Computer vision for automatic detection and classification of fabric defect employing deep learning algorithm

Purpose The purpose of this paper is to focus on the design and development of computer-aided fabric defect detection and classification employing advanced learning algorithm. Design/methodology/approach To make a fast and effective classification of fabric defect, the authors have considered a characteristic of texture, namely its colour. A deep convolutional neural network is formed to learn from the training phase of various defect data sets. In the testing phase, the authors have utilised a learning feature for defect classification. Findings The improvement in the defect classification accuracy has been achieved by employing deep learning algorithm. The authors have tested the defect classification accuracy on six different fabric materials and have obtained an average accuracy of 96.55 per cent with 96.4 per cent sensitivity and 0.94 success rate. Practical implications The authors had evaluated the method by using 20 different data sets collected from different raw fabrics. Also, the authors have tested the algorithm in standard data set provided by Ministry of Textile. In the testing task, the authors have obtained an average accuracy of 94.85 per cent, with six defects being successfully recognised by the proposed algorithm. Originality/value The quantitative value of performance index shows the effectiveness of developed classification algorithm. Moreover, the computational time for different fabric processing was presented to verify the computational range of proposed algorithm with the conventional fabric processing techniques. Hence, this proposed computer vision-based fabric defects detection system is used for an accurate defect detection and computer-aided analysis system.

Download Full-text

Classification of Magnetic Tile Surface Defects Based on Efficientnet Network with Attention

Journal of Physics Conference Series ◽

10.1088/1742-6596/2137/1/012062 ◽

2021 ◽

Vol 2137 (1) ◽

pp. 012062

Author(s):

Chengshuai Fan

Keyword(s):

Classification Accuracy ◽

Surface Defects ◽

Learning Algorithm ◽

Complex Surface ◽

Detection Algorithm ◽

Image Features ◽

Low Contrast ◽

Deep Learning Algorithm ◽

Model Size

Abstract The magnetic tile image has the characteristics of uneven illumination, complex surface texture, and low contrast. Aiming at the problem that the traditional defect detection algorithm is difficult to accurately identify the defects, and the deep learning algorithm is difficult to balance the classification accuracy and the size of the speed model, a defect classification algorithm based on attention-based EfficientNet is proposed. The algorithm first enhances the network’s spatial and location information for image features by integrating the Convolutional Block Attention Module, and improves the network’s ability to identify defects. Then, on this basis, Criss-Cross Attention is added to the network, so that the network can better the context information of the horizontal and vertical cross of image features, so that each pixel can finally capture the full image dependency of all pixels. Experimental results show that the algorithm has higher classification accuracy than EfficientNet-B0, reached 99.11%, and has a better balance between accuracy, speed and model size than other classification models.

Download Full-text

Generic Wrapper Based Model using Haralick Features for Silk Fabric Defect Classification

Journal of University of Shanghai for Science and Technology ◽

10.51201/jusst/21/11966 ◽

2021 ◽

Vol 23 (11) ◽

pp. 867-878

Author(s):

Ms. Shweta Loonkar ◽

◽

Dhirendra S. Mishra ◽

Surya S. Durbha ◽

◽

...

Keyword(s):

Defect Detection ◽

Control Unit ◽

Gabor Transform ◽

Defect Classification ◽

Silk Fabric ◽

Fabric Defect ◽

Segmented Images ◽

Wrapper Method ◽

Haralick Features

Quality control unit of fabric industry looks for the effective defect detection methodology. The research is required to be done in this area to develop such solution. Various models based on combination of suitable feature extraction, selection and classification approaches need to be experimented out for the same. This paper attempts to experiment and provide such models mainly based on generic wrapper based selection approaches. Widely used broader range of Haralick features are prominently used for detection and classification of defects in this research. It also attempts to identify the suitability of these features based on segmented images provided as an input. The research has been carried on TILDA Dataset consisting of 800 Silk Fabric Images with eight different defects present on it and each carrying 100 images per defect. Models generated using generic wrapper based approach has also been compared with the Gabor Transforms. Then identification of suitable Haralick Features for particular type of defects has been carried out. In this 68% classification accuracy has been achieved using generic wrapper method and 40 % accuracy has been achieved using Gabor Transform with respect to fourteen Haralick Features and seven types of defects.

Download Full-text

Review for "Smart grid security enhancement by detection and classification of non‐technical losses employing deep learning algorithm"

10.1002/2050-7038.12521/v1/review4 ◽

2020 ◽

Keyword(s):

Deep Learning ◽

Smart Grid ◽

Learning Algorithm ◽

Grid Security ◽

Security Enhancement ◽

Smart Grid Security ◽

Deep Learning Algorithm

Download Full-text

Review for "Smart grid security enhancement by detection and classification of non‐technical losses employing deep learning algorithm"

10.1002/2050-7038.12521/v1/review2 ◽

2020 ◽

Keyword(s):

Deep Learning ◽

Smart Grid ◽

Learning Algorithm ◽

Grid Security ◽

Security Enhancement ◽

Smart Grid Security ◽

Deep Learning Algorithm

Download Full-text

Faculty Opinions recommendation of Classification of the clinical images for benign and malignant cutaneous tumors using a deep learning algorithm.

Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature ◽

10.3410/f.732648119.793554280 ◽

2018 ◽

Author(s):

Christine Ko

Keyword(s):

Deep Learning ◽

Learning Algorithm ◽

Clinical Images ◽

Deep Learning Algorithm

Download Full-text

Automated Detection and Classification of Desmoplastic Reaction at the Colorectal Tumour Front Using Deep Learning

Cancers ◽

10.3390/cancers13071615 ◽

2021 ◽

Vol 13 (7) ◽

pp. 1615

Author(s):

Ines P. Nearchou ◽

Hideki Ueno ◽

Yoshiki Kajiwara ◽

Kate Lillard ◽

Satsuki Mochizuki ◽

...

Keyword(s):

Deep Learning ◽

Learning Algorithm ◽

Prognostic Significance ◽

Stage Ii ◽

Full Cohort ◽

Test Set ◽

Colorectal Tumour ◽

Desmoplastic Reaction ◽

Deep Learning Algorithm

The categorisation of desmoplastic reaction (DR) present at the colorectal cancer (CRC) invasive front into mature, intermediate or immature type has been previously shown to have high prognostic significance. However, the lack of an objective and reproducible assessment methodology for the assessment of DR has been a major hurdle to its clinical translation. In this study, a deep learning algorithm was trained to automatically classify immature DR on haematoxylin and eosin digitised slides of stage II and III CRC cases (n = 41). When assessing the classifier’s performance on a test set of patient samples (n = 40), a Dice score of 0.87 for the segmentation of myxoid stroma was reported. The classifier was then applied to the full cohort of 528 stage II and III CRC cases, which was then divided into a training (n = 396) and a test set (n = 132). Automatically classed DR was shown to have superior prognostic significance over the manually classed DR in both the training and test cohorts. The findings demonstrated that deep learning algorithms could be applied to assist pathologists in the detection and classification of DR in CRC in an objective, standardised and reproducible manner.

Download Full-text

Classification of knitted fabric defect detection using Artificial Neural Networks

2019 International Conference on Advances in Computing and Communication Engineering (ICACCE) ◽

10.1109/icacce46606.2019.9079951 ◽

2019 ◽

Author(s):

Subrata Das ◽

Amitabh Wahi ◽

S. Sundaramurthy ◽

N Thulasiram ◽

S Keerthika

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Defect Detection ◽

Knitted Fabric ◽

Fabric Defect Detection ◽

Fabric Defect ◽

Artificial Neural

Download Full-text

Ensemble Deep Learning for Cervix Image Selection toward Improving Reliability in Automated Cervical Precancer Screening

Diagnostics ◽

10.3390/diagnostics10070451 ◽

2020 ◽

Vol 10 (7) ◽

pp. 451 ◽

Cited By ~ 2

Author(s):

Peng Guo ◽

Zhiyun Xue ◽

Zac Mtema ◽

Karen Yeates ◽

Ophira Ginsburg ◽

...

Keyword(s):

Deep Learning ◽

Learning Algorithm ◽

Binary Classification ◽

Digital Camera ◽

Deep Learning Algorithm ◽

Average Accuracy ◽

Acceptable Quality ◽

Cervical Precancer ◽

One Class Classification ◽

Learning Architectures

Automated Visual Examination (AVE) is a deep learning algorithm that aims to improve the effectiveness of cervical precancer screening, particularly in low- and medium-resource regions. It was trained on data from a large longitudinal study conducted by the National Cancer Institute (NCI) and has been shown to accurately identify cervices with early stages of cervical neoplasia for clinical evaluation and treatment. The algorithm processes images of the uterine cervix taken with a digital camera and alerts the user if the woman is a candidate for further evaluation. This requires that the algorithm be presented with images of the cervix, which is the object of interest, of acceptable quality, i.e., in sharp focus, with good illumination, without shadows or other occlusions, and showing the entire squamo-columnar transformation zone. Our prior work has addressed some of these constraints to help discard images that do not meet these criteria. In this work, we present a novel algorithm that determines that the image contains the cervix to a sufficient extent. Non-cervix or other inadequate images could lead to suboptimal or wrong results. Manual removal of such images is labor intensive and time-consuming, particularly in working with large retrospective collections acquired with inadequate quality control. In this work, we present a novel ensemble deep learning method to identify cervix images and non-cervix images in a smartphone-acquired cervical image dataset. The ensemble method combined the assessment of three deep learning architectures, RetinaNet, Deep SVDD, and a customized CNN (Convolutional Neural Network), each using a different strategy to arrive at its decision, i.e., object detection, one-class classification, and binary classification. We examined the performance of each individual architecture and an ensemble of all three architectures. An average accuracy and F-1 score of 91.6% and 0.890, respectively, were achieved on a separate test dataset consisting of more than 30,000 smartphone-captured images.

Download Full-text