COVID-19 detection using deep learning models to exploit Social Mimic Optimization and structured chest X-ray images using fuzzy color and stacking approaches.

Data-driven methods in structural health monitoring (SHM) is gaining popularity due to recent technological advancements in sensors, as well as high-speed internet and cloud-based computation. Since the introduction of deep learning (DL) in civil engineering, particularly in SHM, this emerging and promising tool has attracted significant attention among researchers. The main goal of this paper is to review the latest publications in SHM using emerging DL-based methods and provide readers with an overall understanding of various SHM applications. After a brief introduction, an overview of various DL methods (e.g., deep neural networks, transfer learning, etc.) is presented. The procedure and application of vibration-based, vision-based monitoring, along with some of the recent technologies used for SHM, such as sensors, unmanned aerial vehicles (UAVs), etc. are discussed. The review concludes with prospects and potential limitations of DL-based methods in SHM applications.

Data-Driven Structural Health Monitoring and Damage Detection through Deep Learning: State-of-the-Art Review.

In machine vision-based surface inspection tasks, defects are typically considered as local anomalies in homogeneous background. However, industrial workpieces commonly contain complex structures, including hallow regions, welding joints, or rivet holes. Such obvious structural interference will inevitably cause a cluttered background and mislead the classification results. Moreover, the sizes of various surface defects might change significantly. Last but not least, it is extremely time-consuming and not scalable to capture large-scale defect data sets to train deep CNN models. To address the challenges mentioned earlier, we first proposed to incorporate multiple convolutional layers with different kernel sizes to increase the receptive field and to generate multiscale features. As a result, the proposed model can better handle the cluttered background and defects of various sizes. Also, we purposely compress the size of parameters in the newly added convolutional layers for better learning of defect-related features using a limited number of training samples. Evaluated in a newly constructed surface defect data set (images contain complex structures and defects of various sizes), our proposed model achieves more accurate recognition results compared with the state-of-the-art surface defect classifiers. Moreover, it is a lightweight model and can deliver real-time processing speed (>100 frames/s) on a computer equipped with a single NVIDIA TITAN X Graphics Processing Unit (12-GB memory).

A Deep Learning-Based Surface Defect Inspection System Using Multiscale and Channel-Compressed Features

Image-Based Surface Defect Detection Using Deep Learning: A Review

In recent years, more and more scholars devoted themselves to the research of the target detection algorithm due to the continuous development of deep learning. Among them, the detection and recognition of small and complex targets are still a problem to be solved. The authors of this article have understood the shortcomings of the deep learning detection algorithm in detecting small and complex defect targets and would like to share a new improved target detection algorithm in steel surface defect detection. The steel surface defects will affect the quality of steel seriously. We find that most of the current detection algorithms for NEU-DET dataset detection accuracy are low, so we choose to verify a steel surface defect detection algorithm based on machine vision on this dataset for the problem of defect detection in steel production. A series of improvement measures are carried out in the traditional Faster R-CNN algorithm, such as reconstructing the network structure of Faster R-CNN. Based on the small features of the target, we train the network with multiscale fusion. For the complex features of the target, we replace part of the conventional convolution network with a deformable convolution network. The experimental results show that the deep learning network model trained by the proposed method has good detection performance, and the mean average precision is 0.752, which is 0.128 higher than the original algorithm. Among them, the average precision of crazing, inclusion, patches, pitted surface, rolled in scale and scratches is 0.501, 0.791, 0.792, 0.874, 0.649, and 0.905, respectively. The detection method is able to identify small target defects on the steel surface effectively, which can provide a reference for the automatic detection of steel defects.

/pdf/a-new-steel-defect-detection-algorithm-based-on-deep-3hty932xid.pdf

A New Steel Defect Detection Algorithm Based on Deep Learning.

A deep-learning-based approach for fast and robust steel surface defects classification

The invention discloses the image edge processing method of relay measurement. The method has the following steps of an adjustment device step, an identification region dividing step, an upper contactextraction step, an image binarization processing step, an image statistics step, an edge positioning scaling step, an image expansion step, a step of acquiring an upper portion contact gap minimum value, an upper portion contact determination qualification step, a lower portion contact sheet extraction step, a lower portion contact sheet region binarization processing step, a lower portion contact sheet average width acquisition step, a lower portion contact sheet determination qualification step and a relay determination qualification step. By using the image edge processing method of therelay measurement, a product detection speed is fast, a processing information content is large and product detection accuracy is high.

Image edge processing method of relay measurement

The invention discloses an image processing and extending method for relay measurement. The method specifically comprises a device adjustment step, a recognition area division step, an upper contact extraction step, an image binarization step, an image statistical analysis step, an edge positioning scaling step, an image extending step, an upper contact clearance minimum value obtaining step, an upper contact qualification judging step, a lower contact sheet extraction step, a lower contact sheet area binarization step, a lower contact sheet average width obtaining step, a lower contact sheetqualification judging step and a relay qualification judging step. The image processing and extending method for relay measurement is high in product detection speed, large in processed information amount and high in product detection correctness.

Image processing and extending method for relay measurement

The invention discloses the image extraction and image processing method of relay measurement. The method has the following steps of an adjustment device step, an identification region dividing step,an upper contact extraction step, an image binarization processing step, an image statistics step, an edge positioning scaling step, an image expansion step, a step of acquiring an upper portion contact gap minimum value, an upper portion contact determination qualification step, a lower portion contact sheet extraction step, a lower portion contact sheet region binarization processing step, a lower portion contact sheet average width acquisition step, a lower portion contact sheet determination qualification step and a relay determination qualification step. By using the image extraction andimage processing method of the relay measurement, a product detection speed is fast, a processing information content is large and product detection accuracy is high.

Image extraction and image processing method of relay measurement

The invention discloses a relay measuring device and an image processing method thereof. The relay measuring device comprises an observation system, a light source, a workpiece clamping mechanism, a frame supporting system and an image processing terminal. The observation system comprises a telecentric lens, a camera and a fine adjustment sliding table. The workpiece clamping mechanism comprises atool sliding groove and a relay. The relay is arranged on the tool sliding groove, the telecentric lens is arranged on the side, close to the relay, of the camera, the camera is arranged on the fineadjustment sliding table, the camera is connected with the image processing terminal, and the light source, the relay and the camera are arranged on the same horizontal line. The light source adopts arectangular block, so that parallel light irradiates the relay to form a corresponding image, and the image is acquired by the camera; the invention provides a relay measuring device and an image processing method thereof, wherein the relay measuring device is high in product detection speed, large in processing information amount and high in product detection accuracy.

Sun Peize

Papers

A deep-learning-based approach for fast and robust steel surface defects classification

Image edge processing method of relay measurement

Image processing and extending method for relay measurement

Image extraction and image processing method of relay measurement

Relay measuring device and image processing method thereof