Detecting Micro-expression Intensity Changes from Videos Based on Hybrid Deep CNN

2019 ◽  
pp. 387-399 ◽  
Author(s):  
Selvarajah Thuseethan ◽  
Sutharshan Rajasegarar ◽  
John Yearwood
Keyword(s):  
Expression Intensity ◽  
Intensity Changes ◽  
Deep Cnn ◽  
Micro Expression

scholarly journals Boosting of Denoising Effect with Fusion Strategy

2020 ◽  
Vol 10 (11) ◽  
pp. 3857
Author(s):  
Fangjia Yang ◽  
Shaoping Xu ◽  
Chongxi Li
Keyword(s):  
Image Fusion ◽  
State Of The Art ◽  
Latent Image ◽  
Pixel Intensity ◽  
Fusion Strategy ◽  
Adaptive Weight ◽  
Final Weight ◽  
Intensity Changes ◽  
Deep Cnn ◽  
Fusion Framework

Image denoising, a fundamental step in image processing, has been widely studied for several decades. Denoising methods can be classified as internal or external depending on whether they exploit the internal prior or the external noisy-clean image priors to reconstruct a latent image. Typically, these two kinds of methods have their respective merits and demerits. Using a single denoising model to improve existing methods remains a challenge. In this paper, we propose a method for boosting the denoising effect via the image fusion strategy. This study aims to boost the performance of two typical denoising methods, the nonlocally centralized sparse representation (NCSR) and residual learning of deep CNN (DnCNN). These two methods have complementary strengths and can be chosen to represent internal and external denoising methods, respectively. The boosting process is formulated as an adaptive weight-based image fusion problem by preserving the details for the initial denoised images output by the NCSR and the DnCNN. Specifically, we design two kinds of weights to adaptively reflect the influence of the pixel intensity changes and the global gradient of the initial denoised images. A linear combination of these two kinds of weights determines the final weight. The initial denoised images are integrated into the fusion framework to achieve our denoising results. Extensive experiments show that the proposed method significantly outperforms the NCSR and the DnCNN both quantitatively and visually when they are considered as individual methods; similarly, it outperforms several other state-of-the-art denoising methods.

An Empirical Study of Micro-Expression Lie Detection Training

2013 ◽  
Author(s):  
Sarah Lynn Jordan ◽  
D. Brian Wallace ◽  
Saul Kassin ◽  
Maria Hartwig
Keyword(s):  
Empirical Study ◽  
Lie Detection ◽  
Micro Expression

A Tilting Procedure to Enhance Compositional Contrast and Reduce Residual Bragg Contrast in EFTEM Imaging of Planar Interfaces

2000 ◽  
Vol 6 (S2) ◽  
pp. 156-157
Author(s):  
K.T. Moore ◽  
E.A. Stach ◽  
J.M. Howe ◽  
D.C. Elbert ◽  
D.R. Veblen
Keyword(s):  
Electron Scattering ◽  
Planar Interface ◽  
Zone Axis ◽  
Crystalline Material ◽  
Energy Losses ◽  
Inelastic Electron ◽  
Diffraction Contrast ◽  
Background Removal ◽  
Intensity Changes ◽  
Elemental Maps

When acquiring energy-filtered TEM (EFTEM) images of a crystalline material, the detrimental effects of diffraction contrast can often be seen in raw energy-filtered images (EFI) (i.e., pre-edge and post-edge images), jump-ratio images and elemental maps as residual diffraction contrast. Residual diffraction contrast occurs in raw EFI because of plural scattering (i.e., inelastic-elastic and elastic-inelastic electron scattering) and in jump-ratio images and elemental maps because background removal procedures often are unable to completely account for intensity changes due to dynamical effects (elastic scattering) that occur between pre-edge and post-edge images acquired at different energy losses.It is demonstrated in these experiments that, when examining a planar interface, EFTEM images have increased compositional contrast and decreased residual diffraction contrast when the sample is oriented so that the interface is parallel to the electron beam, but not directly on a zone axis.

EczemaNet: A Deep CNN-based Eczema Diseases Classification

2020 ◽  
Author(s):  
Masum Shah Junayed ◽  
Abu Noman Md Sakib ◽  
Nipa Anjum ◽  
Md Baharul Islam ◽  
Afsana Ahsan Jeny
Keyword(s):  
Deep Cnn

scholarly journals Combined deep CNN–LSTM network-based multitasking learning architecture for noninvasive continuous blood pressure estimation using difference in ECG-PPG features

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Da Un Jeong ◽  
Ki Moo Lim
Keyword(s):  
Blood Pressure ◽  
Blood Pressure Measurement ◽  
Patient Specific ◽  
Peak Time ◽  
Simultaneous Prediction ◽  
Deep Cnn ◽  
Pressure Estimation ◽  
The Difference ◽  
Blood Pressure Estimation ◽  
Continuous Blood Pressure

AbstractThe pulse arrival time (PAT), the difference between the R-peak time of electrocardiogram (ECG) signal and the systolic peak of photoplethysmography (PPG) signal, is an indicator that enables noninvasive and continuous blood pressure estimation. However, it is difficult to accurately measure PAT from ECG and PPG signals because they have inconsistent shapes owing to patient-specific physical characteristics, pathological conditions, and movements. Accordingly, complex preprocessing is required to estimate blood pressure based on PAT. In this paper, as an alternative solution, we propose a noninvasive continuous algorithm using the difference between ECG and PPG as a new feature that can include PAT information. The proposed algorithm is a deep CNN–LSTM-based multitasking machine learning model that outputs simultaneous prediction results of systolic (SBP) and diastolic blood pressures (DBP). We used a total of 48 patients on the PhysioNet website by splitting them into 38 patients for training and 10 patients for testing. The prediction accuracies of SBP and DBP were 0.0 ± 1.6 mmHg and 0.2 ± 1.3 mmHg, respectively. Even though the proposed model was assessed with only 10 patients, this result was satisfied with three guidelines, which are the BHS, AAMI, and IEEE standards for blood pressure measurement devices.

Sign in / Sign up

Export Citation Format

Share Document