ASCII Art Classification Model by Transfer Learning and Data Augmentation

In this study, we propose an ASCII art category classification method based on transfer learning and data augmentation. ASCII art is a form of nonverbal expression that visually expresses emotions and intentions. While there are similar expressions such as emoticons and pictograms, most are either represented by a single character or are embedded in the statement as an inline expression. ASCII art is expressed in various styles, including dot art illustration and line art illustration. Basically, ASCII art can represent almost any object, and therefore the category of ASCII art is very diverse. Many existing image classification algorithms use color information; however, since most ASCII art is written in character sets, there is no color information available for categorization. We created an ASCII art category classifier using the grayscale edge image and the ASCII art image transformed from the image as a training image set. We also used VGG16, ResNet-50, Inception v3, and Xception’s pre-trained networks to fine-tune our categorization. As a result of the experiment of fine tuning by VGG16 and data augmentation, an accuracy rate of 80% or more was obtained in the “human” category.

Download Full-text

Deep Learning Technology for Weld Defects Classification Based on Transfer Learning and Activation Features

Advances in Materials Science and Engineering ◽

10.1155/2020/1574350 ◽

2020 ◽

Vol 2020 ◽

pp. 1-16

Author(s):

Chiraz Ajmi ◽

Juan Zapata ◽

Sabra Elferchichi ◽

Abderrahmen Zaafouri ◽

Kaouther Laabidi

Keyword(s):

Deep Learning ◽

Transfer Learning ◽

Data Augmentation ◽

Fine Tuning ◽

Classification Model ◽

Learning Technology ◽

X Ray ◽

Weld Defects ◽

Defects Classification

Weld defects detection using X-ray images is an effective method of nondestructive testing. Conventionally, this work is based on qualified human experts, although it requires their personal intervention for the extraction and classification of heterogeneity. Many approaches have been done using machine learning (ML) and image processing tools to solve those tasks. Although the detection and classification have been enhanced with regard to the problems of low contrast and poor quality, their result is still unsatisfying. Unlike the previous research based on ML, this paper proposes a novel classification method based on deep learning network. In this work, an original approach based on the use of the pretrained network AlexNet architecture aims at the classification of the shortcomings of welds and the increase of the correct recognition in our dataset. Transfer learning is used as methodology with the pretrained AlexNet model. For deep learning applications, a large amount of X-ray images is required, but there are few datasets of pipeline welding defects. For this, we have enhanced our dataset focusing on two types of defects and augmented using data augmentation (random image transformations over data such as translation and reflection). Finally, a fine-tuning technique is applied to classify the welding images and is compared to the deep convolutional activation features (DCFA) and several pretrained DCNN models, namely, VGG-16, VGG-19, ResNet50, ResNet101, and GoogLeNet. The main objective of this work is to explore the capacity of AlexNet and different pretrained architecture with transfer learning for the classification of X-ray images. The accuracy achieved with our model is thoroughly presented. The experimental results obtained on the weld dataset with our proposed model are validated using GDXray database. The results obtained also in the validation test set are compared to the others offered by DCNN models, which show a best performance in less time. This can be seen as evidence of the strength of our proposed classification model.

Download Full-text

Tomato pest classification using deep convolutional neural network with transfer learning, fine tuning and scratch learning

Intelligent Decision Technologies ◽

10.3233/idt-200192 ◽

2021 ◽

pp. 1-10

Author(s):

Gayatri Pattnaik ◽

Vimal K. Shrivastava ◽

K. Parvathi

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Transfer Learning ◽

Data Augmentation ◽

State Of The Art ◽

Deep Convolutional Neural Network ◽

Fine Tuning ◽

Tomato Plants ◽

Random Weights

Pests are major threat to economic growth of a country. Application of pesticide is the easiest way to control the pest infection. However, excessive utilization of pesticide is hazardous to environment. The recent advances in deep learning have paved the way for early detection and improved classification of pest in tomato plants which will benefit the farmers. This paper presents a comprehensive analysis of 11 state-of-the-art deep convolutional neural network (CNN) models with three configurations: transfers learning, fine-tuning and scratch learning. The training in transfer learning and fine tuning initiates from pre-trained weights whereas random weights are used in case of scratch learning. In addition, the concept of data augmentation has been explored to improve the performance. Our dataset consists of 859 tomato pest images from 10 categories. The results demonstrate that the highest classification accuracy of 94.87% has been achieved in the transfer learning approach by DenseNet201 model with data augmentation.

