FREE ELECTRONIC LIBRARY - Dissertations, online materials

Pages:     | 1 |   ...   | 6 | 7 || 9 | 10 |   ...   | 33 |

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

-- [ Page 8 ] --
lines. By fusing color and curvature information, the detection rate could be raised to 99.3% on the UCR dataset and 87.71% on UND collection F and a subset of collection G. The UCR dataset is not publicly available and is hence not covered in Section 3.2. For a description of this dataset see [6].

Another example for ear detection using contour lines of the ear is described by Attrachi et al. [20]. They locate the outer contour of the ear by searching for the longest connected edge in the edge image. By selecting the top, bottom, and left points of the detected boundary, they form a triangle with the selected points. Further the barycenter of the triangle is calculated and selected as reference point for image alignment. Ansari et al.

also use an edge detector in the first step of their ear localization approach [16]. The edges are separated into two categories, namely convex and concave. Convex edges are chosen as candidates for representing the outer contour. Finally the algorithm connects the curve segments and selects the figure enclosing the largest area for being the outer ear contour.

It should be noted that the IITK database and USTB II already contain cut-out ear images.

Hence it can be put into question, whether the detection rates of 93.34% and 98.05% can be reproduced under realistic conditions.

A recent approach on 2D ear detection using edges is described by Prakash and Gupta in [158]. They combine skin segmentation and categorization of edges into convex and concave edges. Afterwards the edges in the skin region are decomposed into edge segments.

These segments are composed to form an edge connectivity graph. Based on this graph the convex hull of all edges, which are believed to belong to the ear, is computed. The enclosed region is then labeled as the ear region. In contrast to [20], Prakash and Gupta prove the feasibility of edge-based ear detection on full profile images, where they achieved a detection rate of 96.63% on a subset of the UND-J2 collection. In [157] propose the same edge connectivity for ear recognition on 3D images. Instead of edges, they use discontinuities in the depth map for extracting the initial edge image and then extract the connectivity graph. In their experiments, they use the 3D representations of the same subset as in [158] and report a detection rate of 99.38%. Moreover they show that the detection rate of their graph-based approach is not influence by rotation and scale.

Jedges and Mate propose another edge-based ear detection approach, which is likely to be inspired by fingerprint recognition techniques. They train a classifier with orientation pattern, which were previously computed from ear images. Like other naive classifiers, their method is not robust against rotation and scale. Additionally the classifier is likely to fail under large pose variations, because this will affect the appearance of the orientation pattern.

Abaza et al. [4] and Islam et al. [86] use weak classifiers based on Haar-wavelets in connection with AdaBoost for ear localization. According to Islam et al., the training of the classifier takes several days, however once the classifier is set up, ear detection is fast and effective. Abaza et al. use a modified version of AdaBoost and report a significantly shorter training phase. The effectiveness of their approach is proved in evaluations on five different databases. They also include some examples of successful detections on images from the internet. As long as the subject’s pose does not change, weak classifiers are suitable for images which contain more than one subject. Depending on the test set Abaza et al. achieved a detection rate between 84% and 98.7% on the Sheffield Face database. On average, their approach successfully detected 95% of all ears.

Yan and Bowyer developed an ear detection method which fuses range images and corresponding 2D color images [201]. Their algorithm starts by locating the concha and then uses active contours for determining the ear’s outer boundary. The concha serves as the reference point for placing the starting shape of the active contour model. Even though the concha is easy to localize in profile images, it may be occluded if the head pose changes or if a subject is wearing a hearing aid or ear phones. In their experiments Yan and Browyer only use ear images with minor occlusions where the concha is visible; hence it could neither be proved nor disproved whether their approach is capable of reliably

3.3 EAR DETECTION detecting ears if the concha is occluded.

Yuan and Mu developed a method for real-time ear tracking in video sequences by applying Continuously Adaptive Mean Shift (CAMSHIFT) to video sequences [209]. The CAMSHIFT algorithm is frequently used in face tracking applications and is based on region matching and a skin color model. For precise ear segmentation, the contour fitting method based on modified active shape models, which have been proposed by Alvarez et al. is applied [14]. Yuan and Mu report a detection rate of 100%, however the test database only consisted of two subjects. Nevertheless their approach appears to be very promising for surveillance applications but needs to be further evaluated in more realistic test scenarios.

