scholarly journals Lychee Surface Defect Detection Based on Deep Convolutional Neural Networks with GAN-Based Data Augmentation

Agronomy ◽  
2021 ◽  
Vol 11 (8) ◽  
pp. 1500
Author(s):  
Chenglong Wang ◽  
Zhifeng Xiao
Keyword(s):  
Defect Detection ◽  
Surface Defect ◽  
Data Augmentation ◽  
Cost Effective ◽  
Deep Convolutional Neural Networks ◽  
Object Boundary ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Original Dataset ◽  
Surface Defect Detection

The performance of fruit surface defect detection is easily affected by factors such as noisy background and foliage occlusion. In this study, we choose lychee as a fruit type to investigate its surface quality. Lychees are hard to preserve and have to be stored at low temperatures to keep fresh. Additionally, the surface of lychees is subject to scratches and cracks during harvesting/processing. To explore the feasibility of the automation of defective surface detection for lychees, we build a dataset with 3743 samples divided into three categories, namely, mature, defects, and rot. The original dataset suffers an imbalanced distribution issue. To address it, we adopt a transformer-based generative adversarial network (GAN) as a means of data augmentation that can effectively enhance the original training set with more and diverse samples to rebalance the three categories. In addition, we investigate three deep convolutional neural network (DCNN) models, including SSD-MobileNet V2, Faster RCNN-ResNet50, and Faster RCNN-Inception-ResNet V2, trained under different settings for an extensive comparison study. The results show that all three models demonstrate consistent performance gains in mean average precision (mAP), with the application of GAN-based augmentation. The rebalanced dataset also reduces the inter-category discrepancy, allowing a DCNN model to be trained equally across categories. In addition, the qualitative results show that models trained under the augmented setting can better identify the critical regions and the object boundary, leading to gains in mAP. Lastly, we conclude that the most cost-effective model, SSD-MobileNet V2, presents a comparable mAP (91.81%) and a superior inference speed (102 FPS), suitable for real-time detection in industrial-level applications.

scholarly journals A Hybrid Capsule Network for Pneumonia Detection Using Image Augmentation Based on Generative Adversarial Network

2021 ◽  
Vol 38 (3) ◽  
pp. 619-627
Author(s):  
Kazim Firildak ◽  
Muhammed Fatih Talu
Keyword(s):  
Classification Accuracy ◽  
Data Augmentation ◽  
Model Parameters ◽  
Classification Problems ◽  
Generative Adversarial Network ◽  
X Ray ◽  
Discrimination Capability ◽  
Adversarial Network ◽  
Original Dataset ◽  
Chest X Ray

Pneumonia, featured by inflammation of the air sacs in one or both lungs, is usually detected by examining chest X-ray images. This paper probes into the classification models that can distinguish between normal and pneumonia images. As is known, trained networks like AlexNet and GoogleNet are deep network architectures, which are widely adopted to solve many classification problems. They have been adapted to the target datasets, and employed to classify new data generated through transfer learning. However, the classical architectures are not accurate enough for the diagnosis of pneumonia. Therefore, this paper designs a capsule network with high discrimination capability, and trains the network on Kaggle’s online pneumonia dataset, which contains chest X-ray images of many adults and children. The original dataset consists of 1,583 normal images, and 4,273 pneumonia images. Then, two data augmentation approaches were applied to the dataset, and their effects on classification accuracy were compared in details. The model parameters were optimized through five different experiments. The results show that the highest classification accuracy (93.91% even on small images) was achieved by the capsule network, coupled with data augmentation by generative adversarial network (GAN), using optimized parameters. This network outperformed the classical strategies.

Evaluation of Data Augmentation on Surface Defect Detection

2021 ◽  
Author(s):  
Isack Farady ◽  
Chih-Yang Lin ◽  
Fityanul Akhyar ◽  
R. Roshini ◽  
John Sahaya Rani Alex
Keyword(s):  
Defect Detection ◽  
Surface Defect ◽  
Data Augmentation ◽  
Surface Defect Detection ◽  
Evaluation Of Data

scholarly journals Deep Metallic Surface Defect Detection: The New Benchmark and Detection Network

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1562 ◽  
Author(s):  
Xiaoming Lv ◽  
Fajie Duan ◽  
Jia-jia Jiang ◽  
Xiao Fu ◽  
Lin Gan
Keyword(s):  
Defect Detection ◽  
Large Scale ◽  
Surface Defect ◽  
Data Augmentation ◽  
Training Data ◽  
Metallic Surface ◽  
Single Shot ◽  
Limited Data ◽  
Detection Model ◽  
Surface Defect Detection

