Eyes detection in compressed domain using classification Eng. Alexandru POPA Technical University of Cluj-Napoca Faculty.

Slides:



Advertisements
Similar presentations
Applications of one-class classification
Advertisements

Component Analysis (Review)
Face Recognition and Biometric Systems Eigenfaces (2)
Biomedical Person Identification via Eye Printing Masoud Alipour Ali Farhadi Ali Farhadi Nima Razavi.
INTERNATIONAL CONFERENCE ON TELECOMMUNICATIONS, ICT '09. TAREK OUNI WALID AYEDI MOHAMED ABID NATIONAL ENGINEERING SCHOOL OF SFAX New Low Complexity.
New Attacks on Sari Image Authentication System Proceeding of SPIE 2004 Jinhai Wu 1, Bin B. Zhu 2, Shipeng Li, Fuzong Lin 1 State key Lab of Intelligent.
Chapter 4: Linear Models for Classification
Face Recognition and Biometric Systems
A Comprehensive Study on Third Order Statistical Features for Image Splicing Detection Xudong Zhao, Shilin Wang, Shenghong Li and Jianhua Li Shanghai Jiao.
Face Recognition & Biometric Systems, 2005/2006 Face recognition process.
Principal Component Analysis
Student Mini-Camp Project Report Pattern Recognition Participant StudentsAffiliations Patrick ChoiClaremont Graduate University Joseph McGrathUniv. of.
Prénom Nom Document Analysis: Data Analysis and Clustering Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
Distinguishing Photographic Images and Photorealistic Computer Graphics Using Visual Vocabulary on Local Image Edges Rong Zhang,Rand-Ding Wang, and Tian-Tsong.
Losslessy Compression of Multimedia Data Hao Jiang Computer Science Department Sept. 25, 2007.
Digital Watermarking. Introduction Relation to Cryptography –Cryptography is Reversibility (no evidence) Established –Watermarking (1990s) Non-reversible.
Image Compression - JPEG. Video Compression MPEG –Audio compression Lossy / perceptually lossless / lossless 3 layers Models based on speech generation.
EE513 Audio Signals and Systems Statistical Pattern Classification Kevin D. Donohue Electrical and Computer Engineering University of Kentucky.
1 An Efficient Classification Approach Based on Grid Code Transformation and Mask-Matching Method Presenter: Yo-Ping Huang Tatung University.
Presented by Tienwei Tsai July, 2005
Cs: compressed sensing
BACKGROUND LEARNING AND LETTER DETECTION USING TEXTURE WITH PRINCIPAL COMPONENT ANALYSIS (PCA) CIS 601 PROJECT SUMIT BASU FALL 2004.
Ajay Kumar, Member, IEEE, and David Zhang, Senior Member, IEEE.
General Tensor Discriminant Analysis and Gabor Features for Gait Recognition by D. Tao, X. Li, and J. Maybank, TPAMI 2007 Presented by Iulian Pruteanu.
Information hiding in stationary images staff corporal Piotr Lenarczyk Military Uniwersity of Technology Institute of Electronics and Telecomunication.
Image Classification 영상분류
Digital Image Processing CCS331 Relationships of Pixel 1.
Ch 4. Linear Models for Classification (1/2) Pattern Recognition and Machine Learning, C. M. Bishop, Summarized and revised by Hee-Woong Lim.
Handwritten Recognition with Neural Network Chatklaw Jareanpon, Olarik Surinta Mahasarakham University.
Advances in digital image compression techniques Guojun Lu, Computer Communications, Vol. 16, No. 4, Apr, 1993, pp
2005/12/021 Fast Image Retrieval Using Low Frequency DCT Coefficients Dept. of Computer Engineering Tatung University Presenter: Yo-Ping Huang ( 黃有評 )
Levels of Image Data Representation 4.2. Traditional Image Data Structures 4.3. Hierarchical Data Structures Chapter 4 – Data structures for.
Chapter 12 Object Recognition Chapter 12 Object Recognition 12.1 Patterns and pattern classes Definition of a pattern class:a family of patterns that share.
Linear Models for Classification
Discriminant Analysis
A NOVEL METHOD FOR COLOR FACE RECOGNITION USING KNN CLASSIFIER
Implementation, Comparison and Literature Review of Spatio-temporal and Compressed domains Object detection. By Gokul Krishna Srinivasan Submitted to Dr.
1 An Efficient Classification Approach Based on Grid Code Transformation and Mask-Matching Method Presenter: Yo-Ping Huang.
MACHINE LEARNING 7. Dimensionality Reduction. Dimensionality of input Based on E Alpaydın 2004 Introduction to Machine Learning © The MIT Press (V1.1)
Introduction to JPEG m Akram Ben Ahmed
CS 376b Introduction to Computer Vision 03 / 17 / 2008 Instructor: Michael Eckmann.
(B1) What are the advantages and disadvantages of digital TV systems? Hint: Consider factors on noise, data security, VOD etc. 1.
JPEG. Introduction JPEG (Joint Photographic Experts Group) Basic Concept Data compression is performed in the frequency domain. Low frequency components.
Automatic Caption Localization in Compressed Video By Yu Zhong, Hongjiang Zhang, and Anil K. Jain, Fellow, IEEE IEEE Transactions on Pattern Analysis and.
LDA (Linear Discriminant Analysis) ShaLi. Limitation of PCA The direction of maximum variance is not always good for classification.
SIMD Implementation of Discrete Wavelet Transform Jake Adriaens Diana Palsetia.
On the relevance of facial expressions for biometric recognition Marcos Faundez-Zanuy, Joan Fabregas Escola Universitària Politècnica de Mataró (Barcelona.
Part 3: Estimation of Parameters. Estimation of Parameters Most of the time, we have random samples but not the densities given. If the parametric form.
Content Based Coding of Face Images
JPEG Compressed Image Retrieval via Statistical Features
An Example of 1D Transform with Two Variables
DCT IMAGE COMPRESSION.
LECTURE 10: DISCRIMINANT ANALYSIS
Classification Discriminant Analysis
Classification Discriminant Analysis
Introduction To Wavelets
Zhengjun Pan and Hamid Bolouri Department of Computer Science
Aline Martin ECE738 Project – Spring 2005
EE513 Audio Signals and Systems
Image Compression Techniques
1-D DISCRETE COSINE TRANSFORM DCT
Generally Discriminant Analysis
LECTURE 09: DISCRIMINANT ANALYSIS
Digital Image Procesing Discrete CosineTrasform (DCT) in Image Processing DR TANIA STATHAKI READER (ASSOCIATE PROFFESOR) IN SIGNAL PROCESSING IMPERIAL.
Research Institute for Future Media Computing
Research Institute for Future Media Computing
Author: Minoru Kuribayashi, Hatsukazu Tanaka
Digital Image Processing
Amari Lewis Aidean Sharghi
Presentation transcript:

Eyes detection in compressed domain using classification Eng. Alexandru POPA Technical University of Cluj-Napoca Faculty of Electronics, Telecommunications and Information Technology

Object detection in digital images The principle of image processing in the compressed domain The Discrete Cosine Transform (DCT) The spatial relationship of DCT coefficients between a block and its sub-blocks Object recognition using classification The linear discriminant classifier (LDA, Fisher classifier) Demo Results Conclusions 2

the approached method consists in feature extraction using image transformations, creation of a new space of features followed by objects classification in that space feature extraction methods: DCT, Wavelet, Gabor DCT gives in general good features for object description. Is the base of the JPEG standard, and the properties of the DCT coefficients blocks, makes them very good for generating features spaces the idea is to make the classification of the objects direct in JPEG compressed domain DCT = Discrete Cosine Transform 3

almost all image processing algorithms are defined in pixel level; rewriting them in the compressed domain is not direct standard implementation schemes decompress the image, apply the algorithm and them recompress the image. The disadvantage is that these schemes are time consuming it is wished to rewrite these algorithms directly in the compressed domain for optimizing the processing chain 4

The formula for DCT applied on a image: Properties: Decorelation – the principal advantage of transformed images is the low redundancy between neighbours pixels. From this fact results uncorrelated coefficients which can be coded independently Energy compactness – the capacity of the transformation to pack the input datas in as few coefficients as possible Separability – the 2D DCT can be calculated in two steps by applying the 1D formula successively on the lines and the columns of an image 5 (1) (2)

a new problem could occur from the fact that various DCT block sizes have to be used in order to ensure optimized performances 8x8 blocks used in JPEG, 4x4 blocks used in image indexing, and 16x16 macro- blocks in MPEG to deal with inter-transfer of DCT coefficients from different blocks with various sizes, the existing approach would have to decompress the pixel data in the spatial domain via the IDCT, redivide the pixels into new blocks with the required size and then apply the DCT again to produce the DCT coefficients it is obvious that the approach is inefficient Bibliography: The Spatial Relationship of DCT Coefficients Between a Block and Its Sub-blocks, Jianmin Jiang and Guocan Feng 6

4x4 block Transformation from 4 blocks of 2x2 pixels in one of 4x4 pixels: The block with the pixels luminance DCT The DCT coefficients of 4 block of 2x2 pixels Matricea A* Ecuation: Original image 7 (3)

Transformation form a 4x4 block to 4 block of 2x2 pixels: DCT The inverse matrix of A* Ecuation : 8 (4) The block with the pixels luminance The DCT coefficients of The 4x4 block Original image4x4 block

geometric classifiers are those classifiers which implies the deduction of some decision borders in the features space a classifier demands a set of training datas (datas + labels) the number of datas must be big enough for a correct learning with generalization capacity for unknown datas 9 Data classification: means that an unknown sample is presented to the classifier, his position regarding the decision boundaries is calculated and depending on it a label is associated

LDA (Linear Discriminant Analysis) using Fisher’s classifier implies finding a line in the features space and projecting the datas from the training set on this line. Describes the datas by their projections Considering a bi-dimensional space we have: 10 Fisher’s criteria for selecting w and w0 parameters: The optimal direction w is the line direction for which: 1) the distance between the projections of the classes centers on w is maximum 2) the variance of the projections from each class is minimum The optimum value w0 is the scalar value which minimize the classification error in the training data set is the label assigned to the i data by the Fisher classifier

11

12

13 The image form which the training set was taken

it was proved that the implementation of Fisher`s classifier in compressed domain was a wise choice because it has good results in eyes regions detection it`s a novelty in the image processing field because this algorithm wasn`t written in compressed domain using the spatial relationship of DCT coefficients between a block and its sub-blocks facilitates the computation of coefficients for big blocks starting from small blocks in the way of speed and computation complexity Others applications that can derive: gaze tracking/focusing automatic system for detecting the vigilance of drivers biometrics applications: person identification using iris recognition, conteaz ă foarte mult structura acesteia precum şi setul de antrenare 14

Thank you for your attention! Questions? 15