Deep Convolutional Network Research Articles

Logo recognition of vehicles based on deep convolutional generative adversarial networks

Vehicle logo recognition plays a critical role in enhancing the efficiency of intelligent transportation systems by enabling accurate vehicle identification and tracking. Despite advancements in image recognition technologies, accurately detecting and classifying vehicle logos in diverse and dynamically changing environments remains a significant challenge. This research introduces an innovative approach utilizing a Deep Convolutional Generative Adversarial Network (DCGAN) framework, tailored specifically for the complex task of vehicle logo recognition. Unlike traditional methods, which heavily rely on manual feature extraction and pre-defined image processing techniques, our method employs a novel DCGAN architecture. This architecture automatically learns the distinctive features of vehicle logos directly from data, enabling more robust and accurate recognition across various conditions. Furthermore, we propose a refined training strategy for both the generator and discriminator components of our DCGAN, optimized through extensive experimentation, to enhance the model’s ability to generate high-fidelity vehicle logo images for improved training efficacy. The technical core of our approach lies in the strategic integration of transfer learning techniques. These techniques significantly boost classification accuracy by leveraging pre-learned features from vast image datasets, thereby addressing the challenge of limited labeled data in the vehicle logo domain. Our experimental results demonstrate a substantial improvement in logo detection and classification accuracy, achieving an Intersection over Union (IoU) ratio of 42.67 % and a classification accuracy of 99.78 %, which markedly surpasses the performance of existing methods. This research not only advances the field of vehicle logo recognition but also contributes to the broader domain of measurement science and technology, offering a technically sound and logically coherent solution to a complex problem.

Optimized encoder-decoder cascaded deep convolutional network for leaf disease image segmentation.

Nowadays, Deep Learning (DL) techniques are being used to automate the identification and diagnosis of plant diseases, thereby enhancing global food security and enabling non-experts to detect these diseases. Among many DL techniques, a Deep Encoder-Decoder Cascaded Network (DEDCNet) model can precisely segment diseased areas from the leaf images to differentiate and classify multiple diseases. On the other hand, the model training depends on the appropriate selection of hyperparameters. Also, this network structure has weak robustness with different parameters. Hence, in this manuscript, an Optimized DEDCNet (ODEDCNet) model is proposed for improved leaf disease image segmentation. To choose the best DEDCNet hyperparameters, a brand-new Dingo Optimization Algorithm (DOA) is included in this model. The DOA depends on the foraging nature of dingoes, which comprises exploration and exploitation phases. In exploration, it attains many predictable decisions in the search area, whereas exploitation enables exploring the best decisions in a provided area. The segmentation accuracy is used as the fitness value of each dingo for hyperparameter selection. By configuring the chosen hyperparameters, the DEDCNet is trained to segment the leaf disease regions. The segmented images are further given to the pre-trained Convolutional Neural Networks (CNNs) followed by the Support Vector Machine (SVM) for classifying leaf diseases. ODEDCNet performs exceptionally well on the PlantVillage and Betel Leaf Image datasets, attaining an astounding 97.33% accuracy on the former and 97.42% accuracy on the latter. Both datasets achieve noteworthy recall, F-score, Dice coefficient, and precision values: the Betel Leaf Image dataset shows values of 97.4%, 97.29%, 97.35%, and 0.9897; the PlantVillage dataset shows values of 97.5%, 97.42%, 97.46%, and 0.9901, all completed in remarkably short processing times of 0.07 and 0.06 seconds, respectively. The achieved outcomes are evaluated with the contemporary optimization algorithms using the considered datasets to comprehend the efficiency of DOA.

Early detection of glaucoma: feature visualization with a deep convolutional network

ABSTRACT Computer-aided diagnosis of ocular disorders like glaucoma can be effectively performed with retinal fundus images. Since the advent of machine learning and later deep learning techniques in medical image analysis, research focusing on automated and early detection of glaucoma has gained prominence. In this paper, we show how a deep Convolutional Neural Network model can be used in visualising the features related to Glaucoma that are consistent with (a subset of) those used by ophthalmologists for diagnosis. However, since the doctors do not necessarily depend entirely on these features but back them up with other important measurements such as visual field testing (HVF), any deep neural network such as CNN may not necessarily be expected to yield 100% accuracy. Further, other important parameters such as Intraocular Pressure (IOP), which may be built into a deep learning model, may not necessarily correlate well with the presence of Glaucoma. In this work, a deep CNN model has been trained and tested on a large number of high-quality fundus images, both normal and glaucomatous. We compare the results with transfer learning models such as VGG16, ResNet50, and MobileNetV2. On an average, we obtained an accuracy of 93.75% in identifying glaucoma, focusing only on the features of the fundus image.

