FREE ELECTRONIC LIBRARY - Dissertations, online materials

Pages:     | 1 |   ...   | 8 | 9 || 11 | 12 |   ...   | 33 |

«Ear Recognition Biometric Identification using 2- and 3-Dimensional Images of Human Ears Anika Pflug Thesis submitted to Gjøvik University College ...»

-- [ Page 10 ] --

3.5 3D EAR RECOGNITION LLE ( 43%) is improved significantly by their method to 60.75%. If the pose variation is only 10 degrees, the improved LLE approach achieved a rank-1 performance of 90%.

In their approach Nanni and Lumini [132] propose to use Sequential Forward Floating Selection (SFFS), which is a statistical iterative method for feature selection in pattern recognition tasks. SFFS tries to find the best set of classifiers by creating a set of rules, which best fits the current feature set. The sets are created by adding one classifier at a time and evaluating its discriminative power with a predefined fitness function. If the new set of rules outperforms the previous version, the new rule is added to the final set of rules. The experiments were carried out on the UND collection E and the single classifiers are fused by using the weighted sum rule. SFFS selects the most discriminative sub-windows which correspond to the fittest set of rules. Nanni and Lumini report a rank-1 recognition rate of 80% and a rank-5 recognition rate of 93%. The EER varies between 6.07% and 4.05% depending on the number of sub-windows used for recognition.

Yiuzono et al. consider the problem of finding corresponding features in ear images as an optimization problem and apply genetic local search for solving it iteratively [210]. They select local sub windows with varying size as the basis for the genetic selection. In [210] Yiuzono et al. present elaborated results, which describe the behavior of genetic local search under different parameters, such as different selection methods and different numbers of chromosomes. On a database of 110 subjects they report a recognition rate of 100%.

Yaqubi et al. use features obtained by a combination of position and scale-tolerant edge detectors over multiple positions and orientations of the image [204]. This feature extraction method is called HMAX model and is inspired by the visual cortex of primates and combines simple features to more complex semantic entities. The extracted features are classified with an SVN and a kNN. The rank-1 performance on a small dataset of 180 cropped ear images from 6 subjects varies between 62% and 100% depending on the kind of basis features.

Moreno et al. implement a feature extractor, which locates seven landmarks on the ear image, which correspond to the salient points from the work of Iannarelli. Additionally they obtain a morphology vector, which describes the ear as a whole. These two features are used as the input for different neural network classifiers. They compare the performance of each of the single feature extraction techniques with different fusion methods.

The proprietary test database is composed of manually cropped ears from 168 from 28 subjects. The best result of 93% rank-1 performance was measures using a compression network. Other configurations yielded error rates between 16% and 57%.

Gutierrez et al. [73] divide the cropped ear images into three equally sized parts. The upper part shows the helix, the middle part shows the concha and the lower part shows the lobule. Each of these sub images is decomposed by wavelet transform and then fed into a modular neural network. In each module of the network a different integrators and learning functions was used. The results of each of the modules are fused in the last step for obtaining the final decision. Depending on the combination between integrator and learning function, the results vary between 88.4% and 97.47% rank-1 performance on the USTB I database. The highest rank-1 performance is achieved with Sugeno measure and conjugate gradient.

In [133] Nasseem et al. propose a general classification algorithm based on the theory of compressive sensing. They assume that most signals are compressible in nature and that any compression function results in a sparse representation of this signal. In their experiments in the UND database and the FEUD database, Nasseem et al. show that their sparse representation method is robust against pose variations and varying lighting conditions. The rank-1 performance varied between 89.13% and 97.83%, depending on the dataset used in the experiment.



Table 3.4: Summary of approaches for 3D ear recognition. Performance (Perf.) always refers to rank-1 performance.

–  –  –

3.5 3D Ear Recognition In 2D ear recognition pose variation and variation in camera position, so-called out-ofplane-rotations, are still unsolved challenges. A possible solution is using 3D models instead of photos as references, because a 3D representation of the subject can be adapted to any rotation, scale and translation. In addition to that, the depth information contained in 3D models can be used for enhancing the accuracy of an ear recognition system. However, most 3D ear recognition systems tend to be computationally expensive. In Table 3.4 all 3D ear recognition systems described in this section are summarized.

Although ICP is originally designed to be an approach for image registration, the registration error can also be used as a measure for the dissimilarity of two 3D images. Because ICP is designed to be a registration algorithm, it is robust against all kinds of translation or rotations. However ICP tends to stop too early, because it gets stuck in local minima.

