Search Results (150)

Distinguishing authentic gold products from high-quality counterfeits is a challenging fine-grained computer vision problem; counterfeit items are engineered to replicate surface texture, hallmark engravings, color, and geometry with remarkable fidelity, making visual discrimination unreliable even for trained professionals. In this paper, we address the problem of visual gold authentication from unconstrained smartphone imagery in three main contributions. First, we introduce GoldNet, a public benchmark dataset designed for this task, comprising 2127 real-world images of authentic and counterfeit gold items collected under diverse real-world conditions. Second, we evaluate fourteen classification architectures spanning classical handcrafted texture descriptors, convolutional neural networks (CNNs), and vision transformers under a rigorous transfer learning protocol, establishing the first comprehensive baseline for this problem. Third, we propose GoldFormer, a hybrid dual-stream algorithm that combines the local texture representations of ResNet-50 with the global contextual modeling capability of the Swin Transformer (Swin-T) through a newly designed Texture-Aware Attention Gate (TAAG) module. The TAAG dynamically modulates Swin feature dimensions using CNN-derived texture energy, providing improved discriminability and per-prediction interpretability without requiring post hoc attribution. Experimental results show that, under matched-resolution 5-fold cross-validation, the proposed GoldFormer attains the highest overall accuracy (95.02%, F1-score 0.9502) at roughly half the FLOPs of its higher-resolution setting, statistically tied with the strongest individual backbone (ViT-B/16, 94.31%; McNemar $p=0.23$) and on par with a training-free soft-voting ensemble (94.92%), while significantly improving on its own Swin-T backbone (93.65%) and adding built-in, attribution-free texture-gate interpretability. GoldFormer surpasses trained human-expert performance (89.80%) by approximately 5 percentage points. Full article

Ensuring safe coexistence between human operators and industrial robot manipulators is a critical challenge in collaborative manufacturing environments. Existing approaches rely either on dedicated safety-rated hardware, which is expensive and difficult to retrofit, or on purely vision-based classifiers that discard the precise kinematic state available from the robot controller, leading to unresolved visual ambiguities when different joint configurations produce similar appearances from fixed camera viewpoints. Kinematics-only approaches, while precise, lack the spatial context needed to disambiguate configurations near workspace boundaries. We propose RGBJointsNet, a late-fusion multimodal deep learning classifier that combines RGB visual features extracted by a frozen EfficientNet-B2 convolutional backbone with a compact kinematic stream processing the 12-dimensional joint angle vector of a dual-UR5 robotic cell. The model maps each observation to one of five mutually exclusive workspace zones: rest ($C_0$), nominal ($C_1$), extended ($C_2$), shared/collision-risk ($C_3$), and joint-limit/singularity ($C_4$). A dedicated simulation environment built on ROS 2 Humble Hawksbill and Gazebo Classic 11 was used to generate a labelled dataset of 54,309 frames and 162,927 RGB images from three calibrated overhead cameras, with analytic ground-truth labels derived from closed-form forward kinematics. Training on a CPU with a feature-caching strategy brings the per-epoch wall-clock time to seconds, making the approach tractable without GPU hardware. On the held-out test set, the model achieves 87.1% overall accuracy and a macro-averaged F1 score of 90.0%, with near-perfect recall of 99.3% for the safety-critical shared zone $C_3$. The trained classifier is integrated as an ROS 2 inference node capable of running at 10$\mathrm{Hz}$ on a standard workstation. Our results demonstrate that joint angle information is a decisive complement to RGB imagery for fine-grained, safety-oriented workspace classification in simulation-derived settings. Full article

