Search Results (77)

This study combines machine vision technology and deep learning models to rapidly assess the activity of anaerobic ammonium oxidation (Anammox) granular sludge. As a highly efficient nitrogen removal technology for wastewater treatment, the Anammox process has been widely applied globally due to its energy-saving and environmentally friendly features. However, existing sludge activity monitoring methods are inefficient, costly, and difficult to implement in real-time. In this study, we collected and enhanced 1000 images of Anammox granular sludge, extracted color features, and used machine learning and deep learning training methods such as XGBoost and the ResNet50d neural network to construct multiple models of sludge image color and sludge denitrification efficiency. The experimental results show that the ResNet50d-based neural network model performed the best, with a coefficient of determination (R²) of 0.984 and a mean squared error (MSE) of 523.38, significantly better than traditional machine learning models (with R² up to 0.952). Additionally, the experiment demonstrated that under a nitrogen load of 2.22 kg-N/(m³·d), the specific activity of Anammox granular sludge reached its highest value of 470.1 mg-N/(g-VSS·d), with further increases in nitrogen load inhibiting sludge activity. This research provides an efficient and cost-effective solution for online monitoring of the Anammox process and has the potential to drive the digital transformation of the wastewater treatment industry. Full article

The internal quality detection is extremely important. To solve the challenges of walnut quality detection, we presented the first comprehensive investigation of walnut quality detection method using X-ray imaging and deep learning model. An X-ray machine vision system was designed, and a walnut kernel detection (called WKD) dataset was constructed. Then, an effective walnut kernel detection network (called WKNet) was developed by employing Transformer, GhostNet, and criss-cross attention (called CCA) module to the YOLO v5s model, aiming to solve the time consuming and parameter redundancy issues. The WKNet achieved an mAP_0.5 of 0.9869, precision of 0.9779, and recall of 0.9875 for walnut kernel detection. The inference time per image is only 11.9 ms. Extensive comparison experiments with the state-of-the-art (SOTA) deep learning models demonstrated the advanced nature of WKNet. The online test of walnut internal quality detection also shows satisfactory performance. The innovative combination of X-ray imaging and WKNet provide significant implications for walnut quality control. Full article

In the production process of cross-cutting boards, real-time measurement of dimensions online has been a long-standing technical problem in the production field. Currently, the detection of board dimensions in the production field relies on manual observation based on workers’ operational experience or stopping the machine for measurement. This paper proposes a machine vision-based real-time online measurement system for dimensional measurements of cross-cutting units. A certain angle measurement model is established by using a face-array industrial camera, and a more accurate edge contour extraction is realized by deep learning. A novel edge intersection extraction algorithm based on line fitting and least squares method was proposed to accurately measure the length, width, diagonal lines of cross-cutting boards using four intersection coordinates. The measurement of 100 cross-cutting boards in the industrial production site shows that the proposed online measurement system for cross-cut board dimensions in this article has high accuracy, with a length perception error of ±50 mm, width of ±2 mm, and diagonal difference of ±5 mm, meeting the production requirements in industrial settings. The on-site shutdown measurement work was reduced, thereby doubling the production efficiency and saving two staff members. Full article

To ensure the effective implementation of food waste reduction in college cafeterias, Capital Normal University developed an automatic plate recognition system based on machine vision technology. The system operates by obtaining images of plates (whether clean or not) and the diners’ faces through multi-directional monitoring, then employs several deep learning models for the automatic localization and identification of the plates. Face recognition technology links the identification results of the plates to the diners. Additionally, the system incorporates innovative educational mechanisms such as online feedback and point redemption to encourage student participation and foster thrifty habits. These initiatives also provide more accurate training samples, enhancing the system’s precision and stability. Our findings indicate that machine vision technology is suitable for rapid identification and location of clean plates. Even without optimized network parameters, the U-Net network demonstrates high recognition accuracy (MIOU of 68.64% and MPA of 78.21%) and ideal convergence speed. Pilot data showed a 13% reduction in overall waste in the cafeteria and over 75% user acceptance of the mechanism. The implementation of this system has significantly improved the efficiency and accuracy of plate recognition, offering an effective solution for food waste prevention in college canteens. Full article

