By Topic

Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP), 2012 Eighth International Conference on

Date 18-20 July 2012

Filter Results

Displaying Results 1 - 25 of 135
  • IIH-MSP 2012: 2012 Eighth International Conference on Intelligent Information Hiding and Multimedia Signal Processing [Cover art]

    Page(s): C4
    Save to Project icon | Request Permissions | PDF file iconPDF (1593 KB)  
    Freely Available from IEEE
  • [Title page i]

    Page(s): i
    Save to Project icon | Request Permissions | PDF file iconPDF (27 KB)  
    Freely Available from IEEE
  • [Title page iii]

    Page(s): iii
    Save to Project icon | Request Permissions | PDF file iconPDF (115 KB)  
    Freely Available from IEEE
  • [Copyright notice]

    Page(s): iv
    Save to Project icon | Request Permissions | PDF file iconPDF (1593 KB)  
    Freely Available from IEEE
  • Table of contents

    Page(s): v - xiii
    Save to Project icon | Request Permissions | PDF file iconPDF (168 KB)  
    Freely Available from IEEE
  • Preface

    Page(s): xiv
    Save to Project icon | Request Permissions | PDF file iconPDF (96 KB)  
    Freely Available from IEEE
  • Conference Committees

    Page(s): xv - xx
    Save to Project icon | Request Permissions | PDF file iconPDF (123 KB)  
    Freely Available from IEEE
  • Reviewers

    Page(s): xxi
    Save to Project icon | Request Permissions | PDF file iconPDF (71 KB)  
    Freely Available from IEEE
  • Ear Detection in 3D Profile Images Based on Surface Curvature

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (328 KB) |  | HTML iconHTML  

    Although a number of different ear recognition techniques have been proposed, not much work has been done in the field of ear detection. In this work we present a new ear detection approach for 3D profile images based on surface curvature and semantic analysis of edge-patterns. The algorithm applies edge-based detection techniques, which are known from 2D approaches, to a 3D data model. As an additional result of the ear detection, the outline of the outer helix is found, which may serve as a basis for further feature extraction steps. As our method does not use a reference ear model, the detector does not need any previous training. Furthermore, the approach is robust against rotation and scale. Experiments using the 3D images from UND-J2 collection resulted in a detection rate of 95.65%. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Can Chronological Information be Used as a Soft Biometric in Keystroke Dynamics?

    Page(s): 7 - 10
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (457 KB) |  | HTML iconHTML  

    Keystroke dynamics is a behavioral biometric modality which uses typing patterns on a keyboard to recognize individuals. The way of typing the password slightly changes with time, because of various factors (including user's training). This modification in the way of typing results in a decrease of performance recognition over time. In this paper, we analyse the correlation between the comparison score between a query, and a reference and the number of times the user has typed the password. After having quantified his correlation, we analyse the possibility of using stacked classification to ake this aspect in consideration during authentication. Then, we verify if it is possible to classify users on their way of evolving their typing pattern. Results show that even if comparison scores are correlated with the number of time the user has typed the password, the use of a stacked classifier does not improve the results much. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Web-Based Benchmark for Keystroke Dynamics Biometric Systems: A Statistical Analysis

    Page(s): 11 - 15
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (216 KB) |  | HTML iconHTML  

    Most keystroke dynamics studies have been evaluated using a specific kind of dataset in which users type an imposed login and password. Moreover, these studies are optimistics since most of them use different acquisition protocols, private datasets, controlled environment, etc. In order to enhance the accuracy of keystroke dynamics' performance, the main contribution of this paper is twofold. First, we provide a new kind of dataset in which users have typed both an imposed and a chosen pairs of logins and passwords. In addition, the keystroke dynamics samples are collected in a web-based uncontrolled environment (OS, keyboards, browser, etc.). Such kind of dataset is important since it provides us more realistic results of keystroke dynamics' performance in comparison to the literature (controlled environment, etc.). Second, we present a statistical analysis of well known assertions such as the relationship between performance and password size, impact of fusion schemes on system overall performance, and others such as the relationship between performance and entropy. We put into obviousness in this paper some new results on keystroke dynamics in realistic conditions. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Authentication of Smartphone Users Based on the Way They Walk Using k-NN Algorithm