Download Full-text

Combining weakly and strongly supervised learning improves strong supervision in Gleason pattern classification

BMC Medical Imaging ◽

10.1186/s12880-021-00609-0 ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Sebastian Otálora ◽

Niccolò Marini ◽

Henning Müller ◽

Manfredo Atzori

Keyword(s):

Supervised Learning ◽

Transfer Learning ◽

Data Augmentation ◽

Model Performance ◽

Classification Problem ◽

Heterogeneous Data ◽

Fine Tuning ◽

Data Sources ◽

Gleason Pattern ◽

Heterogeneous Data Sources

Abstract Background One challenge to train deep convolutional neural network (CNNs) models with whole slide images (WSIs) is providing the required large number of costly, manually annotated image regions. Strategies to alleviate the scarcity of annotated data include: using transfer learning, data augmentation and training the models with less expensive image-level annotations (weakly-supervised learning). However, it is not clear how to combine the use of transfer learning in a CNN model when different data sources are available for training or how to leverage from the combination of large amounts of weakly annotated images with a set of local region annotations. This paper aims to evaluate CNN training strategies based on transfer learning to leverage the combination of weak and strong annotations in heterogeneous data sources. The trade-off between classification performance and annotation effort is explored by evaluating a CNN that learns from strong labels (region annotations) and is later fine-tuned on a dataset with less expensive weak (image-level) labels. Results As expected, the model performance on strongly annotated data steadily increases as the percentage of strong annotations that are used increases, reaching a performance comparable to pathologists ($$\kappa = 0.691 \pm 0.02$$ κ = 0.691 ± 0.02 ). Nevertheless, the performance sharply decreases when applied for the WSI classification scenario with $$\kappa = 0.307 \pm 0.133$$ κ = 0.307 ± 0.133 . Moreover, it only provides a lower performance regardless of the number of annotations used. The model performance increases when fine-tuning the model for the task of Gleason scoring with the weak WSI labels $$\kappa = 0.528 \pm 0.05$$ κ = 0.528 ± 0.05 . Conclusion Combining weak and strong supervision improves strong supervision in classification of Gleason patterns using tissue microarrays (TMA) and WSI regions. Our results contribute very good strategies for training CNN models combining few annotated data and heterogeneous data sources. The performance increases in the controlled TMA scenario with the number of annotations used to train the model. Nevertheless, the performance is hindered when the trained TMA model is applied directly to the more challenging WSI classification problem. This demonstrates that a good pre-trained model for prostate cancer TMA image classification may lead to the best downstream model if fine-tuned on the WSI target dataset. We have made available the source code repository for reproducing the experiments in the paper: https://github.com/ilmaro8/Digital_Pathology_Transfer_Learning

Download Full-text

A method for cloud detection and opacity classification based on ground based sky imagery

Atmospheric Measurement Techniques ◽

10.5194/amt-5-2881-2012 ◽

2012 ◽

Vol 5 (11) ◽

pp. 2881-2892 ◽

Cited By ~ 76

Author(s):

M. S. Ghonima ◽

B. Urquhart ◽

C. W. Chow ◽

J. E. Shields ◽

A. Cazorla ◽

...

Keyword(s):

Training Image ◽

Classification Model ◽

Cloud Detection ◽

New Classification ◽

Short Term ◽

Clear Sky ◽

Cloud Classification ◽

Image Set ◽

The Difference ◽

Solar Power Forecasting

Abstract. Digital images of the sky obtained using a total sky imager (TSI) are classified pixel by pixel into clear sky, optically thin and optically thick clouds. A new classification algorithm was developed that compares the pixel red-blue ratio (RBR) to the RBR of a clear sky library (CSL) generated from images captured on clear days. The difference, rather than the ratio, between pixel RBR and CSL RBR resulted in more accurate cloud classification. High correlation between TSI image RBR and aerosol optical depth (AOD) measured by an AERONET photometer was observed and motivated the addition of a haze correction factor (HCF) to the classification model to account for variations in AOD. Thresholds for clear and thick clouds were chosen based on a training image set and validated with set of manually annotated images. Misclassifications of clear and thick clouds into the opposite category were less than 1%. Thin clouds were classified with an accuracy of 60%. Accurate cloud detection and opacity classification techniques will improve the accuracy of short-term solar power forecasting.

Download Full-text

A method for cloud detection and opacity classification based on ground based sky imagery

Atmospheric Measurement Techniques Discussions ◽

10.5194/amtd-5-4535-2012 ◽

2012 ◽

Vol 5 (4) ◽

pp. 4535-4569 ◽

Cited By ~ 20

Author(s):

M. S. Ghonima ◽

B. Urquhart ◽

C. W. Chow ◽

J. E. Shields ◽

A. Cazorla ◽

...