Therefore ICP requires the two models to be coarsely pre-aligned before fine alignment using ICP can be performed. Chen and Bhanu extract point clouds from the contour of the outer helix and the register these points with the reference model by using ICP [47]. In a later approach Chen and Bhanu use local surface patches (LSP) instead of points lying on the outer helix [49]. As the LSP consist or fewer points than the outer helix, this reduces the processing time while enhancing the rank-1 performance from 93.3% with the outer helix points to 96.63 % with LSP.

Yan and Browyer decompose the ear model into voxels and extract surface features from each of these voxels. For speeding up the alignment process, each voxel is assigned an index in such a way that ICP only needs to align voxel pairs with the same index [200] (see

3.5 3D EAR RECOGNITION Figure 3.8). In [201] Yan and Browyer propose the usage of point clouds for 3D ear recognition. In contrast to [47] all points of the segmented ear model are used. The reported performance measures of 97.3% in [200] and 97.8% in [201] is similar but not directly comparable, because different datasets were used for evaluation.

Cadavid et al. propose a real-time ear recognition system, which reconstructs 3D models from 2D CCTV images using the shape from shading technique [41]. Thereafter the 3D model is compared to the reference 3D images, which are stored in the gallery. Model alignment as well as the computation of the dissimilarity measure is done by ICP. Cadavid et al. report a recognition rate of 95% on a database of 402 subjects. It is stated in [41] that the approach has difficulties with pose variations. In [219] Zhou et. al. use a combination of local histogram features voxel-models. Zhou et. al. report that their approach is faster and with an EER of 1.6% it is also more accurate than the ICP-based comparison algorithms proposed by Chen and Bhanu and Yan and Browyer.

Simlarly to Cadavid et al., Liu et al. reconstruct 3D ear models from 2D views [115].

Based on the two images of a stereo vision camera, a 3D representation of the ear is derived.

Subsequently the resulting 3D meshes serve as the input for PCA. However Liu et al. do not provide any results concerning the accuracy of their system but since they did not publish any further results on their PCA mesh approach, it seems that it is no longer pursued.

Passalis et al. go a different way for comparing 3D ear models in order to make comparison suitable for a real-time system [144]. They compute a reference ear model which is representative for the average human ear. During enrolment, all reference models are deformed until they fit the reference ear model. All translations and deformations, which were necessary to fit the ear to the reference model are then stored as features. If a probe for authentication is given to the system, the model is also adapted to the annotated ear model in order to get the deformation data. Subsequently the deformation data is used to search for an associated reference model in the gallery. In contrast to the previously described systems, only one deformation has to be computed per authentication attempt. All other deformation models can be computed before the actual identification process is started.

This approach is reported to be suitable for real-time recognition systems, because it takes less than 1 milliseconds for comparing two ear templates. The increased computing speed is achieved by lowering the complexity class from O(n)2 for ICP-based approaches to O(n) for their approach. The rank-1 recognition rate is reported to be 94.4%. The evaluation is based on non-public data, which was collected using different sensors.

Heng and Zhang propose a feature extraction algorithm based on slice curve comparison, which is inspired by the principles of computer tomography [116]. In their approach the 3D ear model is decomposed into slices along the orthogonal axis of the longest distance between the lobule and the uppermost part of the helix. The curvature information extracted from each slice is stored in a feature vector together with an index value indicating the slice’s former position in the 3D model. For comparison the longest common sequence between two slice curves with similar indexes is determined. Their approach is only evaluated on a non-public dataset, which consists of 200 images from 50 subjects. No information about pose variations or occlusion during the capturing experiment is given.

Heng and Zhang report a rank-1 performance of 94.5% for the identification experiment and 4.6%EER for the verification experiment.

Islam et al. reconnect point clouds describing 3D ear models to meshes and iteratively reduce the number of faces in the mesh [85]. These simplified meshes are then aligned with each other using ICP and the alignment error is used as the similarity measure for the two simplified meshes. In a later approach Islam et al. extract local surface patches as shown in Figure 3.9 and use them as features [86]. For extracting those LSP, a number of points is selected randomly from the 3D model. Then the data points which are closer to the seed point than a defined radius are selected. PCA is then applied to find the most descriptive features in the LSP. The feature extractor repeats selecting LSP until the desired number of features has been found. Both approaches were evaluated using images from UND. The



Figure 3.8: Examples for surface features in 3D ear images. The left image shows an example for ICP-based comparison as proposed in [47], whereas the right figure illustrates feature extraction from voxels as described in [200].

