory of a low-power accelerator for embedded systems. The trade-off between the network performance and resource consumption has been studied over the publicly available SPARCS dataset. Finally, we show that the proposed network can be implemented on the satellite board while performing with reasonably high accuracy compared with the state-of-the-art. [ABSTRACT FROM AUTHOR]