Image Denoising using Locally Learned Dictionaries Priyam Chatterjee Peyman Milanfar Dept. of Electrical Engineering University of California, Santa Cruz.

Slides:



Advertisements
Similar presentations
Principal Component Analysis Based on L1-Norm Maximization Nojun Kwak IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008.
Advertisements

11/11/02 IDR Workshop Dealing With Location Uncertainty in Images Hasan F. Ates Princeton University 11/11/02.
Carolina Galleguillos, Brian McFee, Serge Belongie, Gert Lanckriet Computer Science and Engineering Department Electrical and Computer Engineering Department.
Computer vision: models, learning and inference Chapter 13 Image preprocessing and feature extraction.
Patch-based Image Deconvolution via Joint Modeling of Sparse Priors Chao Jia and Brian L. Evans The University of Texas at Austin 12 Sep
Computer vision: models, learning and inference
Object Recognition & Model Based Tracking © Danica Kragic Tracking system.
1 Micha Feigin, Danny Feldman, Nir Sochen
Addressing the Medical Image Annotation Task using visual words representation Uri Avni, Tel Aviv University, Israel Hayit GreenspanTel Aviv University,
Image Indexing and Retrieval using Moment Invariants Imran Ahmad School of Computer Science University of Windsor – Canada.
Hiroyuki Takeda, Hae Jong Seo, Peyman Milanfar EE Department University of California, Santa Cruz Jan 11, 2008 Statistical Image Quality Measures.
Uncertainty Representation. Gaussian Distribution variance Standard deviation.
ICIP 2000, Vancouver, Canada IVML, ECE, NTUA Face Detection: Is it only for Face Recognition?  A few years earlier  Face Detection Face Recognition 
EE 290A: Generalized Principal Component Analysis Lecture 6: Iterative Methods for Mixture-Model Segmentation Sastry & Yang © Spring, 2011EE 290A, University.
A New Block Based Motion Estimation with True Region Motion Field Jozef Huska & Peter Kulla EUROCON 2007 The International Conference on “Computer as a.
HMM-BASED PATTERN DETECTION. Outline  Markov Process  Hidden Markov Models Elements Basic Problems Evaluation Optimization Training Implementation 2-D.
Retinex Algorithm Combined with Denoising Methods Hae Jong, Seo Multi Dimensional Signal Processing Group University of California at Santa Cruz.
Region Segmentation. Find sets of pixels, such that All pixels in region i satisfy some constraint of similarity.
A Study of Approaches for Object Recognition
Adaptive Rao-Blackwellized Particle Filter and It’s Evaluation for Tracking in Surveillance Xinyu Xu and Baoxin Li, Senior Member, IEEE.
Fitting. We’ve learned how to detect edges, corners, blobs. Now what? We would like to form a higher-level, more compact representation of the features.
Milanfar et al. EE Dept, UCSC 1 “Locally Adaptive Patch-based Image and Video Restoration” Session I: Today (Mon) 10:30 – 1:00 Session II: Wed Same Time,
Image Denoising with K-SVD Priyam Chatterjee EE 264 – Image Processing & Reconstruction Instructor : Prof. Peyman Milanfar Spring 2007.
Optimal Bandwidth Selection for MLS Surfaces
SUSAN: structure-preserving noise reduction EE264: Image Processing Final Presentation by Luke Johnson 6/7/2007.
Kernel Regression Based Image Processing Toolbox for MATLAB
Cliff Rhyne and Jerry Fu June 5, 2007 Parallel Image Segmenter CSE 262 Spring 2007 Project Final Presentation.
Nonlinear Dimensionality Reduction by Locally Linear Embedding Sam T. Roweis and Lawrence K. Saul Reference: "Nonlinear dimensionality reduction by locally.
Chapter 6-2 Radial Basis Function Networks 1. Topics Basis Functions Radial Basis Functions Gaussian Basis Functions Nadaraya Watson Kernel Regression.
Face Recognition Using Neural Networks Presented By: Hadis Mohseni Leila Taghavi Atefeh Mirsafian.
Image Segmentation by Clustering using Moments by, Dhiraj Sakumalla.
