A Transfer Residual Neural Network Based on ResNet-34 for Detection of Wood Knot Defects

Bilateral Defect Cutting Strategy for Sawn Timber Based on Artificial Intelligence Defect Detection Model

Solid wood is renowned as a superior material for construction and furniture applications. However, characteristics such as dead knots, live knots, piths, and cracks are easily formed during timber's growth and processing stages. These features and defects significantly undermine the mechanical characteristics of sawn timber, rendering it unsuitable for specific applications. This study introduces BDCS-YOLO (Bilateral Defect Cutting Strategy based on You Only Look Once), an artificial intelligence bilateral sawing strategy to advance the automation of timber processing. Grounded on a dual-sided image acquisition platform, BDCS-YOLO achieves a commendable mean average feature detection precision of 0.94 when evaluated on a meticulously curated dataset comprising 450 images. Furthermore, a dual-side processing optimization module is deployed to enhance the accuracy of defect detection bounding boxes and establish refined processing coordinates. This innovative approach yields a notable 12.3% increase in the volume yield of sawn timber compared to present production, signifying a substantial leap toward efficiently utilizing solid wood resources in the lumber processing industry.

Deep learning ResNet34 model-assisted diagnosis of sickle cell disease via microcolumn isoelectric focusing

Traditional methods for sickle cell disease (SCD) screening can be inaccurate and misleading, and the early and accurate diagnosis of SCD is crucial for effective management and treatment. Although microcolumn isoelectric focusing (mIEF) is effective, the hemoglobinopathies must be accurately identified, wherein skilled personnel are required to analyse the bands in mIEF. Further automating and standardizing the diagnostic methods via AI to identify abnormal Hbs would be a useful endeavor. In this study, we propose a novel approach for SCD diagnosis by integrating the high throughput capability of ResNet34 in image analysis, as a deep learning convolutional neural network, for the precise separation of Hb variants using mIEF. Initially, SCD blood samples were subjected to mIEF and the resulting patterns were then captured as digital images. The sensitivity and specificity of the mIEF analysis were 100% and 97.8%, respectively, with a 99.39% accuracy. Comparison with HPLC showed a strong linear correlation (R2 = 0.9934), good agreement with the Bland-Altman plot (average difference ± 1.96 SD, bias = 9.89%) and a 100% match with the DNA analysis. Subsequently, the mIEF images were then input into the ResNet34 model, pre-trained on a large dataset, for feature extraction and classification. The integration of ResNet34 with mIEF demonstrated promising results in terms of precision (90.1%) and accuracy in distinguishing between the various SCD conditions. Overall, the proposed method offers a more effective, automated, and reduced cost approach for SCD diagnosis, which could potentially streamline diagnostic workflows and mitigate the subjectivity and variability inherent in manual assessments.

SegX-Net: A novel image segmentation approach for contrail detection using deep learning

Contrails are line-shaped clouds formed in the exhaust of aircraft engines that significantly contribute to global warming. This paper confidently proposes integrating advanced image segmentation techniques to identify and monitor aircraft contrails to address the challenges associated with climate change. We propose the SegX-Net architecture, a highly efficient and lightweight model that combines the DeepLabV3+, upgraded, and ResNet-101 architectures to achieve superior segmentation accuracy. We evaluated the performance of our model on a comprehensive dataset from Google research and rigorously measured its efficacy with metrics such as IoU, F1 score, Sensitivity and Dice Coefficient. Our results demonstrate that our enhancements have significantly improved the efficacy of the SegX-Net model, with an outstanding IoU score of 98.86% and an impressive F1 score of 99.47%. These results unequivocally demonstrate the potential of image segmentation methods to effectively address and mitigate the impact of air conflict on global warming. Using our proposed SegX-Net architecture, stakeholders in the aviation industry can confidently monitor and mitigate the impact of aircraft shrinkage on the environment, significantly contributing to the global fight against climate change.