This study presents an on-line intelligent lubrication system utilizing specialty grease to address lubricant loss and uneven coating issues in traditional methods. Characterized by scanning electron microscopy (SEM) and Fourier transform infrared spectroscopy (FT-IR), the specialty grease demonstrates superior tribological performance, achieving a 46.7% reduction in the average friction coefficient and 33.3% smaller wear scar diameter under a 392 N load compared to conventional lubricants. The system features an automatic control vehicle design integrating heating, grease supply, lubrication-scraping mechanisms, and a dual closed-loop intelligent control system combining PID-based temperature regulation with machine vision. Experiments identified 50 °C as the optimal heating temperature. Kinematic modeling and grease consumption analysis guided greasing parameters optimization, validated through simulations and practical tests. Evaluated on a 20 m long, 36.5 mm diameter wire rope, the system achieved full coverage within 60 s, forming a uniform lubricant layer of 0.3–1.0 mm thickness (±0.15 mm deviation). It realizes the innovative application of high-adhesion lubricating grease, adaptive process control, and real-time thickness feedback technology, significantly improving the lubrication effect, reducing maintenance costs, and extending the lifespan of the wire rope. This provides intelligent lubrication technology support for the reliable operation of wire ropes in industrial fields. Full article

In laser-directed energy deposition (LDED) additive manufacturing, stress-induced deformation and cracking often occur unexpectedly, and, once initiated, they are difficult to remedy. To address this issue, we previously proposed the Dynamic Counter Method (DCM), which monitors internal stress based on deposition layer shrinkage, enabling real-time stress monitoring without damaging the component. To validate this method, we used AlSi10Mg material, which has a low melting point and high reflectivity, and developed a high-precision segmentation network based on DeeplabV3+ to test its ability to measure shrinkage in high-exposure images. Using a real-time reconstruction model, stress calculations were performed with DCM and thermal–mechanical coupling simulations, and the results were validated through XRD residual stress testing to confirm DCM’s accuracy in calculating internal stress in aluminum alloys. The results show that the DeeplabV3+ segmentation network accurately extracted deposition-layer contours and shrinkage information. Furthermore, DCM and thermal–mechanical coupling simulations showed good consistency in residual stress distribution, with all results falling within the experimental error range. In terms of stress evolution trends, DCM was also effective in predicting stress variations. Based on these findings, two loading strategies were proposed, and, for the first time, DCM’s application in online stress monitoring of large LDED components was validated, offering potential solutions for stress monitoring in large-scale assemblies. Full article

The demand for flexible automation in manufacturing has increased, incorporating vision-guided systems for object grasping. However, a key challenge is in-hand error, where discrepancies between the actual and estimated positions of an object in the robot’s gripper impact not only the grasp but also subsequent assembly stages. Corrective strategies used to compensate for misalignment can increase cycle times or rely on pre-labeled datasets, offline training, and validation processes, delaying deployment and limiting adaptability in dynamic industrial environments. Our main contribution is an online self-supervised learning method that automates data collection, training, and evaluation in real time, eliminating the need for offline processes. Building on this, our system collects real-time data during each assembly cycle, using corrective strategies to adjust the data and autonomously labeling them via a self-supervised approach. It then builds and evaluates multiple regression models through an auto machine learning implementation. The system selects the best-performing model to correct the misalignment and dynamically chooses between corrective strategies and the learned model, optimizing the cycle times and improving the performance during the cycle, without halting the production process. Our experiments show a significant reduction in the cycle time while maintaining the performance. Full article

Rapid online detection of broken rate can effectively guide maize harvest with minimal damage to prevent kernel fungal damage. The broken rate prediction model based on machine vision and machine learning algorithms is proposed in this manuscript. A new dataset of high moisture content maize kernel phenotypic features was constructed by extracting seven features (geometric and shape features). Then, the regression model of the kernel (broken and unbroken) weight prediction and the classification model of kernel defect detection were established using the mainstream machine learning algorithm. In this way, the defect rapid identification and accurate weight prediction of broken kernels achieve the purpose of broken rate quantitative detection. The results prove that LGBM (light gradient boosting machine) and RF (random forest) algorithms were suitable for constructing weight prediction models of broken and unbroken kernels, respectively. The r values of the models built by the two algorithms were 0.985 and 0.910, respectively. SVM (support vector machine) algorithms perform well in constructing maize kernel classification models, with more than 95% classification accuracy. A strong linear relationship was observed between the predicted and actual broken rates. Therefore, this method could help to be an accurate, objective, efficient broken rate online detection method for maize harvest. Full article

