Filters








124,037 Hits in 4.4 sec

An Introduction to Deep Morphological Networks [article]

Keiller Nogueira and Jocelyn Chanussot and Mauro Dalla Mura and Jefersson A. dos Santos
2021 arXiv   pre-print
Encouraged by this, in this work, we propose a novel network, called Deep Morphological Network (DeepMorphNet), capable of doing non-linear morphological operations while performing the feature learning  ...  The recent impressive results of deep learning-based methods on computer vision applications brought fresh air to the research and industrial community.  ...  • a technique, called Deep Morphological Network (Deep-MorphNet), capable of performing and optimization morphological operations.  ... 
arXiv:1906.01751v2 fatcat:feodzexqtbhmpayxrskgwsygim

An Introduction to Deep Morphological Networks

Keiller Nogueira, Jocelyn Chanussot, Mauro Dalla Mura, Jefersson A. Dos Santos
2021 IEEE Access  
INDEX TERMS Convolutional networks, deep learning, deep morphological networks, mathematical morphology.  ...  Aside from performing the operation, the proposed Deep Morphological Network (DeepMorphNet) is also able to learn the morphological filters (and consequently the features) based on the input data.  ...  The use of depthwise convolution simplifies the introduction of morphological operations into the deep network since the linear combination performed by this convolution does not consider the depth (as  ... 
doi:10.1109/access.2021.3104405 fatcat:pk5razl7srdy3oybnld3atpjtm

Some open questions on morphological operators and representations in the deep learning era [article]

Jesus Angulo
2021 arXiv   pre-print
An expected benefit of such convergence between morphology and deep learning is a cross-fertilization of concepts and techniques between both fields.  ...  Indeed, I firmly believe that the convergence between mathematical morphology and the computation methods which gravitate around deep learning (fully connected networks, convolutional neural networks,  ...  In the field of deep learning, Generative Adversarial Networks (GANs) are an approach to generate images from an illustrative dataset [28, 65] .  ... 
arXiv:2105.01339v2 fatcat:d2k2or6ih5difpwawoot7tty6y

Deep Anomaly Detection via Morphological Transformations

Taehyeon Kim, Yoonsik Choe
2020 Proceedings (MDPI)  
The goal of deep anomaly detection is to identify abnormal data by utilizing a deep neural network trained by a normal training dataset.  ...  Additionally, we present a kernel size loss to enhance the proposed neural networks' morphological feature representation power.  ...  Introduction Deep anomaly detection means verifying abnormal data via a deep neural network trained by normal instances.  ... 
doi:10.3390/asec2020-07887 fatcat:dx2q42s7pngu5lzbxsyhomafeu

Morphology and Interaction of Galaxies using Deep Learning

Fernando Caro, Marc Huertas-Company, Guillermo Cabrera
2016 Proceedings of the International Astronomical Union  
In order to understand how galaxies form and evolve, the measurement of the parameters related to their morphologies and also to the way they interact is one of the most relevant requirements.  ...  We tested Deep Learning using images of galaxies obtained from CANDELS to study the accuracy achieved by this tool considering two different frameworks.  ...  , can be useful to build realistic training sets and that are also big enough to allow an optimal training of any convolutional neural network.  ... 
doi:10.1017/s1743921317000205 fatcat:nig6xix7lje2jjd4t2aq3kj26y

Model Fooling Attacks Against Medical Imaging: A Short Survey

Tuomo Sipola, Samir Puuska, Tero Kokkonen
2020 Information & Security An International Journal  
Acknowledgements This research is partially funded by the Cyber Security Network of Competence Centres for Europe (CyberSec4Europe) project of the Horizon 2020 SU-ICT-03-2018 program.  ...  Introduction Artificial Intelligence (AI) based solutions, especially deep learning based on neural networks, are widely used in the medical domain.  ...  We queried the publicly available Google Scholar database to identify publications relevant to deep neural network fooling, deep neural networks in medical imaging and deep neural networks fooled in that  ... 
doi:10.11610/isij.4615 fatcat:vg5xo6wiwfgk5pnm66d2bfgi5u

Morphological Operation Residual Blocks: Enhancing 3D Morphological Feature Representation in Convolutional Neural Networks for Semantic Segmentation of Medical Images [article]

Chentian Li, Chi Ma, William W. Lu
2021 arXiv   pre-print
As the morphological operation is performed well in hand-crafted image segmentation techniques, it is also promising to design an approach to approximate morphological operation in the convolutional networks  ...  Here, we introduced a 3D morphological operation residual block to extract morphological features in end-to-end deep learning models for semantic segmentation.  ...  morphology of an image [1] .  ... 
arXiv:2103.04026v1 fatcat:uhvqvvcbfncvpgyfhifbjdc2ma

Deep Galaxy: Classification of Galaxies based on Deep Convolutional Neural Networks [article]

Nour Eldeen M. Khalifa, Mohamed Hamed N. Taha, Aboul Ella Hassanien, I. M. Selim
2017 arXiv   pre-print
In this paper, a deep convolutional neural network architecture for galaxies classification is presented.  ...  The proposed deep galaxies architecture consists of 8 layers, one main convolutional layer for features extraction with 96 filters, followed by two principles fully connected layers for classification.  ...  Galaxy: Classification of Galaxies based on Deep Convolutional Neural Networks Used Deep Con- volutional Neu- ral Networks. 97.272 %  ... 
arXiv:1709.02245v1 fatcat:tsxso6536fdmtkpwi5s4sjjzym