A fine-tuned YOLOv5 deep learning approach for real-time house number detection

Detection of small objects in natural scene images is a complicated problem due to the blur and depth found in the images. Detecting house numbers from the natural scene images in real-time is a computer vision problem. On the other hand, convolutional neural network (CNN) based deep learning methods have been widely used in object detection in recent years. In this study, firstly, a classical CNN-based approach is used to detect house numbers with locations from natural images in real-time. Faster R-CNN, MobileNet, YOLOv4, YOLOv5 and YOLOv7, among the commonly used CNN models, models were applied. However, satisfactory results could not be obtained due to the small size and variable depth of the door plate objects. A new approach using the fine-tuning technique is proposed to improve the performance of CNN-based deep learning models. Experimental evaluations were made on real data from Kayseri province. Classic Faster R-CNN, MobileNet, YOLOv4, YOLOv5 and YOLOv7 methods yield f1 scores of 0.763, 0.677, 0.880, 0.943 and 0.842, respectively. The proposed fine-tuned Faster R-CNN, MobileNet, YOLOv4, YOLOv5, and YOLOv7 approaches achieved f1 scores of 0.845, 0.775, 0.932, 0.972 and 0.889, respectively. Thanks to the proposed fine-tuned approach, the f1 score of all models has increased. Regarding the run time of the methods, classic Faster R-CNN detects 0.603 seconds, while fine-tuned Faster R-CNN detects 0.633 seconds. Classic MobileNet detects 0.046 seconds, while fine-tuned MobileNet detects 0.048 seconds. Classic YOLOv4 and fine-tuned YOLOv4 detect 0.235 and 0.240 seconds, respectively. Classic YOLOv5 and fine-tuned YOLOv5 detect 0.015 seconds, and classic YOLOv7 and fine-tuned YOLOv7 detect objects in 0.009 seconds. While the YOLOv7 model was the fastest running model with an average running time of 0.009 seconds, the proposed fine-tuned YOLOv5 approach achieved the highest performance with an f1 score of 0.972.

Wood Veneer Defect Detection Based on Multiscale DETR with Position Encoder Net

Wood is one of the main building materials. However, defects on veneers result in substantial waste of wood resources. Traditional veneer defect detection relies on manual experience or photoelectric-based methods, which are either subjective and inefficient or need substantial investment. Computer vision-based object detection methods have been used in many realistic areas. This paper proposes a new deep learning defect detection pipeline. First, an image collection device is constructed and a total of more than 16,380 defect images are collected coupled with a mixed data augmentation method. Then, a detection pipeline is designed based on DEtection TRansformer (DETR). The original DETR needs position encoding functions to be designed and is ineffective for small object detection. To solve these problems, a position encoding net is designed with multiscale feature maps. The loss function is also redefined for much more stable training. The results from the defect dataset show that using a light feature mapping network, the proposed method is much faster with similar accuracy. Using a complex feature mapping network, the proposed method is much more accurate with similar speed.

Automatic resin duct detection and measurement from wood core images using convolutional neural networks

The structure and features of resin ducts provide valuable information about environmental conditions accompanying the growth of trees in the genus Pinus. Therefore analysis of resin duct characteristics has been an increasingly common measurement in dendrochronology. However, the measurement is tedious and time-consuming since it requires thousands of ducts to be manually marked in an image of an enlarged wood surface. Although tools exist to automate some stages of this process, no tool exists to automatically recognize and analyze the resin ducts and standardize them with the tree rings they belong to. This study proposes a new fully automatic pipeline that quantifies the properties of resin ducts in terms of the tree ring area to which they belong. A convolutional neural network underlays the pipeline to detect resin ducts and tree-ring boundaries. Also, a region merging procedure is used to identify connected components corresponding to successive rings. Corresponding ducts and rings are next related to each other. The pipeline was tested on 74 wood images representing five Pinus species. Over 8000 tree-ring boundaries and almost 25,000 resin ducts were analyzed. The proposed method detects resin ducts with a sensitivity of 0.85 and precision of 0.76. The corresponding scores for tree-ring boundary detection are 0.92 and 0.99, respectively.

An Image-Based Framework for Measuring the Prestress Level in CFRP Laminates: Experimental Validation

Image-based methods have been applied to support structural monitoring, product and material testing, and quality control. Lately, deep learning for compute vision is the trend, requiring large and labelled datasets for training and validation, which is often difficult to obtain. The use of synthetic datasets is often applying for data augmentation in different fields. An architecture based on computer vision was proposed to measure strain during prestressing in CFRP laminates. The contact-free architecture was fed by synthetic image datasets and benchmarked for machine learning and deep learning algorithms. The use of these data for monitoring real applications will contribute towards spreading the new monitoring approach, increasing the quality control of the material and application procedure, as well as structural safety. In this paper, the best architecture was validated during experimental tests, to evaluate the performance in real applications from pre-trained synthetic data. The results demonstrate that the architecture implemented enables estimating intermediate strain values, i.e., within the range of training dataset values, but it does not allow for estimating strain values outside those range. The architecture allowed for estimating the strain in real images with an error ∼0.5%, higher than that obtained with synthetic images. Finally, it was not possible to estimate the strain in real cases from the training performed with the synthetic dataset.