To address the challenges of difficult feature extraction and insufficient recognition accuracy caused by the small size of chili flowers, occlusion by branches and leaves, and illumination variations in complex field environments, a dual-backbone-based chili flower pose estimation algorithm, termed DCFP-YOLO, is proposed. Built upon the YOLO11n framework, the proposed method performs classification and recognition of five typical upward-oriented chili flower poses. To alleviate the loss of local detail features of small chili flowers under complex backgrounds, a dual-backbone feature extraction network composed of StarNet and ShuffleNetV2 is constructed. Specifically, the StarNet backbone enhances the extraction of fine-grained local features from key floral regions, while the ShuffleNetV2 backbone improves the perception of global spatial structural information. The complementary fusion of dual-backbone features strengthens the representation capability of chili flower pose features in complex environments. To mitigate the attenuation of shallow detail information during multi-scale feature transmission, a Bidirectional Multi-branch Auxiliary Feature Pyramid Network (BiMAFPN) is designed to enhance feature propagation through cross-scale feature interaction, thereby improving pose recognition performance under occlusion and overlapping conditions. Furthermore, a Programmable Gradient Information (PGI)-assisted training mechanism is introduced to optimize gradient propagation paths and alleviate information bottlenecks in deep networks, thereby enhancing the robustness of multi-pose feature extraction under occlusion, blur, and complex illumination conditions. Experimental results demonstrate that DCFP-YOLO achieves recall, mAP50, and mAP50 values of 87.4%, 92.0%, and 66.9%, respectively, representing improvements of 1.7, 1.3, and 3.5 percentage points over the baseline model. Overall performance surpasses that of current mainstream object detection algorithms. After deployment on the NVIDIA Jetson AGX Orin platform, the model achieves an inference speed of 20.9 frames/s, which can basically satisfy the real-time perception requirements of chili flower pose recognition in complex agricultural environments. The proposed method provides an effective visual perception framework for chili flower pose recognition in complex agricultural environments. Rather than constituting a complete robotic pollination solution, the developed model serves as a potential perception component for future intelligent pollination robotic systems, providing reliable flower pose information for subsequent research on target localization, end-effector alignment, and robotic pollination in unstructured greenhouse environments. Full article

Tomato, as a globally vital economic crop, relies heavily on accurate disease recognition to safeguard food security. However, tomato leaf disease identification constitutes a classic fine-grained visual classification task characterized by minimal inter-class variance, spatially sparse lesion features, and complex background interference. These challenges hinder conventional deep learning models from precisely localizing critical discriminative regions. In response to the aforementioned challenges, we introduce EA-HFA, an innovative framework based on deep neural networks that synergistically integrates an Entropy Attention mechanism alongside a Hierarchical Feature Alignment component. Specifically, the Entropy Attention module leverages information-theoretic entropy to quantify pixel-wise predictive uncertainty, adaptively selecting high-confidence pixels to automatically focus the network on sparse yet highly discriminative lesion features. Concurrently, the Hierarchical Feature Alignment module imposes KL-divergence constraints on the temperature-scaled probability distributions across adjacent network layers, enforcing cross-scale consistency in the localization of discriminative regions. Evaluations conducted on the PlantVillage and AI Challenger 2018 benchmarks reveal that EA-HFA achieves Top-1 accuracies of 99.29% and 97.82%, respectively, yielding performance comparable to established deep learning architectures while maintaining a reasonable computational footprint. Furthermore, qualitative analyses indicate that the model tends to attend to minute lesion-relevant areas, providing a certain level of interpretability for its decision-making process. Thus, EA-HFA holds practical potential as an alternative solution for automated plant disease monitoring in precision farming. Full article