Shih et al. determine ear candidates by localizing arc-shaped edges in an edge image.

Subsequently the arc-shaped ear candidates are verified by using an Adaboost classifier.

They report a detection rate 100% on a dataset, which consists of 376 images from 94 subjects.

Zhou et al. train a 3D shape model in order to recognize the histogram of shape indexes of the typical ear [218]. Similarly to the approaches of Abaza et al. and Islam et al., a sliding window of different sizes is moved over the image. The ear descriptor proposed by Zhou et al. is built from concatenated shape index histograms, which are extracted from subblocks inside the detection window. For the actual detection, an SVM classifier is trained to decide whether an image region is the ear region or not. As far as we know, this is the first ear detection approach, which does not require having corresponding texture images in addition to the range image. Zhou et al. evaluated their approach on images from the UND collections and report a detection rate of 100%. It should be noted that this approach was not tested under rotation, pose variations and major occlusions, but under the impression of the good performance, we think this is an interesting task for future research.

Ear detection methods based on image transformations have the advantage of being robust against out-of-plane rotations. They are designed to highlight specific properties of the outer ear, which occur in each image where the ear is visible no matter in which pose the ear has been photographed. In [17] the Hough transform is used for enhancing regions with a high density of edges. In head profile images, a high density of edges especially occurs in the ear region (see Figure 3.3). In [17] it is reported that the Hough transform based ear detection gets trapped when people wear glasses since the frame introduces additional edges to the image. This especially occurs in the eye and nose region. The ear detection approach based on Hough transform was evaluated on the images in the XM2VTS database (see [6] for a detailed database description), where a detection rate of 91% was achieved.

The ray transform approach proposed in [55] is designed to detect the ear in different poses. Ray transform uses a light ray analogy to scan the image for tubular and curved structures like the outer helix. The simulated ray is reflected in bright tubular regions and hence these regions are highlighted in the transformed image. However, the ray transform also highlights straight edges and edges from other objects, such as hair and glasses (see Figure 3.3). Using this method Alastair et al. achieved am impressive recognition rate of 98.4% on the XM2VTS database. Hence, the ray transform approach by Cummings et al.

outperforms Hough transform, most likely because it is more robust against disruptive factors such as glasses or hair.

A recent approach for 2D ear detection is described in [106]. Kumar et al. propose to extract ears from 2D images by using edge images and active contours. They evaluate their approach on a database, which consists of 100 subjects with 7 images per subject. A special imaging device was used for collecting the data. This device makes sure that the distance to the camera is constant and that the lighting conditions are the same for all images. Within this setting a detection rate of 94.29% is reported.

When putting ear detection into practice, robustness against pose variation and occlusion is of great importance. Nevertheless, most of the ear detection methods described above were not tested with realistic occlusion scenarios, such as occlusion by hair, jewEAR BIOMETRICS: A SURVEY OF DETECTION, FEATURE EXTRACTION AND


–  –  –

ellery or headdresses. A possible reason for this may be the lack of databases containing appropriate images, but this gap has been filled recently by different working groups, who contributed appropriate datasets (see Section 3.2). Furthermore, to our best knowledge there are no investigations on the effect of occlusion in 3D ear images.

3.4 2D Ear Recognition Each ear recognition system consists of a feature extraction and a feature vector comparison step. In this survey we divide ear recognition approaches into four different subclasses namely holistic approaches, local approaches, hybrid approaches and statistical approaches.

In Tables 3.2 and 3.3 all 2D ear recognition approaches mentioned in this paper are summarized in chronological order.

3.4.1 Holistic Descriptors Another approach, which has gained some popularity is the Force Field Transform by Hurley [80]. The Force Field transformation approach assumes that pixels have a mutual attraction proportional to their intensities and inversely to the square of the distance between them rather like Newton’s universal law of gravitation. The associated energy field takes the form of a smooth surface with a number of peaks joined by ridges (see Figure 3.4.1).

3.4 2D EAR RECOGNITION Table 3.2: Summary of approaches for 2D ear recognition, part 1. Unless stated differently, performance always refers to rank-1 performance.

–  –  –



Table 3.3: Summary of approaches for 2D ear recognition, part 2. Unless stated differently, performance always refers to rank-1 performance.