Graph-based consensus clustering for class discovery from gene expression data Zhiwen Yum, Hau-San Wong and Hongqiang Wang Bioinformatics, 2007.
CSE 185 Introduction to Computer Vision
CSC 589 Lecture 22 Image Alignment and least square methods Bei Xiao American University April 13.
Under the guidance of Dr. K R. Rao Ramsanjeev Thota( )
Chapter 2. Image Analysis. Image Analysis Domains Frequency Domain Spatial Domain.
Computer vision.
Computer Vision James Hays, Brown
Gwangju Institute of Science and Technology Intelligent Design and Graphics Laboratory Multi-scale tensor voting for feature extraction from unstructured.
Chapter 15 Modeling of Data. Statistics of Data Mean (or average): Variance: Median: a value x j such that half of the data are bigger than it, and half.
ALIGNMENT OF 3D ARTICULATE SHAPES. Articulated registration Input: Two or more 3d point clouds (possibly with connectivity information) of an articulated.
COMMON EVALUATION FINAL PROJECT Vira Oleksyuk ECE 8110: Introduction to machine Learning and Pattern Recognition.
CSE 185 Introduction to Computer Vision Pattern Recognition 2.
Data Extraction using Image Similarity CIS 601 Image Processing Ajay Kumar Yadav.
School of Electrical & Computer Engineering Image Denoising Using Steerable Pyramids Alex Cunningham Ben Clarke Dy narath Eang ECE November 2008.
Image Enhancement [DVT final project]
Non-Euclidean Example: The Unit Sphere. Differential Geometry Formal mathematical theory Work with small ‘patches’ –the ‘patches’ look Euclidean Do calculus.
Learning to Sense Sparse Signals: Simultaneous Sensing Matrix and Sparsifying Dictionary Optimization Julio Martin Duarte-Carvajalino, and Guillermo Sapiro.
CS654: Digital Image Analysis Lecture 25: Hough Transform Slide credits: Guillermo Sapiro, Mubarak Shah, Derek Hoiem.
Practical Poissonian-Gaussian Noise Modeling and Fitting for Single-image Raw-data Alessandro Foi, Mejdi Trimeche, Vladimir Katkovnik, and Karen Egiazarian.
CS654: Digital Image Analysis
Computer Graphics and Image Processing (CIS-601).
Computer Vision Lecture #10 Hossam Abdelmunim 1 & Aly A. Farag 2 1 Computer & Systems Engineering Department, Ain Shams University, Cairo, Egypt 2 Electerical.
Tony Jebara, Columbia University Advanced Machine Learning & Perception Instructor: Tony Jebara.
Lecture 2: Statistical learning primer for biologists
Student: Chih-Wei Fang ( 方志偉 ) Adviser: Jenn-Jier James Lien ( 連震杰 ) Robotics Laboratory, Department of Computer Science and Information Engineering, National.
Irfan Ullah Department of Information and Communication Engineering Myongji university, Yongin, South Korea Copyright © solarlits.com.
Kernel Methods Arie Nakhmani. Outline Kernel Smoothers Kernel Density Estimators Kernel Density Classifiers.
Performance Measurement of Image Processing Algorithms By Dr. Rajeev Srivastava ITBHU, Varanasi.
Fitting.
Jianchao Yang, John Wright, Thomas Huang, Yi Ma CVPR 2008 Image Super-Resolution as Sparse Representation of Raw Image Patches.
11/25/03 3D Model Acquisition by Tracking 2D Wireframes Presenter: Jing Han Shiau M. Brown, T. Drummond and R. Cipolla Department of Engineering University.
1 C.A.L. Bailer-Jones. Machine Learning. Data exploration and dimensionality reduction Machine learning, pattern recognition and statistical data modelling.
Line Fitting James Hayes.
Machine Learning Dimensionality Reduction
A Graph-based Framework for Image Restoration
Linear regression Fitting a straight line to observations.
Presented by Xu Miao April 20, 2005
Probabilistic Surrogate Models
Lecture 7 Patch based methods: nonlocal means, BM3D, K- SVD, data-driven (tight) frame.
Presentation transcript:

Image Denoising using Locally Learned Dictionaries Priyam Chatterjee Peyman Milanfar Dept. of Electrical Engineering University of California, Santa Cruz Computational Imaging VII – 20 Jan, 2009