Developing a Tuned Three-Layer Perceptron Fed with Trained Deep Convolutional Neural Networks for Cervical Cancer Diagnosis

Cervical cancer is one of the most common types of cancer among women, which has higher death-rate than many other cancer types. The most common way to diagnose cervical cancer is to analyze images of cervical cells, which is performed using Pap smear imaging test. Early and accurate diagnosis can save the lives of many patients and increase the chance of success of treatment methods. Until now, various methods have been proposed to diagnose cervical cancer based on the analysis of Pap smear images. Most of the existing methods can be divided into two groups of methods based on deep learning techniques or machine learning algorithms. In this study, a combination method is presented, whose overall structure is based on a machine learning strategy, where the feature extraction stage is completely separate from the classification stage. However, in the feature extraction stage, deep networks are used. In this paper, a multi-layer perceptron (MLP) neural network fed with deep features is presented. The number of hidden layer neurons is tuned based on four innovative ideas. Additionally, ResNet-34, ResNet-50 and VGG-19 deep networks have been used to feed MLP. In the presented method, the layers related to the classification phase are removed in these two CNN networks, and the outputs feed the MLP after passing through a flatten layer. In order to improve performance, both CNNs are trained on related images using the Adam optimizer. The proposed method has been evaluated on the Herlev benchmark database and has provided 99.23 percent accuracy for the two-classes case and 97.65 percent accuracy for the 7-classes case. The results have shown that the presented method has provided higher accuracy than the baseline networks and many existing methods.

Region Segmentation of Whole-Slide Images for Analyzing Histological Differentiation of Prostate Adenocarcinoma Using Ensemble EfficientNetB2 U-Net with Transfer Learning Mechanism

Recent advances in computer-aided detection via deep learning (DL) now allow for prostate cancer to be detected automatically and recognized with extremely high accuracy, much like other medical diagnoses and prognoses. However, researchers are still limited by the Gleason scoring system. The histopathological analysis involved in assigning the appropriate score is a rigorous, time-consuming manual process that is constrained by the quality of the material and the pathologist's level of expertise. In this research, we implemented a DL model using transfer learning on a set of histopathological images to segment cancerous and noncancerous areas in whole-slide images (WSIs). In this approach, the proposed Ensemble U-net model was applied for the segmentation of stroma, cancerous, and benign areas. The WSI dataset of prostate cancer was collected from the Kaggle repository, which is publicly available online. A total of 1000 WSIs were used for region segmentation. From this, 8100 patch images were used for training, and 900 for testing. The proposed model demonstrated an average dice coefficient (DC), intersection over union (IoU), and Hausdorff distance of 0.891, 0.811, and 15.9, respectively, on the test set, with corresponding masks of patch images. The manipulation of the proposed segmentation model improves the ability of the pathologist to predict disease outcomes, thus enhancing treatment efficacy by isolating the cancerous regions in WSIs.

Piston Sensing for Golay-6 Sparse Aperture System with Double-Defocused Sharpness Metrics via ResNet-34

In pursuit of high imaging quality, optical sparse aperture systems must correct piston errors quickly within a small range. In this paper, we modified the existing deep-learning piston detection method for the Golay-6 array, by using a more powerful single convolutional neural network based on ResNet-34 for feature extraction; another fully connected layer was added, on the basis of this network, to obtain the best results. The Double-defocused Sharpness Metric (DSM) was selected first, as a feature vector to enhance the model performance; the average RMSE of the five sub-apertures for valid detection in our study was only 0.015λ (9 nm). This modified method has higher detecting precision, and requires fewer training datasets with less training time. Compared to the conventional approach, this technique is more suitable for the piston sensing of complex configurations.

