A survey on deep learning based face recognition
مروری بر شناخت چهره مبتنی بر یادگیری عمیق-2019
Deep learning, in particular the deep convolutional neural networks, has received increasing interests in face recognition recently, and a number of deep learning methods have been proposed. This paper summarizes about 330 contributions in this area. It reviews major deep learning concepts pertinent to face image analysis and face recognition, and provides a concise overview of studies on specific face recognition problems, such as handling variations in pose, age, illumination, expression, and heterogeneous face matching. A summary of databases used for deep face recognition is given as well. Finally, some open challenges and directions are discussed for future research.
Keywords: Deep learning | Face recognition | Artificial Neural Network | Convolutional Neural Networks | Autoencoder | Generative Adversarial Networks
Deep learning-assisted literature mining for in vitro radiosensitivity data
استخراج ادبیات با کمک یادگیری عمیق برای داده های تابش آزمایشگاهی -2019
Background and purpose: Integrated analysis of existing radiosensitivity data obtained by the goldstandard clonogenic assay has the potential to improve our understanding of cancer cell radioresistance. However, extraction of radiosensitivity data from the literature is highly labor-intensive. To aid in this task, using deep convolutional neural networks (CNNs) and other computer technologies, we developed an analysis pipeline that extracts radiosensitivity data derived from clonogenic assays from the literature. Materials and methods: Three classifiers (C1–3) were developed to identify publications containing radiosensitivity data derived from clonogenic assays. C1 uses Faster Regions CNN with Inception Resnet v2 (fRCNN-IRv2), VGG-16, and Optical Character Recognition (OCR) to identify publications that contain semi-logarithmic graphs showing radiosensitivity data derived from clonogenic assays. C2 uses fRCNN-IRv2 and OCR to identify publications that contain bar graphs showing radiosensitivity data derived from clonogenic assays. C3 is a program that identifies publications containing keywords related to radiosensitivity data derived from clonogenic assays. A program (iSF2) was developed using Mask RCNN and OCR to extract surviving fraction after 2-Gy irradiation (SF2) as assessed by clonogenic assays, presented in semi-logarithmic graphs. The efficacy of C1–3 and iSF2 was tested using seven datasets (1805 and 222 publications in total, respectively). Results: C1–3 yielded sensitivity of 91.2% ± 3.4% and specificity of 90.7% ± 3.6%. iSF2 returned SF2 values that were within 2.9% ± 2.6% of the SF2 values determined by radiation oncologists. Conclusion: Our analysis pipeline is potentially useful to acquire radiosensitivity data derived from clonogenic assays from the literature.
Keywords: Clonogenic assays | Radiosensitivity | Deep learning | Convolutional neural networks | Radiation oncology
Establishing structure-property localization linkages for elastic deformation of three-dimensional high contrast composites using deep learning approaches
ایجاد پیوندهای محلی سازی ساختار و خاصیت برای تغییر شکل الاستیک کامپوزیت های کنتراست بالا سه بعدی با استفاده از روشهای یادگیری عمیق-2019
Data-driven methods are attracting growing attention in the field of materials science. In particular, it is now becoming clear that machine learning approaches offer a unique avenue for successfully mining practically useful process-structure-property (PSP) linkages from a variety of materials data. Most previous efforts in this direction have relied on feature design (i.e., the identification of the salient features of the material microstructure to be included in the PSP linkages). However due to the rich complexity of features in most heterogeneous materials systems, it has been difficult to identify a set of consistent features that are transferable from one material system to another. With flexible architecture and remarkable learning capability, the emergent deep learning approaches offer a new path forward that circumvents the feature design step. In this work, we demonstrate the implementation of a deep learning feature-engineering-free approach to the prediction of the microscale elastic strain field in a given threedimensional voxel-based microstructure of a high-contrast two-phase composite. The results show that deep learning approaches can implicitly learn salient information about local neighborhood details, and significantly outperform state-of-the-art methods.