Keyword(s):

Training Image ◽

Classification Model ◽

Cloud Detection ◽

New Classification ◽

Short Term ◽

Clear Sky ◽

Cloud Classification ◽

Image Set ◽

The Difference ◽

Solar Power Forecasting

Download Full-text

Transfer learning using AlexNet Convolutional Neural Network for Face Recognition

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.k7776.0991120 ◽

2020 ◽

Vol 9 (11) ◽

pp. 285-294

Keyword(s):

Neural Network ◽

Face Recognition ◽

Transfer Learning ◽

Data Augmentation ◽

Recognition System ◽

Training Data ◽

Fine Tuning ◽

Data Sets ◽

Learning Method ◽

Face Recognition System

This research is aimed to achieve high-precision accuracy and for face recognition system. Convolution Neural Network is one of the Deep Learning approaches and has demonstrated excellent performance in many fields, including image recognition of a large amount of training data (such as ImageNet). In fact, hardware limitations and insufficient training data-sets are the challenges of getting high performance. Therefore, in this work the Deep Transfer Learning method using AlexNet pre-trained CNN is proposed to improve the performance of the face-recognition system even for a smaller number of images. The transfer learning method is used to fine-tuning on the last layer of AlexNet CNN model for new classification tasks. The data augmentation (DA) technique also proposed to minimize the over-fitting problem during Deep transfer learning training and to improve accuracy. The results proved the improvement in over-fitting and in performance after using the data augmentation technique. All the experiments were tested on UTeMFD, GTFD, and CASIA-Face V5 small data-sets. As a result, the proposed system achieved a high accuracy as 100% on UTeMFD, 96.67% on GTFD, and 95.60% on CASIA-Face V5 in less than 0.05 seconds of recognition time.

Download Full-text

Diagnostic Approach for Accurate Diagnosis of COVID-19 Employing Deep Learning and Transfer Learning Techniques through Chest X-ray Images Clinical Data in E-Healthcare

Sensors ◽

10.3390/s21248219 ◽

2021 ◽

Vol 21 (24) ◽

pp. 8219

Author(s):

Amin Ul Haq ◽

Jian Ping Li ◽

Sultan Ahmad ◽

Shakir Khan ◽

Mohammed Ali Alshara ◽

...

Keyword(s):

Transfer Learning ◽

Classification Accuracy ◽

High Performance ◽

Data Augmentation ◽

Early Stage ◽

Accurate Diagnosis ◽

Fine Tuning ◽

Data Set ◽

X Ray ◽

Chest X Ray

COVID-19 is a transferable disease that is also a leading cause of death for a large number of people worldwide. This disease, caused by SARS-CoV-2, spreads very rapidly and quickly affects the respiratory system of the human being. Therefore, it is necessary to diagnosis this disease at the early stage for proper treatment, recovery, and controlling the spread. The automatic diagnosis system is significantly necessary for COVID-19 detection. To diagnose COVID-19 from chest X-ray images, employing artificial intelligence techniques based methods are more effective and could correctly diagnosis it. The existing diagnosis methods of COVID-19 have the problem of lack of accuracy to diagnosis. To handle this problem we have proposed an efficient and accurate diagnosis model for COVID-19. In the proposed method, a two-dimensional Convolutional Neural Network (2DCNN) is designed for COVID-19 recognition employing chest X-ray images. Transfer learning (TL) pre-trained ResNet-50 model weight is transferred to the 2DCNN model to enhanced the training process of the 2DCNN model and fine-tuning with chest X-ray images data for final multi-classification to diagnose COVID-19. In addition, the data augmentation technique transformation (rotation) is used to increase the data set size for effective training of the R2DCNNMC model. The experimental results demonstrated that the proposed (R2DCNNMC) model obtained high accuracy and obtained 98.12% classification accuracy on CRD data set, and 99.45% classification accuracy on CXI data set as compared to baseline methods. This approach has a high performance and could be used for COVID-19 diagnosis in E-Healthcare systems.