    Page(s): 16 - 20
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (202 KB) |  | HTML iconHTML  

    Accelerometer-based biometric gait recognition offers a convenient way to authenticate users on their mobile devices. Modern smartphones contain in-built accelerometers which can be used as sensors to acquire the necessary data while the subjects are walking. Hence, no additional costs for special sensors are imposed to the user. In this publication we extract several features from the gait data and use the k-Nearest Neighbour algorithm for classification. We show that this algorithm yields a better biometric performance than the machine learning algorithms we previously used for classification, namely Hidden Markov Models and Support Vector Machines. We implemented the presented method on a smartphone and demonstrate that it is efficient enough to be applied in practice. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Ear Recognition Using Multi-Scale Histogram of Oriented Gradients

    Page(s): 21 - 24
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1130 KB) |  | HTML iconHTML  

    Ear recognition is a promising biometric measure, especially with the growing interest in multi-modal biometrics. Histogram of Oriented Gradients (HOG) have been effectively and efficiently used solving the problems of object detection and recognition, especially when illumination variations are present. This work presents a robust approach for ear recognition using multi-scale dense HOG features as a descriptor of 2D ear images. The multi-scale features assure to capture the different and complicated structures of ear images. Dimensionality reduction was performed to avoid feature redundancy and provide a more efficient recognition process while being prone to over-fitting. Finally, a test was performed on a large and realistic database and the results were compared to the state of the art ear recognition approaches tested on the same dataset and under the same test procedure. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Privacy Implications of Identity References in Biometrics Databases

    Page(s): 25 - 30
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (173 KB) |  | HTML iconHTML  

    We analyze the privacy implications of identity references in biometric databases in which either raw biometric samples or templates are stored. The analysis was inspired by the privacy requirement imposed by the Norwegian National DPA (Data Protection Act Privacy Advisor) on the fingerprint data collection for one of our research projects. The respective DPA approved maintenance of a fingerprint database but required deletion of personal information, e.g., name, gender, age, and email address which were collected and stored in a 'namelist' (XLS-file) as identity references and maintained on a separate hard-disk from the biometric references. We discuss in this paper whether deletion of identity references, as the simplest anonymization way, is appropriate for privacy protection. We take a closer look at the identity attributes and assess to which degree they achieve privacy for an entity based on the proposed criteria. We analyze different biometric database models against the given criteria to give privacy protection guidelines for the identity reference construction and maintenance in a biometric database. In addition, the possibility of joint protection of identity references and biometric references is also investigated in some proposed models suitable for the identity authentication scenario. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient Segmentation of 3D Face Reconstructions

    Page(s): 31 - 34
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (655 KB) |  | HTML iconHTML  

    The segmentation of the face in 3D reconstructions is a crucial processing step within 3D face recognition systems. At this early processing stage discarding other surface portions such as collars, hats or hairstyle shall reduce the amount of data. In contrast to other approaches, the proposed algorithm uses only the face geometry and is therefore robust with respect to lighting conditions or texture quality. Assuming the skin region of a face is locally flat and closed, a binary mask image is created. Morphology and a simple heuristic are applied on connected components to select and join appropriate components. The implementation is straight forward, yielding just a few parameters and copes the problem without training procedure. A proof of concept is given and results are shown for several cases, limitations of the approach are discussed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hiding Identities in Spin Glasses

    Page(s): 35 - 40
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (170 KB) |  | HTML iconHTML  