The worldwide spread of semiconductor devices has driven a surge in electronic waste (e-waste), which reached 62 million metric tons in 2022 and is projected to exceed 80 million metric tons by 2030. E-waste contains hazardous substances such as cadmium and mercury, yet also represents a $57 billion annual opportunity through the recovery of valuable and critical raw materials (CRMs). However, formal recycling rates remain stagnant at 22.3%, largely due to limitations of current automated sorting methods. These systems primarily rely on visible-light (RGB) imaging, which lacks the spectral resolution needed to distinguish chemically similar polymers, complex metal alloys, and composite substrates on printed circuit boards (PCBs). This paper presents a multidisciplinary synthesis of AI-driven detection and classification for e-waste, bridging materials science and computer vision through three interconnected themes. 1. Material and Economic Context: The toxicological risks and economic drivers of semiconductor recycling are characterized, framing fine-grained material identification as essential for a circular economy. 2. Multispectral Sensing & Fusion: Sensing modalities such as near-infrared (NIR), hyperspectral imaging (HSI), and X-ray fluorescence (XRF) are assessed, and sensor fusion strategies, including early, late, and intermediate fusion, are reviewed for high-throughput industrial settings. 3. Deep Learning Benchmarking: 11 publicly available PCB datasets are analyzed, and the YOLO series (YOLOv3–YOLOv12) is compared with leading non-YOLO detectors, including Faster R-CNN, RT-DETR-L, and RetinaNet. The results show that while YOLOv9s achieves a peak mAP@0.5 of 56.5% and YOLOv11s offers an optimal industrial profile (37.2% mAP@0.5:0.95 at 115 ms edge inference), all RGB-based models fail to detect visually ambiguous surface-mount devices (SMDs), with mAP values below 12%. This confirms a performance ceiling for purely visual systems. The review concludes that transitioning from RGB-centric to multispectral fusion architectures is the primary research frontier and proposes a roadmap for standardized multimodal datasets and edge-deployable fusion models to enable next-generation, high-recovery automated recycling. Full article

Accurate cultivar identification of commercial dried goji berries is essential for raw material sorting, batch consistency assessment, and quality control during processing and distribution. Conventional approaches based on manual judgment or physicochemical analysis are often subjective, labor-intensive, time-consuming, and costly, making them unsuitable for rapid commercial sorting and quality inspection. To develop a rapid, low-cost, and nondestructive method for dried goji berry cultivar identification, this study proposes a visual recognition framework that integrates RGB imaging with lightweight deep learning. A dataset comprising 25,899 RGB images from five cultivars of commercial dried goji berry samples, namely Ningqi No. 7, Linqi No. 5, Ningqi No. 1, Keqi 6082, and Jingqi No. 1, was constructed. Given the pronounced surface shrinkage, complex texture, and subtle inter-cultivar appearance differences of dried goji berries, an image quality enhancement method was designed to strengthen the representation of color gradation, textural details, and edge information. For model development, CoAtNet was selected as the baseline network and redesigned for lightweight deployment. By integrating an improved feature extraction module and an information-preserving downsampling module, the proposed LSH-CoAtNet model enhances fine-grained feature representation while reducing computational cost. On the quality-enhanced image dataset, the proposed method achieved an accuracy of 98.80%, a precision of 98.81%, a recall of 98.80%, and an F1-score of 98.80%. The model contained only 6.41 M parameters and required 1.60 GFLOPs, outperforming the baseline model in both classification performance and computational efficiency. Ablation experiments and five-fold cross-validation further confirmed the effectiveness of the image quality enhancement strategy, the contribution of each improved module, and the stability of the model. Overall, the proposed method, which combines RGB image quality enhancement with LSH-CoAtNet, provides a low-cost, nondestructive, and efficient technical solution for rapid cultivar identification, raw material sorting, batch consistency assessment, and quality control of commercial dried goji berries during processing and distribution. It may also serve as a reference for intelligent classification and quality inspection of other specialty dried horticultural products. Full article

Joint detection of strawberry growth stages and defective fruit is needed for harvest planning and quality screening, but field images make this task difficult because stage-related visual differences are subtle, flowers and early fruits are often small and densely distributed, and occlusion weakens localization reliability. This study develops Multi-Scale Refined Detection and Classification YOLO (MRDC-YOLO), a lightweight detector based on the YOLO11s framework, for this fine-grained detection scenario. The backbone, neck, and detection head are redesigned with three modules: a Multi-Scale Adaptive Edge Enhancement Module (MAEM), a Reparameterized Progressive Feature Aggregation (RPFA) module, and a Decoupled Cross-Scan Head (DCSH). MAEM strengthens boundary and texture responses for visually similar categories, RPFA reduces redundant multi-scale fusion while maintaining features for dense small targets, and DCSH introduces task-aware classification and regression branches with cross-scan-inspired spatial modeling for occlusion-sensitive localization. Experiments on a five-class strawberry dataset containing 5114 images show that MRDC-YOLO achieves 95.63% mAP@0.5 and 82.39% mAP@0.5:0.95. Over YOLO11s, the model yields a 2.06-percentage-point gain in precision and 1.34- and 1.53-percentage-point gains in mAP@0.5 and mAP@0.5:0.95, together with 10.7% fewer parameters and 8.9% lower GFLOPs. These results suggest that MRDC-YOLO improves fine-grained category discrimination and localization while retaining a smaller model size than the YOLO11s baseline. Full article

