Search

BackgroundGoogle Glass is a head-mounted device designed in the shape of a pair of eyeglasses equipped with a 5.0-megapixel integrated camera and capable of taking pictures with simple voice commands. ObjectiveThe objective of our study was to determine whether Google Glass is fit for veterinary forensic pathology purposes. MethodsA total of 44 forensic necropsies of 2 different species (22 dogs and 22 cats) were performed by 2 pathologists; each pathologist conducted 11 necropsies of each species and, for each photographic acquisition, the images were taken with a Google Glass device and a Nikon D3200 digital single-lens reflex (DSLR) camera. The pictures were collected, divided into 3 groups (based on the external appearance of the animal, organs, and anatomical details), and evaluated by 5 forensic pathologists using a 5-point score system. The parameters assessed were overall color settings, region of interest, sharpness, and brightness. To evaluate the difference in mean duration between necropsies conduced with Google Glass and DSLR camera and to assess the battery consumption of the devices, an additional number of 16 necropsies were performed by the 2 pathologists. In these cases, Google Glass was used for photographic reports in 8 cases (4 dogs and 4 cats) and a Nikon D3200 reflex camera in the other 8 cases. Statistical evaluations were performed to assess the differences in ratings between the quality of the images taken with both devices. ResultsThe images taken with Google Glass received significantly lower ratings than those acquired with reflex camera for all 4 assessed parameters (P

Sharing facial pictures through online services, especially on social networks, has become a common habit for thousands of users. This practice hides a possible threat to privacy: the owners of such services, as well as malicious users, could automatically extract information from faces using modern and effective neural networks. In this article, we propose the harmless use of adversarial attacks, i.e., variations of images that are almost imperceptible to the human eye and that are typically generated with the malicious purpose to mislead Convolutional Neural Networks (CNNs). Such attacks have been instead adopted to (1) obfuscate soft biometrics (gender, age, ethnicity) but (2) without degrading the quality of the face images posted online. We achieve the above-mentioned two conflicting goals by modifying the implementations of four of the most popular adversarial attacks, namely FGSM, PGD, DeepFool, and C&W, in order to constrain the average amount of noise they generate on the image and the maximum perturbation they add on the single pixel. We demonstrate, in an experimental framework including three popular CNNs, namely VGG16, SENet, and MobileNetV3, that the considered obfuscation method, which requires at most 4 seconds for each image, is effective not only when we have a complete knowledge of the neural network that extracts the soft biometrics (white box attacks) but also when the adversarial attacks are generated in a more realistic black box scenario. Finally, we prove that an opponent can implement defense techniques to partially reduce the effect of the obfuscation, but substantially paying in terms of accuracy over clean images; this result, confirmed by the experiments carried out with three popular defense methods, namely adversarial training, denoising autoencoder, and Kullback-Leibler autoencoder, shows that it is not convenient for the opponent to defend himself and that the proposed approach is robust to defenses. [ABSTRACT FROM AUTHOR]

The automatic detection of smoke by analyzing the video stream acquired by traditional surveillance cameras is becoming a more and more interesting problem for the scientific community thanks to the necessity to prevent fires at the very early stages. The adoption of a smart visual sensor, namely a computer vision algorithm running in real time, allows one to overcome the limitations of standard physical sensors. Nevertheless, this is a very challenging problem, due to the strong similarity of the smoke with other environmental elements like clouds, fog and dust. In addition to this challenge, data available for training deep neural networks is limited and not fully representative of real environments. Within this context, in this paper we propose a new method for smoke detection based on the combination of motion and appearance analysis with a modern convolutional neural network (CNN). Moreover, we propose a new dataset, called the MIVIA Smoke Detection Dataset (MIVIA-SDD), publicly available for research purposes; it consists of 129 videos covering about 28 h of recordings. The proposed hybrid method, trained and evaluated on the proposed dataset, demonstrated to be very effective by achieving a 94% smoke recognition rate and, at the same time, a substantially lower false positive rate if compared with fully deep learning-based approaches (14% vs. 100%). Therefore, the proposed combination of motion and appearance analysis with deep learning CNNs can be further investigated to improve the precision of fire detection approaches. [ABSTRACT FROM AUTHOR]

Face analysis includes a variety of specific problems as face detection, person identification, gender and ethnicity recognition, just to name the most common ones; in the last two decades, significant research efforts have been devoted to the challenging task of age estimation from faces, as witnessed by the high number of published papers. The explosion of the deep learning paradigm, that is determining a spectacular increasing of the performance, is in the public eye; consequently, the number of approaches based on deep learning is impressively growing and this also happened for age estimation. The exciting results obtained have been recently surveyed on almost all the specific face analysis problems; the only exception stands for age estimation, whose last survey dates back to 2010 and does not include any deep learning based approach to the problem. This paper provides an analysis of the deep methods proposed in the last six years; these are analysed from different points of view: the network architecture together with the learning procedure, the used datasets, data preprocessing and augmentation, and the exploitation of additional data coming from gender, race and face expression. The review is completed by discussing the results obtained on public datasets, so as the impact of different aspects on system performance, together with still open issues. [ABSTRACT FROM AUTHOR]

For several years, fault diagnosis of photovoltaic (PV) plants has been manually performed by the human operator by a visual inspection or automatically, by evaluating electrical measures collected by sensors mounted on each PV module. In recent years, a notable interest of the scientific community has been devoted towards the definition of algorithms able to automatically analyse the sequence of images acquired by a thermal camera mounted on board of an unmanned aerial vehicle (UAV) for early PV anomaly detection. In this paper, we define a model-based approach for the detection of the panels, which uses the structural regularity of the PV string and a novel technique for local hot spot detection, based on the use of a fast and effective algorithm for finding local maxima in the PV panel region. Finally, we introduce the concept of global hot spot detection, namely a multi-frame recognition of PV faults which further improves the anomaly detection accuracy of the proposed method. The algorithm has been designed and optimized so as to run in real-time directly on an embedded system on board of the UAV. The accuracy of the proposed approach has been experimented on several video sequences with a standard protocol in terms of Precision, Recall and F-Score, so that our dataset and our quantitative results can be used for future comparisons and to evaluate the reliability of computer vision techniques designed for thermographic PV inspection. [ABSTRACT FROM AUTHOR]

Graph matching is essential in several fields that use structured information, such as biology, chemistry, social networks, knowledge management, document analysis and others. Except for special classes of graphs, graph matching has in the worst-case an exponential complexity; however, there are algorithms that show an acceptable execution time, as long as the graphs are not too large and not too dense. In this paper we introduce a novel subgraph isomorphism algorithm, VF3, particularly efficient in the challenging case of graphs with thousands of nodes and a high edge density. Its performance, both in terms of time and memory, has been assessed on a large dataset of 12,700 random graphs with a size up to 10,000 nodes, made publicly available. VF3 has been compared with four other state-of-the-art algorithms, and the huge experimentation required more than two years of processing time. The results confirm that VF3 definitely outperforms the other algorithms when the graphs become huge and dense, but also has a very good performance on smaller or sparser graphs. [ABSTRACT FROM PUBLISHER]