Internal defects detection and classification in hollow cylindrical surfaces using single shot detection and MobileNet

Electrolytic capacitor surface defect detection based on deep convolution neural network

The fabric defect detection algorithm based on object detection has become a research hotspot. The method based on the Single Shot MultiBox Detector (SSD) model has a fast detection speed, but the detection accuracy is insufficient. To balance the detection speed and accuracy of the model and meet the actual needs of the industry, an improved fabric defect detection algorithm based on SSD is proposed in this study. The Fully Convolutional Squeeze-and-Excitation (FCSE) block is added into the traditional SSD to improve the detection accuracy of the model. The number of default boxes was adjusted to accommodate the detection of long strip defects on fabric surface. Experimental results on the TILDA and Xuelang dataset confirm that our detection method based on SSD efficiently detected various fabric defects.

Study on the 3D-printed surface defect detection based on multi-row cyclic scanning method

The detection of defects on automotive coated surfaces is of paramount importance to ensure the quality of automotive appearance. However, due to the challenges posed by the lack of sufficient samples of product-specific coated defects, the uneven number of species, and the difficulty of detecting defects in small targets due to the complex background of the body surface. The detection of defects on automotive coated surfaces still relies on experienced manual labor to a significant extent. To address these issues, Poisson fusion is employed to enhance the data for generating defect images, thereby mitigating the limitations of insufficient coated defect samples and an imbalanced distribution of defect species. Based on this, a new YOLOv8-SC defect detection model is proposed, in which the C2f-Star is used to replace the original C2f structure. This aims to improve the model’s ability to extract defects of varying sizes in complex backgrounds, while reducing the number of model parameters and the amount of computation. The content-guided attention fusion (CGAFusion) module, situated before each detection head of the model, has been designed to enhance the model’s capacity to extract defects of varying sizes and complexity. This is achieved through the adaptive fusion of low-level and high-level features. The proposed model’s superiority in terms of detection metrics has been demonstrated through the use of example validation. The experiments were conducted on the enterprise dataset CPD-DET and the public dataset NEU-DET. The results demonstrated that the defective image generation and data enhancement method could significantly improve detection performance and have good generalization. The proposed YOLOv8-SC reduces the model parameters by 12.2% compared to the normal model. Additionally, the mean average precision (mAP) at 50% and 50%–95% thresholds are enhanced by 4.7% and 2.3%, respectively. Furthermore, the accuracy of the model exhibits a discernible positive growth trend with an increase in the sample set size. The design of an automotive coated surface defect detection system is presented at last. When deployed in industrial settings, this system can facilitate the intelligent detection of coated defects.

Aiming at the problems of inefficient detection caused by traditional manual inspection, unclear features and few defect sample in metal surface defect detection, an improved metal surface defect detection technology the siamese network is proposed. The proposed method constructs a deep siamese network with maximum interval, which consists of 4 convolutional layers, 4 max pooling layers and the top fully connected layer to improve the accuracy of the recognition of difficult small targets while ensuring the detection efficiency of the model. The performance of the improved metal surface defect detection technology is compared with other detection methods on the NEU surface defect database. The experimental result verify that the mean average precision of the proposed method is 96.1%, which is higher that of support vector machine, region convolutional neural network, faster region convolutional neural network, single shot multibox detector, you only look once neural network v3.

In this paper, a novel method for the detection of external insulation defects based on the ultrawideband impulse radar is proposed. The circular synthetic aperture radar method was adopted to collect reflected signals in this paper, since the detected object often has a symmetric shape (e.g., insulators, bushings, etc.). The mean suppression method is adopted to filter out the clutters of reflected waveforms from different directions, and thus the reflected signals of defects can be amplified. Then, the defect images are extracted from the processed reflected signals with the back projection algorithm. Moreover, since the example objects studied here are of multi-layer circular structure with different dielectrics for each layer, the accurate wave-propagation time should be calibrated before the calculation of back projection amplitudes. Thus, the multi-layer model is established to figure out the refraction path, while the propagation time is compensated based on the wave speeds of different dielectrics. The non-destructive detection capacity of the proposed UWB detection method is verified by the simulation first, and then the practical detection effectiveness is verified by the comparison experiment of an intact insulator and a defective one. The experimental results indicate that the measured length of the internal crack as an extension of the observed surface cavity is about 30 mm, and the severest defect point is only 4.2 mm away from the latter, which means the defect locating is of high accuracy. The investigation results demonstrate that, due to the good penetrability and imaging resolution, the impulse radar exhibits good potential in the online detection of both surface and internal defects of the external insulation equipment.

