Pattern Recognition Letters

• The image transformation and the super-resolution are integrated for the first time.
• We constructed two datasets of small infrared UAV targets to test the performance.
• It is possible to obtain a large and clear image simultaneously ...

With the development of generative adversarial networks, the super-resolution technique of reconstructing a high-resolution image from a low-resolution has achieved excellent resolution results. However, small, low-resolution images are ...

Display Omitted

Text line segmentation is an important step in the historical document image analysis pipeline to supply useful information for recognition, keyword spotting and indexing. Many handcrafted-based and learning-based approaches have been developed ...

• Performance of the medial seam extraction increase while applying triple smoothing.
• The adaptive slice contributes to improved medial seams segmentation.
• Denoising increases text line extraction results by offering a cleaner text ...

This paper presents a secure face recognition system with advanced template protection schemes for Cyber–Physical–Social Services (CPSS). The implementation of the proposed system consists of five components. The initial step performs image ...

• Encrypted domain-based recognition system.
• Modification of the FaceHashing technique up to three levels of security.
• Two additional prime factors in the RSA cryptosystem.
• Access control via OTP-based smart card.
• Original ...

Fingerprint recognition has emerged as one of the most reliable biometric authentication methods, owing to its uniqueness and permanence. However, the security and confidentiality of the user’s data are key considerations in modern biometric ...

• Reduces image impulse noise using decision-based median and linear filtering.
• Feature vectors were processed with Faster-R-CNN and DBMF to alleviate overfitting.
• Optimizes the matching procedure and automatically eliminates ...

Compared with other biometrics, such as fingerprints and irises, EEG signals contain richer identity information due to their high subject dependence. In this study, we proposed an affective EEG-based person identification by using an affective ...

• An affective transformer is designed for affective EEG-based person identification.
• An interrelated spatial-temporal attention is proposed for feature extraction.
• The gamma band and power spectrum density of EEG contribute more to ...

Word spotting in handwritten documents is challenging due to the high intra-class and inter-class variability of handwritten forms. This paper addresses the word spotting problem in the segmentation and the training scenarios. Overall, this paper ...

• The Pyramid of Bidirectional Character Sequences (PBCS) word text representation.
• Word spotting task as a binary classification problem.
• Combing the strengths of convolutional layers and transformers.

Hypersphere Guided Embedding for Masked Face Recognition has been proposed to address the problem encountered in the Masked Face Recognition task, which arises due to non-biological information from occlusions. While some existing algorithms ...

Display Omitted

• Elucidated the adverse impact of mask information.
• Explored the similarities and disparities between different data distribution.
• Experiments proved the effectiveness of our method.

Multicriteria decision analysis (MCDA) is a widely used tool to support decisions in which a set of alternatives should be ranked or classified based on multiple criteria. Recent studies in MCDA have shown the relevance of considering not only ...

• We use predicted signals features (e.g., trend and variance) to help decision-making.
• A PROMETHEE II extension is proposed to aggregate a tensor with future features.
• The proposal is meaningful mainly when dealing with a ...

LIDAR point clouds are less affected by the weather and possess more depth of field than 2D images. However, sparsity and disorder of point clouds bring challenges for 3D object tracking due to the difficulty in detecting and encoding. In ...

• The OS-DS is an object tracker for Single Target Tracking of LIDAR Point Clouds.
• The orientation-variant auto-encoder gains a effective geometric representation.
• Detection based Sampling module cuts the excessive and useless ...

In the photograph of mobile terminal, image degradation is a multivariate problem, where the spectral of the scene, the lens imperfections, the sensor noise, and the field of view together contribute to the results. Besides eliminating it at the ...

• Proposing a prior quantization model to utilize physical properties of camera.
• Using a synthetic flow for generating the data pairs from corresponding situation.
• Realizing flexible image restoration for mass-produced mobile ...

Incorporating uncertainty quantification into the modeling of deep learning-based model has become a research focus in the deep learning community. Within this group of methods, stochastic differential equation (SDE)-based models have ...

• We propose to construct a more precise uncertainty quantification network using a Milstein method of SDE mathematically.
• Based on Milstein method, our MDSDE-Net improves interpretability and performance in DNN uncertainty ...

