scholarly journals Neural Style Transfer and Geometric Transformations for Data Augmentation on Balinese Carving Recognition using MobileNet

2020 ◽  
Vol 13 (6) ◽  
pp. 349-363
Author(s):  
I Darma ◽  
◽  
Nanik Suciati ◽  
Daniel Siahaan ◽  
◽  
...  
Keyword(s):  
Cultural Heritage ◽  
Data Augmentation ◽  
Recognition Performance ◽  
Training Dataset ◽  
Geometric Transformation ◽  
Style Transfer ◽  
Geometric Transformations ◽  
Feature Extractor ◽  
Improve Accuracy

The preservation of Balinese carving data is a challenge in recognition of Balinese carving. Balinese carvings are a cultural heritage found in traditional buildings in Bali. The collection of Balinese carving images from public images can be a solution for preserving cultural heritage. However, the lousy quality of taking photographs, e.g., skewed shots, can affect the recognition results. Research on the Balinese carving recognition has existed but only recognizes a predetermined image. We proposed a Neural Style Geometric Transformation (NSGT) as a data augmentation technique for Balinese carvings recognition. NSGT is combining Neural Style Transfers and Geometric Transformations for a small dataset solution. This method provides variations in color, lighting, rotation, rescale, zoom, and the size of the training dataset, to improve recognition performance. We use MobileNet as a feature extractor because it has a small number of parameters, which makes it suitable to be applied on mobile devices. Eight scenarios were tested based on image styles and geometric transformations to get the best results. Based on the results, the proposed method can improve accuracy by up to 16.2%.

scholarly journals Evaluation of Data Augmentation Techniques for Facial Expression Recognition Systems

Electronics ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1892
Author(s):  
Simone Porcu ◽  
Alessandro Floris ◽  
Luigi Atzori
Keyword(s):  
Facial Expression ◽  
Facial Expression Recognition ◽  
Data Augmentation ◽  
Generative Adversarial Networks ◽  
Geometric Transformation ◽  
Expression Recognition ◽  
Learning Approaches ◽  
Geometric Transformations ◽  
Augmentation Techniques ◽  
The Impact

Most Facial Expression Recognition (FER) systems rely on machine learning approaches that require large databases for an effective training. As these are not easily available, a good solution is to augment the databases with appropriate data augmentation (DA) techniques, which are typically based on either geometric transformation or oversampling augmentations (e.g., generative adversarial networks (GANs)). However, it is not always easy to understand which DA technique may be more convenient for FER systems because most state-of-the-art experiments use different settings which makes the impact of DA techniques not comparable. To advance in this respect, in this paper, we evaluate and compare the impact of using well-established DA techniques on the emotion recognition accuracy of a FER system based on the well-known VGG16 convolutional neural network (CNN). In particular, we consider both geometric transformations and GAN to increase the amount of training images. We performed cross-database evaluations: training with the "augmented" KDEF database and testing with two different databases (CK+ and ExpW). The best results were obtained combining horizontal reflection, translation and GAN, bringing an accuracy increase of approximately 30%. This outperforms alternative approaches, except for the one technique that could however rely on a quite bigger database.

scholarly journals RAHC_GAN: A Data Augmentation Method for Tomato Leaf Disease Recognition

Symmetry ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 1597
Author(s):  
Hongxia Deng ◽  
Dongsheng Luo ◽  
Zhangwei Chang ◽  
Haifang Li ◽  
Xiaofeng Yang
Keyword(s):  
Data Augmentation ◽  
Recognition Performance ◽  
Tomato Leaf ◽  
Geometric Transformation ◽  
Disease Area ◽  
Data Set ◽  
Multi Scale ◽  
Network Training ◽  
Disease Region ◽  
Leaf Image

