Search

Unmanned aerial vehicle (UAV) remote sensing images used for semantic segmentation possess distinct features compared to urban street scene images, including high resolution and a complex background. Spatial information plays a pivotal role in enhancing the performance of semantic segmentation for high-resolution images. The dual-branch architecture for semantic segmentation incorporates supplementary branches to capture spatial information. However, prior research on dual-branch semantic segmentation neglected the interaction between the contextual and spatial branches, leading to suboptimal model performance. In this discourse, the article introduces a dual-branch semantic segmentation framework. This design advances the system's understanding of spatial information while facilitating inter-branch learning through two key modules. Initially, the spatial calibration feature extraction module employs frequency domain processing and learning tactics distinct from the contextual approach to generate image features under varied noise conditions. Calibration is achieved by generating features from diverse angles. Subsequently, the spatially-guided loss function directs the acquisition of spatial information for the spatial branch by condensing the deep image characteristics for the context branch. To assess the generalization capacity of the proposed method, experiments will be conducted on three different datasets. The proposed method's modules will be integrated into three representative dual-branch networks, allowing assessment of the generalization capacity of the key DBCG components. Empirical evidence demonstrates that this approach is highly effective, significantly surpassing the performance of the baseline network.

Deep-learning-based on convolutional neural networks (CNN) has been widely applied in synthetic aperture radar (SAR) target recognition and made significant progress. However, due to the physical effects of the equipment used to collect images, various degrees of speckle noise will be introduced into SAR images. Traditional CNN-based SAR target recognition methods are premised on the same noise intensity in the training and testing set, which is contrary to the target recognition in practice. To alleviate this problem, we propose a novel speckle noise resistant framework for SAR target recognition, called dual-consistency-alignment-based self-supervised learning. First, original SAR images are randomly added to speckle noise with different thresholds through multiplicative noise, after which contrastive pretraining is performed on unlabeled data. During this period, we combine instance pseudolabel consistency alignment and feature consistency alignment to align multiple threshold speckle noise views with original views under the same targets. Finally, the pretrained model is migrated to the downstream SAR speckle noise target recognition task. In this article, speckle noise modeling is conducted based on moving and stationary target capture and recognition data testing set, and experiment results reveal that this method can adapt to different intensities of speckle noise, is robust to modeled SAR image recognition, and maintains a high recognition rate even in small-sample learning.

Methods for the detection of Acute Lymphoblastic (or Lymphocytic) Leukemia (ALL) are increasingly considering Deep Learning (DL) due to its high accuracy in several fields, including medical imaging. In most cases, such methods use transfer learning techniques to compensate for the limited availability of labeled data. However, current methods for ALL detection use traditional transfer learning, which requires the models to be fully trained on the source domain, then fine-tuned on the target domain, with the drawback of possibly overfitting the source domain and reducing the generalization capability on the target domain. To overcome this drawback and increase the classification accuracy that can be obtained using transfer learning, in this paper we propose our method named “Deep Learning for Acute Lymphoblastic Leukemia” (DL4ALL), a novel multi-task learning DL model for ALL detection, trained using a cross-dataset transfer learning approach. The method adapts an existing model into a multi-task classification problem, then trains it using transfer learning procedures that consider both source and target databases at the same time, interleaving batches from the two domains even when they are significantly different. The proposed DL4ALL represents the first work in the literature using a multi-task cross-dataset transfer learning procedure for ALL detection. Results on a publicly-available ALL database confirm the validity of our approach, which achieves a higher accuracy in detecting ALL with respect to existing methods, even when not using manual labels for the source domain.

The very high recognition accuracy of iris-based biometric systems and the increasing distribution of high-resolution personal images on websites and social media are creating privacy risks that users and the biometric community have not yet addressed properly. Biometric information contained in the iris region can be used to automatically recognize individuals even after several years, potentially enabling pervasive identification, recognition, and tracking of individuals without explicit consent. To address this issue, this paper presents two main contributions. First, we demonstrate, through practical examples, that the risk associated with iris-based identification by means of images collected from public websites and social media is real. Second, we propose an innovative method based on generative adversarial networks (GANs) that can automatically generate novel images with high visual realism, in which all the biometric information associated with an individual in the iris region has been removed and replaced. We tested the proposed method on an image dataset composed of high-resolution portrait images collected from the web. The results show that the generated deidentified images significantly reduce the privacy risks and, in most cases, are indistinguishable from real samples.