With the development of self-driving technology, pedestrian detection models are becoming more useful and important. Although object detection models based on Convolutional Neural Networks have achieved favorable detection results, due to the ...

• We propose OPLA to improve detection in crowded scenes by paying more attention to occluded GTs during label assignment.
• We improve the existing post-processing methods and propose H-NMS for dense pedestrian detection.
• Without any ...

Unlike current state-of-the-art methods based on data augmentation and adversarial frameworks to solve the fair classification problem, this paper proposes the Information Bottleneck Disentanglement Based Sparse Representation algorithm to ensure ...

• A new sparse representation method named IBD-SR is proposed for fair classification.
• IBD-SR attempts to solve the fair classification problem based on information theory.
• IBD-SR integrates sparse structures into information ...

Deep neural networks are known to be vulnerable to adversarial perturbations. The amount of these perturbations are generally quantified using L p metrics, such as L 0, L 2 and L ∞. However, even when the measured perturbations are small, they ...

• Local spatial information loss in chrominance channels does not produce perceptible changes.
• Spatial transformation in chrominance channels can generate adversarial examples with high perceptual quality scores.
• Spatial ...

The major hurdle in building a visible and infrared fusion model is the necessity of large-scale pixel-aligned and time-synchronized image pairs. In this paper, we propose an easy-to-learn visible and infrared image fusion framework that does not ...

Display Omitted

• The proposed image fusion framework can be learned with an unpaired set.
• Aligning images and preparing ground truth is not needed at all.
• A feature line-up method is designed to mix features from each spectrum.
• Our loss ...

Camouflaged Object Detection (COD) is a challenging task aiming to locate the “indistinguishable” object with high similarity to the background. Existing COD methods are highly dependent on the differences in extrinsic appearances while ...

• Introduce polarization information for camouflaged object detection.
• Construct the first polarization-based dataset PCOD with 639 high-quality scenes.
• Design a novel PIE module to extract polarization information from the DoFP ...

Unsupervised k-nearest-neighbor-based outlier detectors play a vital role in data science research. However, the detectors’ performance relies on the choice of the parameter k. However, autonomous selection of the optimal k is poorly documented ...

• Neighborhood consistency (NC) that an object and its k-NN should have consistent outlier scores is introduced.
• Based on NC, we proposed a framework called KFC for automatically selecting k for k-NN-based outlier detectors.
• We ...

This paper designs a consensus control protocol for multi-agent systems(MAS) based on the edge-event-triggering mechanism to achieve a leader-following consensus under Denial-of-service (DoS) attacks. First, the dynamics model of the multi-agent ...

• Designed the follower adaptive compensators without global information.
• Designed the edge-event-triggering conditions for each type of agent.
• Employed state estimations to maximize communication resources when an edge is under ...

Domain adaptation (DA) aims to reduce knowledge gap between domains and improve the prediction ability of models in the target domain. However, the representations learned from feature extraction network often contain redundant information, which ...

Display Omitted

• The effects of the classification layer on the sample of decision boundaries is emphasized.
• The correlation and independence of all representations with domain-specific representations is investigated.
• Removal of redundant ...

Given the visual data of an object, directly predicting the high-degree-of-freedom grasping pose of a dexterous hand is a challenging task. In this paper, we propose a new grasp synthesis framework based on hand-object interaction for ...

• A new grasp synthesis framework for dexterous hands based on hand-object interaction.
• Cascaded finger joint angle estimation strategy to model hand-object interaction.
• A refinement module with hand-object contact constraints to ...

This paper proposes a novel strategy for lightweight 3D hand pose estimation. The strategy decomposes the estimation process into feature extraction and feature exploitation, where feature extraction performs dimension reduction on the original ...

• Proposing a lightweight strategy for rapid 3D hand pose estimation.
• Cascading extraction via CNNs, considering exploitation as path optimization via RL.
• Extending RL into continuous space for better exploitation.
• Leading real-...

As one of the most popular machine learning methods, random forests have been successfully applied to different data analysis tasks such as classification, regression and cluster analysis. Recently, the random forest clustering method has ...

• A discrete sequence clustering method based on random forest is proposed.
• We solve the unsupervised sequence clustering problem in a “supervised” manner.
• Experimental results demonstrate the feasibility and effectiveness of our ...