Measurement of Nonwoven Surface Roughness With Machine Vision Method Presentation : D. Semnani ICSIP 2009, Amsterdam Isfahan University of Technology.

Slides:



Advertisements
Similar presentations
Applications of one-class classification
Advertisements

A Synthetic Environment to Evaluate Alternative Trip Distribution Models Xin Ye Wen Cheng Xudong Jia Civil Engineering Department California State Polytechnic.
Shapelets Correlated with Surface Normals Produce Surfaces Peter Kovesi School of Computer Science & Software Engineering The University of Western Australia.
Automatic Generation of 3D Machining Surfaces With Tool Compensation
Study of propagative and radiative behavior of printed dielectric structures using the finite difference time domain method (FDTD) Università “La Sapienza”,
Level set based Image Segmentation Hang Xiao Jan12, 2013.
Dror Malka and Zeev Zalevsky
Simulation of Fibrous Scaffold Optimal Distribution by Genetic Algorithm Presentation : D. Semnani ICSIP 2009, Amsterdam Isfahan University of Technology.
Extended Gaussian Images
LING 111 Teaching Demo By Tenghui Zhu Introduction to Edge Detection Image Segmentation.
The Global Digital Elevation Model (GTOPO30) of Great Basin Location: latitude 38  15’ to 42  N, longitude 118  30’ to 115  30’ W Grid size: 925 m.
Aline Jaimes Kreinovich, Vladik PhD. CYBER-ShARE Meeting Nov ‘08
SCANNING PROBE MICROSCOPY By AJHARANI HANSDAH SR NO
Facial feature localization Presented by: Harvest Jang Spring 2002.
Multiple People Detection and Tracking with Occlusion Presenter: Feifei Huo Supervisor: Dr. Emile A. Hendriks Dr. A. H. J. Stijn Oomes Information and.
MESA LAB Two papers in IFAC14 Guimei Zhang MESA LAB MESA (Mechatronics, Embedded Systems and Automation) LAB School of Engineering, University of California,
Challenge the future Delft University of Technology Stochastic FEM for analyzing static and dynamic pull-in of microsystems Stephan Hannot, Clemens.
HASSIP/DFG-SPP1114 Workshop “Recent Progress in Wavelet Analysis and Frame Theory” 1 Detection of Cardboard Faults during the Production Process Nataša.
Measures of Information Hartley defined the first information measure: –H = n log s –n is the length of the message and s is the number of possible values.
Instructor: Dr. G. Bebis Reza Amayeh Fall 2005
Chapter Eleven 11.1 Fabric Geometry 11.2 Fabric cover and cover factor
Detection of anisotropy of friction surface images Zbigniew Rudnicki, dr inż., Marek Mruk, mgr Computer Methods and Systems, XI.2007, Krakow.
Distinguishing Photographic Images and Photorealistic Computer Graphics Using Visual Vocabulary on Local Image Edges Rong Zhang,Rand-Ding Wang, and Tian-Tsong.
Implementing a reliable neuro-classifier
CHE/ME 109 Heat Transfer in Electronics LECTURE 8 – SPECIFIC CONDUCTION MODELS.
Spectral Processing of Point-sampled Geometry
Thermo-elastic properties characterization by photothermal microscopy J.Jumel,F.Taillade and F.Lepoutre Eur. Phys. J. AP 23, Journal Club Presentation.
1 A MONTE CARLO EXPERIMENT In the previous slideshow, we saw that the error term is responsible for the variations of b 2 around its fixed component 
Despeckle Filtering in Medical Ultrasound Imaging
EE513 Audio Signals and Systems Statistical Pattern Classification Kevin D. Donohue Electrical and Computer Engineering University of Kentucky.
Digital Terrain Models by M. Varshosaz
Field Validation and Parametric Study of a Thermal Crack Spacing Model David H. Timm - Auburn University Vaughan R. Voller - University of Minnesota Presented.
Department of Biophysical and Electronic Engineering (DIBE)- Università di Genova- ITALY QUALITY ASSESSMENT OF DESPECKLED SAR IMAGES Elena Angiati, Silvana.
Digital Image Fundamentals Selim Aksoy Department of Computer Engineering Bilkent University
Learning Theory Reza Shadmehr logistic regression, iterative re-weighted least squares.
Status of the compression/transmission electronics for the SDD. Cern, march Torino group, Bologna group.
Online Kinect Handwritten Digit Recognition Based on Dynamic Time Warping and Support Vector Machine Journal of Information & Computational Science, 2015.
Probabilistic & Statistical Techniques Eng. Tamer Eshtawi First Semester Eng. Tamer Eshtawi First Semester
11 Background Error Daryl T. Kleist* National Monsoon Mission Scoping Workshop IITM, Pune, India April 2011.
Random Variables (1) A random variable (also known as a stochastic variable), x, is a quantity such as strength, size, or weight, that depends upon a.
IE 300, Fall 2012 Richard Sowers IESE. 8/30/2012 Goals: Rules of Probability Counting Equally likely Some examples.
Optimization formulation Optimization methods help us find solutions to problems where we seek to find the best of something. This lecture is about how.
Target Tracking In a Scene By Saurabh Mahajan Supervisor Dr. R. Srivastava B.E. Project.
Week 21 Order Statistics The order statistics of a set of random variables X 1, X 2,…, X n are the same random variables arranged in increasing order.
Similarity Measurement and Detection of Video Sequences Chu-Hong HOI Supervisor: Prof. Michael R. LYU Marker: Prof. Yiu Sang MOON 25 April, 2003 Dept.
Performance of Digital Communications System
CSCI 631 – Foundations of Computer Vision March 15, 2016 Ashwini Imran Image Stitching.
Week 21 Statistical Model A statistical model for some data is a set of distributions, one of which corresponds to the true unknown distribution that produced.
0 Assignment 1 (Due: 10/2) Input/Output an image: (i) Design a program to input and output a color image. (ii) Transform the output color image C(R,G,B)
To efficiently explore feasibility of especially size-free weaving of a cotton fabric in a lab- setup. Design and fabricate a prototype Yarn Endurance.
Statistical Methods Michael J. Watts
Statistical Methods Michael J. Watts
Radio Coverage Prediction in Picocell Indoor Networks
Yarn Spinning from Electrospun Nanofibres
Supervised Time Series Pattern Discovery through Local Importance
Outlier Processing via L1-Principal Subspaces
Mathematical Foundations of BME Reza Shadmehr
GAUSSIAN PROCESS REGRESSION WITHIN AN ACTIVE LEARNING SCHEME
An Improved Neural Network Algorithm for Classifying the Transmission Line Faults Slavko Vasilic Dr Mladen Kezunovic Texas A&M University.
September 9 to 13, 2013; Reading, United Kingdom
EE513 Audio Signals and Systems
Department of Electrical Engineering
Lesson 9-5 Similar Solids.
Handwritten Characters Recognition Based on an HMM Model
Midterm Exam Closed book, notes, computer Similar to test 1 in format:
Midterm Exam Closed book, notes, computer Similar to test 1 in format:
Multi-Information Based GCPs Selection Method
Intensity Transformation
Wavelet transform application – edge detection
Graphing: Sine and Cosine
Presentation transcript:

Measurement of Nonwoven Surface Roughness With Machine Vision Method Presentation : D. Semnani ICSIP 2009, Amsterdam Isfahan University of Technology

Image Processing in Textile Engineering ICSIP 2009, Amsterdam Online Quality Control of Textiles Detection Of Yarn And Fabric Faults Classification of Products Measuring Uniformity of Fibrous Structures Determination of Woven And Nonwoven Fabrics Surface Roughness 1/13

Spunbond Nonwovens ICSIP 2009, Amsterdam Application & End Use Importance of Surface Friction 2/13

Measurement of Textile Surface Roughness ICSIP 2009, Amsterdam Conventional Measurement Advice K A W A B A T A E v a l u a t i o n S y s t e m Disadvantages 1/12 3/13

Our Method ICSIP 2009, Amsterdam First :Simulate An Ideal Surface Finite element model of human finger Complete and Regular Sine Roughnesses Minimum Sensible Amplitude and Wave Length 2 :Compare of Simulated Ideal Surface with Samples Surface Profile 3 :Surface Roughness Factor determination 4 :Compare Friction Coefficient With Evaluated Surface Roughness Factor 4/13

Simulating Ideal Surface ICSIP 2009, Amsterdam Mathematically Aspect of an Complete sine Surface Adjust the Confine of Amplitude between 0 to mm Rather Than to mm 5/13

Plotting The Simulated Ideal Surface ICSIP 2009, Amsterdam 6/13

Grayscale Image Sample Properties Image Acquisition of Sample Surfaces Conversion and Processing Image Processing of Sample Surfaces ICSIP 2009, Amsterdam Plotting the Surface Profile Of Samples RGB Image Histogram Equalization Gaussian and Wiener Filtering 7/13

Extracted Parameters From Preprocessed Sample Images and Simulated ideal Surface N : Number of picks in the surface T : Variance of distance between picks from point (0,0) in image matrices E : Volume of surface profile I d : Dispersion ratio (presented by Pourdeyhimi) V : Variance of gray scale values of image ICSIP 2009, Amsterdam 8/13

Definition of Normalized Factors For Compare of Ideal And Sample Surfaces ICSIP 2009, Amsterdam s : index of simulated surface r : index of generated profile from real surface 9/13

And Finally : Definition of Surface Roughness Factor ICSIP 2009, Amsterdam 10/13

Friction Standard Test ASTM D1894 ICSIP 2009, Amsterdam Determination The Surface Friction Coefficient of Samples 11/13

ICSIP 2009, Amsterdam Regression Between Surface Roughness Factor (R s ) and Surface Friction Coefficient of Samples 12/13 μ = R s – R ’ s = R s – New Roughness Factor with effect of friction

Final Conclusion Advantages of This Method Present an appropriate roughness factor which originally implies both elements of roughness : 1.Point by point consideration of surface roughness height compare with line by line height measurement in KES 2. Consideration of fabric surface friction in roughness factor determination ICSIP 2009, Amsterdam

Thanks for your Attention