Accurate recognition of tomato diseases is of great significance for agricultural production. Sufficient and insufficient training data of supervised recognition neural network training are symmetry problems. A high precision neural network needs a large number of labeled data, and the difficulty of data sample acquisition is the main challenge to improving the performance of disease recognition. [l.]Moreover, the traditional data augmentation based on geometric transformation can obtain less information, and the generalization is not strong. In order to generate leaves with obvious disease feature and improve the performance of disease recognition, this paper analyzes and solves the problem of insufficient training samples in recognition network training, and proposes a new data augmentation method RAHC_GAN based on GAN, which is used to expand data and identify diseases. First, the proposed hidden variable is used to control the size of the disease area continuously, and the residual attention blocks are used to make the generated adversarial network pay more attention to the disease region in the leaf image, besides, a multi-scale discriminator is used to enrich the detailed texture of the generated image. Then, an expanded data set including original training set images and generated images by RAHC_GAN is established, which is used as the input of four kinds classification networks AlexNet, VGGNet, GoogLeNet and ResNet for performance evaluation. Experimental results show that RAHC_GAN can generate leaves with obvious disease feature, and the generated expanded data set can significantly improve the recognition performance of the classifier. After data augmentation, the recognition effect on the four classifiers is increased by 1.8%, 2.2%, 2.7%, and 0.4% respectively, which are higher than the comparison method. At the same time, the impact of expanded data with different ratio on the recognition performance was evaluated, and the method was extended to apple and grape diseased leaves. The proposed data augmentation method can simulate the distribution of tomato leaf diseases and improve the performance of disease recognition, and it may be extended to solve the problem of insufficient data in other plant research tasks.The tomato leaf data augmented by the traditional data augmentation methods based on geometric transformation usually contain less information, and the generalization is not strong. Therefore, a new data augmentation method, RAHC_GAN, based on generative adversarial networks is proposed in this paper, which is used to expand tomato leaf data and identify diseases. In this method, continuous hidden variables are added at the input of the generator, and the purpose is to continuously control the size of the generated disease area and to supplement the intra class information of the same disease. Additionally, the residual attention block is added to the generator to make it pay more attention to the disease region in the leaf image; a multi-scale discriminator is also used to enrich the detailed texture of the generated image and finally generate leaves with obvious disease features. Then, we use the images generated by RAHC_GAN and the original training images to build an expanded data set, which is used to train four kinds of recognition networks, AlexNet, VGGNet, GoogLeNet, and ResNet, and the performance is evaluated through the test set. Experimental results show that RAHC_GAN can generate leaves with obvious disease features, and the generated expanded data set can significantly improve the recognition performance of the classifier. Furthermore, the results of the apple, grape, and corn data set show that RAHC_GAN can also be used as a method to solve the problem of insufficient data in other plant research tasks.

scholarly journals Data Augmentation Method by Applying Color Perturbation of Inverse PSNR and Geometric Transformations for Object Recognition Based on Deep Learning

2020 ◽  
Vol 10 (11) ◽  
pp. 3755
Author(s):  
Eun Kyeong Kim ◽  
Hansoo Lee ◽  
Jin Yong Kim ◽  
Sungshin Kim
Keyword(s):  
Deep Learning ◽  
Object Recognition ◽  
Data Augmentation ◽  
Color Space ◽  
Original Data ◽  
Training Data ◽  
Geometric Transformation ◽  
Geometric Transformations ◽  
Background Elimination ◽  
Deep Learning Network

Deep learning is applied in various manufacturing domains. To train a deep learning network, we must collect a sufficient amount of training data. However, it is difficult to collect image datasets required to train the networks to perform object recognition, especially because target items that are to be classified are generally excluded from existing databases, and the manual collection of images poses certain limitations. Therefore, to overcome the data deficiency that is present in many domains including manufacturing, we propose a method of generating new training images via image pre-processing steps, background elimination, target extraction while maintaining the ratio of the object size in the original image, color perturbation considering the predefined similarity between the original and generated images, geometric transformations, and transfer learning. Specifically, to demonstrate color perturbation and geometric transformations, we compare and analyze the experiments of each color space and each geometric transformation. The experimental results show that the proposed method can effectively augment the original data, correctly classify similar items, and improve the image classification accuracy. In addition, it also demonstrates that the effective data augmentation method is crucial when the amount of training data is small.

scholarly journals The Effectiveness of Image Augmentation in Deep Learning Networks for Detecting COVID-19: A Geometric Transformation Perspective

2021 ◽  
Vol 8 ◽  
Author(s):  
Mohamed Elgendi ◽  
Muhammad Umer Nasir ◽  
Qunfeng Tang ◽  
David Smith ◽  
John-Paul Grenier ◽  
...  
Keyword(s):  
Deep Learning ◽  
Data Augmentation ◽  
Learning Algorithms ◽  
Training Dataset ◽  
Geometric Transformation ◽  
Detection Accuracy ◽  
X Rays ◽  
X Ray ◽  
Testing Dataset ◽  
The Impact