20 Jan, 2009Image Denoising using Locally Learned Dictionaries2 Overview Data Model Kernel Regression for Denoising Denoising with Locally Learned Dictionaries (K-LLD) Results Conclusions

20 Jan, 2009Image Denoising using Locally Learned Dictionaries3 Data Model Pointwise data model Patchwise model Locally smooth function to be estimated Zero-mean I.I.D. noise Observation denoted as

20 Jan, 2009Image Denoising using Locally Learned Dictionaries4 Steering Kernel Regression (SKR) Optimization problem Solution: Nonlinear filters Polynomial basis Data- dependent weights

20 Jan, 2009Image Denoising using Locally Learned Dictionaries5 SKR Weights Weights based on pixel “self-similarity” in a local patch Covariance matrix takes into account: orientation and strength of edges Gradient Covariance

20 Jan, 2009Image Denoising using Locally Learned Dictionaries6 Steering Kernel Decompose the matrix into three components: Scaling parameter, rotation matrix, and elongation matrix. ElongateRotateScale

20 Jan, 2009Image Denoising using Locally Learned Dictionaries7 SKR Weights Note how the weights adapt to the underlying image structure Noisy Noise-free H. Takeda, S. Farsiu, and P. Milanfar, “Kernel Regression for Image Processing and Reconstruction”, IEEE Trans. on Image Processing, vol. 16, no. 2, pp , February 2007.

20 Jan, 2009Image Denoising using Locally Learned Dictionaries8 Now we extend it ….. is fixed order, everywhere -- not depending on underlying image structure Lower orders fit flat regions, higher order for texture and fine details Global dictionary does not adapt to local image characteristics Dictionary atoms should capture underlying local image structure

20 Jan, 2009Image Denoising using Locally Learned Dictionaries9 Denoising with Locally Learned Dictionaries (K-LLD) Identify dictionary which best captures underlying geometric structure Similar structures will have similar dictionary, similar weights Cluster image based on geometric similarity (K-Means on the SKR weights) Learn dictionary and order of regression for each cluster

20 Jan, 2009Image Denoising using Locally Learned Dictionaries10 K-LLD: Algorithm Outline Calculate weights Learn dictionaries Clustering Iterate Noisy Image Kernel Regression Denoised Image

20 Jan, 2009Image Denoising using Locally Learned Dictionaries11 Class 1 Class K Clustering Stage K-LLD : Algorithm Outline Dictionary Selection Stage Noisy Img Calculate Steering Weights Calculate Steering Weights Coefficient Calculation Stage Coefficient Calculation Stage Denoised Img

20 Jan, 2009Image Denoising using Locally Learned Dictionaries12 Segment Image Segment Image Clustering Stage K-Means Class 1 Class K K-LLD : Algorithm Outline Dictionary Selection Stage Noisy Img Calculate Steering Weights Calculate Steering Weights Coefficient Calculation Stage Coefficient Calculation Stage Denoised Img

20 Jan, 2009Image Denoising using Locally Learned Dictionaries13 Clustering Stage Objective : Cluster image based on geometric similarity of underlying data Feature Selection What features capture data geometry ? Distance Metric What metric captures distance between features ? Clustering Algorithm What algorithm segments the image best ?

20 Jan, 2009Image Denoising using Locally Learned Dictionaries14 K-Means for Clustering Features : normalized steering wts Distance Metric : L 2 Initialization : Randomly initialize cluster centers Run K-Means multiple times and select result that minimizes within-cluster distance

20 Jan, 2009Image Denoising using Locally Learned Dictionaries15 Noise-free Noisy Clustering the noise-free image Clustering the noisy image

20 Jan, 2009Image Denoising using Locally Learned Dictionaries16 Segment Image Segment Image Clustering Stage K-Means Class 1 Class K K-LLD : Algorithm Outline Dictionary Selection Stage Noisy Img Calculate Steering Weights Calculate Steering Weights Coefficient Calculation Stage Coefficient Calculation Stage Denoised Img Dictionary Selection Stage PCA Form Dictionary Form Dictionary

20 Jan, 2009Image Denoising using Locally Learned Dictionaries17 Dictionary Selection Represent each patch in the k th cluster Variable Proj. Solved by PCA Mean patch of k-th cluster Enforce orthonormality

