Journal Article10.1007/S12541-019-00074-4
Convolutional Neural Network Based Surface Inspection System for Non-patterned Welding Defects
56
TL;DR: A convolutional neural network based method that inspects non-patterned welding defects on the surface of the engine transmission using a single RGB camera and a class-specific batch sampling method to train the second stage CNN stably is proposed.
read more
Abstract: In this paper, we propose a convolutional neural network (CNN) based method that inspects non-patterned welding defects (craters, pores, foreign substances and fissures) on the surface of the engine transmission using a single RGB camera. The proposed method consists of two steps: first, extracting the welding area to be inspected from the captured image, and then determining whether the extracted area includes defects. In the first step, to extract the welding area from the captured image, a CNN based approach is proposed to detect a center of the engine transmission in the image. In the second stage, the extracted area is identified by another CNN as defective or non-defective. To train the second stage CNN stably, we propose a class-specific batch sampling method. With our sampling method, biased learning caused by data imbalance (number of collected defective images is much less than that of non-defective images) is effectively prevented. We evaluated our system with a large amount of samples (about 32,000 images) collected manually from the production line, and our system shows a remarkable performance in all experiments.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A review on application of artificial neural network (ANN) for performance and emission characteristics of diesel engine fueled with biodiesel-based fuels
Anh Tuan Hoang,Sandro Nižetić,Hwai Chyuan Ong,Wieslaw Tarelko,Van Viet Pham,Tri Hieu Le,Minh Quang Chau,Xuan Phuong Nguyen +7 more
TL;DR: Biodiesel has been emerging as a potential and promising biofuel for the strategy of reducing toxic emissions and improving engine performance, and the development of a novel approach like the ANN model to anticipate engine performance and exhaust emissions with high accuracy was believed to be the best choice.
230
An automatic welding defect location algorithm based on deep learning
TL;DR: Experiments show that the proposed defect location method could acquire the detection precision up to 88.4 % on the public data set (GDXray Set) which shows a remarkable location performance compared with other related detection methods.
111
Convolutional and generative adversarial neural networks in manufacturing
TL;DR: The paper might be helpful in identifying research gaps, inspire machine learning research in new manufacturing domains, contribute to the development of successful neural network architectures, and getting deeper insights into the manufacturing data.
110
A vision-based method for lap weld defects monitoring of galvanized steel sheets using convolutional neural network
TL;DR: In this article, Li et al. developed a method for automatically detecting typical undercuts, pores and burn-through defects from CCD using concepts of Convolutional Neural Network (CNN) and active vision.
64
Defect detection in welding radiographic images based on semantic segmentation methods
TL;DR: In this article , an end-to-end FPN-ResNet-34 semantic segmentation network-based defect detection algorithm is implemented, and the network architecture is experimentally demonstrated to be suitable for defect features extraction and fusion.
61
References
•Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky,Ilya Sutskever,Geoffrey E. Hinton +2 more
- 03 Dec 2012
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
•Proceedings Article
Rectified Linear Units Improve Restricted Boltzmann Machines
Vinod Nair,Geoffrey E. Hinton +1 more
- 21 Jun 2010
TL;DR: Restricted Boltzmann machines were developed using binary stochastic hidden units that learn features that are better for object recognition on the NORB dataset and face verification on the Labeled Faces in the Wild dataset.
Finding circles by an array of accumulators
TL;DR: This procedure is an extension and improvement of the circle-finding concept sketched by Duda and Hart as an extension of the Hough straight-line finder.
667
Defect detection in textured materials using Gabor filters
Ajay Kumar,Grantham K. H. Pang +1 more
- 01 Dec 2000
TL;DR: In this paper, the authors investigated various approaches for automated inspection of textured materials using Gabor wavelet features and proposed a new supervised defect detection approach to detect a class of defects in textile webs.
Deep convolutional neural networks for detection of rail surface defects
Shahrzad Faghih-Roohi,Siamak Hajizadeh,Alfredo Núñez,Robert Babuska,Bart De Schutter +4 more
- 24 Jul 2016
TL;DR: This paper proposes a deep convolutional neural network solution to the analysis of image data for the detection of rail surface defects, and compares the results of different network architectures characterized by different sizes and activation functions.