Benchmarking for Strain Evaluation in CFRP Laminates Using Computer Vision: Machine Learning versus Deep Learning

The strengthening of concrete structures with laminates of Carbon-Fiber-Reinforced Polymers (CFRP) is a widely adopted technique. retained The application is more effective if pre-stressed CFRP laminates are adopted. The measurement of the strain level during the pre-stress application usually involves laborious and time-consuming applications of instrumentation. Thus, the development of expedited approaches to accurately measure the pre-stressed application in the laminates represents an important contribution to the field. This paper proposes and benchmarks contact-free architecture for measuring the strain level of CFRP laminate based on computer vision. The main objective is to provide a solution that might be economically feasible, automated, easy to use, and accurate. The architecture is fed by digitally deformed synthetic images, generated based on a low-resolution camera. The adopted methods range from traditional machine learning to deep learning. Furthermore, dropout and cross-validation methods for quantifying traditional machine learning algorithms and neural networks are used to efficiently provide uncertainty estimates. ResNet34 deep learning architecture provided the most accurate results, reaching a root mean square error (RMSE) of 0.057‱ for strain prediction. Finally, it is important to highlight that the architecture presented is contact-free, automatic, cost-effective, and measures directly on the laminate surfaces, which allows them to be widely used in the application of pre-stressed laminates.

Rapid Detection of Cardiac Pathologies by Neural Networks Using ECG Signals (1D) and sECG Images (3D)

Usually, cardiac pathologies are detected using one-dimensional electrocardiogram signals or two-dimensional images. When working with electrocardiogram signals, they can be represented in the time and frequency domains (one-dimensional signals). However, this technique can present difficulties, such as the high cost of private health services or the time the public health system takes to refer the patient to a cardiologist. In addition, the variety of cardiac pathologies (more than 20 types) is a problem in diagnosing the disease. On the other hand, surface electrocardiography (sECG) is a little-explored technique for this diagnosis. sECGs are three-dimensional images (two dimensions in space and one in time). In this way, the signals were taken in one-dimensional format and analyzed using neural networks. Following the transformation of the one-dimensional signals to three-dimensional signals, they were analyzed in the same sense. For this research, two models based on LSTM and ResNet34 neural networks were developed, which showed high accuracy, 98.71% and 93.64%, respectively. This study aims to propose the basis for developing Decision Support Software (DSS) based on machine learning models.

Semi-ProtoPNet Deep Neural Network for the Classification of Defective Power Grid Distribution Structures

Power distribution grids are typically installed outdoors and are exposed to environmental conditions. When contamination accumulates in the structures of the network, there may be shutdowns caused by electrical arcs. To improve the reliability of the network, visual inspections of the electrical power system can be carried out; these inspections can be automated using computer vision techniques based on deep neural networks. Based on this need, this paper proposes the Semi-ProtoPNet deep learning model to classify defective structures in the power distribution networks. The Semi-ProtoPNet deep neural network does not perform convex optimization of its last dense layer to maintain the impact of the negative reasoning process on image classification. The negative reasoning process rejects the incorrect classes of an input image; for this reason, it is possible to carry out an analysis with a low number of images that have different backgrounds, which is one of the challenges of this type of analysis. Semi-ProtoPNet achieves an accuracy of 97.22%, being superior to VGG-13, VGG-16, VGG-19, ResNet-34, ResNet-50, ResNet-152, DenseNet-121, DenseNet-161, DenseNet-201, and also models of the same class such as ProtoPNet, NP-ProtoPNet, Gen-ProtoPNet, and Ps-ProtoPNet.

A large-scale image dataset of wood surface defects for automated vision-based quality control processes

The wood industry is facing many challenges. The high variability of raw material and the complexity of manufacturing processes results in a wide range of visible structure defects, which have to be controlled by trained specialists. These manual processes are not only tedious and biased, but also less effective. To overcome the drawbacks of the manual quality control processes, several automated vision-based systems have been proposed. Even though some conducted studies achieved a higher recognition rate than trained experts, researchers have to deal with a lack of large-scale databases and authentic data in this field. To address this issue, we performed a data acquisition experiment set in the industrial environment, where we were able to acquire an extensive set of authentic data from a production line. For this purpose, we designed and implemented a complex technical solution suitable for high-speed acquisition during harsh manufacturing conditions. In this data note, we present a large-scale dataset of high-resolution sawn timber surface images containing more than 43 000 labelled surface defects and covering 10 types of the most common wood defects. Moreover, with each image record, we provide two types of labels allowing researchers to perform semantic segmentation, as well as defect classification, and localization.