Metallic surface defect detection is an essential and necessary process to control the qualities of industrial products. However, due to the limited data scale and defect categories, existing defect datasets are generally unavailable for the deployment of the detection model. To address this problem, we contribute a new dataset called GC10-DET for large-scale metallic surface defect detection. The GC10-DET dataset has great challenges on defect categories, image number, and data scale. Besides, traditional detection approaches are poor in both efficiency and accuracy for the complex real-world environment. Thus, we also propose a novel end-to-end defect detection network (EDDN) based on the Single Shot MultiBox Detector. The EDDN model can deal with defects with different scales. Furthermore, a hard negative mining method is designed to alleviate the problem of data imbalance, while some data augmentation methods are adopted to enrich the training data for the expensive data collection problem. Finally, the extensive experiments on two datasets demonstrate that the proposed method is robust and can meet accuracy requirements for metallic defect detection.

scholarly journals A deep learning segmentation strategy that minimizes the amount of manually annotated images

F1000Research ◽  
2021 ◽  
Vol 10 ◽  
pp. 256
Author(s):  
Thierry Pécot ◽  
Alexander Alekseyenko ◽  
Kristin Wallace
Keyword(s):  
Deep Learning ◽  
Data Augmentation ◽  
Training Data ◽  
Artificial Data ◽  
Deep Convolutional Neural Networks ◽  
Generative Adversarial Network ◽  
Data Set ◽  
Segmentation Strategy ◽  
Adversarial Network ◽  
The Impact

Deep learning has revolutionized the automatic processing of images. While deep convolutional neural networks have demonstrated astonishing segmentation results for many biological objects acquired with microscopy, this technology's good performance relies on large training datasets. In this paper, we present a strategy to minimize the amount of time spent in manually annotating images for segmentation. It involves using an efficient and open source annotation tool, the artificial increase of the training data set with data augmentation, the creation of an artificial data set with a conditional generative adversarial network and the combination of semantic and instance segmentations. We evaluate the impact of each of these approaches for the segmentation of nuclei in 2D widefield images of human precancerous polyp biopsies in order to define an optimal strategy.

scholarly journals Using Conditional Generative Adversarial Networks to Boost the Performance of Machine Learning in Microbiome Datasets

2020 ◽  
Author(s):  
Derek Reiman ◽  
Yang Dai
Keyword(s):  
Machine Learning ◽  
Data Augmentation ◽  
Side Information ◽  
Generative Adversarial Networks ◽  
Disease Prediction ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Original Dataset ◽  
Microbiome Data

AbstractThe microbiome of the human body has been shown to have profound effects on physiological regulation and disease pathogenesis. However, association analysis based on statistical modeling of microbiome data has continued to be a challenge due to inherent noise, complexity of the data, and high cost of collecting large number of samples. To address this challenge, we employed a deep learning framework to construct a data-driven simulation of microbiome data using a conditional generative adversarial network. Conditional generative adversarial networks train two models against each other while leveraging side information learn from a given dataset to compute larger simulated datasets that are representative of the original dataset. In our study, we used a cohorts of patients with inflammatory bowel disease to show that not only can the generative adversarial network generate samples representative of the original data based on multiple diversity metrics, but also that training machine learning models on the synthetic samples can improve disease prediction through data augmentation. In addition, we also show that the synthetic samples generated by this cohort can boost disease prediction of a different external cohort.

scholarly journals Improving effectiveness of different deep learning-based models for detecting COVID-19 from computed tomography (CT) images

2020 ◽  
Author(s):  
Erdi Acar ◽  
Engin Şahin ◽  
İhsan Yılmaz
Keyword(s):  
Deep Learning ◽  
Data Augmentation ◽  
Patient Treatment ◽  
Learning Models ◽  
Prognostic Role ◽  
Deep Convolutional Neural Networks ◽  
Generative Adversarial Network ◽  
Lung Segmentation ◽  
The Third ◽  
Adversarial Network

AbstractComputerized Tomography (CT) has a prognostic role in the early diagnosis of COVID-19 due to it gives both fast and accurate results. This is very important to help decision making of clinicians for quick isolation and appropriate patient treatment. In this study, we combine methods such as segmentation, data augmentation and the generative adversarial network (GAN) to improve the effectiveness of learning models. We obtain the best performance with 99% accuracy for lung segmentation. Using the above improvements we get the highest rates in terms of accuracy (99.8%), precision (99.8%), recall (99.8%), f1-score (99.8%) and roc acu (99.9979%) with deep learning methods in this paper. Also we compare popular deep learning-based frameworks such as VGG16, VGG19, Xception, ResNet50, ResNet50V2, DenseNet121, DenseNet169, InceptionV3 and InceptionResNetV2 for automatic COVID-19 classification. The DenseNet169 amongst deep convolutional neural networks achieves the best performance with 99.8% accuracy. The second-best learner is InceptionResNetV2 with accuracy of 99.65%. The third-best learner is Xception and InceptionV3 with accuracy of 99.60%.

Sign in / Sign up

Export Citation Format

Share Document