In the evolving landscape of computer vision, the integration of machine learning algorithms with cutting-edge hardware platforms is increasingly pivotal, especially in the context of disruptive healthcare systems. This study introduces an optimized implementation of a Convolutional Neural Network (CNN) on the Basys3 FPGA, designed specifically for accelerating the classification of cytotoxicity in human kidney cells. Addressing the challenges posed by constrained dataset sizes, compute-intensive AI algorithms, and hardware limitations, the approach presented in this paper leverages efficient image augmentation and pre-processing techniques to enhance both prediction accuracy and the training efficiency. The CNN, quantized to 8-bit precision and tailored for the FPGA’s resource constraints, significantly accelerates training by a factor of three while consuming only 1.33% of the power compared to a traditional software-based CNN running on an NVIDIA K80 GPU. The network architecture, composed of seven layers with excessive hyperparameters, processes downscale grayscale images, achieving notable gains in speed and energy efficiency. A cornerstone of our methodology is the emphasis on parallel processing, data type optimization, and reduced logic space usage through 8-bit integer operations. We conducted extensive image pre-processing, including histogram equalization and artefact removal, to maximize feature extraction from the augmented dataset. Achieving an accuracy of approximately 91% on unseen images, this FPGA-implemented CNN demonstrates the potential for rapid, low-power medical diagnostics within a broader IoT ecosystem where data could be assessed online. This work underscores the feasibility of deploying resource-efficient AI models in environments where traditional high-performance computing resources are unavailable, typically in healthcare settings, paving the way for and contributing to advanced computer vision techniques in embedded systems. Full article

Sign language (SL) is a means of communication that is used to bridge the gap between the deaf, hearing-impaired, and others. For Arabic speakers who are hard of hearing or deaf, Arabic Sign Language (ArSL) is a form of nonverbal communication. The development of effective Arabic sign language recognition (ArSLR) tools helps facilitate this communication, especially for people who are not familiar with ArSLR. Although researchers have investigated various machine learning (ML) and deep learning (DL) methods and techniques that affect the performance of ArSLR systems, a systematic review of these methods is lacking. The objectives of this study are to present a comprehensive overview of research on ArSL recognition and present insights from previous research papers. In this study, a systematic literature review of ArSLR based on ML/DL methods and techniques published between 2014 and 2023 is conducted. Three online databases are used: Web of Science (WoS), IEEE Xplore, and Scopus. Each study has undergone the proper screening processes, which include inclusion and exclusion criteria. Throughout this systematic review, PRISMA guidelines have been appropriately followed and applied. The results of this screening are divided into two parts: analysis of all the datasets utilized in the reviewed papers, underscoring their characteristics and importance, and discussion of the ML/DL techniques’ potential and limitations. From the 56 articles included in this study, it was noticed that most of the research papers focus on fingerspelling and isolated word recognition rather than continuous sentence recognition, and the vast majority of them are vision-based approaches. The challenges remaining in the field and future research directions in this area of study are also discussed. Full article

The concentricity error of automotive brake piston components critically affects the stability and reliability of the brake system. Traditional contact-based concentricity measurement methods are inefficient. In order to address the issue of low detection efficiency, this paper proposes a non-contact concentricity measurement method based on the combination of machine vision and image processing technology. In this approach, an industrial camera is employed to capture images of the measured workpiece’s end face from the top of the spring. The edge contours are extracted through the implementation of image preprocessing algorithms, which are then followed by the calculation of the outer circle center and the fitting of the inner circle center. Finally, the concentricity error is calculated based on the coordinates of the inner and outer circle centers. The experimental results demonstrate that, in comparison to a coordinate measuring machine (CMM), this method exhibits a maximum error of only 0.0393 mm and an average measurement time of 3.9 s. This technology markedly enhances the efficiency of measurement and fulfills the industry’s requirement for automated inspection. The experiments confirmed the feasibility and effectiveness of this method in practical engineering applications, providing reliable technical support for the online inspection of automotive brake piston components. Moreover, this methodology can be extended to assess concentricity in other complex stepped shaft parts. Full article

