Network For Recognition Research Articles

A Frequency Feature Extraction Method Based on Convolutional Neural Network for Recognition of Incipient Fault

A Frequency Feature Extraction Method Based on Convolutional Neural Network for Recognition of Incipient Fault

Double Gabor-filter palm vein recognition network

Double Gabor-filter palm vein recognition network

Cell counting via attentive recognition network

Cell counting via attentive recognition network

Design of non-electrical protection device for 300Mvar-class large-scale phase-regulating units

Abstract This study investigates the role of non-electrical protective devices in forecasting hazards for large 300Mvar class phase shifter units, which face overvoltage and overcurrent stresses under severe faults, distorting their internal magnetic fields. Utilizing migration learning, the research extracts target and auxiliary data to train autoencoders with sparse constraints. A deep learning-based DSAE-BP online recognition network is constructed using a backpropagation neural network. This network predicts potential safety hazards in large-scale phase-regulating units by analyzing data signals from connected sensors. Experimental results show delay time errors of less than 20ms and ripple rates between 1.40%-1.65% across varied current and voltage conditions, demonstrating the device’s accuracy and stability in fault prediction.

Lightweight high-performance pose recognition network: HR-LiteNet

Lightweight high-performance pose recognition network: HR-LiteNet

Compressing recognition network of cotton disease with spot-adaptive knowledge distillation.

Deep networks play a crucial role in the recognition of agricultural diseases. However, these networks often come with numerous parameters and large sizes, posing a challenge for direct deployment on resource-limited edge computing devices for plant protection robots. To tackle this challenge for recognizing cotton diseases on the edge device, we adopt knowledge distillation to compress the big networks, aiming to reduce the number of parameters and the computational complexity of the networks. In order to get excellent performance, we conduct combined comparison experiments from three aspects: teacher network, student network and distillation algorithm. The teacher networks contain three classical convolutional neural networks, while the student networks include six lightweight networks in two categories of homogeneous and heterogeneous structures. In addition, we investigate nine distillation algorithms using spot-adaptive strategy. The results demonstrate that the combination of DenseNet40 as the teacher and ShuffleNetV2 as the student show best performance when using NST algorithm, yielding a recognition accuracy of 90.59% and reducing FLOPs from 0.29 G to 0.045 G. The proposed method can facilitate the lightweighting of the model for recognizing cotton diseases while maintaining high recognition accuracy and offer a practical solution for deploying deep models on edge computing devices.

Research on deep learning-based action recognition and quantitative assessment method for sports skills

Abstract The current sports training lacks data-based scientific training tools, and the use of action recognition technology to collect and mine sports data can effectively identify and evaluate sports skill actions. In this paper, a Transformer-based convolutional neural human action recognition network is proposed, which integrates the C3D convolutional network with the visual Transformer structure, using the 3D convolutional kernel for the extraction of time-domain features and using the Transformer network to accurately classify the feature sequences. The OpenPose algorithm is used to extract the essential points of the skeletal joints to estimate the human action posture. Through the dynamic time regularization algorithm, athletes’ sports movements are matched with standard movements to achieve a quantitative assessment of sports skill movements. The experimental results show that the method in this paper has better performance than similar neural network models in the task of sports action recognition and evaluation, and its class average accuracy mAP value and GFLOPs/V value are 0.9291 and 25.01, respectively, which substantially improves the recognition efficiency of sports skill actions.

Practical Innovation of Students’ Civic Education Model Based on Artificial Intelligence Technology

Abstract Integrating Artificial Intelligence (AI) into education, particularly civic education, represents a transformative shift. This study explores the innovative fusion of AI with teaching methodologies, aiming to enhance educational outcomes and foster comprehensive student development. We construct a multidimensional civic education framework by employing theoretical and empirical approaches, examining the dynamics between educators, students, content, and pedagogical strategies. We assess student academic performance and behavior by utilizing the Multi-Task Classroom Behavior Recognition Network (MCBRN) and multivariate analysis of variance (ANOVA). Our findings reveal that the AI-enhanced teaching model significantly boosts student engagement and learning achievements in the experimental group, with behavior recognition accuracy reaching 96.9%. Moreover, these students demonstrated superior examination scores and overall competency levels compared to the control group (P<0.05), highlighting the effectiveness of this novel approach in elevating the quality of civic education through personalized and efficient learning experiences.

Convolution-Enhanced Bi-Branch Adaptive Transformer With Cross-Task Interaction for Food Category and Ingredient Recognition.