Single-Shot 3D Reconstruction via Nonlinear Fringe Transformation: Supervised and Unsupervised Learning Approaches.

The field of computer vision has been focusing on achieving accurate three-dimensional (3D) object representations from a single two-dimensional (2D) image through deep artificial neural networks. Recent advancements in 3D shape reconstruction techniques that combine structured light and deep learning show promise in acquiring high-quality geometric information about object surfaces. This paper introduces a new single-shot 3D shape reconstruction method that uses a nonlinear fringe transformation approach through both supervised and unsupervised learning networks. In this method, a deep learning network learns to convert a grayscale fringe input into multiple phase-shifted fringe outputs with different frequencies, which act as an intermediate result for the subsequent 3D reconstruction process using the structured-light fringe projection profilometry technique. Experiments have been conducted to validate the practicality and robustness of the proposed technique. The experimental results demonstrate that the unsupervised learning approach using a deep convolutional generative adversarial network (DCGAN) is superior to the supervised learning approach using UNet in image-to-image generation. The proposed technique's ability to accurately reconstruct 3D shapes of objects using only a single fringe image opens up vast opportunities for its application across diverse real-world scenarios.

Synthetic CT generation based on CBCT using improved vision transformer CycleGAN

Cone-beam computed tomography (CBCT) is a crucial component of adaptive radiation therapy; however, it frequently encounters challenges such as artifacts and noise, significantly constraining its clinical utility. While CycleGAN is a widely employed method for CT image synthesis, it has notable limitations regarding the inadequate capture of global features. To tackle these challenges, we introduce a refined unsupervised learning model called improved vision transformer CycleGAN (IViT-CycleGAN). Firstly, we integrate a U-net framework that builds upon ViT. Next, we augment the feed-forward neural network by incorporating deep convolutional networks. Lastly, we enhance the stability of the model training process by introducing gradient penalty and integrating an additional loss term into the generator loss. The experiment demonstrates from multiple perspectives that our model-generated synthesizing CT(sCT) has significant advantages compared to other unsupervised learning models, thereby validating the clinical applicability and robustness of our model. In future clinical practice, our model has the potential to assist clinical practitioners in formulating precise radiotherapy plans.

Study of a Deep Convolution Network with Enhanced Region Proposal Network in the Detection of Cancerous Lung Tumors.

A deep convolution network that expands on the architecture of the faster R-CNN network is proposed. The expansion includes adapting unsupervised classification with multiple backbone networks to improve the Region Proposal Network in order to improve accuracy and sensitivity in detecting minute changes in images. The efficiency of the proposed architecture is investigated by applying it to the detection of cancerous lung tumors in CT (computed tomography) images. This investigation used a total of 888 images from the LUNA16 dataset, which contains CT images of both cancerous and non-cancerous tumors of various sizes. These images are divided into 80% and 20%, which are used for training and testing, respectively. The result of the investigation through the experiment is that the proposed deep-learning architecture could achieve an accuracy rate of 95.32%, a precision rate of 94.63%, a specificity of 94.84%, and a high sensitivity of 96.23% using the LUNA16 images. The result shows an improvement compared to a reported accuracy of 93.6% from a previous study using the same dataset.

A lightweight deep convolutional network with inverted residuals for matching optical and SAR images

ABSTRACT Matching optical and synthetic aperture radar (SAR) images is often challenged by intricate geometric distortion and nonlinear radiation differences, leading to insufficient and unevenly distributed corresponding points. To tackle this issue, we propose a lightweight deep convolutional network with inverted residuals for optical and SAR image matching. Initially, a fully convolutional neural network (FCNN) is designed to extract high-level and semantic features, robustly capturing universal characteristics between optical and SAR images, adept at handling geometric distortion and nonlinear radiation changes. Notably, we integrate a lightweight architecture with inverted residuals into FCNN to adeptly extract local and global contextual information, facilitating feature reuse and minimizing the loss of crucial features. Additionally, a vector-refined module is deployed to refine dense features, filtering out redundant information. Subsequently, a coarse-to-fine strategy is employed to further eliminate gross errors or incorrect matches. Finally, we evaluate the performance of the proposed network in optical and SAR image matching against manually-designed methods and state-of-the-art deep learning techniques. Experimental results demonstrate that our network significantly surpasses existing methods in terms of the number of correct matches and matching accuracy. Specifically, our proposed network achieves at least a 2.8 times increase in correct matches and an 18% improvement in matching accuracy compared to existing methods.