LeafScans-Orchard is a curated, multi-year RGB image dataset of orchard plant leaves designed to support research in computer vision, machine learning, and plant phenotyping. The dataset comprises 9708 high-quality leaf scans acquired during collection campaigns conducted between 2015 and 2025, covering seven orchard crop species: apple, pear, sweet cherry, sour cherry, plum, peach, and apricot. In total, the dataset includes 67 cultivar labels. All samples were acquired using flatbed scanning under controlled conditions on a uniform background, ensuring high visual consistency and minimal background variability. The original scans were captured at 1200 dpi and subsequently converted into a public release format at 300 dpi, stored as lossless TIFF images to preserve morphological and textural details. Each image corresponds to a single leaf and is organized in a hierarchical directory structure by species, cultivar, and acquisition year, accompanied by image-level metadata and aggregated species–cultivar–year counts. LeafScans-Orchard is suitable for plant species classification, cultivar recognition, leaf morphology analysis, texture analysis, and general visual feature extraction. In addition to the main release, a representative subset of 300 original 1200 dpi scans is provided to support high-resolution analyses. The dataset is particularly suited for fine-grained classification, morphology-driven analysis, and methodological studies under controlled imaging conditions. Full article

Early non-invasive correction of neonatal auricular deformities is highly dependent on timely and precise diagnosis. However, clinical practice is often compromised by the subjectivity of visual assessments and the lack of objective tracking metrics, which frequently leads to missed optimal treatment windows. To address these challenges, we developed an interpretable deep learning-based diagnostic system for the automated screening and fine-grained classification of these deformities. Methodologically, a large-scale, multi-source dataset (n = 4644) was curated to support model training. The system pairs an automated object detector (YOLOv11) for background-reduced region-of-interest isolation with a cascaded classification pipeline optimized via ConvNeXt-Tiny. Crucially, we introduced a supervised contrastive learning module to project high-dimensional morphological features into a continuous severity score, enabling quantitative longitudinal tracking of therapeutic efficacy. To evaluate generalization and robustness, the framework underwent rigorous evaluation across three independent real-world cohorts and one controlled synthetic stress test. The system achieved 88.2% accuracy (Area Under the Curve (AUC): 0.949) in binary screening and 87.4% accuracy (macro-AUC: 0.976) in multi-class subtyping on the internal baseline. To enhance interpretability and build clinical trust, Gradient-weighted Class Activation Mapping (Grad-CAM) was utilized to explore the spatial distribution of the model’s attention, which frequently aligned with key anatomical landmarks. Furthermore, the learned severity scores robustly quantified post-intervention improvements (p = 0.0004), effectively capturing subtle anatomical normalization. While validation for rare subtypes remains underpowered, and the severity score currently functions mainly as a learned morphological similarity index requiring future clinical calibration, this study ultimately provides an objective and standardized web-based tool to facilitate the early intervention and precision management of neonatal auricular anomalies. Full article