Figure 3.9: Example for local surface patch (LSP) features as proposed in [86] recognition rate reported for [85] is 93.

98% and the recognition rate reported for [86] is 93.5%. However, none of the approaches has been tested with pose variation and different scaling.

Zheng et al. extract the shape index at each point in the 3D model and use it for projecting the 3D model to 2D space [211]. The 3D shape index at each pixel is represented by a grey value at the corresponding position in the 2D image. Then SIFT features are extracted from the shape index map. For each of the SIFT points a local coordinate system is calculated where the z-axis correspondents to the feature point’s normal. Hence the z-values of the input image are normalized according to the normal of the SIFT feature point they were assigned to. As soon as the z values have been normalized, they are transformed into a grey level image. As a result, Zheng et al. get a local grey level image for each of the selected SIFT features. Next LBP are extracted for feature representation in each of these local grey level images. Comparison is first performed by coarsely comparing the shape indexes of key pints and then using Earth mover’s distance for comparing LBP histograms from the corresponding normalized grey images. Zheng et al. evaluated their approach on a subset of the UND-J2 Collected and achieved a rank-1 performance of 96.39%.

3.6 Open challenges and future applications As the most recent publications on 2D and 3D ear recognition show, the main application of this technique is personal identification in unconstrained environments. This includes applications for smart surveillance, such as in [40] but also the forensic identification of perpetrators on CCTV images or for border control systems. Traditionally these application


fields are part of face recognition systems but as the ear is located next to the face, it can provide valuable additional information to supplement the facial images.

Multi modal ear and face recognition systems can serve as a means of achieving pose invariance and more robustness against occlusion in unconstrained environments. In most public venues surveillance cameras are located overhead in order to capture as many persons as possible and to protect them from vandalism. In addition, most of the persons will not look straight into the camera, so in most cases no frontal images of the persons will be available. This fact poses serious problems to biometric systems, using facial features for identification. If the face is not visible from a frontal angle, the ear can serve as a valuable additional characteristic in these scenarios.

Because of the physical proximity of the face and the ear, there are also many possibilities for the biometric fusion of these two modalities. Face and ear images can be fused on the feature level, on the template level and on the score level. Against the background of this application, there are some unsolved challenges, which should be addressed by future research in this field.

Pages:     | 1 |   ...   | 8 | 9 || 11 | 12 |   ...   | 33 |

Similar works:

 Troy Rhoades A Thesis In The Humanities Program Presented in Partial Fulfillment of the Requirements For the Degree of Doctor of Philosophy at Concordia University Montreal, Quebec, Canada June, 2011 © Troy Rhoades 2011 CONCORDIA UNIVERSITY SCHOOL OF GRADUATE STUDIES This is to certify that the thesis prepared By: Troy Rhoades Entitled: The Elusive Made Present: Art and Incipiency of Images and submitted in...»

«BLOW THE TRUMPET IN BLACK ZION: A PHENOMENOLOGICAL EXPLORATION OF THE ZIONIST CHRISTIAN CHURCH OF SOUTH AFRICA By Victoria Morongwa Peagler A Dissertation Presented to the Faculty of the School of Intercultural Studies FULLER THEOLOGICAL SEMINARY In Partial Fulfillment of the Requirements for the Degree Doctor of Philosophy in Intercultural Studies April 2010 UMI Number: 3444427 All rights reserved INFORMATION TO ALL USERS The quality of this reproduction is dependent upon the quality of the...»

«Forthcoming in Philosophical Perspectives 15 (2001) Russellianism and Explanation David Braun University of Rochester Russellianism is a semantic theory that entails that sentences (1) and (2) express the same proposition, as long as the names 'Mark Twain' and 'Samuel Clemens' refer to the same person. (1) Albert believes that Mark Twain is an author. (2) Albert believes that Samuel Clemens is an author. Many philosophers think that the Substitution Objection decisively refutes Russellianism....»

«Intelligent Fault Location for Smart Power Grids Hanif Livani Dissertation submitted to the faculty of the Virginia Polytechnic Institute and State University in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Electrical Engineering Cansin Yaman Evrenosoglu, Co-Chair Jaime De La Reelopez, Co-Chair Virgilio A. Centeno William T. Baumann Serkan Gugercin March 6 2014 Blacksburg, VA Keywords: Fault Location, Fault Classification, Smart Power Grids, Support Vector...»

