Date: 2011.11.23 Advisor: Jian-Jung Ding Reporter: Hsin-Hui Chen.

Slides:



Advertisements
Similar presentations
A Secret Information Hiding Scheme Based on Switching Tree Coding Speaker: Chin-Chen Chang.
Advertisements

CSE 589 Applied Algorithms Spring 1999 Image Compression Vector Quantization Nearest Neighbor Search.
Spatial and Temporal Data Mining
דורון דמרי מקסים גורביץ מנחה : דמיטרי פורמן Cached Vector Quantization.
Side match vector quantization. 2 preface To compress image, using VQ, usual method is to encode blocks indepentently. However, there are many interblock.
JPEG.
Vector Quantization. 2 outline Introduction Two measurement : quality of image and bit rate Advantages of Vector Quantization over Scalar Quantization.
A New Dynamic Finite-State Vector Quantization Algorithm for Image Compression Jyi-Chang Tsai, Chaur-Heh Hsieh, and Te-Cheng Hsu IEEE TRANSACTIONS ON IMAGE.
Smart Traveller with Visual Translator for OCR and Face Recognition LYU0203 FYP.
Fast vector quantization image coding by mean value predictive algorithm Authors: Yung-Gi Wu, Kuo-Lun Fan Source: Journal of Electronic Imaging 13(2),
CS559-Computer Graphics Copyright Stephen Chenney Image File Formats How big is the image? –All files in some way store width and height How is the image.
CS 395 T Real-Time Graphics Architectures, Algorithms, and Programming Systems Spring’03 Vector Quantization for Texture Compression Qiu Wu Dept. of ECE.
1 An Efficient VQ-based Data Hiding Scheme Using Voronoi Clustering Authors:Ming-Ni Wu, Puu-An Juang, and Yu-Chiang Li.
Chapter 9 DTW and VQ Algorithm  9.1 Basic idea of DTW  9.2 DTW algorithm  9.3 Basic idea of VQ  9.4 LBG algorithm  9.5 Improvement of VQ.
Smooth Side-Match Classified Vector Quantizer with Variable Block Size IEEE Transaction on image processing, VOL. 10, NO. 5, MAY 2001 Department of Applied.
Planar-Oriented Ripple Based Greedy Search Algorithm for Vector Quantization Presenter: Tzu-Meng Huang Adviser:Dr. Yeou-Jiunn Chen Date:2011/11/ /11/161.
Advances in digital image compression techniques Guojun Lu, Computer Communications, Vol. 16, No. 4, Apr, 1993, pp
1 Information Hiding Based on Search Order Coding for VQ Indices Source: Pattern Recognition Letters, Vol.25, 2004, pp.1253 – 1261 Authors: Chin-Chen Chang,
1 資訊隱藏技術之研究 The Study of Information Hiding Mechanisms 指導教授: Chang, Chin-Chen ( 張真誠 ) 研究生: Lu, Tzu-Chuen ( 呂慈純 ) Department of Computer Science and Information.
Using Set Partitioning in Hierarchical Trees in the EZW Algorithm Yeon Hyang Kim William L’Huillier.
A Fast LBG Codebook Training Algorithm for Vector Quantization Presented by 蔡進義.
Vector Quantization CAP5015 Fall 2005.
2016/2/171 Image Vector Quantization Indices Recovery Using Lagrange Interpolation Source: IEEE International Conf. on Multimedia and Expo. Toronto, Canada,
JPEG. Introduction JPEG (Joint Photographic Experts Group) Basic Concept Data compression is performed in the frequency domain. Low frequency components.
Tamal Bose, Digital Signal and Image Processing © 2004 by John Wiley & Sons, Inc. All rights reserved. Figure 11-1 (p. 624) (a) Image coder; (b) image.
Presentation III Irvanda Kurniadi V. ( )
S.R.Subramanya1 Outline of Vector Quantization of Images.
Advisor: Chang, Chin-Chen Student: Chen, Chang-Chu
Chair Professor Chin-Chen Chang Feng Chia University Jan. 2008
An Image Database Retrieval Scheme Based Upon Multivariate Analysis and Data Mining Presented by C.C. Chang Dept. of Computer Science and Information.
The Johns Hopkins University
A Secret Information Hiding Scheme Based on Switching Tree Coding
Data Mining and Its Applications to Image Processing
Chapter 3 向量量化編碼法.
A Color Image Hiding Scheme Based on SMVQ and Modulo Operator
Source :Journal of visual Communication and Image Representation
Chair Professor Chin-Chen Chang Feng Chia University
High-capacity image hiding scheme based on vector quantization
Advisor: Chin-Chen Chang1, 2 Student: Wen-Chuan Wu2
指導教授: Chang, Chin-Chen (張真誠)
A Data Hiding Scheme Based Upon Block Truncation Coding
第七章 資訊隱藏 張真誠 國立中正大學資訊工程研究所.
Hiding Data in a Color Palette Image with Hybrid Strategies
Foundation of Video Coding Part II: Scalar and Vector Quantization
Advisor: Chin-Chen Chang1, 2 Student: Yi-Pei Hsieh2
第 四 章 VQ 加速運算與編碼表壓縮 4-.
Density-Based Image Vector Quantization Using a Genetic Algorithm
Chapter 7 漸進式影像傳輸.
Dynamic embedding strategy of VQ-based information hiding approach
Chair Professor Chin-Chen Chang Feng Chia University
第 九 章 影像邊緣偵測 9-.
Hung, K. -L. and Chang, C. -C. , IEE Image and Signal Processing, vol
A Self-Reference Watermarking Scheme Based on Wet Paper Coding
A Color Image Hiding Scheme Based on SMVQ and Modulo Operator
Hiding Information in VQ Index Tables with Reversibility
Information Hiding and Its Applications
Zhe-Ming Lu, Chun-He Liu, Dian-Guo Xu, Sheng-He Sun,
Authors: Chin-Chen Chang, Yi-Hui Chen, and Chia-Chen Lin
Efficient Huffman Decoding
A Virtual Image Cryptosystem Based upon Vector Quantization
Hung, K. -L. and Chang, C. -C. , IEE Image and Signal Processing, vol
A Robust and Recoverable Tamper Proofing Technique for Image Authentication Authors: Chin-Chen Chang & Kuo-Lung Hung Speaker : Chin-Chen Chang.
A Self-Reference Watermarking Scheme Based on Wet Paper Coding
De-clustering and Its Application to Steganography
A Data Hiding Scheme Based Upon Block Truncation Coding
Predictive Grayscale Image Coding Scheme Using VQ and BTC
資訊偽裝術 張真誠 講座教授 多媒體暨網路安全實驗室
Chair Professor Chin-Chen Chang Feng Chia University Jan. 2008
A New Image Compression Scheme Based on Locally Adaptive Coding
Presentation transcript:

Date: Advisor: Jian-Jung Ding Reporter: Hsin-Hui Chen

 Vector Quantization(VQ)-Based Image Coding  Block Truncation Coding(BTC)  Wavelet-Based Image Coding

 Scalar Quantization (SQ) A real number  Vector Quantization (VQ) A set of real numbers

 Vector Quantization (VQ)  Side-Match Vector Quantization (SMVQ)  Classified Vector Quantization (CVQ)  Tree Structured Vector Quantization (TSVQ)

 Drawbacks of VQ  Block Effect  Time Complexity for LBG algorithm  Block Effect  SMVQ  Derailment  CSMVQ  Time Complexity  CVQ  TSVQ  PCA

…… … … … w k k = w x h i i Original Image codeword Codebook Index Table Find the closest codeword Encoder

i codeword Codebook Output: i

k k = w x h i codeword Codebook Look-up Table Similar block Reconstructed Image w h Decoder Index Table

 LBG  Splitting

Block Effect

…… … … … Original Image =>VQ Residual blocks Seed blocks =>SMVQ

codeword State Codebook Super Codebook (Traditional VQ Codebook) Generate

codeword Super Codebook Find N Closest Codewords from Super Codebook

Derailment

codeword Super Codebook codeword State Codebook Error <= TH Error > TH

Block indicator: Bit “1” => VQ Bit “0”=> SMVQ

Compared to SMVQ: More Robust to derailment But less coding efficiency

Two Thresholds: TH c TH D State Codebook Super Codebook Size Choose one

If Var(U)<=TH c and Var(V)<=TH c : If (Var(U) TH c ) or (Var(U)>THc and Var(V)<=THc ): If Var(U)>TH c and Var(V)>TH c : State Codebook Size Decision Class(X)=1 Class(X)=2 Class(X)=3

4N Three State Codebooks: 2N N N Class(X)=1 Class(X)=2 Class(X)=3

State Codebook Super Codebook min(X, CW i )>TH D min(X, CW i )<=TH D CW i

Spent much time to full search

…… … … … w k k = w x h i i Original Image codeword Codebook Index Table Find the closest codeword Full Search

 Classified Vector Quantization (CVQ)  Tree Structured Vector Quantization (TSVQ)  Principal Component Analysis (PCA)

 Comparable image quality to VQ  Less computational time

Encoder …… … … … w Original Image Codebook1 CVQ Encoder Block Classifier Block Classifier …… Codebook2 Codebook N Output index

VQ Codebook Tree Structured VQ Codebook

K i codeword Codebook M x K Covariance Matrix K x K C

Covariance Matrix K x K C CV=VD V D K x K V: Eigenvectors matrix D: Eigenvalues matrix

sort V D K x K V: Eigenvectors matrix D: Eigenvalues matrix Find the eigenvector with the largest eigenvalue Projection coordinate

K i codeword Codebook M x K Codebook Projection Values

K i codeword Codebook M x K Codebook Projection Values

K codeword Codebook Codebook Projection Values …… … … … i Original Image Find the closest codebook projection value Projection coordinateProjection value i Search Range

…… … … … Original Image BTC Bit map a a b b

 An Example: Average Value Original Block Reconstructed Block Bit map a a b b

 Embedded Zero Wavelet (EZW)  Set Partitioning in Hierarchical Tree(SPIHT)  JPEG2000

 Parent-Descendant Relationship

 Scan Order Thresholds Bitstream ….

Q&A 