1 Image Compression Based on Regression Equation Advisor: H. C. Wu, Y. K. Chan Speaker: Hsin-Nan Tsai ( 蔡信男 ) Date: May 4, 2005.

Slides:



Advertisements
Similar presentations
Packet Video Error Concealment With Auto Regressive Model Yongbing Zhang, Xinguang Xiang, Debin Zhao, Siwe Ma, Student Member, IEEE, and Wen Gao, Fellow,
Advertisements

Secure Layer Based Compound Image Compression using XML Compression Author : D. Maheswari 1, V.Radha Source : Computational Intelligence and Computing.
A Comprehensive Study on Third Order Statistical Features for Image Splicing Detection Xudong Zhao, Shilin Wang, Shenghong Li and Jianhua Li Shanghai Jiao.
International Conference on Image Analysis and Recognition (ICIAR’09). Halifax, Canada, 6-8 July Video Compression and Retrieval of Moving Object.
1 Preprocessing for JPEG Compression Elad Davidson & Lilach Schwartz Project Supervisor: Ari Shenhar SPRING 2000 TECHNION - ISRAEL INSTITUTE of TECHNOLOGY.
Image deblocking using local segmentation By Mirsad Makalic Supervisor: Dr. Peter Tischer.
Handwritten Thai Character Recognition Using Fourier Descriptors and Robust C-Prototype Olarik Surinta Supot Nitsuwat.
Fast vector quantization image coding by mean value predictive algorithm Authors: Yung-Gi Wu, Kuo-Lun Fan Source: Journal of Electronic Imaging 13(2),
Segmentation-Based Image Compression 以影像切割為基礎的影像壓縮技術 Speaker: Jiun-De Huang Advisor: Jian-Jiun Ding Graduate Institute of Communication Engineering National.
New Segmentation Methods Advisor : 丁建均 Jian-Jiun Ding Presenter : 蔡佳豪 Chia-Hao Tsai Date: Digital Image and Signal Processing Lab Graduate Institute.
1 Hiding Data in Images by Simple LSB Substitution Source: Pattern Recognition, Vol. 37, pp , 2004 Authors: Chi-Kwong Chan and L.M. Cheng Speaker:
Colored Watermarking Technology Based on Visual Cryptography Author: Hsien-Chu Wu, Chwei-Shyong Tsai, Shu-Chuan Huang Speaker: Shu-Chuan Huang Date: May.
COMPARISON OF IMAGE ANALYSIS FOR THAI HANDWRITTEN CHARACTER RECOGNITION Olarik Surinta, chatklaw Jareanpon Department of Management Information System.
Handwritten Recognition with Neural Network Chatklaw Jareanpon, Olarik Surinta Mahasarakham University.
Post-processing of JPEG image using MLP Fall 2003 ECE539 Final Project Report Data Fok.
Smooth Side-Match Classified Vector Quantizer with Variable Block Size IEEE Transaction on image processing, VOL. 10, NO. 5, MAY 2001 Department of Applied.
Fractal Video Compression 碎形視訊壓縮方法 Chia-Yuan Chang 張嘉元 Department of Applied Mathematics National Sun Yat-Sen University Kaohsiung, Taiwan.
2005/12/021 Fast Image Retrieval Using Low Frequency DCT Coefficients Dept. of Computer Engineering Tatung University Presenter: Yo-Ping Huang ( 黃有評 )
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,
Design of PCA and SVM based face recognition system for intelligent robots Department of Electrical Engineering, Southern Taiwan University, Tainan County,
Palette Partition Based Data Hiding for Color Images Yu-Chiang Li, Piyu Tsai, Chih-Hung Lin, Hsiu-Lien Yeh, and Chien-Ting Huang Speaker : Yu-Chiang Li.
Blind image data hiding based on self reference Source : Pattern Recognition Letters, Vol. 25, Aug. 2004, pp Authors: Yulin Wang and Alan Pearmain.
Reporter :Chien-Wen Huang Date : Information Sciences, Vol. 176, No. 22, Nov. 2006, pp Received 29 December 2004; received in revised.
1 Security of fragile watermarking scheme for image authentication Authors: K. C. Liao, W. B. Lee, and C. W. Liao Source: The Imaging Science Journal,
