Glossary of Technical Terms Correlation filter: a set of carefully designed correlation templates with regard to shift invariance as well as distortion-

Slides:



Advertisements
Similar presentations
QR Code Recognition Based On Image Processing
Advertisements

Object Specific Compressed Sensing by minimizing a weighted L2-norm A. Mahalanobis.
Image Enhancement in the Frequency Domain (2)
for image processing and computer vision
On the Dimensionality of Face Space Marsha Meytlis and Lawrence Sirovich IEEE Transactions on PAMI, JULY 2007.
Facial feature localization Presented by: Harvest Jang Spring 2002.
Sreya Chakraborty Under the guidance of Dr. K. R. Rao Multimedia Processing Lab (MPL) University of Texas at Arlington.
Chapter 1: Introduction to Pattern Recognition
HMM-BASED PATTERN DETECTION. Outline  Markov Process  Hidden Markov Models Elements Basic Problems Evaluation Optimization Training Implementation 2-D.
Image Enhancement in the Frequency Domain Part I Image Enhancement in the Frequency Domain Part I Dr. Samir H. Abdul-Jauwad Electrical Engineering Department.
Detecting Image Region Duplication Using SIFT Features March 16, ICASSP 2010 Dallas, TX Xunyu Pan and Siwei Lyu Computer Science Department University.
Detection of Weld Defects in Rails by Ultrasonic Software Statistical and algorithmic ultrasonic software techniques are used in the analysis of ultrasonic.
Some Properties of the 2-D Fourier Transform Translation Distributivity and Scaling Rotation Periodicity and Conjugate Symmetry Separability Convolution.
On Signal Reconstruction from Fourier Magnitude Gil Michael Department of Electrical Engineering Technion - Israel Institute of Technology Haifa 32000,
Methods of Image Compression by PHL Transform Dziech, Andrzej Slusarczyk, Przemyslaw Tibken, Bernd Journal of Intelligent and Robotic Systems Volume: 39,
Feature extraction Feature extraction involves finding features of the segmented image. Usually performed on a binary image produced from.
Face Recognition Using Neural Networks Presented By: Hadis Mohseni Leila Taghavi Atefeh Mirsafian.
VEHICLE NUMBER PLATE RECOGNITION SYSTEM. Information and constraints Character recognition using moments. Character recognition using OCR. Signature.
 C. C. Hung, H. Ijaz, E. Jung, and B.-C. Kuo # School of Computing and Software Engineering Southern Polytechnic State University, Marietta, Georgia USA.
Project Description The memristor was proposed in 1971 by Leon Chua [1] on the basis of symmetry using the classical relationships describing resistance,
Kansas State University Department of Computing and Information Sciences CIS 830: Advanced Topics in Artificial Intelligence From Data Mining To Knowledge.
MULTITEMP 2005 – Biloxi, Mississippi, USA, May 16-18, 2005 Remote Sensing Laboratory Dept. of Information and Communication Technology University of Trento.
TELECOMMUNICATIONS Dr. Hugh Blanton ENTC 4307/ENTC 5307.
DOOR ENTRY SYSTEM Alina Dinca László Papp Adrian Ulges Csaba Domokos Cercel Constantin Team:
Wireless Communication Technologies 1 Outline Introduction OFDM Basics Performance sensitivity for imperfect circuit Timing and.
REVISED CONTEXTUAL LRT FOR VOICE ACTIVITY DETECTION Javier Ram’ırez, Jos’e C. Segura and J.M. G’orriz Dept. of Signal Theory Networking and Communications.
Methods in Gravitational Shear Measurements Michael Stefferson Mentor: Elliott Cheu Arizona Space Grant Consortium Statewide Symposium Tucson, Arizona.
MRI registration Using the phase correlation method Author: Robin Kramer.
1 BIEN425 – Lecture 8 By the end of the lecture, you should be able to: –Compute cross- /auto-correlation using matrix multiplication –Compute cross- /auto-correlation.
Image Restoration using Iterative Wiener Filter --- ECE533 Project Report Jing Liu, Yan Wu.
Chapter 21 R(x) Algorithm a) Anomaly Detection b) Matched Filter.
BARCODE IDENTIFICATION BY USING WAVELET BASED ENERGY Soundararajan Ezekiel, Gary Greenwood, David Pazzaglia Computer Science Department Indiana University.
Glossary of Technical Terms Cellular Automata: A regular array of identical finite state automata whose next state is determined solely by their current.
Implementing GIST on the GPU. Refrence Original Work  Aude Oliva, Antonio Torralba  Modeling the shape of the scene: a holistic representation of the.
Wideband Radar Simulator for Evaluation of Direction-of-Arrival Processing Sean M. Holloway Center for the Remote Sensing of Ice Sheets, University of.
Templates, Image Pyramids, and Filter Banks
Voice Activity Detection based on OptimallyWeighted Combination of Multiple Features Yusuke Kida and Tatsuya Kawahara School of Informatics, Kyoto University,
3D Face Recognition Using Range Images
Digital Watermarking Using Phase Dispersion --- Update SIMG 786 Advanced Digital Image Processing Mahdi Nezamabadi, Chengmeng Liu, Michael Su.
Beamformer dimensionality ScalarVector Features1 optimal source orientation selected per location. Wrong orientation choice may lead to missed sources.
Computer Science Department, Duke UniversityPhD Defense TalkMay 4, 2005 FAST PATTERN MATCHING IN 3D IMAGES ON GPUS Patrick Eibl, Dennis Healy, Nikos P.
1 An Efficient Classification Approach Based on Grid Code Transformation and Mask-Matching Method Presenter: Yo-Ping Huang.
Spectrum Sensing In Cognitive Radio Networks
LIGO-G Z The Q Pipeline search for gravitational-wave bursts with LIGO Shourov K. Chatterji for the LIGO Scientific Collaboration APS Meeting.
Objects localization and recognition
MultiModality Registration Using Hilbert-Schmidt Estimators By: Srinivas Peddi Computer Integrated Surgery II April 6 th, 2001.
Comparison of Image Registration Methods David Grimm Joseph Handfield Mahnaz Mohammadi Yushan Zhu March 18, 2004.
Outline Carrier design Embedding and extraction for single tile and Multi-tiles (improving the robustness) Parameter α selection and invisibility Moment.
What is Digital Image processing?. An image can be defined as a two-dimensional function, f(x,y) # x and y are spatial (plane) coordinates # The function.
Performance Measurement of Image Processing Algorithms By Dr. Rajeev Srivastava ITBHU, Varanasi.
Detection of nerves in Ultrasound Images using edge detection techniques NIRANJAN TALLAPALLY.
Doc.: IEEE /0034r1 May 2007 Slide 1Submission Huawei Technologies Simulation Results for Spectral Correlation Sensing with Real DTV Signals IEEE.
DETECTION OF COPY MOVE FORGERY IN DIGITAL IMAGES.
Feature Matching and Signal Recognition using Wavelet Analysis Dr. Robert Barsanti, Edwin Spencer, James Cares, Lucas Parobek.
An Adaptive Face-recognition Method Based On Phase Information Presented By:- Suvendu Kumar Dash Department of Electronics and Communication Engineering.
Date of download: 7/2/2016 Copyright © 2016 SPIE. All rights reserved. Illustration of quantities in Eq. : Ath is the ratio of the striped area under the.
Peter Tummeltshammer, Martin Delvai
OCR Reading.
The Q Pipeline search for gravitational-wave bursts with LIGO
Transfer Learning in Astronomy: A New Machine Learning Paradigm
Advanced Wireless Networks
Watermarking with Side Information
Object Recognition in the Dynamic Link Architecture
朝陽科技大學 資訊工程系 謝政勳 Application of GM(1,1) Model to Speech Enhancement and Voice Activity Detection 朝陽科技大學 資訊工程系 謝政勳
Digital Image Processing Week IV
Whitening-Rotation Based MIMO Channel Estimation
Non-negative Matrix Factorization (NMF)
Title of your poster Project Description Scientific Challenges
Geology 491 Spectral Analysis
Presenter: Shih-Hsiang(士翔)
Presentation transcript:

Glossary of Technical Terms Correlation filter: a set of carefully designed correlation templates with regard to shift invariance as well as distortion- tolerance. Fast Fourier Transform (FFT): efficient method to transform spatial correlation into a Fourier-domain element-by-element multiplication. Cross-correlation: the two-dimensional spatial correlation for the large matrices. Project Description Motivation: Recognition of spectral patterns through the utilization of an optical correlator. Previous Works: Correlation filters have been utilized with some success in automatic target recognition (ATR) applications. [1] Reason: To develop a model for improved target recognition that factors in prior knowledge of target IR signature. Goal: Evaluation of the MACH (Maximum Average Correlation Height) filter for ATR and aim point analysis. Scientific Challenges Strike a balance between robustness (with respect to noise) and simplicity in order to be realizable in the real world. Closing rate of an intercept is (> 4 km/sec). Correlation filters are designed (with respect to target class, aspect angle, etc.) to provide the optimal (i.e., the most invariant response) of the filter with respect to the target image. Potential Applications Target recognition; facial feature recognition; mammography (breast tumor detection) Recognition of Spectral Patterns Team Member: Victoria Hahn Example Representative Tank Imagery Model Set Up Methodology 1.Calculate correlation surface: cross-correlate image and each correlation filter [1]: where:, represents the correlation image, represents the k th pre-processed image. The symbol represents the two-dimensional spatial correlation. Moreover, represents the filter coefficients in the spatial domain. 1.Specifically, the “Fast Fourier Transform” correlation (i.e., FFT) is employed to transform a spatial correlation into a Fourier-domain, element-by-element multiplication. where: the variables for target class are specified as c. The aspect angle is represented by the variable . The function, (  ), computes the two dimensional Fast Fourier Transform of its argument; the function, (  ) computes its inverse. The symbol (  ) denotes an element-by- element multiplication. is the k th pre-processed image, and H * is the selected filter. 3.A post-processing function, Peak-to-Sidelobe Ratio (PSR), must be applied to the correlation surface to judge the relative strengths of the correlation peaks. The PSR surface is then searched for the maximum value. where: peak is a peak response in the correlation surface; μ is the mean response local to the peak; and σ is the standard deviation local to the peak. Results 1.Simulation was performed and the the results of how the target aim point error is affected was graphed. 2.It was found that the target aim point error was similarly affected. Specifically, consistent with the original model, the aim point error is quite good through a -6 SNR. [2] References 1.Mahalanobis, A. “Improving the False Alarm Capabilities of Composite Correlation Filters” Proc. of SPIE Vol Mahalanobis, A. et al “Utilization of Optical Correlator for Automatic Target Recognition” Proc. of SPIE Vol Acknowledgments This project was mentored by Dr. Gabitov, whose help is acknowledged with great appreciation. Support from a University of Arizona TRIF (Technology Research Initiative Fund) grant to J. Lega is also gratefully acknowledged. Figure 1 shows the results of the target aim point error. As shown, the aim point error is quite good through a SNR of -6 dB. Input Noise (SNR) Aimpoint Errort Article Results Input Noise (SNR) Simulation Results Aimpoint Errort Figure 2 shows the results of the simulation for the project extension; a bipolar threshold condition was examined in the algorithm to permit the option to detect targets that are colder (i.e., minimum value), in which case, the absolute value of the minimum value was computed.