We propose a lightweight detection algorithm based on the Single Shot MultiBox Detector (SSD) algorithm in order to facilitate sheep management and to realize sheep facial identification, and we take the self-constructed dataset as the research object. First, the SSD replaces the VGG16 backbone network with MobileNetv3, a lightweight neural network, to create a hybrid model that is much smaller. Second, the ECA attention mechanism is incorporated into the backend of the 72 × 160 bottleneck layer. Finally, the SmoothL1 loss function is substituted with the BalancedL1 loss function. The optimized model’s size decreases significantly from the original SSD’s 132 MB to just 22.4 MB. It achieves a mean average precision of 83.47% and maintains an average frame rate of 68.53 frames per second. Compared to the basic SSD model, the mean average precision has increased by 3.25 percentage points, the model size has decreased by 109.6 MB, and the detection speed has improved by 9.55 frames per second. In comparative experiments using the same dataset with different object detection models, the proposed model outperforms the SSD, Faster R-CNN, Retinanet, and CenterNet in terms of mean average precision, with improvements of 3.25 percentage points, 4.71 percentage points, 2.38 percentage points, and 8.13 percentage points, respectively. The detection speed has shown significant improvements, increasing by 9.55, 58.55, 53.1, and 12.37 frames per second, respectively. The improved model presented in this paper significantly reduces the model’s size and computational requirements while maintaining an excellent performance. This provides a valuable reference for the digitalization of animal husbandry and livestock farming.

Instruments detect and respond to various parameters, playing a crucial role in civil and industrial applications. However, the current instrument recognition algorithm still suffers from low detection accuracy, a large amount of model calculation, and a low degree of automatic recognition. In this article, we propose an efficient real-time automatic instrument indication acquisition algorithm based on a lightweight deep convolutional neural network and hybrid attention fine-grained features. In this algorithm, we divide instrument identification into three subtasks, which are instrument object detection, instrument fine-grained recognition, and instrument indication acquisition. In the instrument object detection task, we propose a lightweight instrument detection algorithm, which uses a lightweight feature extraction backbone network and a single-scale object detection algorithm to reduce the computational load. In the instrument fine-grained recognition task, this article proposes a fine-grained classification network based on attention hybrid clipping, which can effectively recognize the instrument fine-grained category and range features. In the instrument indication acquisition task, the edge detection and polar coordinate change are used to realize an automated instrument identification and reading system, which can meet the needs of high-precision real-time monitoring of the instrument indication in various complex scenarios. In addition, we have created and made publicly available an instrument image dataset that contains 3457 images of various types of instruments in actual scenes. The recognition accuracy of the instrument reading recognition algorithm proposed in this article is 92.9% on the created dataset, and the average recognition time per image is 348 ms on the i7-8700 CPU.

Recognition of age and gender has become a significant part of the biometric system, protection, and treatment. It is widely used for people to access age-related content. It is used by social media in the distribution of layered advertising and promotions to expand its scope. Application of face detection has grown to a great extent that we should upgrade it using various methods to achieve more accurate results. In this paper, we have developed a lightweight deep Convolution neural network model for real-time age and gender prediction. For making the training dataset more diverse, Wiki, UTKFace, and Adience datasets have been merged into one containing 18728 images. Using this vast mixed dataset, we have achieved accuracy of 48.59% and 80.76% for age and gender respectively. Further, the model is tested in real-time. Different experimental investigations on the prepared dataset show that with most recent approaches, our model provides competitive prediction accuracy.

Endoanal ultrasound is widely used for the detection of external and internal anal sphincter defects in patients with fecal incontinence. Recently, 3-dimensional transperineal ultrasound has been introduced as a noninvasive imaging method for the detection of these sphincter defects. This study was designed to assess agreement between 3-dimensional transperineal ultrasound and 2-dimensional endoanal ultrasound regarding the detection of anal sphincter defects in women with fecal incontinence. This study was designed as a prospective observational study. The study took place in a university hospital. Between October 2008 and June 2009, all women with concerns of fecal incontinence underwent 2-dimensional endoanal ultrasound as well as 3-dimensional transperineal ultrasound. The main outcome measures are the presence of external and internal anal sphincter defects. Fifty-five patients were included. External and internal anal sphincter defects were observed with 2-dimensional endoanal ultrasound in 27 (49%) and 15 (27%) patients. Three-dimensional transperineal ultrasound detected an external and internal sphincter defect in 19 (35%) and 16 (29%) patients. The Cohen κ coefficient for the detection of external (κ = 0.63) and internal (κ = 0.78) anal sphincter defects was good. This study's limitations include the absence of a surgical examination as the reference standard in the determination of sphincter defects. This study shows good agreement between 3-dimensional transperineal ultrasound and 2-dimensional endoanal ultrasound regarding the detection of anal sphincter defects. Based on these data, 3-dimensional transperineal ultrasound might be considered as a valuable alternative noninvasive investigation method.

Small object detection is a challenging computer vision problem due to their low feature representation in the images and factors such as occlusions and noise. In images captured from a camera mounted on an unmanned aerial vehicle (UAV), objects are usually acquired in small sizes depending on the UAV flight altitude. The state-of-the-art object detectors often have lower detection accuracy with small objects. New approaches of combining features at multi-levels in the network helps in improving the object detection performance. In this paper, we propose a multi-scale approach of low-level feature combinations with deconvolutional modules on a single shot multibox detection (SSD) object detector to improve the small object detection in images acquired from a UAV. The proposed SSD based architecture is evaluated on UAV datasets to compare its performance with the state-of-the-art detectors.

