ECE 484 Digital Image Processing Lec 17 - Part II Review & Final Projects Topics

Similar documents
Image Analysis & Retrieval. CS/EE 5590 Special Topics (Class Ids: 44873, 44874) Fall 2016, M/W Lec 13

Dimension Reduction CS534

Image Analysis & Retrieval. CS/EE 5590 Special Topics (Class Ids: 44873, 44874) Fall 2016, M/W Lec 18.

Data Mining Chapter 3: Visualizing and Exploring Data Fall 2011 Ming Li Department of Computer Science and Technology Nanjing University

Unsupervised learning in Vision

CNN for Low Level Image Processing. Huanjing Yue

Image Analysis & Retrieval Lec-01: Introduction

Image Analysis & Retrieval

Understanding Faces. Detection, Recognition, and. Transformation of Faces 12/5/17

Image Analysis & Retrieval Lec 10 - Classification II

Image Analysis & Retrieval

Image Analysis & Retrieval. CS/EE 5590 Special Topics (Class Ids: 44873, 44874) Fall 2016, M/W Lec 16

Recognition, SVD, and PCA

CHAPTER 3 PRINCIPAL COMPONENT ANALYSIS AND FISHER LINEAR DISCRIMINANT ANALYSIS

CSC 411: Lecture 14: Principal Components Analysis & Autoencoders

One Network to Solve Them All Solving Linear Inverse Problems using Deep Projection Models

Lecture 4 Face Detection and Classification. Lin ZHANG, PhD School of Software Engineering Tongji University Spring 2018

Linear Discriminant Analysis in Ottoman Alphabet Character Recognition

Data Mining Final Project Francisco R. Ortega Professor: Dr. Tao Li

Applications Video Surveillance (On-line or off-line)

Slides adapted from Marshall Tappen and Bryan Russell. Algorithms in Nature. Non-negative matrix factorization

Announcements. Recognition I. Gradient Space (p,q) What is the reflectance map?

Image-Based Face Recognition using Global Features

Lec 08 Feature Aggregation II: Fisher Vector, Super Vector and AKULA

ECE 484 Digital Image Processing Lec 12 - Mid Term Review

Deep Learning for Computer Vision

CSC 411: Lecture 14: Principal Components Analysis & Autoencoders

FACE RECOGNITION BASED ON GENDER USING A MODIFIED METHOD OF 2D-LINEAR DISCRIMINANT ANALYSIS

Bilevel Sparse Coding

FACE RECOGNITION USING SUPPORT VECTOR MACHINES

Dimensionality Reduction, including by Feature Selection.

Modelling and Visualization of High Dimensional Data. Sample Examination Paper

Large-Scale Face Manifold Learning

Robust Face Recognition via Sparse Representation Authors: John Wright, Allen Y. Yang, Arvind Ganesh, S. Shankar Sastry, and Yi Ma

Optimizing feature representation for speaker diarization using PCA and LDA

Unsupervised Learning

CHAPTER 5 GLOBAL AND LOCAL FEATURES FOR FACE RECOGNITION

[Nirgude* et al., 4(1): January, 2017] ISSN Impact Factor 2.675

Neural Networks for unsupervised learning From Principal Components Analysis to Autoencoders to semantic hashing

COSC160: Detection and Classification. Jeremy Bolton, PhD Assistant Teaching Professor

Direct Matrix Factorization and Alignment Refinement: Application to Defect Detection

AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation

Final Project Face Detection and Recognition

22 October, 2012 MVA ENS Cachan. Lecture 5: Introduction to generative models Iasonas Kokkinos

Recognition: Face Recognition. Linda Shapiro EE/CSE 576

When Sparsity Meets Low-Rankness: Transform Learning With Non-Local Low-Rank Constraint For Image Restoration

Dimension reduction for hyperspectral imaging using laplacian eigenmaps and randomized principal component analysis

Image Analysis & Retrieval Lec 12 - Mid-Term Review

COMP 551 Applied Machine Learning Lecture 16: Deep Learning

Face Recognition for Mobile Devices

Feature selection. Term 2011/2012 LSI - FIB. Javier Béjar cbea (LSI - FIB) Feature selection Term 2011/ / 22

Eigenfaces and Fisherfaces A comparison of face detection techniques. Abstract. Pradyumna Desale SCPD, NVIDIA

FACE RECOGNITION UNDER LOSSY COMPRESSION. Mustafa Ersel Kamaşak and Bülent Sankur

CSE 255 Lecture 5. Data Mining and Predictive Analytics. Dimensionality Reduction

Dimension reduction : PCA and Clustering

Deep Learning for Robust Normal Estimation in Unstructured Point Clouds. Alexandre Boulch. Renaud Marlet

Partial Least Squares Regression on Grassmannian Manifold for Emotion Recognition

CSE 6242 A / CS 4803 DVA. Feb 12, Dimension Reduction. Guest Lecturer: Jaegul Choo

Discriminate Analysis

CSE 258 Lecture 5. Web Mining and Recommender Systems. Dimensionality Reduction

Two-view geometry Computer Vision Spring 2018, Lecture 10

Name: Math 310 Fall 2012 Toews EXAM 1. The material we have covered so far has been designed to support the following learning goals:

Estimating cross-section semiconductor structure by comparing top-down SEM images *

ECE407 Project. Implementation of the Fisher Linear Discriminant (FLD) based algorithm for Face Recognition. Arindam Bose UIC ID:

Deep Learning for Computer Vision II

Linear Discriminant Analysis for 3D Face Recognition System

GENDER CLASSIFICATION USING SUPPORT VECTOR MACHINES

Colorado School of Mines. Computer Vision. Professor William Hoff Dept of Electrical Engineering &Computer Science.