Recently, visual food analysis has received more and more attention in the computer vision community due to its wide application scenarios, e.g., diet nutrition management, smart restaurant, and personalized diet recommendation. Considering that food images are unstructured images with complex and unfixed visual patterns, mining food-related semantic-aware regions is crucial. Furthermore, the ingredients contained in food images are semantically related to each other due to the cooking habits and have significant semantic relationships with food categories under the hierarchical food classification ontology. Therefore, modeling the long-range semantic relationships between ingredients and the categories-ingredients semantic interactions is beneficial for ingredient recognition and food analysis. Taking these factors into consideration, we propose a multi-task learning framework for food category and ingredient recognition. This framework mainly consists of a food-orient Transformer named Convolution-Enhanced Bi-Branch Adaptive Transformer (CBiAFormer) and a multi-task category-ingredient recognition network called Structural Learning and Cross-Task Interaction (SLCI). In order to capture the complex and unfixed fine-grained patterns of food images, we propose a query-aware data-adaptive attention mechanism called Bi-Branch Adaptive Attention (BiA-Attention) in CBiAFormer, which consists of a local fine-grained branch and a global coarse-grained branch to mine local and global semantic-aware regions for different input images through an adaptive candidate key/value sets assignment for each query. Additionally, a convolutional patch embedding module is proposed to extract the fine-grained features which are neglected by Transformers. To fully utilize the ingredient information, we propose SLCI, which consists of cross-layer attention to model the semantic relationships between ingredients and two cross-task interaction modules to mine the semantic interactions between categories and ingredients. Extensive experiments show that our method achieves competitive performance on three mainstream food datasets (ETH Food-101, Vireo Food-172, and ISIA Food-200). Visualization analyses of CBiAFormer and SLCI on two tasks prove the effectiveness of our method. Codes will be released upon publication. Code and models are available at https://github.com/Liuyuxinict/CBiAFormer.

Insights on 'Complex-Valued Iris Recognition Network'

Insights on 'Complex-Valued Iris Recognition Network'

Leveraging technological advances to assess dyadic visual cognition during infancy in high- and low-resource settings.

Caregiver-infant interactions shape infants' early visual experience; however, there is limited work from low-and middle-income countries (LMIC) in characterizing the visual cognitive dynamics of these interactions. Here, we present an innovative dyadic visual cognition pipeline using machine learning methods which captures, processes, and analyses the visual dynamics of caregiver-infant interactions across cultures. We undertake two studies to examine its application in both low (rural India) and high (urban UK) resource settings. Study 1 develops and validates the pipeline to process caregiver-infant interaction data captured using head-mounted cameras and eye-trackers. We use face detection and object recognition networks and validate these tools using 12 caregiver-infant dyads (4 dyads from a 6-month-old UK cohort, 4 dyads from a 6-month-old India cohort, and 4 dyads from a 9-month-old India cohort). Results show robust and accurate face and toy detection, as well as a high percent agreement between processed and manually coded dyadic interactions. Study 2 applied the pipeline to a larger data set (25 6-month-olds from the UK, 31 6-month-olds from India, and 37 9-month-olds from India) with the aim of comparing the visual dynamics of caregiver-infant interaction across the two cultural settings. Results show remarkable correspondence between key measures of visual exploration across cultures, including longer mean look durations during infant-led joint attention episodes. In addition, we found several differences across cultures. Most notably, infants in the UK had a higher proportion of infant-led joint attention episodes consistent with a child-centered view of parenting common in western middle-class families. In summary, the pipeline we report provides an objective assessment tool to quantify the visual dynamics of caregiver-infant interaction across high- and low-resource settings.

Enhancing Face Recognition with Detachable Self-Supervised Bypass Networks.

Attributed to the development of deep networks and abundant data, automatic face recognition (FR) has quickly reached human-level capacity in the past few years. However, the FR problem is not perfectly solved in case of large poses and uncontrolled occlusions. In this paper, we propose a novel bypass enhanced representation learning (BERL) method to improve face recognition under unconstrained scenarios. The proposed method integrates self-supervised learning and supervised learning together by attaching two auxiliary bypasses, a 3D reconstruction bypass and a blind inpainting bypass, to assist robust feature learning for face recognition. Among them, the 3D reconstruction bypass enforces the face recognition network to encode pose independent 3D facial information, which enhances the robustness to various poses. The blind inpainting bypass enforces the face recognition network to capture more facial context information for face inpainting, which enhances the robustness to occlusions. The whole framework is trained in end-to-end manner with two self-supervised tasks above and the classic supervised face identification task. During inference, the two auxiliary bypasses can be detached from the face recognition network, avoiding any additional computational overhead. Extensive experimental results on various face recognition benchmarks show that, without any cost of extra annotations and computations, our method outperforms state-of-the-art methods. Moreover, the learnt representations can also well generalize to other face-related downstream tasks such as the facial attribute recognition with limited labeled data.