Download Full-text

Data Augmentation and Fine-Tuning the Radiography Images to Detect COVID-19 Patients with Pre-trained Network of Transfer Learning

Proceedings of Data Analytics and Management - Lecture Notes on Data Engineering and Communications Technologies ◽

10.1007/978-981-16-6289-8_65 ◽

2022 ◽

pp. 795-808

Author(s):

Birjit Gope ◽

Rachna Kohar

Keyword(s):

Transfer Learning ◽

Data Augmentation ◽

Fine Tuning ◽

Trained Network

Download Full-text

De novo design and bioactivity prediction of SARS-CoV-2 main protease inhibitors using recurrent neural network-based transfer learning

BMC Chemistry ◽

10.1186/s13065-021-00737-2 ◽

2021 ◽

Vol 15 (1) ◽

Author(s):

Marcos V. S. Santana ◽

Floriano P. Silva-Jr

Keyword(s):

Transfer Learning ◽

De Novo ◽

Chemical Space ◽

De Novo Design ◽

Generative Model ◽

Fine Tuning ◽

Classification Model ◽

Learning Platform ◽

Bioactivity Prediction ◽

Main Protease

AbstractThe global pandemic of coronavirus disease (COVID-19) caused by SARS-CoV-2 (severe acute respiratory syndrome coronavirus 2) created a rush to discover drug candidates. Despite the efforts, so far no vaccine or drug has been approved for treatment. Artificial intelligence offers solutions that could accelerate the discovery and optimization of new antivirals, especially in the current scenario dominated by the scarcity of compounds active against SARS-CoV-2. The main protease (Mpro) of SARS-CoV-2 is an attractive target for drug discovery due to the absence in humans and the essential role in viral replication. In this work, we developed a deep learning platform for de novo design of putative inhibitors of SARS-CoV-2 main protease (Mpro). Our methodology consists of 3 main steps: (1) training and validation of general chemistry-based generative model; (2) fine-tuning of the generative model for the chemical space of SARS-CoV- Mpro inhibitors and (3) training of a classifier for bioactivity prediction using transfer learning. The fine-tuned chemical model generated > 90% valid, diverse and novel (not present on the training set) structures. The generated molecules showed a good overlap with Mpro chemical space, displaying similar physicochemical properties and chemical structures. In addition, novel scaffolds were also generated, showing the potential to explore new chemical series. The classification model outperformed the baseline area under the precision-recall curve, showing it can be used for prediction. In addition, the model also outperformed the freely available model Chemprop on an external test set of fragments screened against SARS-CoV-2 Mpro, showing its potential to identify putative antivirals to tackle the COVID-19 pandemic. Finally, among the top-20 predicted hits, we identified nine hits via molecular docking displaying binding poses and interactions similar to experimentally validated inhibitors.

Download Full-text

Breast Infrared Thermography Segmentation Based on Adaptive Tuning of a Fully Convolutional Network

Current Medical Imaging Formerly Current Medical Imaging Reviews ◽

10.2174/1573405615666190503142031 ◽

2020 ◽

Vol 16 (5) ◽

pp. 611-621

Author(s):

Mazhar Basyouni Tayel ◽

Azza Mahmoud Elbagoury

Keyword(s):

Neural Networks ◽

Infrared Thermography ◽

Transfer Learning ◽

Convolutional Neural Networks ◽

Data Augmentation ◽

Semantic Segmentation ◽

Image Features ◽

Fine Tuning ◽

Fully Convolutional Neural Networks ◽

End To End

Background: Accurate segmentation of Breast Infrared Thermography is an important step for early detection of breast pathological changes. Automatic segmentation of Breast Infrared Thermography is a very challenging task, as it is difficult to find an accurate breast contour and extract regions of interest from it. Although several semi-automatic methods have been proposed for segmentation, their performance often depends on hand-crafted image features, as well as preprocessing operations. Objective: In this work, an approach to automatic semantic segmentation of the Breast Infrared Thermography is proposed based on end-to-end fully convolutional neural networks and without any pre or post-processing. Methods: The lack of labeled Breast Infrared Thermography data limits the complete utilization of fully convolutional neural networks. The proposed model overcomes this challenge by applying data augmentation and two-tier transfer learning from bigger datasets combined with adaptive multi-tier fine-tuning before training the fully convolutional neural networks model. Results: Experimental results show that the proposed approach achieves better segmentation results: 97.986% accuracy; 98.36% sensitivity and 97.61% specificity compared to hand-crafted segmentation methods. Conclusion: This work provided an end-to-end automatic semantic segmentation of Breast Infrared Thermography combined with fully convolutional networks, adaptive multi-tier fine-tuning and transfer learning. Also, this work was able to deal with challenges in applying convolutional neural networks on such data and achieving the state-of-the-art accuracy.

Download Full-text