«Cambridge University Press 978-0-521-87347-5 The Cambridge Companion to Epicureanism Edited by James Warren Excerpt More information james warren Introduction Philosophy, as long as a drop of blood shall pulse in its world-subduing and absolutely free heart, will never grow tired of answering its adversaries with the cry of Epicurus: ‘The truly impious man is not he who denies the gods worshipped by the multitude, but he who affirms of the gods what the multitude believes about them’. Karl...»

 Copyright by Tania Heather Cantrell The Dissertation Committee for Tania Heather Cantrell certifies that this is the approved version of the following dissertation: How Do News Issues Help Frame Telenovela Plots? A Framing Analysis of Brazilian Print National Press and TV Globo’s 8 p.m. Telenovela Duas Caras [Two Faced/s] Committee: Stephen D. Reese, Co-Supervisor Joseph D. Straubhaar, Co-Supervisor Renita Coleman Dustin Harp América...»

«Expressing Disagreement What disagreement can teach us about semantics, and what semantics can teach us about disagreement* Isidora Stojanovic Institut Jean-Nicod (CNRS & ENS, PSL Research University), 29 rue d'Ulm, 75005 Paris, France isidora.stojanovic@ens.fr preliminary draft for the conference “Faces of Disagreement” Montreal, 26-28 May 2016 Abstract. This paper is an occasion to take stock of the place that the argument from (faultless) disagreement has occupied in philosophy of...»

«Maternal Sensitivity in Mother-Infant Interactions for Infants with and without Prenatal Alcohol Exposure Jennifer M. Nash A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy University of Washington 2013 Reading Committee: Tracy Jirikowic, Chair Marcia Ciol Deborah Kartin Susan Spieker Program Authorized to Offer Degree: Rehabilitation Science ©Copyright 2013 Jennifer M. Nash 2 University of Washington Abstract Maternal Sensitivity in...»

«Rabbinic Discourse on Divination in the Babylonian Talmud by Stephanie L. Bolz A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy (Near Eastern Studies) in The University of Michigan 2012 Doctoral Committee: Professor Gabriele Boccaccini, Co-Chair Professor Richard Kalmin, Co-Chair, The Jewish Theological Seminary Associate Professor Brian B. Schmidt Assistant Professor Rachel Neis © Stephanie L. Bolz 2012 ACKNOWLEDGMENTS In the process...»

«The International Association of Buddhist Universities (IABU) Buddhist Philosophy and Meditation Practice Academic Papers presented at the 2nd IABU Conference Mahachulalongkornrajavidyalaya University, Main Campus Wang Noi, Ayutthaya, Thailand The International Association of Buddhist Universities 2012 IABU Editorial Committee: Ven. Dr. Khammai Dhammasami Prof. Padmasiri de Silva Prof. Sarah Shaw Dr. Dion Peoples Jamie Cresswell Toshiichi Endo (2) Preface Mahachulalongkornrajavidyalaya...»

«EXPLORING THE IMPACT OF ONGOING COLONIAL VIOLENCE ON ABORIGINAL STUDENTS IN THE POSTSECONDARY CLASSROOM by Sheila Cote-Meek A thesis submitted in conformity with the requirements for the degree of Doctor of Philosophy Graduate Department of Sociology and Equity Studies in Education Ontario Institute for Studies in Education University of Toronto © Copyright by Sheila Cote-Meek 2010 EXPLORING THE IMPACT OF ONGOING COLONIAL VIOLENCE ON ABORIGINAL STUDENTS IN THE POSTSECONDARY CLASSROOM Doctor of...»

«Young Children’s Representations of Emotions and Attachment in Their Spontaneous Patterns of Behaviour: An Exploration of a Researcher’s Understanding C. Arnold PhD Young Children’s Representations of Emotions and Attachment in Their Spontaneous Patterns of Behaviour: An Exploration of a Researcher’s Understanding C. Arnold PhD “A thesis submitted in partial fulfilment of the University’s requirements for the degree of Doctor of Philosophy” Awarding Institution: Coventry...»

<<  HOME   |    CONTACTS
2016 www.dissertation.xlibx.info - Dissertations, online materials

Materials of this site are available for review, all rights belong to their respective owners.
If you do not agree with the fact that your material is placed on this site, please, email us, we will within 1-2 business days delete him.