Defect Detection on Randomly Textured Surfaces by Convolutional Neural Networks

Jung, Shing-Yun; Tsai, Yuan Hui; Chiu, Wei‐Yao; Hu, Jingyan; Sun, Chuen-Tsai

doi:10.1109/aim.2018.8452361

Cited by 29 publications

(18 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It achieves 92% accuracy on the large reflective oil-leak stain, 86% on the large non-reflective oil-leak stain, 89% on the small reflective oil-leak stain and 74% on the small non-reflective oil-leak stain. To further evaluate the H-CNN performance, we compare it with the LBP(local binary pattern) [5], the Sobel [9] and the DNN(deep neural networks) [16]. In the experiment, we make modifications for the three methods shown in Fig.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Surface Defect Detection using Hierarchical Features

Ling

Huang

et al. 2019

2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)

View full text Add to dashboard Cite

In this paper, we propose an instance level hierarchical features based convolution neural network model(H-CNN) for detecting surface defects. The H-CNN uses different convolutional layers' extracted features to generate defect masks. The H-CNN first generates proposal regions. Then, it proposes a fully convolutional neural network to extract different level's convolutional features and detect instance level defects. We applied the H-CNN model in freight train detection system for detecting oil-leaks, and the results demonstrate that the H-CNN can effectively identify and generate defect masks. It achieves 92% accuracy on the large reflective oil-leak stain, 86% on the large non-reflective oil-leak stain, 89% on the small reflective oil-leak stain and 74% on the small non-reflective oilleak stain. Its image process speed is 0.467s per frame.

show abstract

Section: Resultsmentioning

confidence: 99%

“…In recent years, deep learning has been applied in detecting objects [12], including instance level object segmentation [13] and surface defect detection [14]- [16]. Li et al [17] proposed an improved YOLO(you only look once) detection network for real-time steel strip surface defect detection.…”

Section: Introductionmentioning

confidence: 99%

Surface Defect Detection using Hierarchical Features

Ling

Huang

et al. 2019

2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)

View full text Add to dashboard Cite

show abstract

“…Park et al [17] proposed a method for automatic visual inspection of defects on the surface of wood products based on a convolution neural network (CNN), which was an effective algorithm for wood defect detection, but was not put into actual application. Jung et al [18] employed three different architectures of CNN to classify regular wood and four types of defect images. Comparing the performance of the three CNN models, the deep CNN achieved a high classification accuracy of 99.8% for defect detection, but its running speed was slow because the network went deeper.…”

Section: Introductionmentioning

confidence: 99%

Defect Detection of Industry Wood Veneer Based on NAS and Multi-Channel Mask R-CNN

Shi

Zhu

et al. 2020

Sensors

View full text Add to dashboard Cite

Wood veneer defect detection plays a vital role in the wood veneer production industry. Studies on wood veneer defect detection usually focused on detection accuracy for industrial applications but ignored algorithm execution speed; thus, their methods do not meet the required speed of online detection. In this paper, a new detection method is proposed that achieves high accuracy and a suitable speed for online production. Firstly, 2838 wood veneer images were collected using data collection equipment developed in the laboratory and labeled by experienced workers from a wood company. Then, an integrated model, glance multiple channel mask region convolution neural network (R-CNN), was constructed to detect wood veneer defects, which included a glance network and a multiple channel mask R-CNN. Neural network architect search technology was used to automatically construct the glance network with the lowest number of floating-point operations to pick out potential defect images out of numerous original wood veneer images. A genetic algorithm was used to merge the intermediate features extracted by the glance network. Multi-Channel Mask R-CNN was then used to classify and locate the defects. The experimental results show that the proposed method achieves a 98.70% overall classification accuracy and a 95.31% mean average precision, and only 2.5 s was needed to detect a batch of 50 standard images and 50 defective images. Compared with other wood veneer defect detection methods, the proposed method is more accurate and faster.

show abstract

“…In order to solve this problem, researchers have done a lot of work [4][5][6]. In machine vision technology, scratch detection has been addressed mainly in the field of image processing by utilizing an optical microscope under good lighting conditions [7][8][9][10][11][12][13], Convolutional Neural Networks (CNN) [14][15][16], and mathematical morphology [17][18][19][20][21][22].…”

Section: Introductionmentioning

confidence: 99%

“…A deep learning algorithm for surface scratch detection has also been proposed. A SpiralNet framework of a deep learning and optimization method to train the network was proposed for the task of automatic crack detection on highly imbalanced training samples [12]. The algorithm, which automatically detects defects on randomly textured surfaces, was designed by employing three different architectures of convolutional neural networks [13].…”

Section: Introductionmentioning

confidence: 99%

Image-Based Scratch Detection by Fuzzy Clustering and Morphological Features

Tan

Fei

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

Detection of scratch defects on randomly textured surfaces remains challenging due to their unnoticeable visual features. In this paper, an algorithm for piezoelectric ceramic plate surface scratch defects based on the combination of fuzzy c-means clustering and morphological features is proposed. Foreground membership of each gray value is calculated firstly on a reference set of training images by fuzzy c-means clustering and the interpolation method, then an enhanced image is obtained by multiplying the foreground membership function and gray image. The location relationship between regions and the gradient direction of regions is extracted from the binary image of the enhanced image. Based on the morphological features, isolated non-scratched defects are filtered out and the intermittent scratches are merged. Experiments show that the algorithm can be used to detect scratch defects on the surface of a piezoelectric ceramics plate with randomly textured surfaces.

show abstract

Defect Detection on Randomly Textured Surfaces by Convolutional Neural Networks

Cited by 29 publications

References 18 publications

Surface Defect Detection using Hierarchical Features

Surface Defect Detection using Hierarchical Features

Defect Detection of Industry Wood Veneer Based on NAS and Multi-Channel Mask R-CNN

Image-Based Scratch Detection by Fuzzy Clustering and Morphological Features

Contact Info

Product

Resources

About