MASTF-net: An EEG Emotion Recognition Network Based on Multi-Source Domain Adaptive Method Based on Spatio-Temporal Image and Frequency Domain Information

MASTF-net: An EEG Emotion Recognition Network Based on Multi-Source Domain Adaptive Method Based on Spatio-Temporal Image and Frequency Domain Information

CGLF-Net: Image Emotion Recognition Network by Combining Global Self-Attention Features and Local Multiscale Features

CGLF-Net: Image Emotion Recognition Network by Combining Global Self-Attention Features and Local Multiscale Features

Facial age recognition based on deep manifold learning.

Facial age recognition has been widely used in real-world applications. Most of current facial age recognition methods use deep learning to extract facial features to identify age. However, due to the high dimension features of faces, deep learning methods might extract a lot of redundant features, which is not beneficial for facial age recognition. To improve facial age recognition effectively, this paper proposed the deep manifold learning (DML), a combination of deep learning and manifold learning. In DML, deep learning was used to extract high-dimensional facial features, and manifold learning selected age-related features from these high-dimensional facial features for facial age recognition. Finally, we validated the DML on Multivariate Observations of Reactions and Physical Health (MORPH) and Face and Gesture Recognition Network (FG-NET) datasets. The results indicated that the mean absolute error (MAE) of MORPH is 1.60 and that of FG-NET is 2.48. Moreover, compared with the state of the art facial age recognition methods, the accuracy of DML has been greatly improved.

IAR-Net: A Human–Object Context Guided Action Recognition Network for Industrial Environment Monitoring

IAR-Net: A Human–Object Context Guided Action Recognition Network for Industrial Environment Monitoring

Using Deep Learning-Based Defect Detection and 3D Quantitative Assessment for Steel Deck Pavement Maintenance

Efficient distress detection and identification analysis are of great significances for long-span steel bridge deck pavement maintenance. This paper proposes a pavement distress recognition method based on road quality detection equipment and deep learning. Firstly, the sub-block image is used as the processing unit, and the three-dimensional image is divided into fracture surface element and background surface element. A pavement crack recognition network (PDRNet) based on convolutional neural network is proposed, which is used for automatic recognition of pavement background element and pavement crack element. Then, considering the pixel-level neighborhood characteristics of cracks in 3D pavement images, the PDRNet model is used to detect and quantitatively evaluate pavement cracks, which combines the crack elevation detection method to extract the complete contour of cracks in the crack surface element. Finally, the distress database containing three-dimensional markers is integrated into the pavement maintenance management platform. Results show that the PDRNet proposed in this paper has high prediction accuracy on the verification set and shows good robustness to various distress, and the average accuracy is above 88%. The established spatial-temporal integration platform overcomes the communication bottleneck between different types of data, and is important to improve the maintenance management level and predict the long-term development of distress.

Robust Table Structure Recognition Network Based on Local and Global Perspectives

Robust Table Structure Recognition Network Based on Local and Global Perspectives

A Hybrid BCI Integrating EEG and Eye-Tracking for Assisting Clinical Communication in Patients With Disorders of Consciousness.

Assessing communication abilities in patients with disorders of consciousness (DOCs) is challenging due to limitations in the behavioral scale. Electroencephalogram-based brain-computer interfaces (BCIs) and eye-tracking for detecting ocular changes can capture mental activities without requiring physical behaviors and thus may be a solution. This study proposes a hybrid BCI that integrates EEG and eye tracking to facilitate communication in patients with DOC. Specifically, the BCI presented a question and two randomly flashing answers (yes/no). The subjects were instructed to focus on an answer. A multimodal target recognition network (MTRN) is proposed to detect P300 potentials and eye-tracking responses (i.e., pupil constriction and gaze) and identify the target in real time. In the MTRN, the dual-stream feature extraction module with two independent multiscale convolutional neural networks extracts multiscale features from multimodal data. Then, the multimodal attention strategy adaptively extracts the most relevant information about the target from multimodal data. Finally, a prototype network is designed as a classifier to facilitate small-sample data classification. Ten healthy individuals, nine DOC patients and one LIS patient were included in this study. All healthy subjects achieved 100% accuracy. Five patients could communicate with our BCI, with 76.1±7.9% accuracy. Among them, two patients who were noncommunicative on the behavioral scale exhibited communication ability via our BCI. Additionally, we assessed the performance of unimodal BCIs and compared MTRNs with other methods. All the results suggested that our BCI can yield more sensitive outcomes than the CRS-R and can serve as a valuable communication tool.

Class Activation Regularization-Based Facial Emotion Recognition Network and Its Application in Students' Emotional Engagement Assessment

Class Activation Regularization-Based Facial Emotion Recognition Network and Its Application in Students' Emotional Engagement Assessment