Aug 2026· International Journal of Engineering Research and Science· Vol 12, pp. 30-43· 0 citations
TL;DR
The laboratory validation (TRL4) of a low-cost embedded computer-vision demonstrator for automated surface-defect detection in beech (Fagus sylvatica) sawn timber, developed as the first operational module of the SMARTWOOD-AI technology-transfer platform is presented.
Abstract
The digital transformation of the wood-processing industry increasingly relies on computer vision, artificial intelligence (AI), and embedded sensing technologies to automate timber quality assessment. This study presents the laboratory validation (TRL4) of a low-cost embedded computer-vision demonstrator for automated surface-defect detection in beech (Fagus sylvatica) sawn timber, developed as the first operational module of the SMARTWOOD-AI technology-transfer platform. The system integrates a Raspberry Pi 4 single-board computer with a Sony IMX500 intelligent camera and employs an interpretable computer-vision pipeline based on 21 handcrafted colour (HSV), texture (Gray-Level Co-occurrence Matrix and Local Binary Patterns), and edge-density (Canny) features classified using a Random Forest algorithm. A dataset comprising 24 beech boards (192 labelled image regions) was evaluated using a board-level train/validation partitioning strategy to prevent data leakage. The classifier achieved an average accuracy of 88.2% (±7.1%) during five-fold cross-validation and 82.5% accuracy on an independent validation set, with high sensitivity for defect detection (recall = 0.93, F1-score = 0.88). The results demonstrate the technical feasibility of the proposed embedded inspection architecture and establish a reproducible experimental baseline for future integration of deep-learning models, digital twins, and intelligent cutting optimisation within the SMARTWOOD-AI platform.
Quality inspection of imported saw-ginned cotton mainly involves the determination of color grade and impurity grade. Traditional manual grading and High Volume Instrument (HVI) testing are limited by subjectivity, insufficient accuracy, single-indicator measurement, and long inspection cycles. To address these limitations, this study developed a machine vision-based intelligent identification system for saw-ginned cotton quality grading. The system integrates a portable image acquisition box, a cloud-based intelligent recognition service, and a HarmonyOS-based mobile application. A total of 6363 saw-ginned cotton images were collected using the self-developed image acquisition device for model training and testing. Based on U-Net background segmentation, a dual-branch parallel recognition framework was established for cotton color grading and impurity grading. The CA-ResNet50 model, integrating ResNet50, the Efficient Channel Attention (ECA) mechanism, and the AdamW optimization strategy, was constructed for cotton color grade recognition. The AD-UNet model, incorporating Atrous Spatial Pyramid Pooling (ASPP)-based multi-scale contextual modeling and the DySample adaptive upsampling mechanism, was developed for impurity segmentation. In addition, the HarmonyOS-based mobile application supports information query, image acquisition, intelligent recognition, and data traceability. Experimental results showed that the CA-ResNet50 color grading model achieved an F1-Score of 94.8%. Based on the AD-UNet impurity segmentation results and the calculated impurity area ratio, the accuracy of impurity grade determination reached 97.3%. The average cloud-based inference time for a single image was approximately 0.8 s, and the complete workflow, including sample flattening, image acquisition, and recognition, required approximately 10 min. The proposed system improves the accuracy, efficiency, objectivity, and traceability of saw-ginned cotton quality identification, providing technical support for rapid inspection and quality supervision of imported cotton.
Jun Lyu, Junyi Luo, Kai Zheng et al.· Agronomy· 0 citations
The proposed framework provides reproducible reference results for evaluating supervised machine learning approaches to defective pixel detection while analyzing the influence of feature extraction window size on classification performance and reconstructed image quality.
Bárbaro M. López-Portilla, Kristian Balzer, Lorena Carballo et al.· Applied Sciences· 0 citations
The quality grading of birch (Betula spp.) veneer logs, an economically important raw material in the Baltic region, is still largely manual, causing pricing inconsistencies, and automated grading under industrial conditions remains rarely studied. We evaluated deep-learning computer vision models for recognising wood defects and assigning a quality class on a sorting line. The algorithm and a scaler evaluated 153 logs using the same images. The recognition differed considerably between the defects: the central core-zone defects were recognised well (recall: core discolouration 97%, pith and drying cracks 91%, core rot 88%), while the dead and rotten knots and the less conspicuous defects were recognised poorly (knots 44%, ingrown bark 52%). The quality class assigned by the algorithm coincided with that of the scaler in 57% of the cases, and the algorithm tended to assign a lower class, mainly because of the over-indication of the core rot. For reference, manual grading itself was not fully repeatable: line scalers agreed with a detailed control scaler in 79% of the cases (69 to 88% between scalers). Automated grading is already accurate for core discolouration and pith and drying cracks, while knot detection remains the main limitation for industrial deployment.