–  –  –

Using this method, Hurley et al. achieved a rank-1 performance of more than 99% on the XM2VTS database (252 images). Building on these results, Abdel-Mottaleb and Zhou use a 3D representation of the force field for extracting points lying on the peak of the 3D force field [7]. Because the force field converged at the outline of the ear, the peaks in the 3D representation basically represent the ear contour. Nonetheless, the force field method is more robust against noise than other edge detector, such as Sobel or Canny. Using this approach, Abdel-Mottaleb and Zhou achieved a rank-1 performance of 87.93% on a dataset with consists of 103 ear images from 29 subjects.

Dong and Mu [63] add pose invariance to the edges, which are extracted by using the force field method. This is achieved with null space kernel fishier discriminant analysis (NKFDA), which has the property of representing non-linear relations between two datasets. Dong and Mu conducted experiments on the USTB IV dataset. Before feature extraction, the ear region was cropped out manually from the images and the pose is normalized. For pose variations of 30 degrees they report a rank-1 recondition rate of 72.2%.

For pose variations of 45 degrees the rank-1 performance dropped to 48.1%.

In a recent publication of Kumar and Wu [107] they present an ear recognition approach, which uses the phase information of Log-Gabor filters for encoding the local structure of the ear. The encoded phase information is stored in normalized grey level images. In the experiments, the Log-Gabor approach outperformed force field features and a landmarkbased feature extraction approach. Moreover, different combinations of Log-Gabor filters were compared with each other. The rank-e performance for the Log-Gabor approaches ranges between 92.06% and 95.93% on a database which contains 753 images from 221 subjects.

The rich structure of the outer ear results in specific texture information, which can be measured using Gabor filters. Wang and Yuan [190] extract local frequency features by using a battery of Gabor filters and then select the most distinctive features by using general discriminant analysis. In their experiments on the USTB II database, they compared the performance impact of different settings for the Gabor filters. Different combinations of orientation and scales in the filter sets are compared with each other and it was found that neither the number of scales nor the number of orientations has a major impact on the rankperformance. The total rank-1 performance of Wang and Yuan’s approach is 99.1%. In a similar approach Arbab-Zavar and Nixon [18] measured the performance of Gabor filters in the XM2VTS database where they report a rank-1 performance of 91.5%. A closer look at the Gabor filter response showed that the feature vectors are corrupted by occlusion or other disruptive factors. In order to overcome this, a more robust comparison method is proposed, which resulted in an improved recognition rate of 97.4%.

Pages:     | 1 |   ...   | 6 | 7 || 9 | 10 |   ...   | 33 |

Similar works:

«Philosophy Compass (2015): 1–11, 10.1111/phc3.12290 The Importance of Knowledge Ascriptions Michael J. Hannon* Fordham University Abstract Knowledge ascriptions of the form ‘S knows that p’ are a central area of research in philosophy. But why do humans think and talk about knowledge? What are knowledge ascriptions for? This article surveys a variety of proposals about the role (or roles) of knowledge ascriptions and attempts to provide a unified account of these seemingly distinct views....»

«Knowledge Driven Search Intent Mining A thesis submitted in partial fulfilment of the requirements for the degree of Doctor of Philosophy By ASHUTOSH JADHAV B.E., Veermata Jijabai Technological Institute, 2006 M.S., Wright State University, 2008 Wright State University Dayton, Ohio 45435 WRIGHT STATE UNIVERSITY GRADUATE SCHOOL April 18, 2016 I HEREBY RECOMMEND THAT THE THESIS PREPARED UNDER MY SUPERVISION BY Ashutosh Jadhav ENTITLED Knowledge Driven Search Intent Mining BE ACCEPTED IN PARTIAL...»

«Development of a Neurostimulation Method Using Pulsed Ultrasound by Yusuf Zahid Tufail A Dissertation Presented in Partial Fulfillment of the Requirements for the Degree Doctor of Philosophy Approved March 2011 by the Graduate Supervisory Committee: William Tyler, Chair Carsten Duch Jitendran Muthuswamy Marco Santello Stephen Tillery ARIZONA STATE UNIVERSITY May 2011 UMI Number: 3453551 All rights reserved INFORMATION TO ALL USERS The quality of this reproduction is dependent upon the quality...»