Wheat is a major staple crop, and storage mold growth poses a severe threat to grain safety and quality stability. Natural mold development in stored wheat exhibits subtle, localized, and highly heterogeneous characteristics. Existing unimodal methods and global fusion approaches generally suffer from insufficient local feature sensitivity, hindering fine-grained mold severity grading. To address this limitation, we propose a Mask-Guided Fine-Grained Fusion Network, a weakly supervised framework based on local RGB–HSI fusion. This framework employs a dynamic parallel A/B experimental design to construct time-matched proxy labels via weakly supervised learning. A standardized preprocessing pipeline including single-kernel extraction, foreground segmentation, and cross-modal registration is established to resolve RGB–HSI spatial misalignment, ensuring physical-level spatial consistency of multimodal features. The model incorporates a Foreground-Aware Spectral Recalibration (FASR) module to suppress background noise, a Mask-Guided Dilated Cross-modal Local Attention (MDCLA) mechanism to establish fine-grained local mappings between RGB visual phenotypes and hyperspectral responses, and a sample-level adaptive fusion strategy to dynamically weight features by modal reliability, enhancing representation of complex samples across all mold stages. Experiments show that the Mask-Guided Fine-Grained Fusion Network achieves 0.9689 classification accuracy, 0.9698 Macro-F1 score, and 0.0593 Mean Absolute Error (MAE), significantly outperforming state-of-the-art unimodal deep models and global attention fusion baselines. This work provides a proof-of-principle framework for fine-grained non-destructive mold risk assessment in stored wheat. Full article

Breast cancer is a highly prevalent malignancy among women globally and arises from the uncontrolled proliferation of abnormal cells in breast tissue. Timely and precise diagnosis is critical for effective treatment and enhanced survival. Histopathological image analysis is considered the gold standard; nevertheless, manual assessment is labor-intensive and prone to variability. Existing deep learning and transformer-based approaches demonstrate strong effectiveness; however, they incur significant computational complexity and limited efficiency in capturing multi-scale features. To address these challenges, this research presents a framework that integrates ConvMixer, multi-scale patch learning, and an Adaptive Combined Runge–Kutta–Harris Hawks Optimization (AC-RUNHHO) algorithm. The model effectively captures both fine-grained cellular patterns and global tissue structures, while adaptive optimization improves convergence and hyperparameter tuning. The framework is evaluated on a breast cancer histology dataset comprising 4000 histopathological images across four classes. Experimental results demonstrate robust performance under the evaluated experimental conditions, achieving 98.63% accuracy, 98.63% precision, 98.62% recall, and 98.62% F1-score. Ablation and cross-validation analyses further confirm the generalization capability of the model. Overall, the developed framework demonstrates promising performance in computer-aided breast histopathological image classification, achieving high predictive accuracy and providing interpretable visual explanations. Full article

Saudi Arabia is expanding its domestic coffee sector under Vision 2030, yet coffee farming remains vulnerable to leaf diseases and pest damage. Image-based artificial intelligence studies conducted under Saudi field conditions remain limited, particularly in relation to assessing image-based visible disease severity. This study designs a hierarchical deep learning framework for screening coffee leaf diseases using field-collected images of Saudi coffee leaves. Three tasks were addressed: binary health status classification, four-class disease or pest damage identification, and binary visible severity classification. A dataset of 550 RGB images was collected from Al-Dayer Governorate, Jazan, under natural field conditions. ResNet50, DenseNet121, and EfficientNet-B0 were evaluated via transfer learning in two phases: a Saudi-only phase and an integrated phase that combined Saudi data with selected JMuBEN and JMuBEN2 samples. In the Saudi-only phase, ResNet50 achieved 96.47% accuracy for binary classification, while DenseNet121 achieved 68.66% and 78.12% for disease and visible severity classification, respectively. In the integrated phase, performance improved to 99.74%, 97.76%, and 97.37%. These integrated-phase results are interpreted as evidence that dataset expansion and increased visual diversity can improve model performance, rather than as definitive estimates of field deployment performance. The results show that binary classification is feasible under limited local data, whereas fine-grained disease classification is more constrained by dataset size and class imbalance. Grad-CAM visualizations were used to support qualitative interpretability and should not be interpreted as biological validation of disease localization. The framework is positioned as a decision-support screening approach that requires further expert-validated, multi-farm, and multi-season evaluation before deployment. Full article