Parallel Architecture & Programing Models for Face Recognition

Computer vision: models, learning and inference. Chapter 13 Image preprocessing and feature extraction

Rotation Invariance Neural Network

IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 14, NO. 1, JANUARY Face Recognition Using LDA-Based Algorithms

Scaled Machine Learning at Matroid

Locality Preserving Projections (LPP) Abstract

Dimension reduction for hyperspectral imaging using laplacian eigenmaps and randomized principal component analysis:midyear Report

Efficient Module Based Single Image Super Resolution for Multiple Problems

Robust Principal Component Analysis (RPCA)

Vignette: Reimagining the Analog Photo Album

Face detection and recognition. Many slides adapted from K. Grauman and D. Lowe

CSE 152 : Introduction to Computer Vision, Spring 2018 Assignment 5

Generalized Principal Component Analysis CVPR 2007

CS231N Section. Video Understanding 6/1/2018

CSC321: Neural Networks. Lecture 13: Learning without a teacher: Autoencoders and Principal Components Analysis. Geoffrey Hinton

Detecting Burnscar from Hyperspectral Imagery via Sparse Representation with Low-Rank Interference

Face Recognition A Deep Learning Approach

A REVIEW ON FACIAL RECOGNITION ALGORITHMS & THEIR APPLICATION IN RETAIL STORES

Face detection and recognition. Detection Recognition Sally

Learning based face hallucination techniques: A survey

Performance Evaluation of Optimised PCA and Projection Combined PCA methods in Facial Images

Adaptive Video Compression using PCA Method

Lecture 3: Camera Calibration, DLT, SVD

Is Bigger CNN Better? Samer Hijazi on behalf of IPG CTO Group Embedded Neural Networks Summit (enns2016) San Jose Feb. 9th

Announcements. Recognition I. Optical Flow: Where do pixels move to? dy dt. I + y. I = x. di dt. dx dt. = t

Machine Learning. Deep Learning. Eric Xing (and Pengtao Xie) , Fall Lecture 8, October 6, Eric CMU,

Recognition. Computer Vision I. CSE252A Lecture 20

Tutorial on Machine Learning Tools

Supplementary Material : Partial Sum Minimization of Singular Values in RPCA for Low-Level Vision

CSE 481C Imitation Learning in Humanoid Robots Motion capture, inverse kinematics, and dimensionality reduction

Image Restoration: From Sparse and Low-rank Priors to Deep Priors

Computational Methods CMSC/AMSC/MAPL 460. Vectors, Matrices, Linear Systems, LU Decomposition, Ramani Duraiswami, Dept. of Computer Science

Transcription:

ECE 484 Digital Image Processing Lec 17 - Part II Review & Final Projects opics Zhu Li Dept of CSEE, UMKC Office: FH560E, Email: lizhu@umkc.edu, Ph: x 2346. http://l.web.umkc.edu/lizhu slides created with PS Office Linux and EqualX equation editor Z. Li, ECE 484 Digital Image Processing, 2018 p.1

Outline Part II Summary & Exam 2 Exam 2 Image Dimension Reduction (SVD, PCA, LEM) Eigenface Fisherface Conv Neural Networks raining of CNN Course Projects Z. Li, ECE 484 Digital Image Processing, 2018 p.2

Exam 2 ime & Venu 11/29, in class. Format: close book, but can bringing in an A4 cheating sheet Multiple choices Problem solving Coverage: only the stuffs covered after the exam 1. Relax, more conceptual than gory details. Z. Li, ECE 484 Digital Image Processing, 2018 p.3

SVD projection decomposition for non square matrix: A mxn: Z. Li, Image Analysis & Retrv, Spring 2018 p.4

SVD as Signal Decomposition A (mxn) = U (mxm) S (mxn) V (nxn) he 1 st order SVD approx. of A is: Z. Li, Image Analysis & Retrv, Spring 2018 p.5

SVD approximation of an image Very easy function [x]=svd_approx(x0, k) dbg=0; if dbg x0= fix(100*randn(4,6)); k=2; end [u, s, v]=svd(x0); [m, n]=size(s); x = zeros(m, n); sgm = diag(s); for j=1:k x = x + sgm(j)*u(:,j)*v(:,j)'; end Z. Li, Image Analysis & Retrv, Spring 2018 p.6

Min Error Reconstruction Derivation of PCA Algorithm GOAL: Z. Li, Image Analysis & Retrv, Spring 2018 p.7

