scholarly journals Predicting the Particle Size Distributions of Spherical Particle Sets from Synthetic Images: A Comparison of 9 Classic Image Features

2021 ◽  
Author(s):  
javad Manashti ◽  
Francois Duhaime ◽  
Matthew Toews ◽  
Pouyan Pirnia
Keyword(s):  
Particle Size ◽  
Feature Extraction ◽  
Spherical Particle ◽  
Discrete Element ◽  
Local Binary Patterns ◽  
Extraction Methods ◽  
Size Distributions ◽  
Particle Size Distributions ◽  
Histograms Of Oriented Gradients ◽  
Synthetic Images

The two objectives of this paper were to demonstrate use the of the discrete element method for generating synthetic images of spherical particle configurations, and to compare the performance of 9 classic feature extraction methods for predicting the particle size distributions (PSD) from these images. The discrete element code YADE was used to generate synthetic images of granular materials to build the dataset. Nine feature extraction methods were compared: Haralick features, Histograms of Oriented Gradients, Entropy, Local Binary Patterns, Local Configuration Pattern, Complete Local Binary Patterns, the Fast Fourier transform, Gabor filters, and Discrete Haar Wavelets. The feature extraction methods were used to generate the inputs of neural networks to predict the PSD. The results show that feature extraction methods can predict the percentage passing with a root-mean-square error (RMSE) on the percentage passing as low as 1.7%. CLBP showed the best result for all particle sizes with a RMSE of 3.8 %. Better RMSE were obtained for the finest sieve (2.1%) compared to coarsest sieve (5.2%).

Continuous Particle Size Distributions in a Bubbling Fluidized Bed Using Discrete Element Method

2012 ◽  
Author(s):  
Meire Pereira de Souza Braun ◽  
Alice Jordam Caserta ◽  
Helio Aparecido Navarro
Keyword(s):  
Particle Size ◽  
Discrete Element Method ◽  
Fluidized Bed ◽  
Gas Bubbles ◽  
Discrete Element ◽  
Size Distributions ◽  
Particle Size Distributions ◽  
Bubbling Fluidized Bed ◽  
Continuous Particle ◽  
Element Method

The focus of this paper is to study the behavior of systems with continuous particle size distributions over a gas-solid flow in a bubbling fluidized bed. A lognormal distribution with particle-size range between 800 micrometers and 900 micrometers was used to perform numerical simulations to investigate gas bubbles formation for a polydispersed system. Different drag models were used to predict the bubbles. Species segregation for a binary mixture and a monodispersed system were also studied. Discrete Element Method (DEM) simulations were performed using the source code MFIX (“Multiphase Flow with Interphase eXchanges”) [1] developed at NETL (“National Energy Technology Laboratory”). The bubble size of a single injected bubble depended strongly on gas-particle drag model used. The influence of the gas bubbles in the mixture and segregation was analyzed and discussed. The results were compared with experimental results from the literature and a good agreement were obtained.

scholarly journals Inter-Device Periocular Recognition Under Near-Infrared Light

2016 ◽  
Vol 21 (4) ◽  
pp. 33-44
Author(s):  
Michał Włodarczyk ◽  
Paweł Krotewicz ◽  
Damian Kacperski ◽  
Wojciech Sankowski ◽  
Kamil Grabowski
Keyword(s):  
Feature Extraction ◽  
Near Infrared ◽  
Local Binary Patterns ◽  
Extraction Methods ◽  
Infrared Light ◽  
Scale Invariant ◽  
Histograms Of Oriented Gradients ◽  
Decision Module ◽  
The Impact ◽  
Periocular Recognition

Abstract Periocular biometrics is a relatively new field of research, and only several publications on this topic can be found in the literature. It can become a promising feature that can be used independently or as a complement to other biometrics. In this work, the recognition rates of periocular biometrics on a single acquisition device and inter-device database is verified and the impact of different image sources on the performance of recognition algorithms is investigated. For this purpose a NearInfrared Light database was collected. The database contains images taken by two acquisition devices. In order to test the periocular biometric trait, three feature extraction methods are chosen: Histograms of Oriented Gradients, Local Binary Patterns and Scale Invariant Feature Transform. The fusion of these methods is also proposed and it is tested on inter-device database. The feasibility of applying periocular recognition as an individual decision module for a biometric system is assessed. Experimental results yield Equal Error Rate of 17.65 for right eye using inter-device database of 640 gallery periocular images for each eye side taken from 32 different individuals (20 images per individual for each eye side). These results are obtained by the optimal weighted sum fusion of the three feature extraction methods.

Sign in / Sign up

Export Citation Format

Share Document