Deep graph layer information mining convolutional network

Graph convolution network is a powerful method of deep learning of graph structure data. Existing methods usually adjust the neighborhood information aggregation mode or optimize the graph topology layer by layer for improving the graph convolution network. However, these methods seldom consider the discriminative information about hierarchical characteristics nodes (some special nodes only can be correctly classified in one layer and are the misclassification nodes in the other layers of deep graph convolutional networks) in the different layers for complementing the neighborhood topology information. To further find these information, a deep graph layer information mining convolutional network (GLIM) can alternately measure the neighborhood ranking information on topology structure and update the residual identity mapping node information on the different layers for enhancing the model classification performance. Moreover, GLIM can construct a unified framework with the various hyper-parameters for the different graph learning method based on graph convolution network. Experiments show GLIM outperforms the state-of-the-art methods for semi-supervised node classification in three cite datasets (Cora, CiteSeer,and PubMed) and three image datasets (MNIST, Cifar10 and Cifar100).

Scalogram-Based Gait Abnormalities Classification Using Deep Convolutional Networks for Neurological and Non-Neurological Disorders

Scalogram-Based Gait Abnormalities Classification Using Deep Convolutional Networks for Neurological and Non-Neurological Disorders

Boosting the Performance of Deep Ear Recognition Systems Using Generative Adversarial Networks and Mean Class Activation Maps

Ear recognition is a complex research domain within biometrics, aiming to identify individuals using their ears in uncontrolled conditions. Despite the exceptional performance of convolutional neural networks (CNNs) in various applications, the efficacy of deep ear recognition systems is nascent. This paper proposes a two-step ear recognition approach. The initial step employs deep convolutional generative adversarial networks (DCGANs) to enhance ear images. This involves the colorization of grayscale images and the enhancement of dark shades, addressing visual imperfections. Subsequently, a feature extraction and classification technique, referred to as Mean-CAM-CNN, is introduced. This technique leverages mean-class activation maps in conjunction with CNNs. The Mean-CAM approach directs the CNN to focus specifically on relevant information, extracting and assessing only significant regions within the entire image. The process involves the implementation of a mask to selectively crop the pertinent area of the image. The cropped region is then utilized to train a CNN for discriminative classification. Extensive evaluations were conducted using two ear recognition datasets: mathematical analysis of images (MAI) and annotated web ears (AWEs). The experimental results indicate that the proposed approach shows notable improvements and competitive performance: the Rank-1 recognition rates are 100.00% and 76.25% for MAI and AWE datasets, respectively.

Accurate Classification of Tunnel Lining Cracks Using Lightweight ShuffleNetV2-1.0-SE Model with DCGAN-Based Data Augmentation and Transfer Learning

Cracks in tunnel lining surfaces directly threaten structural integrity; therefore, regular inspection of cracks is essential. Lightweight convolutional neural networks (LCNNs) have recently offered a promising alternative to conventional manual inspection. However, the effectiveness of LCNNs is still adversely affected by the lack of sufficient crack images, which limits the potential detection performance. In this paper, transfer learning was used to optimize deep convolutional generative adversarial networks (DCGANs) for crack image synthesis to significantly improve the accuracy of LCNNs. In addition, an improved LCNN model named ShuffleNetV2-1.0-SE was proposed, incorporating the squeeze–excitation (SE) attention mechanism into ShuffleNetV2-1.0 and realizing highly accurate classification results while maintaining lightness. The results show that the DCGAN-based data enhancement method can significantly improve the classification accuracy of ShuffleNetV2-1.0-SE for tunnel lining cracks. ShuffleNetV2-1.0-SE achieves an accuracy of 98.14% on the enhanced dataset, which is superior to multiple advanced LCNN models.

A maize seed variety identification method based on improving deep residual convolutional network.

