Neighborhood Preserving Embedding on Grassmann Manifold for Image-set Analysis

2021 ◽  
pp. 108335
Author(s):  
Dong Wei ◽  
Xiaobo Shen ◽  
Quansen Sun ◽  
Xizhan Gao ◽  
Zhenwen Ren
Keyword(s):  
Grassmann Manifold ◽  
Image Set

Supervised Dimensionality Reduction on Grassmannian for Image Set Recognition

2019 ◽  
Vol 31 (1) ◽  
pp. 156-175
Author(s):  
Tianci Liu ◽  
Zelin Shi ◽  
Yunpeng Liu
Keyword(s):  
Visual Recognition ◽  
Grassmann Manifold ◽  
Optimization Techniques ◽  
High Dimensional ◽  
Data Sets ◽  
Great Success ◽  
Unconstrained Optimization Problem ◽  
Natural Geometry ◽  
Image Set ◽  
Matrix Manifolds

Modeling videos and image sets by linear subspaces has achieved great success in various visual recognition tasks. However, subspaces constructed from visual data are always notoriously embedded in a high-dimensional ambient space, which limits the applicability of existing techniques. This letter explores the possibility of proposing a geometry-aware framework for constructing lower-dimensional subspaces with maximum discriminative power from high-dimensional subspaces in the supervised scenario. In particular, we make use of Riemannian geometry and optimization techniques on matrix manifolds to learn an orthogonal projection, which shows that the learning process can be formulated as an unconstrained optimization problem on a Grassmann manifold. With this natural geometry, any metric on the Grassmann manifold can theoretically be used in our model. Experimental evaluations on several data sets show that our approach results in significantly higher accuracy than other state-of-the-art algorithms.

Grassmann manifold for nearest points image set classification

2015 ◽  
Vol 68 ◽  
pp. 190-196 ◽  
Author(s):  
Hengliang Tan ◽  
Zhengming Ma ◽  
Sumin Zhang ◽  
Zengrong Zhan ◽  
Beibei Zhang ◽  
...  
Keyword(s):  
Grassmann Manifold ◽  
Image Set Classification ◽  
Image Set ◽  
Nearest Points

Oral Immune Activation by Disgust and Disease-Related Pictures

2015 ◽  
Vol 29 (3) ◽  
pp. 119-129 ◽  
Author(s):  
Richard J. Stevenson ◽  
Deborah Hodgson ◽  
Megan J. Oaten ◽  
Luba Sominsky ◽  
Mehmet Mahmut ◽  
...  
Keyword(s):  
Immune Response ◽  
Immune Responses ◽  
Innate Immune Response ◽  
Negative Control ◽  
Innate Immune ◽  
Innate Immune Responses ◽  
Immune Markers ◽  
Before And After ◽  
Secondary Analyses ◽  
Image Set

Abstract. Both disgust and disease-related images appear able to induce an innate immune response but it is unclear whether these effects are independent or rely upon a common shared factor (e.g., disgust or disease-related cognitions). In this study we directly compared these two inductions using specifically generated sets of images. One set was disease-related but evoked little disgust, while the other set was disgust evoking but with less disease-relatedness. These two image sets were then compared to a third set, a negative control condition. Using a wholly within-subject design, participants viewed one image set per week, and provided saliva samples, before and after each viewing occasion, which were later analyzed for innate immune markers. We found that both the disease related and disgust images, relative to the negative control images, were not able to generate an innate immune response. However, secondary analyses revealed innate immune responses in participants with greater propensity to feel disgust following exposure to disease-related and disgusting images. These findings suggest that disgust images relatively free of disease-related themes, and disease-related images relatively free of disgust may be suboptimal cues for generating an innate immune response. Not only may this explain why disgust propensity mediates these effects, it may also imply a common pathway.

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 Automatic Detection of Discrimination Actions from Social Images

Electronics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 325
Author(s):  
Zhihao Wu ◽  
Baopeng Zhang ◽  
Tianchen Zhou ◽  
Yan Li ◽  
Jianping Fan
Keyword(s):  
Action Recognition ◽  
State Of The Art ◽  
Automatic Detection ◽  
Experimental Results ◽  
Practical Approach ◽  
Detection And Identification ◽  
Art Methods ◽  
Image Set ◽  
Social Images ◽  
Relationship Identification

In this paper, we developed a practical approach for automatic detection of discrimination actions from social images. Firstly, an image set is established, in which various discrimination actions and relations are manually labeled. To the best of our knowledge, this is the first work to create a dataset for discrimination action recognition and relationship identification. Secondly, a practical approach is developed to achieve automatic detection and identification of discrimination actions and relationships from social images. Thirdly, the task of relationship identification is seamlessly integrated with the task of discrimination action recognition into one single network called the Co-operative Visual Translation Embedding++ network (CVTransE++). We also compared our proposed method with numerous state-of-the-art methods, and our experimental results demonstrated that our proposed methods can significantly outperform state-of-the-art approaches.

Sign in / Sign up

Export Citation Format

Share Document