«LINGUISTIC TRANSFER IN ANDEAN SPANISH: SYNTAX OR PRAGMATICS? BY ANTJE MUNTENDAM DISSERTATION Submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Spanish in the Graduate College of the Urbana, Illinois University of Illinois at Urbana-Champaign, 2009 Urbana, Illinois Urbana, Illinois Doctoral Committee: Assistant Professor Karlos Arregui-Urbina, Chair Professor Rakesh Bhatt Professor Silvina Montrul Professor Pieter Muysken, Radboud University Nijmegen...»

«ABSTRACT Title of Dissertation: A QUALITATIVE STUDY OF CHARACTERISTICS, COMPETENCIES, AND STRATEGIES OF TRANSITION STAFF WORKING WITH URBAN LATINO/A YOUTH WITH DISABILITIES Omayra Muñoz-Lorenzo, Doctor of Philosophy, 2012 Dissertation Directed by: Dr. Ellen Fabian Department of Counseling, Higher and Special Education The purpose of this qualitative study was to explore characteristics, competencies, and strategies of transition program employment representatives who attain successful...»

«‘DIVINE SIMPLICITY: A DOGMATIC ACCOUNT’ Steven J. Duby A Thesis Submitted for the Degree of PhD at the University of St Andrews Full metadata for this item is available in Research@StAndrews:FullText at: http://research-repository.st-andrews.ac.uk/ Please use this identifier to cite or link to this item: http://hdl.handle.net/10023/5935 This item is protected by original copyright ‘Divine Simplicity: A Dogmatic Account’ Steven J. Duby A Thesis presented for the Degree of Doctor of...»


«Assertive Community Treatment Implementation Resource Kit DRAFT VERSION Implementation Resource Kit User’s Guide Table of Contents Acknowledgments Foreword Introduction Background Project Philosophy and Values Components of the Assertive Community Treatment Implementation Resource Kit How to Use the Resource Kit Materials—An Implementation Plan A Word About Terminology Implementing Evidence-Based Practices Project Annotated Bibliography for Assertive Community Treatment Special Populations...»

«Investigaciones Fenomenológicas, vol. Monográfico 4/I (2013): Razón y vida, 351-360. e-ISSN: 1885-1088 THE MELODY OF LIFE. MERLEAU-PONTY, READER OF JACOB VON UEXKÜLL LA MELODÍA DE LA VIDA. MERLEAU-PONTY, LECTOR DE JACOB VON UEXKÜLL Luís António Umbelino Associação Portuguesa de Filosofia Fenomenológica (APFFEN)/ Universidade de Coimbra, Portugal luis.um@megamail.pt Abstract: This paper aims to meditate on the Resumen: Este artículo trata de meditar acerca importance of Jacob von...»

«COMPUTATIONAL AND RHEOLOGICAL STUDY OF WAX DEPOSITION AND GELATION IN SUBSEA PIPELINES by Hyun Su Lee A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy (Chemical Engineering) in The University of Michigan 2008 Doctoral Committee: Professor H. Scott Fogler, Chair Professor Werner J.A. Dahm Professor Robert M. Ziff Assistant Professor Joerg Lahann Hyun Su Lee © 2008 All Rights Reserved To My wife Myung-Jin ii ACKNOWLEDGEMENTS First and...»

«The Diverse Geographies of Jewishness: Exploring the Intersections between Race, Religion, and Citizenship among Israeli Migrants in Toronto by Tamir Arviv A thesis submitted in conformity with the requirements for the degree of Doctor of Philosophy Department of Geography and Planning University of Toronto © Copyright by Tamir Arviv 2016 ii The Diverse Geographies of Jewishness: Exploring the Intersections between Race, Religion, and Citizenship among Israeli Migrants in Toronto Tamir Arviv...»

«Interacting With Surfaces In Four Dimensions Using Computer Graphics TR93-011 March, 1993 David Banks Department of Computer Science University of North Carolina at Chapel Hill Chapel Hill, NC 27599-3175 UNO is an Equal Opportunity/Affirmative Action Institution. Interacting With Surfaces In Four Dimensions Using Computer Graphics A dissertation submitted to the faculty of the University ofNonh Carolina in partial fulfillment of lhe requirements for the degree of Doctor of Philosophy in lhe...»

<<  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.