Seed quality and safety are related to national food security, and seed variety purity is an essential indicator in seed quality detection. This study established a maize seed dataset comprising 5877 images of six different types and proposed a maize seed recognition model based on an improved ResNet50 framework. Firstly, we introduced the ResStage structure in the early stage of the original model, which facilitated the network's learning process and enabled more efficient information propagation across the network layers. Meanwhile, in the later residual blocks of the model, we introduced both the efficient channel attention (ECA) mechanism and depthwise separable (DS) convolution, which reduced the model's parameter cost and enabled the capturing of more precise and detailed features. Finally, a Swish-PReLU mixed activation function was introduced globally to improve the overall predictive power of the model. The results showed that our model achieved an impressive accuracy of 91.23% in corn seed classification, surpassing other related models. Compared with the original model, our model improved the accuracy by 7.07%, reduced the loss value by 0.19, and decreased the number of parameters by 40%. The research suggested that this method can efficiently classify corn seeds, holding significant value in seed variety identification.

Deep Convolutional Network Based on Attention Mechanism for Matching Optical and SAR Images

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.

Enforcing Traffic Safety: A Deep Learning Approach for Detecting Motorcyclists’ Helmet Violations Using YOLOv8 and Deep Convolutional Generative Adversarial Network-Generated Images

In this study, we introduce an innovative methodology for the detection of helmet usage violations among motorcyclists, integrating the YOLOv8 object detection algorithm with deep convolutional generative adversarial networks (DCGANs). The objective of this research is to enhance the precision of existing helmet violation detection techniques, which are typically reliant on manual inspection and susceptible to inaccuracies. The proposed methodology involves model training on an extensive dataset comprising both authentic and synthetic images, and demonstrates high accuracy in identifying helmet violations, including scenarios with multiple riders. Data augmentation, in conjunction with synthetic images produced by DCGANs, is utilized to expand the training data volume, particularly focusing on imbalanced classes, thereby facilitating superior model generalization to real-world circumstances. The stand-alone YOLOv8 model exhibited an F1 score of 0.91 for all classes at a confidence level of 0.617, whereas the DCGANs + YOLOv8 model demonstrated an F1 score of 0.96 for all classes at a reduced confidence level of 0.334. These findings highlight the potential of DCGANs in enhancing the accuracy of helmet rule violation detection, thus fostering safer motorcycling practices.

DCGAN-DTA: Predicting drug-target binding affinity with deep convolutional generative adversarial networks

BackgroundIn recent years, there has been a growing interest in utilizing computational approaches to predict drug-target binding affinity, aiming to expedite the early drug discovery process. To address the limitations of experimental methods, such as cost and time, several machine learning-based techniques have been developed. However, these methods encounter certain challenges, including the limited availability of training data, reliance on human intervention for feature selection and engineering, and a lack of validation approaches for robust evaluation in real-life applications.ResultsTo mitigate these limitations, in this study, we propose a method for drug-target binding affinity prediction based on deep convolutional generative adversarial networks. Additionally, we conducted a series of validation experiments and implemented adversarial control experiments using straw models. These experiments serve to demonstrate the robustness and efficacy of our predictive models. We conducted a comprehensive evaluation of our method by comparing it to baselines and state-of-the-art methods. Two recently updated datasets, namely the BindingDB and PDBBind, were used for this purpose. Our findings indicate that our method outperforms the alternative methods in terms of three performance measures when using warm-start data splitting settings. Moreover, when considering physiochemical-based cold-start data splitting settings, our method demonstrates superior predictive performance, particularly in terms of the concordance index.ConclusionThe results of our study affirm the practical value of our method and its superiority over alternative approaches in predicting drug-target binding affinity across multiple validation sets. This highlights the potential of our approach in accelerating drug repurposing efforts, facilitating novel drug discovery, and ultimately enhancing disease treatment. The data and source code for this study were deposited in the GitHub repository, https://github.com/mojtabaze7/DCGAN-DTA. Furthermore, the web server for our method is accessible at https://dcgan.shinyapps.io/bindingaffinity/.

