A Digital-Pixel-Sensor-Based Global Feature Extraction Processor for Real-Time Object Recognition

A directional-edge-feature-based real-time image recognition system has been developed. By employing a digital-pixel-sensor-embedded feature extraction VLSI processor, the delay due to the image data transfer between the image sensor and the feature extraction circuits, the most serious bottleneck in such systems, has been reduced dramatically. Parallel feature vector-generation and template-matching processor functions implemented on an FPGA further accelerate the processing speed. As a result, the latency between the image capture and the final recognition has been reduced to only 906 mus, making this system suitable for time critical applications. In addition, the capability of the system for automatic adaptation to more significant features has also been experimentally demonstrated.

Android, the most widely used mobile operating system, is also the most vulnerable to malware due to its high popularity. This has significantly focused on Android malware detection in mobile security. While extensive research has been conducted using various methods, new malware’s emergence underscores this field’s dynamic nature and the need for continuous research. The motivation that drives malware developers to create Android malware constantly is the potential to access Android devices, thereby gaining access to sensitive user information. This study, which is a complex and in-depth exploration, aims to detect Android malware using a meta-classifier that combines the single-classifier light gradient boosting machine, support vector machine, and random forest. The process involves converting disassembled malware codes into grey images for global and local feature extraction. The classification accuracy is 97% at best on a malware dataset of 3,963 samples. The main contribution of this paper is to produce an Android APK malware detector model that works by combining multiple machine learning algorithms trained using the dataset resulting from local and global feature extraction algorithms.

LocalFace: Learning significant local features for deep face recognition

Convolutional neural networks (CNNs) have been widely used in the field of hyperspectral image change detection (HSI-CD) due to their excellent feature extraction capabilities. However, traditional convolution methods usually rely on a limited number of convolution kernels when extracting local features, and the local information only covers a small range of details, making it difficult to flexibly extract local changes at different levels in the image. In addition, CNNs have certain limitations in modeling global dependencies. In recent years, state-space model (SSM)-based methods (such as mamba) have effectively solved the quadratic complexity problem of transformer in capturing long-distance global dependencies. However, due to the processing method of expanding images into sequences, the spatial location structure of the image is destroyed, the spatial correlation between adjacent pixels is weakened, and spatial location information is easily lost, resulting in poor performance on complex hyperspectral datasets. To address these issues, we propose a wavelet-augmented dual-branch position-embedding mamba network (WDP-Mamba) for hyperspectral image change detection. This network combines the complementary advantages of mamba and wavelet convolution (WTconv) in global feature extraction and local edge feature extraction. Specifically, our method includes the following key innovations: 1) a novel state-space model, the adaptive position residual state space block (APRSSB) is designed, embedding learnable positional encodings within the mamba framework. Through a dual-temporal spatial-spectral scoring mechanism, the model dynamically preserves the topological relationships of pixel positions, enabling global dependency modeling with linear complexity; 2) a multi-level frequency-domain aware (MLFA) module is proposed to fully extract representative local features by decomposing information into frequency components of different scales and analyzing signals locally in multiple time and frequency windows. Extensive experiments on three hyperspectral datasets show that WDP-Mamba outperforms existing methods in both qualitative and quantitative assessments. Compared with other comparative models, WDP-Mamba achieves significant improvements in multiple performance metrics with a lower number of parameters, demonstrating its superior performance in the HSI-CD task.

In recent years, the automatic traffic signs recognition(TSR) has attracted researches' attention and it becomes a great challenge in Intelligent Transport System (ITS). Because of complex environmental or weather reasons, it is difficult for TSR to achieve high correct recognition rate and meet real-time at the same time. This paper focus on the traffic signs feature extraction and proposes a new effective approach to recognize the traffic signs with combining local feature and global feature. Center Symmetry Local Binary Pattern (CSLBP) is the improvement of Local Binary Pattern(LBP), We modify the CSLBP with multi sampling as the local feature. The global feature is the low frequency coefficients of Discrete Wavelet Transform (DWT) which owns good multi resolution ability. After extracted the two kinds of feature, we cascade them as the new feature to represent the traffic signs image. The final feature as the input data to classify the traffic signs with Support Vector Machine (SVM). In the GTSRB database, the result shows that the proposed approach achieves a accuracy of 97.67% which is superior to single feature approach and greatly reduces the recognition time.

Sentence similarity is widely used in various natural language tasks such as natural language inference, paraphrase identification, and question answering. However, a variety of linguistic expressions and ambiguities of words in sentences make it difficult to measure sentence similarity. Many studies show that using local features or global features of a sentence will produce satisfactory sentence representations that can be utilized to measure sentence similarity. Local features reflect the relationships of adjacent words for each sentence and the sequence information of a sentence are usually expressed by global features. However, local features lack abilities to capture sequence information while a small amount of extracted global features is not enough to produce sentence representations with good qualities. In this paper, we propose A Hybrid Model combining Local and Global features into a Siamese Network (HM-LGSN) for sentence similarity calculation. We first propose a new convolution neural network architecture called group convolution neural network to extract the most representative local features (or word semantic features). Then we combine these new features with pre-trained embeddings of words as input to the Bidirectional Gated Recurrent Units to extract global features of sentences. Finally, we select the global features to form sentence representations and calculate sentence similarity through Manhattan distance. The experimental results on SICK, MSRVID, STS-B datasets show that the accuracy of our proposed model is significantly improved by combining local features and global features.