Chest X-ray imaging technology used for the early detection and screening of COVID-19 pneumonia is both accessible worldwide and affordable compared to other non-invasive technologies. Additionally, deep learning methods have recently shown remarkable results in detecting COVID-19 on chest X-rays, making it a promising screening technology for COVID-19. Deep learning relies on a large amount of data to avoid overfitting. While overfitting can result in perfect modeling on the original training dataset, on a new testing dataset it can fail to achieve high accuracy. In the image processing field, an image augmentation step (i.e., adding more training data) is often used to reduce overfitting on the training dataset, and improve prediction accuracy on the testing dataset. In this paper, we examined the impact of geometric augmentations as implemented in several recent publications for detecting COVID-19. We compared the performance of 17 deep learning algorithms with and without different geometric augmentations. We empirically examined the influence of augmentation with respect to detection accuracy, dataset diversity, augmentation methodology, and network size. Contrary to expectation, our results show that the removal of recently used geometrical augmentation steps actually improved the Matthews correlation coefficient (MCC) of 17 models. The MCC without augmentation (MCC = 0.51) outperformed four recent geometrical augmentations (MCC = 0.47 for Data Augmentation 1, MCC = 0.44 for Data Augmentation 2, MCC = 0.48 for Data Augmentation 3, and MCC = 0.49 for Data Augmentation 4). When we retrained a recently published deep learning without augmentation on the same dataset, the detection accuracy significantly increased, with a χMcNemar′s statistic2=163.2 and a p-value of 2.23 × 10−37. This is an interesting finding that may improve current deep learning algorithms using geometrical augmentations for detecting COVID-19. We also provide clinical perspectives on geometric augmentation to consider regarding the development of a robust COVID-19 X-ray-based detector.

scholarly journals Small facial image dataset augmentation using conditional GANs based on incomplete edge feature input

2021 ◽  
Vol 7 ◽  
pp. e760
Author(s):  
Shih-Kai Hung ◽  
John Q. Gan
Keyword(s):  
Data Augmentation ◽  
Image Data ◽  
Training Dataset ◽  
Generative Adversarial Networks ◽  
Facial Image ◽  
Deep Convolutional Neural Networks ◽  
Training Samples ◽  
Translation Methods ◽  
Edge Features

Image data collection and labelling is costly or difficult in many real applications. Generating diverse and controllable images using conditional generative adversarial networks (GANs) for data augmentation from a small dataset is promising but challenging as deep convolutional neural networks need a large training dataset to achieve reasonable performance in general. However, unlabeled and incomplete features (e.g., unintegral edges, simplified lines, hand-drawn sketches, discontinuous geometry shapes, etc.) can be conveniently obtained through pre-processing the training images and can be used for image data augmentation. This paper proposes a conditional GAN framework for facial image augmentation using a very small training dataset and incomplete or modified edge features as conditional input for diversity. The proposed method defines a new domain or space for refining interim images to prevent overfitting caused by using a very small training dataset and enhance the tolerance of distortions caused by incomplete edge features, which effectively improves the quality of facial image augmentation with diversity. Experimental results have shown that the proposed method can generate high-quality images of good diversity when the GANs are trained using very sparse edges and a small number of training samples. Compared to the state-of-the-art edge-to-image translation methods that directly convert sparse edges to images, when using a small training dataset, the proposed conditional GAN framework can generate facial images with desirable diversity and acceptable distortions for dataset augmentation and significantly outperform the existing methods in terms of the quality of synthesised images, evaluated by Fréchet Inception Distance (FID) and Kernel Inception Distance (KID) scores.

scholarly journals GPR B-Scan Image Denoising via Multi-Scale Convolutional Autoencoder with Data Augmentation

Electronics ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 1269
Author(s):  
Jiabin Luo ◽  
Wentai Lei ◽  
Feifei Hou ◽  
Chenghao Wang ◽  
Qiang Ren ◽  
...  
Keyword(s):  
Image Denoising ◽  
Data Augmentation ◽  
Noise Suppression ◽  
Random Noise ◽  
Similarity Index ◽  
Structural Similarity ◽  
Training Dataset ◽  
Generative Adversarial Network ◽  
Multi Scale ◽  
Convolutional Autoencoder

Ground-penetrating radar (GPR), as a non-invasive instrument, has been widely used in civil engineering. In GPR B-scan images, there may exist random noise due to the influence of the environment and equipment hardware, which complicates the interpretability of the useful information. Many methods have been proposed to eliminate or suppress the random noise. However, the existing methods have an unsatisfactory denoising effect when the image is severely contaminated by random noise. This paper proposes a multi-scale convolutional autoencoder (MCAE) to denoise GPR data. At the same time, to solve the problem of training dataset insufficiency, we designed the data augmentation strategy, Wasserstein generative adversarial network (WGAN), to increase the training dataset of MCAE. Experimental results conducted on both simulated, generated, and field datasets demonstrated that the proposed scheme has promising performance for image denoising. In terms of three indexes: the peak signal-to-noise ratio (PSNR), the time cost, and the structural similarity index (SSIM), the proposed scheme can achieve better performance of random noise suppression compared with the state-of-the-art competing methods (e.g., CAE, BM3D, WNNM).

scholarly journals Military Barracks as Cultural Heritage in Italy: A Comparison between before-1900- and 1900-to-1950-Built Barracks

