scholarly journals Deep Learning for Computer Vision: A Brief Review

2018 ◽  
Vol 2018 ◽  
pp. 1-13 ◽  
Author(s):  
Athanasios Voulodimos ◽  
Nikolaos Doulamis ◽  
Anastasios Doulamis ◽  
Eftychios Protopapadakis
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Review Paper ◽  
Machine Learning Techniques ◽  
Future Directions ◽  
Boltzmann Machines ◽  
Learning Techniques ◽  
Previous State ◽  
Human Pose ◽  
Learning Schemes

Over the last years deep learning methods have been shown to outperform previous state-of-the-art machine learning techniques in several fields, with computer vision being one of the most prominent cases. This review paper provides a brief overview of some of the most significant deep learning schemes used in computer vision problems, that is, Convolutional Neural Networks, Deep Boltzmann Machines and Deep Belief Networks, and Stacked Denoising Autoencoders. A brief account of their history, structure, advantages, and limitations is given, followed by a description of their applications in various computer vision tasks, such as object detection, face recognition, action and activity recognition, and human pose estimation. Finally, a brief overview is given of future directions in designing deep learning schemes for computer vision problems and the challenges involved therein.

DeepLearning for Computer Vision Problems

2021 ◽  
pp. 92-109
Author(s):  
Khadidja Zairi
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Machine Learning ◽  
Computer Vision ◽  
Deep Learning ◽  
Machine Learning Techniques ◽  
Nonlinear Transformations ◽  
Learning Techniques ◽  
Large Databases ◽  
Previous State

Deep learning is a combined area between neural network and machine learning. Over the last years, deep learning methods have been shown to outperform previous state-of-the-art machine learning techniques in several fields. With computer vision being one of the most prominent cases, the deep learning methodology applies nonlinear transformations and model abstractions of high levels in large databases. Therefore, an overview of DL methodology is provided along with its major modal principals and its hierarchy, which are presented and compared with the more conventional algorithms. Likewise, its popularity and usefulness in the artificial intelligence world are discussed, and some important techniques that increase DL performance are highlighted.

scholarly journals Application of deep learning algorithms and architectures in the new generation of mobile networks

2021 ◽  
Vol 18 (3) ◽  
pp. 397-426
Author(s):  
Dejan Dasic ◽  
Miljan Vucetic ◽  
Nemanja Ilic ◽  
Milos Stankovic ◽  
Marko Beko
Keyword(s):  
Deep Learning ◽  
Mobile Networks ◽  
Spectrum Management ◽  
Network Control ◽  
Machine Learning Techniques ◽  
Modulation Classification ◽  
Learning Methods ◽  
Future Directions ◽  
Learning Techniques ◽  
New Generation

Operators of modern mobile networks are faced with significant challenges in providing the requested level of service to an ever increasing number of user entities. Advanced machine learning techniques based on deep architectures and appropriate learning methods are recognized as promising ways of tackling the said challenges in many aspects of mobile networks, such as mobile data and mobility analysis, network control, network security and signal processing. Having firstly presented the background of deep learning and related technologies, the paper goes on to present the architectures used for deployment of deep learning in mobile networks. The paper continues with an overview of applications and services related to the new generation of mobile networks that employ deep learning methods. Finally, the paper presents practical use case of modulation classification as implementation of deep learning in an application essential for modern spectrum management. We complete this work by pinpointing future directions for research.

scholarly journals Review on Computer Aided Sewer Pipeline Defect Detection and Condition Assessment

2019 ◽  
Vol 4 (1) ◽  
pp. 10 ◽  
Author(s):  
Saeed Moradi ◽  
Tarek Zayed ◽  
Farzaneh Golkhoo
Keyword(s):  
Computer Vision ◽  
Visual Inspection ◽  
Review Paper ◽  
Condition Assessment ◽  
Machine Learning Techniques ◽  
Future Research ◽  
Infrastructure Management ◽  
Advantages And Disadvantages ◽  
Current State ◽  
Learning Techniques

Physical and operational inspection of sewer pipelines is critical to sustaining an acceptable level of system serviceability. Emerging inspection tools in addition to developments in sensor and lens technologies have facilitated sewer condition assessment and increased the quality and consistency of provided data. Meanwhile, sewer networks are too vast to be adequately investigated manually so the development of innovative computer vision techniques for automation applications has become an interest point of recent studies. This review paper presents the current state of inspection technology practices in sewer pipelines. An overall inspection tool comparison was conducted and the advantages and disadvantages of each method were discussed. This was followed by a comprehensive review of recent studies on visual inspection automation using computer vision and machine learning techniques. Finally, current achievements and limitations of existing automation methods were debated to outline open challenges and future research for both infrastructure management and computer science researchers.

scholarly journals Auto-Colorization of Historical Images Using Deep Convolutional Neural Networks

Mathematics ◽  
2020 ◽  
Vol 8 (12) ◽  
pp. 2258
Author(s):  
Madhab Raj Joshi ◽  
Lewis Nkenyereye ◽  
Gyanendra Prasad Joshi ◽  
S. M. Riazul Islam ◽  
Mohammad Abdullah-Al-Wadud ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
User Study ◽  
Mean Squared Error ◽  
Color Image ◽  
Machine Learning Techniques ◽  
Global Features ◽  
Black And White ◽  
Historical Images ◽  
Learning Techniques