基於 (7,4) 漢明碼的隱寫技術 Chair Professor Chin-Chen Chang ( 張真誠 ) National Tsing Hua University National Chung Cheng University Feng Chia University
Michael Gormish Prepared by:Emin Sinan Mimaroglu
Advisor: Chang, Chin-Chen Student: Chen, Chang-Chu
基於(7,4)漢明碼的隱寫技術 Chair Professor Chin-Chen Chang (張真誠)
JPEG Compressed Image Retrieval via Statistical Features
Source: The Journal of Systems and Software, Volume 67, Issue 2, pp ,
Chapter 3 向量量化編碼法.
Lossy Compression of DNA Microarray Images
Advisor: Chin-Chen Chang1, 2
Reversible Data Hiding in JPEG Images using Ordered Embedding
Source : Signal Processing, Volume 133, April 2017, Pages
V. Mezaris, I. Kompatsiaris, N. V. Boulgouris, and M. G. Strintzis
A Color Image Hiding Scheme Based on SMVQ and Modulo Operator
A Data Hiding Scheme Based Upon Block Truncation Coding
A Digital Watermarking Scheme Based on Singular Value Decomposition
Author: Ye Li, Meng Joo Er, and Dayong Shen Speaker: Kai-Wen, Weng
Aline Martin ECE738 Project – Spring 2005
Hiding Data in a Color Palette Image with Hybrid Strategies
Advisor: Chin-Chen Chang1, 2 Student: Yi-Pei Hsieh2
Source: Pattern Recognition Vol. 38, May, 2005, pp
An efficient reversible image authentication method using improved PVO and LSB substitution techniques Source : Signal Processing: Image Communication,
Source: Signal Processing: Image Communication 64 (2018) 78-88
Color Image Retrieval based on Primitives of Color Moments
Dynamic embedding strategy of VQ-based information hiding approach
第 九 章 影像邊緣偵測 9-.
A Self-Reference Watermarking Scheme Based on Wet Paper Coding
A Color Image Hiding Scheme Based on SMVQ and Modulo Operator
Digital Steganography Utilizing Features of JPEG Images
Partial reversible data hiding scheme using (7, 4) hamming code
Zhe-Ming Lu, Chun-He Liu, Dian-Guo Xu, Sheng-He Sun,
Authors: Chin-Chen Chang, Yi-Hui Chen, and Chia-Chen Lin
第 十 章 隱像術.
Support vector machine-based text detection in digital video
Data hiding method using image interpolation
A Robust and Recoverable Tamper Proofing Technique for Image Authentication Authors: Chin-Chen Chang & Kuo-Lung Hung Speaker : Chin-Chen Chang.
Source: Pattern Recognition Letters 29 (2008)
Partial reversible data hiding scheme using (7, 4) hamming code
A Self-Reference Watermarking Scheme Based on Wet Paper Coding
On SVD-based watermarking algorithm
Source: IEEE Transactions on Circuits and Systems,
An imperceptible spatial domain color image watermarking scheme
A Data Hiding Scheme Based Upon Block Truncation Coding
Source: Pattern Recognition, Volume 40, Issue 2, February 2007, pp
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
Authors: Chin-Chen Chang, Yi-Hui Chen, and Chia-Chen Lin
Presentation transcript:

1 Image Compression Based on Regression Equation Advisor: H. C. Wu, Y. K. Chan Speaker: Hsin-Nan Tsai ( 蔡信男 ) Date: May 4, 2005

2 Outline Introduction The proposed method Experimental results Conclusions

3 Introduction YIQ model Quadtree structure Edge detection Quadratic regression equation

4 Image compression RGB YIQ YIQYIQ RGBRGB = ×

5 Image compression (cont.) Quadtree (128x128) (64x64) NWNESW SE Breadth First Traversal Order treelist:

6 Image compression (cont.) Edge detection ∆X ∆Y If PCD > DiffTH Count = Count + 1 If Count > CountTH quadtree()

7 Image compression (cont.) Quadratic regression equation The coefficients a 0, a 1, and a 2 of this equation can be figured out by following three equations:.,, and i is the i-th pixel in an image block, and n is the number of pixels in the image block.