    Biometric traits are increasingly viewed as the ultimate proof of identity. Unfortunately, biometrics also raises many privacy concerns. In order to overcome these, template protection technologies have been developed in which privacy protection is embedded at the technological level. Standard template protection schemes, however either require secret key management or are vulnerable to brute force and cross-matching attacks and they are unsuitable for identification purposes. Here I review a new key-binding mechanism that I have recently proposed and explain why it is expected to be robust against brute force and cross-matching attacks and how it can be used for identification. The security principle underlying this new template protection scheme is the complexity of the energy landscape of spin glasses. The idea is to exploit the mixed ferromagnetic and spin glass phase of the Hopfield neural network to encode the key as a local minimum configuration of the energy functional, "lost" amidst the exponentially growing number of valleys and minima representing the spin glass. The correct fingerprint will be able to retrieve the key by dynamical evolution to the nearest attractor. Other fingerprints will be driven far away from the key. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sparse Representation for Accurate Person Recognition Using Hand Vein Biometrics

    Page(s): 41 - 44
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1104 KB) |  | HTML iconHTML  

    The sparse representation theories are emerging as a more elegant and powerful technique to represent and analyze the biometric samples. In this paper, we study the feasibility of sparse representation on hand vein biometric data. Since hand vein data consists of rich set of textures, we first represent this texture information using Gabor transform. We then employ the sparse representation classifier to accurately classify this texture information to accurately recognize the individual using hand vein biometrics. Extensive experiments are carried out on public available hand vein data set of 100 users. Finally, the efficacy of the proposed scheme is also validated on the low quality (noisy) hand vein samples. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Finger-vein Verification Using Gabor Filter and SIFT Feature Matching

    Page(s): 45 - 48
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (374 KB) |  | HTML iconHTML  

    In this paper, a novel method to verify the infrared finger-vein patterns is proposed for biometric purposes. Firstly, we select parameters for Gabor filter with eight orientations to exploit finger-vein network, then we extract vein patterns by the fusion of two distinct orientation results. Secondly, we utilize SIFT features to offset the effect of images rotation and shift impact during finger-vein verification. Finally, the number of matching SIFT features between the registered and test finger vein patterns is calculated as the similarity measurement to verify the personal identification. The experiment results show that EER is low to 0.46%, which demonstrates our proposed approach is valid and effective for finger-vein verification. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Revocable ID-based Signature Scheme with Batch Verifications

    Page(s): 49 - 54
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (299 KB) |  | HTML iconHTML  

    Signature scheme is one of important primitives in modern cryptography, which may offer functionalities of user identification, non-repudiation, and message authentication. With the advent of identity (ID)-based public key system (IDPKS) with bilinear pairings, many cryptographic schemes and protocols based on the IDPKS system have been proposed. Though the IDPKS system has the advantage to eliminate certificate management, it is a critical issue to revoke misbehaving or compromised users in this system. Quite recently, Tseng and Tsai presented a practical revocation mechanism using a public channel for the IDPKS system. In this paper, we adopt Tseng and Tsai's revocation concept to propose the first revocable ID-based signature scheme with batch verifications (RID-SBV). Meanwhile, we discuss the several cases of batch verifications. Under the computational Diffie-Hellman assumption, we demonstrate that the proposed RID-SBV scheme is a provably secure signature scheme. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Lossless Data Hiding Based on Smart Boundary Adjustment

    Page(s): 55 - 58
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2014 KB) |  | HTML iconHTML  

    In this paper, we propose a lossless data hiding based on smart boundary adjustment approach. More specifically, by preserving either the minimum or the maximum pixel values of the blocks, data bits can be effectively embedded into the blocks without any occurrence of overflow and underflow. Experiments confirm that perceived quality is good and the payload is large while our peak signal-to-noise ratio (PSNR) is competitive to existing techniques. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Based on Binary Encoding Methods and Visual Cryptography Schemes to Hide Data

    Page(s): 59 - 62
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (337 KB) |  | HTML iconHTML  

