SymNet: A Simple Symmetric Positive Definite Manifold Deep Learning Method for Image Set Classification

2021 ◽  
pp. 1-15
Author(s):  
Rui Wang ◽  
Xiao-Jun Wu ◽  
Josef Kittler
Keyword(s):  
Deep Learning ◽  
Positive Definite ◽  
Learning Method ◽  
Symmetric Positive Definite ◽  
Image Set Classification ◽  
Image Set

scholarly journals Neighborhood preserving sparse representation based on Nyström method for image set classification on symmetric positive definite matrices

2019 ◽  
Vol 13 ◽  
pp. 174830261987399 ◽  
Author(s):  
Chu Li ◽  
Xiao-Jun Wu
Keyword(s):  
Sparse Representation ◽  
Positive Definite ◽  
Positive Definite Matrices ◽  
Nyström Method ◽  
Nystrom Method ◽  
Symmetric Positive Definite ◽  
Image Set Classification ◽  
Image Set ◽  
Symmetric Positive Definite Matrices ◽  
Kernel Representation

In the field of pattern recognition, using the symmetric positive-definite matrices to represent image set has been widely studied, and sparse representation-based classification algorithm on the symmetric positive-definite matrix manifold has attracted great attention in recent years. However, the existing kernel representation-based classification methods usually use kernel trick with implicit kernel to rewrite the optimization function and will have some problems. To address the problem, a neighborhood preserving explicit kernel representation-based classification-based Nyström method is proposed on symmetric positive-definite manifold by embedding the symmetric positive-definite matrices into a Reproducing Kernel Hilbert Space with an explicit kernel based on Nyström method. Thus, we can take full advantage of kernel space characteristics. Through the experimental results, we demonstrate the better performance of our method in the task of image set classification.

LNTP-MDBN: Big Data Integrated Learning Framework for Heterogeneous Image Set Classification

2019 ◽  
Vol 15 (2) ◽  
pp. 227-236
Author(s):  
D. Franklin Vinod ◽  
V. Vasudevan
Keyword(s):  
Big Data ◽  
Medical Image ◽  
Research Study ◽  
Big Data Analytics ◽  
Learning Framework ◽  
Image Set Classification ◽  
Filtering Technique ◽  
Image Set ◽  
Hidden Patterns ◽  
Global Data

Background: With the explosive growth of global data, the term Big Data describes the enormous size of dataset through the detailed analysis. The big data analytics revealed the hidden patterns and secret correlations among the values. The major challenges in Big data analysis are due to increase of volume, variety, and velocity. The capturing of images with multi-directional views initiates the image set classification which is an attractive research study in the volumetricbased medical image processing. Methods: This paper proposes the Local N-ary Ternary Patterns (LNTP) and Modified Deep Belief Network (MDBN) to alleviate the dimensionality and robustness issues. Initially, the proposed LNTP-MDBN utilizes the filtering technique to identify and remove the dependent and independent noise from the images. Then, the application of smoothening and the normalization techniques on the filtered image improves the intensity of the images. Results: The LNTP-based feature extraction categorizes the heterogeneous images into different categories and extracts the features from each category. Based on the extracted features, the modified DBN classifies the normal and abnormal categories in the image set finally. Conclusion: The comparative analysis of proposed LNTP-MDBN with the existing pattern extraction and DBN learning models regarding classification accuracy and runtime confirms the effectiveness in mining applications.

scholarly journals Siamese Reconstruction Network: Accurate Image Reconstruction from Human Brain Activity by Learning to Compare

2019 ◽  
Vol 9 (22) ◽  
pp. 4749
Author(s):  
Lingyun Jiang ◽  
Kai Qiao ◽  
Linyuan Wang ◽  
Chi Zhang ◽  
Jian Chen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Human Brain ◽  
Brain Activity ◽  
Feature Space ◽  
Training Data ◽  
Reconstruction Method ◽  
Learning Method ◽  
Training Samples ◽  
Visual Reconstruction ◽  
Relationship Of

Decoding human brain activities, especially reconstructing human visual stimuli via functional magnetic resonance imaging (fMRI), has gained increasing attention in recent years. However, the high dimensionality and small quantity of fMRI data impose restrictions on satisfactory reconstruction, especially for the reconstruction method with deep learning requiring huge amounts of labelled samples. When compared with the deep learning method, humans can recognize a new image because our human visual system is naturally capable of extracting features from any object and comparing them. Inspired by this visual mechanism, we introduced the mechanism of comparison into deep learning method to realize better visual reconstruction by making full use of each sample and the relationship of the sample pair by learning to compare. In this way, we proposed a Siamese reconstruction network (SRN) method. By using the SRN, we improved upon the satisfying results on two fMRI recording datasets, providing 72.5% accuracy on the digit dataset and 44.6% accuracy on the character dataset. Essentially, this manner can increase the training data about from n samples to 2n sample pairs, which takes full advantage of the limited quantity of training samples. The SRN learns to converge sample pairs of the same class or disperse sample pairs of different class in feature space.

A Deep Learning Method for Frame Selection in Videos for Structure from Motion Pipelines

2021 ◽  
Author(s):  
Francesco Banterle ◽  
Rui Gong ◽  
Massimiliano Corsini ◽  
Fabio Ganovelli ◽  
Luc Van Gool ◽  
...  
Keyword(s):  
Deep Learning ◽  
Structure From Motion ◽  
Learning Method ◽  
Frame Selection

scholarly journals Integrating Machine/Deep Learning Methods and Filtering Techniques for Reliable Mineral Phase Segmentation of 3D X-ray Computed Tomography Images

Energies ◽  
2021 ◽  
Vol 14 (15) ◽  
pp. 4595
Author(s):  
Parisa Asadi ◽  
Lauren E. Beckingham
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Random Forest ◽  
Ct Images ◽  
Ct Imaging ◽  
Learning Method ◽  
Learning Methods ◽  
X Ray ◽  
Machine Learning Methods ◽  
Filtering Techniques

X-ray CT imaging provides a 3D view of a sample and is a powerful tool for investigating the internal features of porous rock. Reliable phase segmentation in these images is highly necessary but, like any other digital rock imaging technique, is time-consuming, labor-intensive, and subjective. Combining 3D X-ray CT imaging with machine learning methods that can simultaneously consider several extracted features in addition to color attenuation, is a promising and powerful method for reliable phase segmentation. Machine learning-based phase segmentation of X-ray CT images enables faster data collection and interpretation than traditional methods. This study investigates the performance of several filtering techniques with three machine learning methods and a deep learning method to assess the potential for reliable feature extraction and pixel-level phase segmentation of X-ray CT images. Features were first extracted from images using well-known filters and from the second convolutional layer of the pre-trained VGG16 architecture. Then, K-means clustering, Random Forest, and Feed Forward Artificial Neural Network methods, as well as the modified U-Net model, were applied to the extracted input features. The models’ performances were then compared and contrasted to determine the influence of the machine learning method and input features on reliable phase segmentation. The results showed considering more dimensionality has promising results and all classification algorithms result in high accuracy ranging from 0.87 to 0.94. Feature-based Random Forest demonstrated the best performance among the machine learning models, with an accuracy of 0.88 for Mancos and 0.94 for Marcellus. The U-Net model with the linear combination of focal and dice loss also performed well with an accuracy of 0.91 and 0.93 for Mancos and Marcellus, respectively. In general, considering more features provided promising and reliable segmentation results that are valuable for analyzing the composition of dense samples, such as shales, which are significant unconventional reservoirs in oil recovery.

Sign in / Sign up

Export Citation Format

Share Document