Keywords: Materials informatics | Convolutional neural networks | Deep learning | Localization | Structure-property linkages
Weld image deep learning-based on-line defects detection using convolutional neural networks for Al alloy in robotic arc welding
تشخیص نقص تصویر جوش تشخیص عمیق مبتنی بر یادگیری عمیق برخط با استفاده از شبکه های عصبی همگرا برای آلیاژ آل در جوش قوس رباتیک-2019
Accurate on-line weld defects detection is still challenging for robotic welding manufacturing due to the complexity of weld defects. This paper studied deep learning–based on-line defects detection for aluminum alloy in robotic arc welding using Convolutional Neural Networks (CNN) and weld images. Firstly, an image acquisition system was developed to simultaneously collect weld images, which can provide more information of the real-time weld images from different angles including top front, top back and back seam. Then, a new CNN classification model with 11 layers based on weld image was designed to identify weld penetration defects. In order to improve the robustness and generalization ability of the CNN model, weld images from different welding current and feeding speed were captured for the CNN model. Based on the actual industry challenges such as the instability of welding arc, the complexity of the welding environment and the random changing of plate gap condition, two kinds of data augmentation including noise adding and image rotation were used to boost the CNN dataset while parameters optimization was carried out. Finally, non-zero pixel method was proposed to quantitatively evaluate and visualize the deep learning features. Furthermore, their physical meaning were clearly explained. Instead of decreasing the interference from arc light as in traditional way, the CNN model has taken full use of those arc lights by combining them in a various way to form the complementary features. Test results shows that the CNN model has better performance than our previous work with the mean classification accuracy of 99.38%. This paper can provide some guidance for on-line detection of manufacturing quality in metal additive manufacturing (AM) and laser welding.
Keywords: Deep learning | Defects detection | Al alloy | Robotic arc welding | Convolutional neural networks | Weld images | Feature visualization
Deep learning based predictive modeling for structure-property linkages
مدل سازی پیش بینی مبتنی بر یادگیری عمیق برای پیوندهای ساختار و ویژگی-2019
Crystal plasticity finite element method (CPFEM) based simulations have been traditionally used for analyses of deformation in metals. However, CPFEM simulations are computationally expensive, especially for problems like fatigue where analyses are based on deformation cycles. Moreover, correlations of structure-property linkages based on homogenization and localization are not easily conceived. In this work deep learning based models have been proposed that are able to predict macroscopic properties based on features extracted from the microstructure with minimal human bias. The model is able to predict property against a given structure within dual phase, isotropic elastic-plastic regime. A systematic approach for finding optimal depth and width of neural network has been identified that reduces the overall development effort. It is observed that in the absence of a large training dataset, performance of a convolutional neural network (CNN) model degrades if too many layers and/or too many neurons are used. The CNN model is able to identify soft and hard regions of microstructures and is able to correlate structure-property relation in forward sense i.e. for homogenization. In this work, it has been demonstrated that human intervention is not needed for feature extraction and selection leading to minimization of researcher’s bias. The drawback of CNN model interpretability is overcome by using Respond-CAM feature visualization.
Keywords: Machine learning | Crystal plasticity | Convolutional neural networks | Micromechanics | Deep learning | ICME
DeepOtsu: Document enhancement and binarization using iterative deep learning
DeepOtsu: تقویت و باینری سازی اسناد با استفاده از یادگیری عمیق تکراری-2019
This paper presents a novel iterative deep learning framework and applies it to document enhancement and binarization. Unlike the traditional methods that predict the binary label of each pixel on the input image, we train the neural network to learn the degradations in document images and produce uniform images of the degraded input images, which in turn allows the network to refine the output iteratively. Two different iterative methods have been studied in this paper: recurrent refinement (RR) that uses the same trained neural network in each iteration for document enhancement and stacked refinement (SR) that uses a stack of different neural networks for iterative output refinement. Given the learned nature of the uniform and enhanced image, the binarization map can be easily obtained through use of a global or local threshold. The experimental results on several public benchmark data sets show that our proposed method provides a new, clean version of the degraded image, one that is suitable for visualization and which shows promising results for binarization using Otsu’s global threshold, based on enhanced images learned iteratively by the neural network.
Keywords: Document enhancement and binarization | Convolutional neural networks | Iterative deep learning | Recurrent refinement
A comparative study of deep learning architectures on melanoma detection
مطالعه تطبیقی معماریهای یادگیری عمیق در تشخیص ملانوما-2019
Melanoma is the most aggressive type of skin cancer, which significantly reduces the life expectancy. Early detection of melanoma can reduce the morbidity and mortality associated with skin cancer. Dermoscopic images acquired by dermoscopic instruments are used in computational analysis for skin cancer detection. However, some image quality limitations such as noises, shadows, artefacts exist that could compromise the robustness of the skin image analysis. Hence, developing an automatic intelligent system for skin cancer diagnosis with accurate detection rate is crucial. In this paper, we evaluate the performance of several state-of-the-art convolutional neural networks in dermoscopic images of skin lesions. Our experiment is conducted on a graphics processing unit (GPU) to speed up the training and deployment process. To enhance the quality of images, we employ different pre-processing steps. We also apply data augmentation methodology such as horizontal and vertical flipping techniques to address the class skewness problem. Both pre-processing and data augmentation could help to improve the final accuracy.