20 Jan, 2009Image Denoising using Locally Learned Dictionaries18 Dictionary Selection PCA in each cluster to form a dictionary Describe data without fitting noise Number of atoms based on cluster geometry Clusters with flat regions need fewer atoms, finer details need more constant Singular values patch size No. of atoms

20 Jan, 2009Image Denoising using Locally Learned Dictionaries19 Example : House Image Dictionary atoms for AWGN of std. dev. 15 Cluster Atom 1 Atom 2 Atom 3

20 Jan, 2009Image Denoising using Locally Learned Dictionaries20 Example : Noise-free case Cluster Atom 1 Atom 2 Atom 3 Atom 4 Few of the atoms in the dictionaries for different clusters

20 Jan, 2009Image Denoising using Locally Learned Dictionaries21 Example : Noise-free clustering Cluster Atom 1 Atom 2 Atom 3 Atom 4 Few of the atoms in the dictionaries for different clusters Brick facade

20 Jan, 2009Image Denoising using Locally Learned Dictionaries22 Data Representation Data represented as For point-wise estimator, local weights should be considered Cluster boundaries not necessarily described well by dictionary Protects against errors in clustering Unknown, to be estimated

20 Jan, 2009Image Denoising using Locally Learned Dictionaries23 Algorithm Outline Segment Image Segment Image Clustering Stage Class 1 Class K K-Means Noisy Img Calculate Steering Weights Calculate Steering Weights Coefficient Calculation Stage Coefficient Calculation Stage Denoised Img Dictionary Selection Stage PCA Form Dictionary Form Dictionary Kernel Regression Denoised Img

20 Jan, 2009Image Denoising using Locally Learned Dictionaries24 Kernel Regression Weighted least squares solution Final estimate Coefficient Calculation center pixel of patch.

20 Jan, 2009Image Denoising using Locally Learned Dictionaries25 Kernel Regression Denoised Img Algorithm Outline Segment Image Segment Image Clustering Stage Class 1 Class K K-Means Noisy Img Calculate Steering Weights Calculate Steering Weights Dictionary Selection Stage PCA Form Dictionary Form Dictionary

20 Jan, 2009Image Denoising using Locally Learned Dictionaries26 Iteration Re-learn weights (features) from denoised image Perform clustering of updated image using new features Learn dictionary from updated image Kernel regression on input noisy image Preserves edges and finer structures

20 Jan, 2009Image Denoising using Locally Learned Dictionaries27 Algorithm Outline Segment Image Segment Image Clustering Stage Class 1 Class K K-Means Noisy Img Calculate Steering Weights Calculate Steering Weights Kernel Regression Dictionary Selection Stage PCA Form Dictionary Form Dictionary

20 Jan, 2009Image Denoising using Locally Learned Dictionaries28 K-LLD: Algorithm Outline Calculate weights Learn dictionaries Clustering Iterate Noisy Image Kernel Regression Denoised Image Original Noisy Image

20 Jan, 2009Image Denoising using Locally Learned Dictionaries29 Performance Gain Performance gain by iterating

Results – AWG noise (std dev 25) K-LLD, MSE SSIM BM3D, MSE SSIM Original Parrot Image K-SVD, MSE SSIM SKR, MSE SSIM Noisy Image

20 Jan, 2009Image Denoising using Locally Learned Dictionaries31 More Results MSE SSIM

Results – Real noise & color ISKRK-LLDBM3D

Color Results ISKR, Order 2 BM3DOriginal Image K-LLD

20 Jan, 2009Image Denoising using Locally Learned Dictionaries34 Conclusions Data adaptive method having multiple degrees of freedom Denoising through a local data representation of images Can be extended to have adaptive patch size based on geometry of data in each cluster

20 Jan, 2009Image Denoising using Locally Learned Dictionaries35 Thank you P. Chatterjee and P. Milanfar, “Clustering-based Denoising with Locally Learned Dictionaries”, Accepted for publication in IEEE Trans. Image Processing Available at:

20 Jan, 2009Image Denoising using Locally Learned Dictionaries36 Iterative Scheme Why iterate ? Weights true to underlying structure in presence of lesser noise Better weights means better clustering Dictionary captures underlying data better when learned on less noisy image