A surface defect detection method via fusing multi-level features

Surface defect detection is very important to ensure product quality, but most of the surface defects of industrial products are characterized by low contrast, big size difference and category similarity, which brings challenges to the automatic detection of defects. To solve these problems, we propose a defect detection method based on convolutional neural network. In this method, a backbone network with semantic supervision is applied to extract the features of different levels. While a multi-level feature fusion module is proposed to fuse adjacent feature maps into high-resolution feature maps successively, which significantly improves the prediction accuracy of the network. Finally, an Encoding module is used to obtain the global context information of the high-resolution feature map, which further improves the pixel classification accuracy. Experiments show that the proposed method is superior to other methods in NEU_SEG (mIoU of 85.27) and MT (mIoU of 77.82) datasets, and has the potential of real-time detection.

Defect Detection of Mechanical Design Products Using Deep Neural Network

In industrial production, defect detection is one of the key methods to control the quality of mechanical design products. Although defect detection algorithms based on traditional machine learning can greatly improve detection efficiency, manual feature extraction is required and the design process is complicated. With the rapid development of CNN, major breakthroughs have been made in computer vision. Therefore, building a surface defect detection algorithm for mechanical design products based on DCNNs plays a very important role in improving industrial production efficiency. This paper studies the surface defect detection algorithm of mechanical products based on deep convolutional neural network, focusing on solving two types of problems: defect recognition and defect segmentation. Aiming at the problem of defect recognition, this paper studies a defect recognition algorithm based on fully convolutional block detection. This algorithm introduces the idea of block detection into the ResNet fully convolutional neural network. While realizing the local discrimination mechanism, it overcomes the shortcomings of the traditional block detection receptive field. Compared with the original ResNet image classification algorithm, this algorithm has stronger generalization ability and detection ability of small defects. Aiming at the problem of defect segmentation, this paper studies a defect segmentation algorithm based on improved Deeplabv3+.

Surface Defect Detection of Vehicle Light Guide Plates Based on an Improved RetinaNet

Aiming at the vehicle navigation light guide plate (LGP) image characteristics, such as complex and gradient texures, uneven brightness, and small defects, this paper proposes a visual inspection method for LGP defects based on an improved RetinaNet. First, we use ResNeXt50 with higher accuracy under the same parameters as the backbone network, and propose the lightweight module Ghost_module to replace the 1×1 convolution in the lower half of the ResNeXt_block. This can reduce the resource parameters and consumption, and speed up training and inference. Second, we propose and use an improved feature pyramid network (IFPN) module to improve the feature fusion network in RetinaNet. It can more effectively fuse the shallow semantic information and high-level semantic information in the backbone feature extraction network, and further improve the detection ability of small target defects. Finally, the defect detection dataset constructed based on the vehicle LGP images collected at a industrial site, and experiments are performed on the vehicle LGP dataset and Aluminum Profile Defect Identification dataset (Aluminum Profile DID). The experimental results show that the proposed method is both efficient and effective. It achieves a better average detection rate of 98.6% on the vehicle LGP dataset. The accuracy and real-time performance can meet the requirements of industrial detection.

YOLOv4-MN3 for PCB Surface Defect Detection

Surface defect detection for printed circuit board (PCB) is indispensable for managing PCB production quality. However, automatic detection of PCB surface defects is still a challenging task because, even within the same category of surface defect, defects present great differences in morphology and pattern. Although many computer vision-based detectors have been established to handle these problems, current detectors struggle to achieve high detection accuracy, fast detection speed and low memory consumption simultaneously. To address those issues, we propose a cost-effective deep learning (DL)-based detector based on the cutting-edge YOLOv4 to detect PCB surface defect quickly and efficiently. The YOLOv4 is improved upon with respect to its backbone network and the activation function in its neck/prediction network. The improved YOLOv4 is evaluated with a customized dataset, collected from a PCB factory. The experimental results show that the improved detector achieved a high performance, scoring 98.64% on mean average precision (mAP) at 56.98 frames per second (FPS), outperforming the other compared SOTA detectors. Furthermore, the improved YOLOv4 reduced the parameter space of YOLOv4 from 63.96 M to 39.59 M and the number of multiply-accumulate operations (Madds) from 59.75 G to 26.15 G.

Transmission line surface defect detection method based on uav autonomous inspection

The existing transmission line surface defect detection methods have the problem of incomplete image data set, resulting in a low recognition success rate. A transmission line surface defect detection method based on uav autonomous inspection is designed. The safety of power grid operation is evaluated, the local linearization process is transformed into linear equation expression, the image data set is obtained by uav autonomous inspection, the transmission line state is judged, the corresponding constraint conditions are set, the type of transmission line surface defects are identified, the number of image poles and towers is matched, and the detection mode is optimized by edge detection algorithm. Experimental results: The average recognition success rate of the transmission line surface defect detection method in this paper and the other two detection methods is 59.89%, 51.89% and 52.03%, proving that the transmission line surface defect detection method integrating UAV technology inspection has a wider application space.