Conditional Generative Adversarial Network for Defect Classification with Class Imbalance

Lu, Yiwei; Liu, Kuan-Liang; Hsu, Chia‐Yu

doi:10.1109/smile45626.2019.8965320

Cited by 14 publications

(12 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because each SurfNetv2 block was implemented by a simple 3 × 3 Convolution block and a Residual-R block, the network architecture of the proposed feature extraction layer is simpler than the general CNN-based backbone models, such as VGG16, ResNet18, etc. According to [ 34 ], stacking more network layers can obtain a better recognition ability. Therefore, we built the proposed feature extraction module by stacking multiple SurfNetv2 blocks so that the network can learn more and better features during the down-sampling process.…”

Section: The Proposed Methodsmentioning

confidence: 99%

“…They introduced a three-level Gaussian pyramid to generate multi-level information of defects, and established three VGG16 [ 33 ] networks to learn the information and predict the final recognition result. Lu et al [ 34 ] used pix2pix GAN to generate more defect images to adjust the data distribution for class imbalance. Then, they used the Dense Convolutional Network (DenseNet) [ 35 ] as the classifier model to obtain a better result of surface defect classification with manipulated data.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

SurfNetv2: An Improved Real-Time SurfNet and Its Applications to Defect Recognition of Calcium Silicate Boards

Tsai

Chen

2020

Sensors

View full text Add to dashboard Cite

This paper presents an improved Convolutional Neural Network (CNN) architecture to recognize surface defects of the Calcium Silicate Board (CSB) using visual image information based on a deep learning approach. The proposed CNN architecture is inspired by the existing SurfNet architecture and is named SurfNetv2, which comprises a feature extraction module and a surface defect recognition module. The output of the system is the recognized defect category on the surface of the CSB. In the collection of the training dataset, we manually captured the defect images presented on the surface of the CSB samples. Then, we divided these defect images into four categories, which are crash, dirty, uneven, and normal. In the training stage, the proposed SurfNetv2 is trained through an end-to-end supervised learning method, so that the CNN model learns how to recognize surface defects of the CSB only through the RGB image information. Experimental results show that the proposed SurfNetv2 outperforms five state-of-the-art methods and achieves a high recognition accuracy of 99.90% and 99.75% in our private CSB dataset and the public Northeastern University (NEU) dataset, respectively. Moreover, the proposed SurfNetv2 model achieves a real-time computing speed of about 199.38 fps when processing images with a resolution of 128 × 128 pixels. Therefore, the proposed CNN model has great potential for real-time automatic surface defect recognition applications.

show abstract

Section: The Proposed Methodsmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

SurfNetv2: An Improved Real-Time SurfNet and Its Applications to Defect Recognition of Calcium Silicate Boards

Tsai

Chen

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…In many real world problem such as emotion classification [188], plant disease classification [189], medical image classification [190], industrial defect classification [191] etc., it is more likely that more than one class exists and needs to be recognized. Multiclass classification have been shown to suffer learning difficulties than binary class classification, because multiclass classification increases the data complexity and intensify the imbalanced distribution [192].…”

Section: Multiclass Imbalancementioning

confidence: 99%

A Survey on Generative Adversarial Networks for imbalance problems in computer vision tasks

Sampath

Maurtua

Martín

et al. 2020

Preprint

View full text Add to dashboard Cite

Any computer vision application development starts off by acquiring images and data, then preprocessing and pattern recognition steps to perform a task. When the acquired images are highly imbalanced and not adequate, the desired task may not be achievable. Unfortunately, the occurrence of imbalance problems in acquired image datasets in certain complex real-world problems such as anomaly detection, emotion recognition, medical image analysis, fraud detection, metallic surface defect detection, disaster prediction, etc., are inevitable. The performance of computer vision algorithms can significantly deteriorate when the training dataset is imbalanced. In recent years, Generative Adversarial Networks (GANs) have gained immense attention by researchers across a variety of application domains due to their capability to model complex real-world image data. It is particularly important that GANs can not only be used to generate synthetic images, but also its fascinating adversarial learning idea showed good potential in restoring balance in imbalanced datasets. In this paper, we examine the most recent developments of GANs based techniques for addressing imbalance problems in image data. The real-world challenges and implementations of synthetic image generation based on GANs are extensively covered in this survey. Our survey first introduces various imbalance problems in computer vision tasks and its existing solutions, and then examine key concepts such as deep generative image models and GANs. After that, we propose a taxonomy to summarize GANs based techniques for addressing imbalance problems in computer vision tasks into three major categories: 1. Image level imbalances in classification, 2. object level imbalances in object detection and 3. pixel level imbalances in segmentation tasks. We elaborate the imbalance problems of each group, and further provide GANs based solutions in each group. Readers will understand how GANs based techniques can handle the problem of imbalances and boost performance of the computer vision algorithms.

show abstract

“…In many real world problems such as emotion classification [190], plant disease classification [191], medical image classification [192], industrial defect classification [193] etc., it is more likely that more than one class exists and needs to be recognized. Multiclass classification has been shown to suffer more learning difficulties than binary class classification, because multiclass classification increases the data complexity and intensifies the imbalanced distribution [194].…”

Section: Multiclass Imbalancementioning

confidence: 99%

A Survey on Generative Adversarial Networks for imbalance problems in computer vision tasks

Sampath

Maurtua

Martín

et al. 2020

Preprint

View full text Add to dashboard Cite

Any computer vision application development starts off by acquiring images and data, then preprocessing and pattern recognition steps to perform a task. When the acquired images are highly imbalanced and not adequate, the desired task may not be achievable. Unfortunately, the occurrence of imbalance problems in acquired image datasets in certain complex real-world problems such as anomaly detection, emotion recognition, medical image analysis, fraud detection, metallic surface defect detection, disaster prediction, etc., are inevitable. The performance of computer vision algorithms can significantly deteriorate when the training dataset is imbalanced. In recent years, Generative Adversarial Networks (GANs) have gained immense attention by researchers across a variety of application domains due to their capability to model complex real-world image data. It is particularly important that GANs can not only be used to generate synthetic images, but also its fascinating adversarial learning idea showed good potential in restoring balance in imbalanced datasets.In this paper, we examine the most recent developments of GANs based techniques for addressing imbalance problems in image data. The real-world challenges and implementations of synthetic image generation based on GANs are extensively covered in this survey. Our survey first introduces various imbalance problems in computer vision tasks and its existing solutions, and then examines key concepts such as deep generative image models and GANs. After that, we propose a taxonomy to summarize GANs based techniques for addressing imbalance problems in computer vision tasks into three major categories: 1. Image level imbalances in classification, 2. object level imbalances in object detection and 3. pixel level imbalances in segmentation tasks. We elaborate the imbalance problems of each group, and provide GANs based solutions in each group. Readers will understand how GANs based techniques can handle the problem of imbalances and boost performance of the computer vision algorithms.

show abstract

Conditional Generative Adversarial Network for Defect Classification with Class Imbalance

Cited by 14 publications

References 5 publications

SurfNetv2: An Improved Real-Time SurfNet and Its Applications to Defect Recognition of Calcium Silicate Boards

SurfNetv2: An Improved Real-Time SurfNet and Its Applications to Defect Recognition of Calcium Silicate Boards

A Survey on Generative Adversarial Networks for imbalance problems in computer vision tasks

A Survey on Generative Adversarial Networks for imbalance problems in computer vision tasks

Contact Info

Product

Resources

About