The detection of diatoms into the organs is considered an important “biological marker” for the diagnosis of drowning in human pathology, but it still has a high possibility for false positive results. The aims of this study were: (1) to evaluate the contribution of pathological examination in drowning cases and (2) to investigate the differences in the number and location of diatoms between animals who died in drowning and non-drowning conditions. For these purposes, 30 dead adult dogs were selected for the study and subdivided into five groups. The group A comprised six cadavers dead for drowning; the group B comprised six control animals; the groups C, D, and E comprised six animals dead for causes other than drowning and subsequently immersed in water for 24, 48, and 72 h, respectively. On each animal, a complete macroscopic and histological examination and diatom test were performed. Diatoms test and quantification were also performed on drowning mediums. Pathological findings of the animals in the group A showed pulmonary congestion, oedema, and hemorrages in the lung. However, similar injuries were also observed in control and experimentally submerged cadavers. In contrast, we observed a statistically differences between drowning animals and all experimentally submerged groups and control animals regarding diatom numbers recovered from organ tissue samples (p < 0.05). Therefore, these findings suggest that the number of diatoms may be used as a valid tool to differentiate animals who died in drowning and non-drowning conditions, even if the latter were found in an aquatic environment.

The use of seaweeds as additives in animal nutrition may be a valid option to traditional feed as they represent a rich source of minerals, carbohydrates and antioxidants. The aim of this study was to analyze the chemical composition and in vitro antioxidant capacity of two tropical eucheumatoids, Kappaphycus alvarezii and Kappaphycus striatus, in Malaysian wild offshore waters. The chemical analysis was performed via inductively coupled plasma–optical emission spectroscopy for evaluating the concentration of toxic (Cd, Pb, Hg, As) and essential elements (Mn, Fe, Cu, Ni, Zn, Se); NMR spectroscopy was used for carrageenans investigation. Furthermore, the soluble and fat-soluble antioxidant capacities were determined by FRAP, DPPH and ABTS assays. The chemical analysis revealed a higher content of trace elements in K. alvarezii as compared to K. striatus, and both exhibited a high mineral content. No significant differences in metal concentrations were found between the two species. Both samples showed a mixture of prevailing κ- and t-carrageenans. Finally, the levels of soluble and fat-soluble antioxidants in K. alvarezii were significantly higher than in K. striatus. Our findings suggest that K. alvarezii could be used as a potential feed additive because of its favorable chemical and nutritional features.

Loranthus europaeus is a well-known and important medicinal plant, with a long history of traditional medicine use. Several studies showed that it contains many bioactive compounds with a wide range of pharmacological effects. In light of these past researches, L. europaeus were chosen to consider its potential antimicrobial action. To this aim, different protocols were performed to selectively extract protein compounds, from L. europaeus yellow fruits, and evaluate the antimicrobial activity against four phytopathogenic fungi (Aspergillus niger, Alternaria spp., Penicillium spp., Botritis cinereus) and a number of foodborne bacterial pathogens (Listeria monocytogenes, Staphylococcus aureus strains, Salmonella Typhimurium and Escherichia coli) by using serial dilutions and colony formation assays. Results evidenced no antifungal activity but a notable bactericidal efficiency of a crude protein extract against two foodborne pathogens, with minimum inhibitory concentration (MIC) and minimum bactericidal concentration (MBC) values between 0.2 and 0.5 mg/mL, being S. aureus strains the most susceptible bacteria. Moreover, a strong bactericidal activity against S. aureus M7 was observed by two partially purified protein fractions of about 600 and 60 kDa molecular mass in native conditions. Therefore, these plant protein extracts could be used as natural alternative preventives to control food poisoning diseases and preserve foodstuff avoiding health hazards of chemically antimicrobial applications.