Enhancement of Cultural Heritage such as historical images is very crucial to safeguard the diversity of cultures. Automated colorization of black and white images has been subject to extensive research through computer vision and machine learning techniques. Our research addresses the problem of generating a plausible colored photograph of ancient, historically black, and white images of Nepal using deep learning techniques without direct human intervention. Motivated by the recent success of deep learning techniques in image processing, a feed-forward, deep Convolutional Neural Network (CNN) in combination with Inception- ResnetV2 is being trained by sets of sample images using back-propagation to recognize the pattern in RGB and grayscale values. The trained neural network is then used to predict two a* and b* chroma channels given grayscale, L channel of test images. CNN vividly colorizes images with the help of the fusion layer accounting for local features as well as global features. Two objective functions, namely, Mean Squared Error (MSE) and Peak Signal-to-Noise Ratio (PSNR), are employed for objective quality assessment between the estimated color image and its ground truth. The model is trained on the dataset created by ourselves with 1.2 K historical images comprised of old and ancient photographs of Nepal, each having 256 × 256 resolution. The loss i.e., MSE, PSNR, and accuracy of the model are found to be 6.08%, 34.65 dB, and 75.23%, respectively. Other than presenting the training results, the public acceptance or subjective validation of the generated images is assessed by means of a user study where the model shows 41.71% of naturalness while evaluating colorization results.

scholarly journals Detection and Severity Evaluation of Combined Rail Defects Using Deep Learning

Vibration ◽  
2021 ◽  
Vol 4 (2) ◽  
pp. 341-356
Author(s):  
Jessada Sresakoolchai ◽  
Sakdirat Kaewunruen
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Machine Learning Techniques ◽  
Rolling Stock ◽  
Raw Data ◽  
Learning Techniques ◽  
Combined Defects

Various techniques have been developed to detect railway defects. One of the popular techniques is machine learning. This unprecedented study applies deep learning, which is a branch of machine learning techniques, to detect and evaluate the severity of rail combined defects. The combined defects in the study are settlement and dipped joint. Features used to detect and evaluate the severity of combined defects are axle box accelerations simulated using a verified rolling stock dynamic behavior simulation called D-Track. A total of 1650 simulations are run to generate numerical data. Deep learning techniques used in the study are deep neural network (DNN), convolutional neural network (CNN), and recurrent neural network (RNN). Simulated data are used in two ways: simplified data and raw data. Simplified data are used to develop the DNN model, while raw data are used to develop the CNN and RNN model. For simplified data, features are extracted from raw data, which are the weight of rolling stock, the speed of rolling stock, and three peak and bottom accelerations from two wheels of rolling stock. In total, there are 14 features used as simplified data for developing the DNN model. For raw data, time-domain accelerations are used directly to develop the CNN and RNN models without processing and data extraction. Hyperparameter tuning is performed to ensure that the performance of each model is optimized. Grid search is used for performing hyperparameter tuning. To detect the combined defects, the study proposes two approaches. The first approach uses one model to detect settlement and dipped joint, and the second approach uses two models to detect settlement and dipped joint separately. The results show that the CNN models of both approaches provide the same accuracy of 99%, so one model is good enough to detect settlement and dipped joint. To evaluate the severity of the combined defects, the study applies classification and regression concepts. Classification is used to evaluate the severity by categorizing defects into light, medium, and severe classes, and regression is used to estimate the size of defects. From the study, the CNN model is suitable for evaluating dipped joint severity with an accuracy of 84% and mean absolute error (MAE) of 1.25 mm, and the RNN model is suitable for evaluating settlement severity with an accuracy of 99% and mean absolute error (MAE) of 1.58 mm.

Assessing the Accuracy of Fault Interpretation using Machine Learning Techniques when Risking Faults for CO2 Storage Site Assessment

2021 ◽  
pp. 1-55
Author(s):  
Emma A. H. Michie ◽  
Behzad Alaei ◽  
Alvar Braathen
Keyword(s):  
Deep Learning ◽  
New Technologies ◽  
Co2 Storage ◽  
Fault Reactivation ◽  
Machine Learning Techniques ◽  
Close Similarity ◽  
Storage Site ◽  
Site Assessment ◽  
Learning Techniques ◽  
Fault Interpretation

Generating an accurate model of the subsurface for the purpose of assessing the feasibility of a CO2 storage site is crucial. In particular, how faults are interpreted is likely to influence the predicted capacity and integrity of the reservoir; whether this is through identifying high risk areas along the fault, where fluid is likely to flow across the fault, or by assessing the reactivation potential of the fault with increased pressure, causing fluid to flow up the fault. New technologies allow users to interpret faults effortlessly, and in much quicker time, utilizing methods such as Deep Learning. These Deep Learning techniques use knowledge from Neural Networks to allow end-users to compute areas where faults are likely to occur. Although these new technologies may be attractive due to reduced interpretation time, it is important to understand the inherent uncertainties in their ability to predict accurate fault geometries. Here, we compare Deep Learning fault interpretation versus manual fault interpretation, and can see distinct differences to those faults where significant ambiguity exists due to poor seismic resolution at the fault; we observe an increased irregularity when Deep Learning methods are used over conventional manual interpretation. This can result in significant differences between the resulting analyses, such as fault reactivation potential. Conversely, we observe that well-imaged faults show a close similarity between the resulting fault surfaces when both Deep Learning and manual fault interpretation methods are employed, and hence we also observe a close similarity between any attributes and fault analyses made.

Sign in / Sign up

Export Citation Format

Share Document