Objective. Effective seizure prediction can reduce patient burden, improve clinical treatment accuracy, and lower healthcare costs. However, existing deep learning-based seizure prediction methods primarily rely on single models, which have limitations in feature extraction. This study aims to develop a hybrid model that integrates the advantages of convolutional neural networks (CNNs) and Transformer to enhance seizure prediction performance.Approach. We propose FusionXNet, a hybrid model inspired by CNNs and Transformer architectures, for seizure prediction. Specifically, we design a token synthesis unit to extract local features using convolution operations and capture global electroencephalography (EEG) representations via attention mechanisms. By merging local and global features extracted from the EEG segments, FusionXNet enhances feature representations, which are subsequently fed into a classifier for final seizure prediction.Main results. We evaluate the model on the publicly available Boston Children's Hospital and the Massachusetts Institute of Technology dataset, conducting segment-based and event-based experiments in both patient-specific and cross-patient settings. In event-based patient-specific experiments, FusionXNet achieves a sensitivity of 97.602% and a false positive rate (FPR) of 0.059 h-1. The results demonstrate that the proposed model effectively predicts seizures with high sensitivity and a low FPR, outperforming existing methods.Significance. The proposed FusionXNet model provides a robust and efficient approach for seizure prediction by leveraging both local and global feature extraction. The high sensitivity and low FPR indicate its potential for real-world clinical applications, improving patient management and reducing healthcare costs.

Face recognition is considered as one of the relatively new and interesting concepts in the area of biometrics and comprises a huge number of applications. This study involves implementation of a robust recognition system by employing global and random local facial features of an individual. The proposed scheme considers the extraction of global facial features and some randomly selected local facial features. In order to exploit global information of a whole face image, Principal Component Analysis (PCA) algorithm is used. On the other hand, the randomly selected sub-images of a whole face image are concatenated and subsequently PCA is applied on the concatenated regions. In addition, the proposed scheme involves the optimization of random sub-image locations and sizes by considering different settings and choosing the most optimized one. Finally, Weighted Sum Rule fusion is employed to combine the calculated scores of the global and local feature extractors. The reliability of the proposed facial recognition system is investigated on several data sets of ORL, FERET, and Extended Yale face databases. Demonstration of results based on the recognition performance and ROC analysis clarifies that the proposed scheme achieves a considerable improvement compared to the global and local feature extractors implemented in this study.

In the harsh underground environment, the transmission gear in the rocker arm of the shearer is susceptible to impact load, frequently leading to failures that result in economic losses or casualties. Therefore, real-time and accurate gear fault diagnosis is crucial. Existing diagnostic models struggle with insufficient feature extraction and low diagnostic accuracy when addressing nonlinear, nonsmooth signals with strong noise in this environment. Therefore, an innovative parallel integration model of Swin Transformer and multiscale convolution is proposed to extract both global and local features under different fault modes and noise conditions. A spatial interaction block (SIB) is introduced into the Swin Transformer branch to enhance global information acquisition. In multiscale convolutional neural network (CNN) branches, depthwise separable convolutions with different expansion coefficients are utilized for multiscale extraction of local features to reduce computational complexity. Considering the differences between global and local features, a feature interaction module (FIM) is added between the two branches to realize the interaction between local and global features, considerably improving the model diagnosis performance. Furthermore, to meet the high real-time diagnosis requirements, a cloud-edge collaboration (CEC) framework is designed to realize the timely alarm of gear faults through the efficient collaboration between edge nodes and the industrial cloud platform. Using the vibration data collected from the rocker arm loading test bed of Taizhong Coal Machinery and the gear data provided by Southeast University for validation, the results show that the diagnostic precision of the proposed method can reach up to 99.55%. Even when the signal-to-noise ratio (SNR) is −2 db, the accuracy is still 93.67%, which is superior to other advanced comparison models, and significantly reduces the completion time of fault diagnosis tasks, and has strong anti-noise and real-time diagnosis capabilities.

Infrared and visible image fusion improves the visual representation of scenes. Current deep learning-based fusion methods typically rely on either convolution operations for local feature extraction or Transformers for global feature extraction, often neglecting the contribution of multi-scale features to fusion performance. To address this limitation, we propose MRMAFusion, a nested connection model that relies on the multi-scale restoration-Transformer (Restormer) and multi-dimensional attention. We construct an encoder–decoder architecture on UNet++ network with multi-scale local and global feature extraction using convolution blocks and Restormer. Restormer can provide global dependency and more comprehensive attention to texture details of the target region along the vertical dimension, compared to extracting features by convolution operations. Along the horizontal dimension, we enhance MRMAFusion’s multi-scale feature extraction and reconstruction capability by incorporating multi-dimensional attention into the encoder’s convolutional blocks. We perform extensive experiments on the public datasets TNO, NIR and RoadScene and compare with other state-of-the-art methods for both objective and subjective evaluation.