Deep Feature Extraction for Cymbidium Species Classification Using Global–Local CNN

Cymbidium is the most famous and widely distributed type of plant in the Orchidaceae family. It has extremely high ornamental and economic value. With the continuous development of the Cymbidium industry in recent years, it has become increasingly difficult to classify, identify, develop, and utilize orchids. In this study, a classification model GL-CNN based on a convolutional neural network was proposed to solve the problem of Cymbidium classification. First, the image set was expanded by four methods (mirror rotation, salt-and-pepper noise, image sharpening, and random angle flip), and then a cascade fusion strategy was used to fit the multiscale features obtained from the two branches. Comparing the performance of GL-CNN with other four classic models (AlexNet, ResNet50, GoogleNet, and VGG16), the results showed that GL-CNN achieves the highest classification prediction accuracy with a value of 94.13%. This model can effectively detect different species of Cymbidium and provide a reference for the identification of Cymbidium germplasm resources.

Surface Detection of Solid Wood Defects Based on SSD Improved with ResNet

Due to the lack of forest resources in China and the low detection efficiency of wood surface defects, the output of solid wood panels is not high. Therefore, this paper proposes a method for detecting surface defects of solid wood panels based on a Single Shot MultiBox Detector algorithm (SSD) to detect typical wood surface defects. The wood panel images are acquired by an independently designed image acquisition system. The SSD model included the first five layers of the VGG16 network, the SSD feature mapping layer, the feature detection layer, and the Non-Maximum Suppression (NMS) module. We used TensorFlow to train the network and further improved it on the basis of the SSD network structure. As the basic network part of the improved SSD model, the deep residual network (ResNet) replaced the VGG network part of the original SSD network to optimize the input features of the regression and classification tasks of the predicted bounding box. The solid wood panels selected in this paper are Chinese fir and pine. The defects include live knots, dead knots, decay, mildew, cracks, and pinholes. A total of more than 5000 samples were collected, and the data set was expanded to 100,000 through data enhancement methods. After using the improved SSD model, the average detection accuracy of the defects we obtained was 89.7%, and the average detection time was 90 ms. Both the detection accuracy and the detection speed were improved.

A large-scale image dataset of wood surface defects for automated vision-based quality control processes

The wood industry is facing many challenges. The high variability of raw material and the complexity of manufacturing processes results in a wide range of visible structure defects, which have to be controlled by trained specialists. These manual processes are not only tedious and biased, but also less effective. To overcome the drawbacks of the manual quality control processes, several automated vision-based systems have been proposed. Even though some conducted studies achieved a higher recognition rate than trained experts, researchers have to deal with a lack of large-scale databases and authentic data in this field. To address this issue, we performed a data acquisition experiment set in the industrial environment, where we were able to acquire an extensive set of authentic data from a production line. For this purpose, we designed and implemented a complex technical solution suitable for high-speed acquisition during harsh manufacturing conditions. In this data note, we present a large-scale dataset of high-resolution sawn timber surface images containing more than 43 000 labelled surface defects and covering 10 types of the most common wood defects. Moreover, with each image record, we provide two types of labels allowing researchers to perform semantic segmentation, as well as defect classification, and localization.

Segmentation of Drilled Holes in Texture Wooden Furniture Panels Using Deep Neural Network

Drilling operations are an essential part of furniture from MDF laminated boards required for product assembly. Faults in the process might introduce adverse effects to the furniture. Inspection of the drilling quality can be challenging due to a big variety of board surface textures, dust, or woodchips in the manufacturing process, milling cutouts, and other kinds of defects. Intelligent computer vision methods can be engaged for global contextual analysis with local information attention for automated object detection and segmentation. In this paper, we propose blind and through drilled holes segmentation on textured wooden furniture panel images using the UNet encoder-decoder modifications enhanced with residual connections, atrous spatial pyramid pooling, squeeze and excitation module, and CoordConv layers for better segmentation performance. We show that even a lightweight architecture is capable to perform on a range of complex textures and is able to distinguish the holes drilling operations’ semantical information from the rest of the furniture board and conveyor context. The proposed model configurations yield better results in more complex cases with a not significant or small bump in processing time. Experimental results demonstrate that our best-proposed solution achieves a Dice score of up to 97.89% compared to the baseline U-Net model’s Dice score of 94.50%. Statistical, visual, and computational properties of each convolutional neural network architecture are addressed.