Resource-efficient, sensor-based human activity recognition with lightweight deep models boosted with attention

With their automatic feature extraction capabilities, deep learning models have become more widespread in sensor-based human activity recognition, particularly on larger datasets. However, their direct use on mobile and wearable devices is challenging due to the extensive resource requirements. Concurrently, attention-based models are emerging to improve recognition performance by dynamically emphasizing relevant parts of features and disregarding the irrelevant ones, particularly in the computer vision domain. This study introduces a novel application of attention mechanisms to smaller deep architectures, investigating whether smaller models can achieve comparable recognition performance to larger models in sensor-based human activity recognition systems while keeping resource usage at lower levels. For this purpose, we integrate the convolutional block attention module into a hybrid model, deep convolutional and long short-term memory network. Experiments are conducted using five public datasets in three model sizes: lightweight, moderate and original. The results show that applying attention to the lightweight model enables achieving similar recognition performances to the moderate-size model, and the lightweight model requires approximately 2–13 times fewer parameters and 3.5 times fewer flops. We also conduct experiments with sensor data at lower sampling rates and from fewer sensors attached to different body parts. The results show that attention improves recognition performance under lower sampling rates, as well as under higher sampling rates when model sizes are smaller, and mitigates the impact of missing data from one or more body parts, making the model more suitable for real-world sensor-based applications.

Spatiotemporal smoothing aggregation enhanced multi-scale residual deep graph convolutional networks for skeleton-based gait recognition

Spatiotemporal smoothing aggregation enhanced multi-scale residual deep graph convolutional networks for skeleton-based gait recognition

HAMMF: Hierarchical attention-based multi-task and multi-modal fusion model for computer-aided diagnosis of Alzheimer’s disease

Alzheimer’s disease (AD) is a progressive neurodegenerative condition, and early intervention can help slow its progression. However, integrating multi-dimensional information and deep convolutional networks increases the model parameters, affecting diagnosis accuracy and efficiency and hindering clinical diagnostic model deployment. Multi-modal neuroimaging can offer more precise diagnostic results, while multi-task modeling of classification and regression tasks can enhance the performance and stability of AD diagnosis. This study proposes a Hierarchical Attention-based Multi-task Multi-modal Fusion model (HAMMF) that leverages multi-modal neuroimaging data to concurrently learn AD classification tasks, cognitive score regression, and age regression tasks using attention-based techniques. Firstly, we preprocess MRI and PET image data to obtain two modal data, each containing distinct information. Next, we incorporate a novel Contextual Hierarchical Attention Module (CHAM) to aggregate multi-modal features. This module employs channel and spatial attention to extract fine-grained pathological features from unimodal image data across various dimensions. Using these attention mechanisms, the Transformer can effectively capture correlated features of multi-modal inputs. Lastly, we adopt multi-task learning in our model to investigate the influence of different variables on diagnosis, with a primary classification task and a secondary regression task for optimal multi-task prediction performance. Our experiments utilized MRI and PET images from 720 subjects in the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset. The results show that our proposed model achieves an overall accuracy of 93.15% for AD/NC recognition, and the visualization results demonstrate its strong pathological feature recognition performance.

Knowledge graph learning algorithm based on deep convolutional networks

Knowledge graphs (KGs) serve as invaluable tools for organizing and representing structural information, enabling powerful data analysis and retrieval. In this paper, we propose a novel knowledge graph learning algorithm based on deep convolutional neural networks (KGLA-DCNN) to enhance the classification accuracy of KG nodes. Leveraging the hierarchical and relational nature of KGs, our algorithm utilizes deep convolutional neural networks to capture intricate patterns and dependencies within the graph. We evaluate the effectiveness of KGLA-DCNN on two benchmark datasets, Cora and Citeseer, renowned for their challenging node classification tasks. Through extensive experiments, we demonstrate that our proposed algorithm significantly improves classification accuracy compared to state-of-the-art methods, showcasing its capability to leverage the rich structural information inherent in KGs. The results highlight the potential of deep convolutional neural networks in enhancing the learning and representation capabilities of knowledge graphs, paving the way for more accurate and efficient knowledge discovery in diverse domains.

Single-Pixel Imaging Based on Deep Learning Enhanced Singular Value Decomposition.

We propose and demonstrate a single-pixel imaging method based on deep learning network enhanced singular value decomposition. The theoretical framework and the experimental implementation are elaborated and compared with the conventional methods based on Hadamard patterns or deep convolutional autoencoder network. Simulation and experimental results show that the proposed approach is capable of reconstructing images with better quality especially under a low sampling ratio down to 3.12%, or with fewer measurements or shorter acquisition time if the image quality is given. We further demonstrate that it has better anti-noise performance by introducing noises in the SPI systems, and we show that it has better generalizability by applying the systems to targets outside the training dataset. We expect that the developed method will find potential applications based on single-pixel imaging beyond the visible regime.