    Encoding data based on binary encoding methods and visual cryptography schemes is presented in this paper. First, a visual cryptography scheme is used to share pixels of a covert data to form two shadow matrices by using a specified sharing matrix. Then, the two shadow matrices are encoded into a host image to form an overt image by using a specific encoding rule. The overt image contains four groups of binary codes (specification codes), i.e. identification codes, covert-data dimension codes, sharing-matrix dimension codes, and information codes, to denote the parameters used for sharing and encoding. According to the test results, the proposed method performs well. Moreover, the overt image and the host image look almost the same, and the decoded covert data is exactly the same as the original covert data. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Design and Implementation of a Flash Player Supporting Stereoscopic Image

    Page(s): 63 - 66
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (469 KB) |  | HTML iconHTML  

    Adobe Flash is one of the popular multimedia presentation types in modern computer applications. A Flash player renders 2D vector graphics images, while the image quality is not degraded no matter how it is scaled up or down. A variety of Flash animations and games have been implemented on mobile devices recently, but they are difficult to be played smoothly without a high end processor. Since the OpenVG standard was released and the accelerator was realized, the performance of vector graphics rendering on embedded devices are enhanced. The stereoscopic 3D application has been getting more attention, so we developed a Flash player with a depth map configuration tool to convert a 2D images to 3D based on Depth-Image-Based Rendering (DIBR) algorithm. The enhanced Flash player which supports OpenVG renderer library was realized to display the stereoscopic image by modifying the Gnash to translate the Flash SWF format to the OpenVG, which is then processed by the OpenVG accelerator. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Efficient Algorithm for Protecting and Authenticating Medical Image

    Page(s): 67 - 70
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (312 KB) |  | HTML iconHTML  

    With the advance in the medical image from photographic ï¬lm (analogy) to digital ï¬le, how to avoid medical image modiï¬ed by malice and hide the patient's information into their medical image has become the promising research issue. It is difï¬cult to embed the information of patient to medical images because most pixels of this kind of images are close to black or white. In this paper, an effective method based on singular value decomposition (SVD) is presented to hide the patient's information into medical images which can be used to protect and authenticate their images, called Non-ROI Hidding Algorithm (NRHA). More precisely, the SVD is ï¬rst employed to ï¬nd the features of medical image, and then the information of patient will be hidden in the non-ROI area of the image. To evaluate the performance of the proposed algorithm, we use it to hide the information of patient to several digital medical images. Our experimental results indicate that the proposed method can be used to avoid malicious attacks because it provides an effective way to distinguish good images from malicious ones. As a result, the patient information can be protected by using the proposed method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hiding Secret Messages in Huffman Trees

    Page(s): 71 - 74
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (241 KB) |  | HTML iconHTML  

    A novel scheme for hiding information in Huffman trees is presented. Huffman trees are graphical representations of Huffman codes, which are optimal prefix-free codes generated by a simple algorithm given the distribution of the symbols. Huffman codes are used by MP3 and JPEG file formats for compressing audio and image files, but are also used for text documents and other digital media. The capacity, robustness and security of the information hiding scheme are analyzed and measured empirically. The results show that the scheme achieves a low capacity relative to the size of the cover-object and that the channel is not robust against an active adversary which knows about the channel. The security results show that an informed passive adversary's detection accuracy is greater than 90% if she has access to the symbol distribution and equivalent to pure guessing otherwise. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Perspective Rectification of Integral Images Produced Using Hexagonal Lens Arrays

    Page(s): 75 - 78
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (444 KB) |  | HTML iconHTML  

    Nowadays a plethora of three-dimensional (3D) systems claim users' increasing preference for delivering 3D content. In recent years an increasing number of systems utilize autostereoscopic techniques and hence provide glasses free viewing and adequate resolutions in full color. In addition certain autostereoscopic techniques like Integral Imaging provide two-dimensional (2D) parallax and further increase anticipation for high fidelity 3D content viewing to professional and home users. In this paper we extend the results of previous research to provide perspective distortion rectification for Integral Images generated using hexagonal instead of square lenses. In the proposed method we demonstrate the utilization of a fundamental property of distorted coplanar hexagonal lattices in the image rectification framework that improve the rectification accuracy and robustness. Finally we provide experimental results over a number of images to evaluate the accuracy of the method using objective metrics. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.