J. Magaznieks, M. Millers, Agris Gabrāns· Forests· 0 citations
Automatic inspection of small, irregular stamped parts remains challenging due to their compact size, random orientation on conveyors, and susceptible metallic surface reflections, coupled with local, weak, and densely distributed defects. This study presents an integrated vision-based dynamic defect detection and robotic sorting system to address these issues. The framework seamlessly unifies conveyor-based image acquisition, YOLO-CGMS-based defect recognition, hand–eye coordinate mapping, and Delta robot trajectory planning. To drive real-time visual perception, the YOLO-CGMS architecture modifies the YOLOv8n baseline by incorporating C2f-CRM, GRF-SPPF, MCA, and Inner-GIoU modules, optimizing small-defect feature extraction and bounding-box regression. Evaluated on a factory-collected dataset, YOLO-CGMS achieved an mAP50 of 88.7% and an inference speed of 236.23 frames/s, using only 2.8 M parameters and 7.3 GFLOPs. Compared with YOLOv8n, mAP and execution speed increased by 5.1 percentage points and 12.18 frames/s, respectively, while the parameter size and computational cost dropped by 0.2 M and 0.8 GFLOPs. Furthermore, physical sorting capability was validated on a developed prototype platform, yielding a mean hand–eye positioning error of 2.66 mm. Across 200 dynamic trials, the system successfully sorted 161 defective workpieces, translating to an 80.5% success rate and a mean cycle time of 2.6 s per part. These findings confirm that the proposed system reliably links closed-loop visual perception with physical execution, providing a practical foundation for the automated quality control of complex stamped components.
Objective: The objective of this study is to investigate the development of a small-scale tintometric system prototype based on computer vision, with the aim of offering a cost-effective solution tailored for small and medium-sized enterprises, promoting raw material savings and higher reliability in paint mixtures.
Theoretical Framework: Grounded on industrial automation in the paint sector, computer vision applied to color analysis (RGB/CMYK), artificial intelligence, and low-cost embedded systems (ESP32).
Method: Experimental technological development. A belt conveyor was constructed with dosing pumps and sensors controlled by an ESP32 microcontroller connected via serial interface to a Jupyter Notebook. Data collection involved physical validation of digital inputs and visual feedback.
Results and Discussion: Results showed technical feasibility and high precision in RGB/CMYK color analysis, successfully replicating conventional machine functions while reducing human error and waste.
Research Implications: Promotes technological modernization, chemical waste reduction, and automated AI-driven quality control for small and medium paint manufacturers. Integrates accessible computer vision and cheap embedded hardware (ESP32) to establish a closed-loop quality control system in an industry traditionally dependent on subjective human inspection.
Originality/Value: This study contributes to the literature by integrating low-cost computer vision and standard embedded systems (ESP32) to create a closed-loop quality control framework for an industry that has historically relied heavily on subjective human visual inspection. The relevance and value of this research are evidenced by providing an affordable and highly efficient alternative that lowers implementation barriers for small and medium-sized businesses, standardizing the process and increasing final product reliability.
J. Pudo, Anderson L. de Jesus, Eduardo Sousa Pereira de Aguiar et al.· Revista de Gestão Social e A...· 0 citations
The purpose of this study is to provide more reliable technical support for industrial quality inspection. To tackle the limitations of inadequate detection precision and low levels of automation inherent in conventional quality inspection processes for mechanical components, this study presents a framework for three-dimensional (3D) point cloud reconstruction and defect detection that leverages recognition-driven feedback mechanisms. Based on binocular structured light technology and an improved VoteNet model, a complete process from 3D data acquisition to defect identification is built. First, the imaging principle and calibration methodology of the pinhole camera model are investigated, and a high-contrast calibration target featuring white circular markers on a black background is adopted to perform binocular system calibration. A least-squares ellipse fitting algorithm is employed to pinpoint the centroid of each marker, which enhances calibration precision and exhibits greater robustness against minor fluctuations in ambient lighting typical of industrial environments. Then, the 3D point cloud reconstruction is carried out. The structured light projector and the camera cooperate to collect multi-view images. After statistical filtering and radius filtering, noise is removed, and then the occluded area is interpolated to complete, and finally, high-quality point cloud data is output. In defect detection, the VoteNet model is improved for the disorder and sparseness of point clouds, and the symmetric function is introduced to optimize feature coding, and a three-layer multi-scale feature fusion structure is designed. The experiment is based on the MachPart-Defects data set, and the results look ideal: the maximum average measurement error after multi-view point cloud precise registration is only 0.0556 mm, and the maximum average relative measurement error is as low as 0.95%. The overall F1 value of the improved VoteNet model reaches 92.4%, which is better than the mainstream algorithms such as dilate gated convolutional neural network, and the F1 value of detecting tiny defects below 0.1 mm is 86.9%. Especially in the detection of defects such as cracks and burrs. Even in the complex scene where the surface of the part is highly reflective, the detection accuracy of the model can be maintained above 82%. The technical process constructed in this study can basically meet the requirements of industrial quality inspection in terms of accuracy and stability, and can provide a reference for quality control of the machinery manufacturing industry.
Zhang Li· Engineering Research Express· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