Unmanned aerial vehicle (UAV) object detection plays an essential role in modern visual perception, but it remains challenging because UAV imagery typically contains extremely small, densely distributed objects embedded in complex backgrounds. Conventional detectors, including the recent YOLOv12, are prone to losing critical spatial details during downsampling and often exhibit task misalignment between classification and localization, particularly under severe scale variations. To address these problems, this study proposes SPTD-YOLO, a small-object-aware pyramidal and task-aligned dynamic detector. Specifically, a Small Object Enhanced Pyramid (SOEP) is developed by incorporating SPDConv and CSPOmniKernel to preserve and refine shallow, fine-grained features. In addition, a high-resolution P₂ detection layer is introduced to increase spatial grid density and strengthen the structural representation of tiny objects. Furthermore, a Task-Aligned Dynamic Detection Head (TADDH) is designed to decouple and coordinate classification and regression through dynamic convolution and a synergistic dual-gating mechanism. Experiments on VisDrone2019 show that SPTD-YOLO improves mAP@0.5 by 8.37% and mAP@0.5:0.95 by 5.11% over YOLOv12 while maintaining practical efficiency for UAV edge deployment. Full article

Manual classification of breast cancer is resource-intensive, slow, and subject to inter-observer variability, motivating automated deep learning solutions. Most current methods rely on unimodal imaging data and struggle with domain generalization (DG) across varied clinical environments. We propose a Dual-Stage Multimodal Alignment approach that integrates breast ultrasound (US) imagery with clinical text reports to improve diagnostic stability. The method proceeds in two stages: (1) Local Correlation Alignment (LCA), which aligns fine-grained visual features with textual embeddings to capture localized lesion attributes, and (2) Global Attention Alignment (GAA), which applies multi-head self-attention to the joint visual–textual sequence to encourage domain-invariant representations. We evaluate the approach on a harmonized, leakage-free repository of 6880 images aggregated from six public US datasets (BUS-CoT, BrEaST, BUS-BRA, BUS-UCLM, BLUI, BUSI) under three protocols: independent benchmarking on BUS-CoT, pooled cross-dataset evaluation, and zero-shot domain generalization on unseen unimodal target domains. On the BUS-CoT benchmark, the 198M-parameter model reaches 0.8177 accuracy and 0.8852 AUC, on par with the 7-billion-parameter Qwen2.5-VL-7B with chain-of-thought reasoning (0.8064 accuracy, 0.8354 AUC) while using roughly 1/35 the parameter count. In the pooled setting, it is competitive with single-domain state-of-the-art methods on individual subsets (e.g., 0.9576 AUC on BUSI, 0.8741 accuracy on BUS-BRA). Under zero-shot transfer without clinical text, per-domain AUC ranges from 0.7360 to 0.8060 across four unseen targets, providing a lower bound under cross-scanner shift. These results indicate that task-specific multimodal alignment can rival large vision-language models in breast US diagnosis at a fraction of the parameter count. Full article

From the perspective of applied surface science, heritage textiles from the Kashgar region can be regarded as fragile fibrous surface systems in which stains, abrasion, yarn breakage, yarn shedding, holes, and color fading represent measurable surface-degradation phenomena. However, manual inspection of these complex, woven, embroidered, and aged surfaces is time-consuming and difficult to standardize. To support non-contact surface-condition documentation, this study proposes an improved YOLOv8-based framework, YOLOv8-MABFT, for surface defect detection and condition-level assessment of Kashgar heritage textiles. The model integrates the C2f-Faster-EMA module and an RT-DETR-informed decoder head to improve the detection of weak-boundary and fine-grained surface defects. A dataset of 8247 high-resolution annotated images was constructed, covering six surface-degradation categories: stains, broken yarn, yarn shedding, holes, abrasion, and color fading. Experimental results show that YOLOv8-MABFT achieves an F1-score of 94.6%, a precision of 91.4%, a recall of 98.0%, and an mAP@0.5 of 94.0%, outperforming Faster R-CNN, SSD, YOLOv5n, YOLOv7n, and YOLOv8n while maintaining lightweight computational characteristics. CAM-based visualizations indicate that the improved model focuses more consistently on defect-related surface regions rather than surrounding decorative textures. Based on detected defects, seven surface-condition variables were constructed and input into a Random Forest classifier for four-level condition prediction. SHAP analysis shows that Distribution and Severity are the main contributors to condition classification. Overall, the proposed framework provides an applied surface-science tool for non-contact surface defect detection, surface-condition documentation, and preliminary condition-level assessment of fragile textile substrates. Full article