: This report describes techniques for very large scale integration (VLSI) implementation of arithmetic algorithms. The report describes an algorithm for performing area-time efficient division, on-line techniques for performing bit-serial calculations, and iterative algorithms for performing square root. Keywords include: Very large scale integration (VLSI); and Floating point chip design.

Abstract. Complex geometric distortions and nonlinear radiation differences between optical and synthetic aperture radar (SAR) images present challenges for the matching of sufficient and evenly distributed corresponding points. To address this problem, this paper proposes a deep convolutional network based on an attention mechanism for matching optical and SAR images. In order to obtain robust feature points, we employ phase consistency instead of image intensity and gradient information for feature detection. A deep convolutional network (DCN) is designed to extract high-level semantic features between optical and SAR images, providing robustness to geometric distortion and nonlinear radiation changes. Notably, incorporating multiple inverted residual structures in the DCN facilitates efficient extraction of local and global features, promoting feature reuse, and reducing the loss of key features. Furthermore, a dense feature fusion module based on coordinate attention is designed, focusing on the spatial positional information of effective features, integrating key features into deep descriptors to enhance the robustness of deep descriptors to nonlinear radiometric differences. A coarse-to-fine strategy is then employed to enhance accuracy by eliminating mismatches. Experimental results demonstrate that the proposed network performs better than the manually designed descriptors-based methods and the stateof- the-art deep learning networks in both matching effectiveness and accuracy. Specifically, the number of matches achieved is approximately 2 times greater than that of other methods, with a 10% improvement in F-measure.

Person re-identification with part prediction alignment

Camouflaged object detection (COD) aims to accurately detect objects that blend in with their backgrounds. While deep learning-based methods have significantly improved detection accuracy, the persistent similarity in chromatic and textural characteristics between camouflaged objects and their environments continues to pose substantial challenges, particularly in complex scenarios. Existing COD methods still encounter two primary challenges: (1) the difficulty in effectively fusing detailed features with semantic representations, leading to suboptimal balance between local and global features in the fused features; (2) progressive information dilution in conventional top-down decoder architectures, resulting in imprecise boundary localization. To address these dual challenges of multi-scale feature enhancement and semantic information dilution, we propose a D ual-Branch C ross-Layer I nformation F low Network (DCIFNet) for camouflaged object detection in complex scenes. Specifically, our framework integrates a hybrid CNN-ViT architecture for parallel extraction of localized patterns and global contextual features. Subsequently, a global local fusion (GLF) module is employed to iteratively and adaptively fuse the global and local features at each stage using gating weights. Additionally, a novel Dense Connection Decoder (DCD) module is designed to mitigate the information dilution problem associated with traditional top-down decoders. Extensive experiments show that DCIFNet outperforms other mainstream COD models in most performance metrics on four widely used benchmark datasets. On the COD10K dataset, compared with the latest SOTA work of PRNet, DCIFNet improves the metrics of \({S_{\alpha}}\) , \({E_{\phi}}\) , and \(F_{\beta}^{w}\) by 0.11 \(\%\) , 0.11 \(\%\) , and 1.38 \(\%\) , respectively, demonstrating a significant performance enhancement. The code is available https://github.com/WateverOk/DCIFNet .

Pore-based fingerprint recognition has become more attractive in recent years because of its uniqueness and difficulty in forgeability. However, most of the existing methods use pore features for fingerprint verification rather than fingerprint indexing, and most of them use only local features of pores to evaluate the similarities between fingerprints. In this article, we present a hierarchical pore-based high-resolution fingerprint indexing system using two kinds of pore features (including pore-based global and local features). Our work consists of two major parts. First, we design a united model named deep pore-based global and local features model (DPGL) to extract pore-based global and local features of fingerprints simultaneously. The most important is the DPGL framework makes full use of pore information. It applies deconvolution module to learn a spatial attention mask that explicitly exploits self-supervision on pore locations. Second, we design a novel hierarchical pore-based fingerprint indexing approach. In the proposed approach, the reference fingerprints are primely selected based on pore-based global features. The fingerprints retained are selected based on pore-based local features subsequently. Finally, the candidate fingerprints are ranked according to pore information matching. Experiments on two datasets show that DPGL not only can accomplish the extraction of pore-based global and local features successfully, but also can achieve self-supervision on pore information. Compared with other state-of-the-art pore-based fingerprint indexing methods, the proposed approach reduces the pre-selection error rate by about 50% at penetration rate 1%, and performs at least 65% reduction in retrieval time.