Justification of PCA Algorithm Remaining dimension x is centered! Z. Li, Image Analysis & Retrv, Spring 2018 p.8

PCA reconstruction error minimization GOAL: Use Lagrange-multipliers for the constraints, KK condition: Z. Li, Image Analysis & Retrv, Spring 2018 p.9

Justification of PCA Z. Li, Image Analysis & Retrv, Spring 2018 p.10

PCA Algorithm Center the data: X = X repmat(mean(x), [n, 1]); Principal component #1 points in the direction of the largest variance Each subsequent principal component is orthogonal to the previous ones, and points in the directions of the largest variance of the residual subspace Solved by finding Eigen Vectors of the Scatter/Covarinace matrix of data: S = cov(x); [A, eigv]=eig(s) Z. Li, Image Analysis & Retrv, Spring 2018 p.11

PCA & Fisher s Linear Discriminant Between-class scatter S B i ( i - )( i - ) i= 1 ithin-class scatter S = otal scatter c = å c å å i= 1 x Î k ( x i k - )( - ) i k i 1 2 2 S c = å å here i= 1 x Î k ( x i k - )( - ) c is the number of classes k i is the mean of class i i is number of samples of i.. = S B + S 1 Z. Li, Image Analysis & Retrv, Spring 2018 p.12

Eigen vs Fisher Projection PCA 1 2 Fisher PCA (Eigenfaces) PCA = arg max Maximizes projected total scatter Fisher s Linear Discriminant fld = arg max Maximizes ratio of projected between-class to projected within-class scatter, solved by the generalized Eigen problem: S S S B Z. Li, Image Analysis & Retrv, Spring 2018 p.13

Dealing with Singularity of S w fld = PCA = fld PCA = arg max arg max PCA PCA S S S B PCA PCA Since S is rank N-c, project training set via PCA first to subspace spanned by first N-c principal components of the training set. Apply FLD to N-c dimensional subspace yielding c-1 dimensional feature space. Fisher s Linear Discriminant projects away the within-class variation (lighting, expressions) found in training set. Fisher s Linear Discriminant preserves the separability of the classes. Z. Li, Image Analysis & Retrv, Spring 2018 p.14

Subspace Learning for Face Recognition Project face images to a subspace with basis A Matlab: x=faces*a(:,1:kd) eigf 2 eigf 3 eigf 1 = 10.9* + 0.4* + 4.7* Z. Li, Image Analysis & Retrv, Spring 2018 p.15

Subspace/ransform Method It is interesting to compare Fisherface with Eigenface basis = A x in R wxh y in R d Eigenface Fisherface Z. Li, Image Analysis & Retrv, Spring 2018 p.16

CNN Processing Pipeline e can generate successive convolution features into higher level of representation: (notice w/o padding, shrinking) this gives us low level to high level features deeper feature, has larger receptive field, i.e, how many pixels it derives from Z. Li, ECE 484 Digital Image Processing, 2018 p.17

LeNet A landmark work: conv layers generate w x h x k feature maps FC layers map features to vectors How is label prediction done from final 4096 dimensional feature? Z. Li, ECE 484 Digital Image Processing, 2018 p.18

Pixel Level Loss Function Given an image patch in the input side, the residual is pixel level loss a bicubic upsampled image is prediction, the residual to be-learn is the difference between teh ground truth {y j } and predicted image. Z. Li, ECE 484 Digital Image Processing, 2018 p.19

Outline Part II Summary. Course Projects Denoising filtering (BM3D) eighted Nuclear Norm Minimization with Application to Image Denoising (NNM) Deep learning denoising - DnCNN Deep learning denoising - Universal Denoising Network Super-resolution - handcrafted (SR Forrest) Super-resolution - deep learning (EDSR) Papers are available at: https://umkc.box.com/s/lrek4ool84th4l3epjt5fi3sh53alc5 f Z. Li, ECE 484 Digital Image Processing, 2018 p.20

BM3D BM3D denoising filtering source code: http://www.cs.tut.fi/~foi/gcf-bm3d/bm3d.zip Z. Li, ECE 484 Digital Image Processing, 2018 p.21

NNM eighted Nuclear Norm Minimization and Its Applications to Low Level Vision code: http://www4.comp.polyu.edu.hk/~cslzhang/code/nnm_code.zip Z. Li, ECE 484 Digital Image Processing, 2018 p.22

DnCNN Architecture Z. Li, ECE 484 Digital Image Processing, 2018 p.23

Universal Denoising Networks Architecture: Results Z. Li, ECE 484 Digital Image Processing, 2018 p.24

SR Forrest Data dependent local projection model for SR Z. Li, ECE 484 Digital Image Processing, 2018 p.25

EDSR Super Resolution with Residual Networks code: https://github.com/thstkdgus35/edsr-pyorch Z. Li, ECE 484 Digital Image Processing, 2018 p.26

Summary Deep Leanring in Denoising Just beginning to show advantages, room for innovation combining handcrafted with deep would be the best Deep Learning in SR EDSR like residual learning gives best results ask-linked SR has more room Z. Li, ECE 484 Digital Image Processing, 2018 p.27