The speedy progress of computer vision and machine learning engineering has inaugurated novel means for improving the purchasing experiment in brick-and-mortar stores. This paper examines the utilization of YOLOv (You Only Look Once) and DeepSORT (Deep Simple Online and Real-Time Tracking) algorithms for the real-time detection and analysis of the purchasing penchant in brick-and-mortar market surroundings. By leveraging these algorithms, stores can track customer behavior, identify popular products, and monitor high-traffic areas, enabling businesses to adapt quickly to customer preferences and optimize store layout and inventory management. The methodology involves the integration of YOLOv5 for accurate and rapid object detection combined with DeepSORT for the effective tracking of customer movements and interactions with products. Information collected in in-store cameras and sensors is handled to detect tendencies in customer behavior, like repeatedly inspected products, periods expended in specific intervals, and product handling. The results indicate a modest improvement in customer engagement, with conversion rates increasing by approximately 3 percentage points, and a decline in inventory waste levels, from 88% to 75%, after system implementation. This study provides essential insights into the further integration of algorithm technology in physical retail locations and demonstrates the revolutionary potential of real-time behavior tracking in the retail industry. This research determines the foundation for future developments in functional strategies and customer experience optimization by offering a solid framework for creating intelligent retail systems. Full article

Mildew in maize kernels is typically caused by various fungi, necessitating prompt detection and treatment to minimize losses during harvest and storage. In this study, a deep learning YOLOv5s algorithm based on machine vision technology was employed to develop a maize seed surface mildew detection model and to enhance its portability for deployment on additional mobile devices. To guarantee the fruitful progression of this research, an initial experiment was conducted on maize seeds to obtain a sufficient number of images of mildewed maize kernels, which were classified into three grades (sound, mild, and severe). Subsequently, a maize seed image was extracted to create an image of a single maize seed, which was then divided to establish the data set. An enhanced YOLOv5s–ShuffleNet–CBAM model was ultimately developed. The results demonstrated that the model achieved with an mAP50 value of 0.955 and a model size of 2.4 MB. This resulted in a notable reduction in the model parameters and calculation amount while simultaneously enhancing model precision. Furthermore, K-fold cross-validation demonstrated the model stability, and Grad-CAM validated the model effectiveness. In the future, the proposed lightweight model in this study can be applied to other crops in the context of portable or online inspection systems, thus advancing effective and high-quality agricultural applications. Full article

Demand and market value for pennywort largely depend on the quality of the leaves, which can be affected by various ambient environment or fertigation variables during cultivation. Although early detection of defects in pennywort leaves would enable growers to take quick action, conventional manual detection is laborious and time consuming as well as subjective. Therefore, the objective of this study was to develop an automatic leaf defect detection algorithm for pennywort plants grown under controlled environment conditions, using machine vision and deep learning techniques. Leaf images were captured from pennywort plants grown in an ebb-and-flow hydroponic system under fluorescent light conditions in a controlled plant factory environment. Physically or biologically damaged leaves (e.g., curled, creased, discolored, misshapen, or brown spotted) were classified as defective leaves. Images were annotated using an online tool, and Mask R-CNN models were implemented with the integrated attention mechanisms, convolutional block attention module (CBAM) and coordinate attention (CA) and compared for improved image feature extraction. Transfer learning was employed to train the model with a smaller dataset, effectively reducing processing time. The improved models demonstrated significant advancements in accuracy and precision, with the CA-augmented model achieving the highest metrics, including a mean average precision (mAP) of 0.931 and an accuracy of 0.937. These enhancements enabled more precise localization and classification of leaf defects, outperforming the baseline Mask R-CNN model in complex visual recognition tasks. The final model was robust, effectively distinguishing defective leaves in challenging scenarios, making it highly suitable for applications in precision agriculture. Future research can build on this modeling framework, exploring additional variables to identify specific leaf abnormalities at earlier growth stages, which is crucial for production quality assurance. Full article

An online inspection method based on machine vision was proposed and validated to address the issues of high work intensity, low efficiency, low accuracy, and risk of missed inspection in traditional sampling methods for screw threads of rebar head. Firstly, an industrial camera was used to capture real-time images of the processed rebar thread heads, preprocess the images, and locate the target positions in the images to reduce the complexity and running time of subsequent algorithms. Then, the Canny operator was used to roughly extract the edge feature information of the rebar head, and the Shi–Tomasi algorithm was used for corner inspection to achieve precise optimization of sub-pixel level corners. Based on robust linear regression, the diagonal points were fitted with lines to detect the corresponding size parameters. Finally, an inspection system on screw threads of rebar head parameter was designed and developed, which consisted of an image-acquisition device, Siemens PLC controller, and inspection software. Test results show that this method can achieve online inspection without contact, with inspection accuracy reaching the micrometer level, and 8–10 rebar heads can be inspected per second. Full article