8 Image compression (cont.) Quadratic regression equation The coefficients b 0, b 1, and b 2 of this equation can be figured out by following three equations:.,, and i is the i-th pixel in an image block, and n is the number of pixels in the image block.

9 Image compression (cont.) Compute coefficients colorlist

10 Image compression (cont.) Compress Y values …325 12… 256 Y values JPEG compression Ydata …

11 Image compression (cont.) Compressed file: treelist || colorlist || Ydata

12 Image decompression Extract treelist r is the numbers of 1-bits s is the numbers of 0-bits treelist: × r + 1 = s Compressed file: treelist || colorlist || Ydata

13 Image decompression (cont.) Extract colorlist Compressed file: colorlist || Ydata 6 × s

14 Image decompression (cont.) Decompress Ydata Ydata JPEG Decompression …625 12… 256 Y values …

15 Image decompression (cont.) Restore quadtree Y values root(256x256) 128x128 64x

16 Image decompression (cont.) Substitution coefficients root(256x256) 128x128 64x YIQ values 256

17 Image decompression (cont.) YIQ RGB YIQ values 256 Lena 256

18 Experimental results The PSNRs of the decompressed images in different sizes of regression equation coefficients

19 Experimental results (cont.) The PSNRs and CRs of the testing image compressed by JPEG method

20 Experimental results (cont.) The PSNRs and CRs of the testing image compressed by our method

21 Experimental results (cont.) F GIRL HOUSE SAILBOAT SPLASH The PSNRs of the testing images encoded by JPEG method in different CRs in different CRs CR Image

22 Experimental results (cont.) F GIRL HOUSE SAILBOAT SPLASH The PSNRs of the testing images encoded by our method in different CRs CR Image

23 Experimental results (cont.) Blocking and Gibbs effects The decompressed images of GIRL4 decoded by our and JPEG methods (a) PSNR: dB(b) PSNR: dB

24 Conclusions Comparing to JPEG, the proposed method has good performance with low compression rate

25 子宮頸癌細胞抹片影像初始輪廓切割 Speaker: Jun-Dong Chang Advisor: Yung-Kuan Chan, Hsien-Chu Wu Date: 2005/05/04

26 Introduction Automatic recognition reduces the carelessness and mistakes caused in artificial recognition. Initial Contour Segmentation is a pre-process of ACM (Active Contour Model) System. Initial Contour Segmentation (Background, Cytoplasm, Nucl eus)

27 Color & Texture Analyzing ~ Training Image

28 Color & Texture Analyzing ~ Training Image (cont.) Background Cytoplasm Nucleus

29 Regression Function (cont.) Background

30 Regression Function (cont.) Cytoplasm

31 Regression Function (cont.) Nucleus

32 Initial Contour Segmentation i = arg(min(Dx)), for x = b, c, n. Query Image Background arg(min(Dx))

33 Initial Contour Segmentation (cont.) Background

34 Initial Contour Segmentation (cont.) Cytoplasm

35 Initial Contour Segmentation (cont.) Nucleus

36 Experimental Results ~ Image 1

37 Experimental Results ~ Image 2

38 Experimental Results ~ Image 3

39 Experimental Results ~ Image 4

40 Conclusions Most of blocks are segmented at the correct lay ers. Blocks of Background Layer are segmented to Cytoplasm Layer. Regression Function just analyses 2D relation. We have to correct segmentation errors to impr ove the accuracy of initial contour segmentation.

41 Future Work SVM (Support Vector Machine) Neighboring Block