The use of computer vision and deep learning in boundary documentation for land registration stems from the ongoing demand for appropriate mapping approaches of unregistered land rights to eradicate the global challenge of tenure insecurity. Previous research has yielded promising results towards automated extraction of photo‐visible cadastral boundaries from high‐resolution imagery. Nonetheless, the extraction of invisible cadastral boundaries is still a challenge. This study investigates the place of sensor/s on‐board unmanned aerial vehicles and deep learning algorithms in detecting cadastral boundaries. It develops a participatory boundary marking procedure using low‐cost markers to bring monument to previously invisible and ill‐defined cadastral boundaries. After that, the researchers trained and tested the accuracy of a convolutional neural network, namely single shot multi‐box detector (SSD) based on Residual Neural Network (ResNet) and Visual Geometry Group (VGG) backbone networks to automatically detect cadastral boundary markers from unmanned aerial vehicle imagery. SSD based on ResNet34 performed best with 0.88 precision, 0.92 recall and 0.91 F measure or (F1) score. VGG19‐based SSD yielded a precision of 0.47, recall of 0.53 and F1 score of 0.50. The horizontal accuracy of the cadastral map generated varied from 0.089 to 0.496 m per parcel, with a standard deviation of 0.120 m. Results show that this approach is practical for cadastral mapping in rural areas.

Accurate identification of vehicles and estimating density in traffic surveillance systems is a challenging task, particularly in scenarios with closely spaced lanes. Single Shot MultiBox Detector (SSD) is introduced in vehicle detection and classification due to its speed and accuracy. It utilizes a transfer learning technique that enables them to utilize features from pretrained Convolutional Neural Networks (CNNs). Although the utilization of multi-scale feature maps in SSD has achieved efficient results in vehicle detection, it struggles to identify key features of vehicles due to its one-stage detection approach. Furthermore, the use of VGG16 as the backbone network in these approaches leads to the loss of fine-grained details, posing challenges in accurately localizing and classifying small vehicles. Also, there is no interaction between high- and low-level features, which restricts the networks ability to effectively integrate and utilize both features for accurate vehicle detection. To overcome these limitations, an improved SSD approach is introduced in this paper, leveraging interactive multi-scale attention characteristics to accurately detect and classify vehicles. This approach utilizes ResNet50 as the network backbone to overcome the limitations of traditional SSDs in detecting small vehicles. Also, an attention block is incorporated into it to focus on key details and assign higher attention to relevant pixels within the feature map. Also, the network employs a parallel detection framework and shares multi-scale layers (both high and low), enabling efficient detection of vehicles with various sizes. Then, traffic density is estimated based on the weights assigned to the categorized vehicles obtained from the improved SSD and the recorded area. Finally, traffic is classified as high, low, or moderate by comparing the estimated density to a threshold value. By adding attention characteristics of different scales to the original detection branch and replacing the VGG16 with ResNet50 of the SSD technique using our method, the feature representation capability and detection accuracy are both significantly improved.

Emotions can be detected through facial expressions, voice signals, and physiological signals such as Galvanic Skin Response (GSR), Electroencephalogram (EEG), and Electrocardiogram (ECG). However, there have been limited studies on using GSR signals for emotion detection. Emotion recognition systems (ERS) use artificial intelligence to diagnose emotions and trigger appropriate actions accurately. This study introduces a novel lightweight deep Convolutional Neural Network (LWDCNN) for emotion classification using GSR data. The LWDCNN model reduces computational complexity while improving the speed and accuracy of the classification. GSR data is normalized based on suitable segmentation. A seven-fold cross-validation technique is employed to classify emotions using LWDCNN based on the arousal and valence dimensions. Emotions are classified based on the social and non-social context of the subjects using GSR data from the AMIGOS (A Dataset for Affect, Personality, and Mood Research on Individuals and Groups) database in both individual (non-social) and group (social) settings. The accuracy of valence classification is 78.83% for individual settings and 79.96% for group settings. The accuracy of arousal classification is 80.62% for individual settings and 84.42% for group settings. This model can effectively be used to diagnose the subjects' mental health by detecting the appropriate emotions. Goa College of Engineering, Affiliated with Goa University, Goa, India.

The design and study of pulsed eddy current sensors for detecting surface defects in small-diameter rods are highly significant. Accurate detection and identification of surface defects in small-diameter rods may be attained by the ongoing optimization of sensor design and enhancement of detection technologies. This article presents the construction of a non-coaxial differential eddy current sensor (Tx-Rx sensor) and examines the detection of surface defects in a small diameter bar. A COMSOL 3D model is developed to examine the variations in eddy current distribution and defect signal characteristics between the plate and rod components. The position of the excitation coil on the bar and the eddy current disruption around the defect are examined. Additionally, a Tx-Rx sensor has been developed and enhanced concerning coil dimensions, coil separation, and elevation height. An experimental system is established to detect bar structures with surface defects of varying depths, and a model correlating differential signal attenuation with defect depth is proposed, achieving a quantitative relative error of less than 5%, thereby offering a reference for the quantitative detection of bar surface defects.