Improved faster R-CNN for fabric defect detection based on Gabor filter with Genetic Algorithm optimization

Chen, Mengqi; Yu, Lingjie; Zhi, Chao; Sun, Runjun; Zhu, Shiping; Gao, Zhongyuan; Ke, Zhenxia; Zhu, Mengqiu; Zhang, Yuming

doi:10.1016/j.compind.2021.103551

Cited by 123 publications

(59 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the main contributions of this work is applying a standard Genetic Algorithm (GA) to optimize each CNN layer in the models. The GA layer is used to optimize the weights in the CNN layer, which in turn improves the accuracy of the classification models [25,26,27]. Each model is trained and tested using three different encoding methods, label encoding, one-hot vector encoding, and finally using k-mer encoding.…”

Section: Classification Methodsmentioning

confidence: 99%

“…www.ijacsa.thesai.org 3) CNN-LSTM and CNN-bidirectional LSTM layers: Long Short-Term Memory (LSTM) [11] is an RNN that can learn the long-term dependencies in a sequence. It is used in the prediction and classification of sequences [10,11,26]. It consists of a succession of cells, each of which has three gates: input, output, and forget.…”

Section: ) Convolutional Neural Network (Cnn)mentioning

confidence: 99%

See 1 more Smart Citation

A Deep Learning Approach for Viral DNA Sequence Classification using Genetic Algorithm

El-Tohamy¹,

Maghwary²,

Badr³

2022

IJACSA

View full text Add to dashboard Cite

DNA sequence classification is one of the major challenges in biological data processing. The identification and classification of novel viral genome sequences drastically help in reducing the dangers of a viral outbreak like COVID-19. The more accurate the classification of these viruses, the faster a vaccine can be produced to counter them. Thus, more accurate methods should be utilized to classify the viral DNA. This research proposes a hybrid deep learning model for efficient viral DNA sequence classification. A genetic algorithm (GA) was utilized for weight optimization with Convolutional Neural Networks (CNN) architecture. Furthermore, Long Short-Term Memory (LSTM) as well as Bidirectional CNN-LSTM model architectures are employed. Encoding methods are needed to transform the DNA into numeric format for the proposed model. Three different encoding methods to represent DNA sequences as input to the proposed model were experimented: k-mer, label encoding, and one hot vector encoding. Furthermore, an efficient oversampling method was applied to overcome the imbalanced dataset issues. The performance of the proposed GA optimized CNN hybrid model using label encoding achieved the highest classification accuracy of 94.88% compared with other encoding methods.

show abstract

Section: Classification Methodsmentioning

confidence: 99%

Section: ) Convolutional Neural Network (Cnn)mentioning

confidence: 99%

A Deep Learning Approach for Viral DNA Sequence Classification using Genetic Algorithm

El-Tohamy¹,

Maghwary²,

Badr³

2022

IJACSA

View full text Add to dashboard Cite

show abstract

“…The convolutional neural network is one of the most popular deep learning models. It can realize parallel computing and has high speed and high efficiency characteristics [52,53]. CNN is widely used in medical image analysis, remote sensing image analysis, noise signal analysis, and other fields.…”

Section: Convolutional Neural Network Modelmentioning

confidence: 99%

A Survey of Multi-Focus Image Fusion Methods

Zhou

Zhi

et al. 2022

Applied Sciences

Self Cite

View full text Add to dashboard Cite

As an important branch in the field of image fusion, the multi-focus image fusion technique can effectively solve the problem of optical lens depth of field, making two or more partially focused images fuse into a fully focused image. In this paper, the methods based on boundary segmentation was put forward as a group of image fusion method. Thus, a novel classification method of image fusion algorithms is proposed: transform domain methods, boundary segmentation methods, deep learning methods, and combination fusion methods. In addition, the subjective and objective evaluation standards are listed, and eight common objective evaluation indicators are described in detail. On the basis of lots of literature, this paper compares and summarizes various representative methods. At the end of this paper, some main limitations in current research are discussed, and the future development of multi-focus image fusion is prospected.

show abstract

“…Until now, many different defect detection methods have been developed using image processing and machine learning methods. These methods can be examined in two main groups [1]: traditional image processing methods and convolutional neural networks (CNNs)-based methods. Traditional methods rely on extracting color and texture-based features of the fabric image.…”

Section: Introductionmentioning

confidence: 99%

“…The ability of CNN-based methods to obtain high-level features from fabric images has enabled them to be used extensively in this field. Chen et al [1] developed a defect detection system by using Gabor transform, www.dergipark.gov.tr/tdfd genetic algorithm and CNN architecture. By integrating Gabor kernels into the Faster R-CNN architecture, the feature calculation capability of the CNN architecture has been improved.…”

Section: Introductionmentioning

confidence: 99%

Detecting of Circular Knitting Fabric Defects Using VGG16 Architecture

Hanbay

2022

Türk Doğa Ve Fen Dergisi

View full text Add to dashboard Cite

Although the conventional image processing methods can detect fabric defects, fabric defect detection is an open research problem due to the diversity of defect types. In this paper, the feasibility of VGG16 deep learning architecture for fabric defect detection has been demonstrated. A new fabric defect database is used. The pre-trained model of VGG16 architecture on the new database is built. Thus, the training time of the model is reduced. The experimental results show that the VGG16 model outperforms the traditional Shearlet transform and GLCM methods.

show abstract

Improved faster R-CNN for fabric defect detection based on Gabor filter with Genetic Algorithm optimization

Cited by 123 publications

References 35 publications

A Deep Learning Approach for Viral DNA Sequence Classification using Genetic Algorithm

A Deep Learning Approach for Viral DNA Sequence Classification using Genetic Algorithm

A Survey of Multi-Focus Image Fusion Methods

Detecting of Circular Knitting Fabric Defects Using VGG16 Architecture

Contact Info

Product

Resources

About