Keywords: Cancer classification | Computational diagnosis | Convolutional neural networks | Deep learning | Melanoma detection
Automated crater detection algorithms from a machine learning perspective in the convolutional neural network era
الگوریتم های تشخیص خودکار دهانه از دیدگاه یادگیری ماشین در دوره شبکه عصبی حلقوی-2019
Convolutional Neural Networks (CNN) offer promising opportunities to automatically glean scientifically relevant information directly from annotated images, without needing to handcraft features for detection. Crater counting started with hand counting hundreds, thousands, or even millions of craters in order to determine the age of geological units on planetary bodies of the solar system. Automated crater detection algorithms have attempted to speed up this process. Previous research has employed computer vision techniques with handcrafted features such as light and shadow patterns, circle finding, or edge detection. This research continues, but now some researchers use techniques like convolutional neural networks that enable the algorithm to develop its own features. As the field of machine learning undergoes exponential growth in terms of paper count and research methods, the crater counting application can benefit from the new research, especially when conducting joint interdisciplinary projects. Despite these advancements, the crater counting community has not yet adopted standard methods for automating the process despite decades of research. This survey enumerates challenges for both planetary geologists and machine learning researchers, looks at the recent automatic crater detection advancements using machine learning techniques (primarily in methods using CNNs), and makes recommendations for the path toward greater automation.
Keywords: Crater detection | Feature extraction | Automation | Machine learning | Convolutional neural networks | Mars
A deep learning model to recognize food contaminating beetle species based on elytra fragments
یک مدل یادگیری عمیق برای تشخیص گونه های سوسک آلوده به مواد غذایی بر اساس قطعات الیترا-2019
Insect pests are often associated with food contamination and public health risks. Accurate and timely speciesspecific identification of pests is a key step to scale impacts, trace back the contamination process and promptly set intervention measures, which usually have serious economic impact. The current procedure involves visual inspection by human analysts of pest fragments recovered from food samples, a time-consuming and error-prone process. Deep Learning models have been widely applied for image recognition, outperforming other machine learning algorithms; however only few studies have applied deep learning for food contamination detection. In this paper, we describe our solution for automatic identification of 15 storage product beetle species frequently detected in food inspection. Our approach is based on a convolutional neural network trained on a dataset of 6900 microscopic images of elytra fragments, obtaining an overall accuracy of 83.8% in cross validation. Notably, the classification performance is obtained without the need of designing and selecting domain specific image features, thus demonstrating the promising prospects of Deep Learning models in detecting food contamination.
Keywords: Food contamination | Beetle species identification | Deep learning | Convolutional neural networks | Transfer learning
Multi-agent microgrid energy management based on deep learning forecaster
مدیریت انرژی میکروگیدر چند عامل مبتنی بر پیشگویی یادگیری عمیق-2019
This paper presents a multi-agent day-ahead microgrid energy management framework. The objective is to minimize energy loss and operation cost of agents, including conventional distributed generators, wind turbines, photovoltaics, demands, battery storage systems, and microgrids aggregator agent. To forecast market prices, wind generation, solar generation, and load demand, a deep learning-based approach is designed based on a combination of convolutional neural networks and gated recurrent unit. Each agent utilizes the designed learning approach and its own historical data to forecast its required parameters/data for scheduling purposes. To preserve the information privacy of agents, the alternating direction method of multipliers (ADMM) is utilized to find the optimal operating point of microgrid distributedly. To enhance the convergence performance of the distributed algorithm, an accelerated ADMM is presented based on the concept of over-relaxation. In the proposed framework, the agents do not need to share with other parties either their historical data for forecasting purposes or commercially sensitive information for scheduling purposes. The proposed framework is tested on a realistic test system. The forecast values obtained by the proposed forecasting method are compared with several other methods and the accelerated distributed algorithm is compared with the standard ADMM and analytical target cascading.
Keywords: Microgrid energy management system | Short-term forecasting | Deep learning | Convolutional neural networks | Gated recurrent unit | Alternating direction method of multipliers