Cardiotocographic Diagnosis of Fetal Health based on Multiclass Morphologic Pattern Predictions using Deep Learning Classification

Julia H. Miao, Kathleen H.
2018 International Journal of Advanced Computer Science and Applications  
The testing results showed that the developed deep neural network model achieved an accuracy of 88.02%, a recall of 84.30%, a precision of 85.01%, and an F-score of 0.8508 in average.  ...  The developed model is used to distinguish and classify the presence or absence of multiclass morphologic patterns for outcome predictions of complications during pregnancy.  ...  ACKNOWLEDGMENT The authors would like to thank Dr. Joaquim P. Marques de Sa from the Biomedical Engineering Institute, Porto, Portugal; and Dr. Joao Bernardes and Dr.  ... 
doi:10.14569/ijacsa.2018.090501 fatcat:v7chiqftgbhktlnonzf4fvgrr4

Automating Morphological Profiling with Generic Deep Convolutional Networks [article]

Nick Pawlowski, Juan C Caicedo, Shantanu Singh, Anne E Carpenter, Amos Storkey
2016 bioRxiv   pre-print
We propose to transfer activation features of generic deep convolutional networks to extract features for morphological profiling.  ...  Morphological profiling aims to create signatures of genes, chemicals and diseases from microscopy images. Current approaches use classical computer vision-based segmentation and feature extraction.  ...  Acknowledgements We want to thank Mike Ando (Google, Inc.) for helpful discussions about the use of transfer learning for the domain of morphological profiling.  ... 
doi:10.1101/085118 fatcat:vifx5qckbvhadb427n5chjdvre

Urban Morphological Feature Extraction and Multi-Dimensional Similarity Analysis Based on Deep Learning Approaches

Chenyi Cai, Zifeng Guo, Baizhou Zhang, Xiao Wang, Biao Li, Peng Tang
2021 Sustainability  
A deep convolutional neural network, GoogLeNet, was implemented with the plots' figure–ground images, by quantifying the morphological features into 2048-dimensional feature vectors.  ...  The study of urban morphology contributes to the evolution of cities and sustainable development.  ...  Deep Learning for Morphological Analysis Compared with conventional methods, the advantages of the deep learning method is that it is an end-to-end (e.g., image to segmentation label) process, with the  ... 
doi:10.3390/su13126859 fatcat:dahhvjpu3nhchdmfequyccjqsy

Detection of myocardial ischemia by intracoronary ECG using convolutional neural networks

M R Bigler, C Seiler
2021 European Heart Journal  
Deep learning methods such as convolutional neural networks (CNN) are employed to extract data-derived features and to recognize natural patterns.  ...  The underlying morphology responsible for the network prediction differed between the trained networks but was focused on the ST-segment and the T-wave for myocardial ischemia detection.  ...  Deep learning methods such as convolutional neural networks (CNN) are employed to extract data-derived features and to recognize natural patterns.  ... 
doi:10.1093/eurheartj/ehab724.3049 fatcat:jrjzmhtcnrcazcvyec4vrve4ly

Towards Automatic Recognition of Pure Mixed Stones using Intraoperative Endoscopic Digital Images [article]

Vincent Estrade, Michel Daudon, Emmanuel Richard, Jean-Christophe Bernhard, Franck Bladou, Gregoire Robert, Baudouin Denis de Senneville
2021 arXiv   pre-print
To explain the predictions of the deep neural network model, coarse localisation heat-maps were plotted to pinpoint key areas identified by the network.  ...  A deep convolutional neural network (CNN) was trained to predict the composition of both pure and mixed stones.  ...  To attempt to understand decisions made by a deep neural network in this setting.  ... 
arXiv:2105.10686v1 fatcat:2narsfrogndijo5hno7acqv7ce

On Machine-Learning Morphological Image Operators

Nina S. T. Hirata, George A. Papakostas
2021 Mathematics  
In the last part we focus on recent morphological image operator learning methods that take advantage of deep-learning frameworks.  ...  In this work, we present an overview of this topic, divided in three parts. First, we review and discuss the representation structure of morphological image operators.  ...  The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, or in the decision to publish the results.  ... 
doi:10.3390/math9161854 fatcat:4ltnuorihfbszmszl2zgzsh65i

Image Classification Algorithm for Determining the Light Curve Morphologies of ASAS-SN Eclipsing Binaries [article]

Burak Ulas
2020 arXiv   pre-print
A deep learning algorithm containing the convolutional neural networks is employed on the images to achieve a satisfying classification.  ...  The results show that our algorithm estimates the morphological class of an external input image data with an accuracy value of 92  ...  CONCLUSION We presented a deep learning algorithm using convolutional neural networks to classify the morphological classes of ASAS-SN eclipsing binaries' light curves.  ... 
arXiv:2012.08435v1 fatcat:og64nfgt5ravdkw4qtkdtz5r2a
« Previous Showing results 1 — 15 out of 124,037 results