2021 ◽  
Vol 13 (2) ◽  
pp. 782
Author(s):  
Federico Camerin ◽  
Nicola Camatti ◽  
Francesco Gastaldi
Keyword(s):  
Cultural Heritage ◽  
Local Development ◽  
Cultural Economic ◽  
Italian Case ◽  
Depth Analysis ◽  
International Good ◽  
The Cold War ◽  
The Military ◽  
Military Barracks

This paper addresses the fundamental role that cultural heritage can play in local development processes to guarantee community wellbeing, quality of life, and quality of society. The enhancement of cultural heritage’s tangible and intangible values may result in sustainable and resilient territory, but a number of issues emerge when dealing with the reuse of specific inherited assets, such as former military barracks. This paper conducts an in-depth analysis of these assets, especially those released from the military after the end of the Cold War. We thus explore the Italian case through the comparison of before-1900 and 1900-to-1950 former military barracks. The objectives are the following. First, to discover how these two types of military sites are approached (or no) as proper heritage. Second, to understand how the reuse management is carrying out and how it deals with conservative and profit-driven approaches towards the achievement of cultural, economic, environmental, and social sustainability. Third, to compare the Italian case with similar international good practices to discover common/different trends and innovative solutions to be applied in Italy.

scholarly journals The Influence of Interpretation through Guiding Tour, Quality of Reception and Relics’ Worship on the Satisfaction of Pilgrims Attending the Iasi Feast

2021 ◽  
Vol 13 (12) ◽  
pp. 6905
Author(s):  
Maria Tătărușanu ◽  
Gina Ionela Butnaru ◽  
Valentin Niță ◽  
Angelica-Nicoleta Neculăesei ◽  
Elena Ciortescu
Keyword(s):  
Cultural Heritage ◽  
Cultural Tourism ◽  
Heritage Preservation ◽  
Beneficial Effects ◽  
Religious Tourism ◽  
Guided Tours ◽  
The Relationship ◽  
Heritage Interpretation ◽  
Cultural Heritage Preservation

Recently, in line with the increased attention paid to cultural tourism in general and to religious tourism in particular, researchers and practitioners have become increasingly interested in the analysis of various aspects related to cultural heritage in order to capitalize on its value by means of its interpretation, thus providing beneficial effects both for tourists and for tourism’s sustainable development. The aim of this research is to analyze the extent to which the methods of interpretation of the religious cultural heritage: guiding tours, quality reception, and relic worship influence the satisfaction of tourists participating in the “Saint Parascheva” pilgrimage, held annually by the Metropolitan Cathedral in Iasi. The data were collected by means of a survey (N = 932) and the information was processed by using the SPSS version 25 program. Our results indicate the significant influence that the potential to worship relics has on pilgrims’ satisfaction compared to other interpretation methods, such as the relationship with the Cathedral’s staff or the possibility of participating in guided tours. Pilgrims’ satisfaction is also perceived differently depending on certain aspects of their socio-demographic profile, i.e., their age and the perceived faith level. This study is relevant for researchers, managers, and students interested in the field of cultural heritage interpretation in genera, and in the field of religious heritage in particular, and could significantly contribute to improving pilgrims’ satisfaction as well as cultural heritage preservation.

scholarly journals Data Augmentation-Assisted Makeup-Invariant Face Recognition

2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Muhammad Sajid ◽  
Nouman Ali ◽  
Saadat Hanif Dar ◽  
Naeem Iqbal Ratyal ◽  
Asif Raza Butt ◽  
...  
Keyword(s):  
Face Recognition ◽  
Data Augmentation ◽  
Recognition Performance ◽  
Recognition Task ◽  
Face Images ◽  
Face Features ◽  
Face Datasets ◽  
Exponential Rates ◽  
Interpersonal Situations

Recently, face datasets containing celebrities photos with facial makeup are growing at exponential rates, making their recognition very challenging. Existing face recognition methods rely on feature extraction and reference reranking to improve the performance. However face images with facial makeup carry inherent ambiguity due to artificial colors, shading, contouring, and varying skin tones, making recognition task more difficult. The problem becomes more confound as the makeup alters the bilateral size and symmetry of the certain face components such as eyes and lips affecting the distinctiveness of faces. The ambiguity becomes even worse when different days bring different facial makeup for celebrities owing to the context of interpersonal situations and current societal makeup trends. To cope with these artificial effects, we propose to use a deep convolutional neural network (dCNN) using augmented face dataset to extract discriminative features from face images containing synthetic makeup variations. The augmented dataset containing original face images and those with synthetic make up variations allows dCNN to learn face features in a variety of facial makeup. We also evaluate the role of partial and full makeup in face images to improve the recognition performance. The experimental results on two challenging face datasets show that the proposed approach can compete with the state of the art.

Sign in / Sign up

Export Citation Format

Share Document