Professional Documents
Culture Documents
Thesis Proposal On: Source Printer Classification Using Printer Specific Local Texture Descriptor Using CNN
Thesis Proposal On: Source Printer Classification Using Printer Specific Local Texture Descriptor Using CNN
04/02/21
SOURCE PRINTER CLASSIFICATION USING PRINTER
SPECIFIC LOCAL TEXTURE DESCRIPTOR USING CNN
ç
__ __
&
__ __
__ __
PRESENTENTED BY
GOPAL DAHAL
20 0 1
ME CE 16907
SEPTEMBER 2019
1
OVERVIEW
04/02/21
o Introduction
o Problem Statement
o Objectives
o Significance of Study
o Literature Review
o Methodology
o Expected Outcomes
o Validation Criteria
o Timeline
o References
2
INTRODUCTION
04/02/21
Printed text document as source of Information
Financial, Judicial Purpose, Lease, Agreements, Invoice, Bills
04/02/21
Lagging of cost efficient document classification
Training Overhead
04/02/21
Modify the existing algorithm purposed by Sharad Joshi, Nitin
Khanna (Source Printer Classification using Printer Specific Local
Texture Descriptor) to enhance printer classification for cross font
documents
5
SIGNIFICANCE OF STUDY
04/02/21
Examining printed documents for potential forgeries and
copyright infringement
6
LITERATURE REVIEW
04/02/21
Sharad Joshi and Nitin Khanna[1] proposed Source Printer Classification using
Printer Specific Local Texture Descriptor Using SVM Classifier
M.-J. Tsai, I. Yuadi, and Y.-H. Tao, “Decision-theoretic Model to Identify Printed
Sources,” Multimedia Tools and Applications, pp. 1–45, 2018.
Sharad Joshi and Nitin Khanna[2] proposed Single Classifier-based Passive
System for Source Printer Classification Using Local Texture Features
A. Ferreira, L. Bondi, L. Baroffio, P. Bestagini, J. Huang, J. dos Santos, S. Tubaro,
and A. Rocha, “Data-driven feature characterization techniques for laser printer
attribution,” IEEE Transactions on Information Forensics and Security, 2017.
M.-J. Tsai, C.-L. Hsu, J.-S. Yin, and I. Yuadi, “Japanese character based printed
source identification,” in Proc. IEEE Int. Symposium on Circuits and Systems
(ISCAS), Lisbon, Portugal, May 2015, pp. 2800–2803. 7
REFERENCED METHODOLOGY
04/02/21
Flowchart of the Referenced algorithm 8
RESEARCH METHODOLOGY
04/02/21
Preprocessing
Forged color image is converted to its grayscale representation.
Grayscaleintensity=0.299×R+0.587×G+0.114×B
Feature Extraction
Grayscale image is decomposed by dyadic wavelet transform to get four sub bands LL1
(approximation), LH1 (horizontal), HL1 (vertical) and HH1 (diagonal).
c j+1 [n]=∑ h[k] cj [ n+2jk]
d j+1 [n]=∑ g[k] cj [ n+2jk]
Divide LL1 and HH1 into blocks of fixed size.
Divide LL1 and HH1 into fixed sized overlapping blocks. For eg- LL1 and HH1 sub
bands are divided into 16X16 pixel blocks with 8 pixel overlapping in both row and column.
9
RESEARCH METHODOLOGY
04/02/21
10
PROPOSED RESEARCH METHODOLOGY
04/02/21
11
04/02/21
Windows 10
Intel Core i7-4720 @2.60GHz*8cores
16GB RAM
Python 2.7
04/02/21
Identify source printer for the scanned copy of printed document
13
VALIDATION CRITERIA
04/02/21
PerformanceMeasuring criteria such as Accuracy, False Positive
Rate (FPR), False Negative Rate (FNR) will be used for
measuring the performance. The AD, FPR and FNR value will be
compared with the referenced Algorithm.
14
TIME SCHEDULE
04/02/21
15
REFERENCES
04/02/21
1. S. Joshi and N. Khanna, “Source Printer Classification using Printer Specific Local Texture
Descriptor,” IEEE Transactions on Information Forensics and Security, 2019.
2. S. Joshi and N. Khanna, “Single Classifier-based Passive System for Source Printer Classification
Using Local Texture Features,” IEEE Transactions on Information Forensics and Security, vol. 13, no.
7, pp. 1603–1614, 2018.
3. A.Ferreira, Luca Bondi, , “A sorted neighborhood approach for detecting duplicated regions in image
forgeries based on DWT and SVD,” in Proceedings of IEEE International Conference onMultimedia
and Expo (ICME ’07), pp. 1750–1753, IEEE, Beijing, China, 2007.
4. H.-J. Lin, C.-W. Wang, and Y.-T. Kao, “Fast copy-move forgery detection,” WSEAS Transaction on
Signal Processing, pp. 188-197, 2009.
5. S. Bayram,H. T. Sencar, andN.Memon, “An efficient and robust method for detecting copy-move
forgery,” in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal
Processing (ICASSP ’09), pp. 1053–1056, April 2009.
6. T. Mahmood, T.Nawaz , A. Irtaza, R. Ashraf, M. Shah, and M. T.Mahmood5,”Copy-Move Forgery
Detection Technique for Forensic Analysis in Digital Images”, Hindawi Publishing 16
Corporation,Mathematical Problems in Engineering ,Volume 2016, Article ID 8713202, 13 pages
REFERENCES
04/02/21
• M. Ghorbani, M. Firouzmand, and A. Faraahi, “DWT-DCT (QCD) based copy-move image forgery
detection,” 18th IEEE International Conference on Systems, Signals and Image Processing (IWSSIP), 2011,
pp. 1-4.
• G. Muhammad, M. Hussain, and G. Bebisi, “Passive copy move image forgery detection using undecimated
dyadic wavelet transform”, Digital Investigation, vol. 9, no. 1, pp. 49–57, 2012.
• Pradyumna Deshpande , Prashasti Kanikar ,“Pixel Based Digital Image Forgery Detection Techniques”,
International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622, Vol. 2, Issue 3,
2012, pp. 539-543.
• B.S.Charulatha, Paul Rodrigues, T.Chitralekha, Arun Rajaraman,"A Comparative study of different distance
metrics that can be used in Fuzzy Clustering Algorithms",National Conference on Architecture, Software
systems and Green computing-2013(NCASG2013)
• Devanshi Chauhana, Dipali Kasatb, Sanjeev Jainc, Vilas Thakared,"Survey On Keypoint Based Copy-move
Forgery Detection Methods on Image",International Conference on Computational Modeling and Security
(CMS 2016)
Amani Alahmadi1 , Muhammad Hussain1 ,Hatim Aboalsamh1 ,Ghulam Muhammad1 · George Bebis2 ,
Hassan Mathkour1,” Passive detection of image forgery using DCT and local binary Pattern”, SIViP ,DOI
10.1007/s11760-016-0899-0, © Springer-Verlag London 2016
17
04/02/21
THANK YOU
18