AdaBoost Multiple Feature Selection and Combination for Face Recognition

Gabor features have been recognized as one of the most successful face representations. Encouraged by the results given by this approach, other kind of facial representations based on Steerable Gaussian first order kernels and Harris corner detector are proposed in this paper. In order to reduce the high dimensional feature space, PCA and LDA techniques are employed. Once the features have been extracted, AdaBoost learning algorithm is used to select and combine the most representative features. The experimental results on XM2VTS database show an encouraging recognition rate, showing an important improvement with respect to face descriptors only based on Gabor filters.

Bioinformatics inspired algorithm for stereo correspondence

In this paper, we exploit the analogy between protein sequence alignment and image pair correspondence to design a bioinformatics-inspired framework for stereo matching based on dynamic programming. This approach also led to the creation of a meaningfulness graph, which helps to predict matching validity according to image overlap and pixel similarity. Finally, we propose an automatic procedure to estimate automatically all matching parameters. This work is evaluated qualitatively and quantitatively using a standard benchmarking dataset and by conducting stereo matching experiments between images captured at different resolutions. Results confirm the validity of the computer vision/bioinformatics analogy to develop a versatile and accurate low complexity stereo matching algorithm.

A sequential algorithm for sparse support vector classifiers

Support vector machines (SVMs), though accurate, are not preferred in applications requiring high classification speed or when deployed in systems of limited computational resources, due to the large number of support vectors involved in the model. To overcome this problem we have devised a primal SVM method with the following properties: (1) it solves for the SVM representation without the need to invoke the representer theorem, (2) forward and backward selections are combined to approach the final globally optimal solution, and (3) a criterion is introduced for identification of support vectors leading to a much reduced support vector set. In addition to introducing this method the paper analyzes the complexity of the algorithm and presents test results on three public benchmark problems and a human activity recognition application. These applications demonstrate the effectiveness and efficiency of the proposed algorithm.


--------------------------------------------------------------------------------

Optimization of Weighted Finite State Transducer for Speech Recognition

There is considerable interest in creating embedded, speech recognition hardware using the weighted finite state transducer (WFST) technique but there are performance and memory usage challenges. Two system optimization techniques are presented to address this; one approach improves token propagation by removing the WFST epsilon input arcs; another one-pass, adaptive pruning algorithm gives a dramatic reduction in active nodes to be computed. Results for memory and bandwidth are given for a 5,000 word vocabulary giving a better practical performance than conventional WFST; this is then exploited in an adaptive pruning algorithm that reduces the active nodes from 30,000 down to 4,000 with only a 2 percent sacrifice in speech recognition accuracy; these optimizations lead to a more simplified design with deterministic performance.

Common-sense reasoning for human action recognition

This paper presents a novel method that leverages reasoning capabilities in a computer vision system dedicated to human action recognition. The proposed methodology is decomposed into two stages. First, a machine learning based algorithm - known as bag of words - gives a first estimate of action classification from video sequences, by performing an image feature analysis. Those results are afterward passed to a common-sense reasoning system, which analyses, selects and corrects the initial estimation yielded by the machine learning algorithm. This second stage resorts to the knowledge implicit in the rationality that motivates human behaviour. Experiments are performed in realistic conditions, where poor recognition rates by the machine learning techniques are significantly improved by the second stage in which common-sense knowledge and reasoning capabilities have been leveraged. This demonstrates the value of integrating common-sense capabilities into a computer vision pipeline. © 2012 Elsevier B.V. All rights reserved.

Sensitivity and specificity of frequency-doubling technology, tendency-oriented perimetry, and Humphrey Swedish interactive threshold algorithm-fast perimetry in a glaucoma practice

PURPOSE: To evaluate the sensitivity and specificity of the screening mode of the Humphrey-Welch Allyn frequency-doubling technology (FDT), Octopus tendency-oriented perimetry (TOP), and the Humphrey Swedish Interactive Threshold Algorithm (SITA)-fast (HSF) in patients with glaucoma. DESIGN: A comparative consecutive case series. METHODS: This was a prospective study which took place in the glaucoma unit of an academic department of ophthalmology. One eye of 70 consecutive glaucoma patients and 28 age-matched normal subjects was studied. Eyes were examined with the program C-20 of FDT, G1-TOP, and 24-2 HSF in one visit and in random order. The gold standard for glaucoma was presence of a typical glaucomatous optic disk appearance on stereoscopic examination, which was judged by a glaucoma expert. The sensitivity and specificity, positive and negative predictive value, and receiver operating characteristic (ROC) curves of two algorithms for the FDT screening test, two algorithms for TOP, and three algorithms for HSF, as defined before the start of this study, were evaluated. The time required for each test was also analyzed. RESULTS: Values for area under the ROC curve ranged from 82.5%-93.9%. The largest area (93.9%) under the ROC curve was obtained with the FDT criteria, defining abnormality as presence of at least one abnormal location. Mean test time was 1.08 ± 0.28 minutes, 2.31 ± 0.28 minutes, and 4.14 ± 0.57 minutes for the FDT, TOP, and HSF, respectively. The difference in testing time was statistically significant (P <.0001). CONCLUSIONS: The C-20 FDT, G1-TOP, and 24-2 HSF appear to be useful tools to diagnose glaucoma. The test C-20 FDT and G1-TOP take approximately 1/4 and 1/2 of the time taken by 24 to 2 HSF. © 2002 by Elsevier Science Inc. All rights reserved.

Toward Unconstrained Ear Recognition From Two-Dimensional Images

Ear recognition, as a biometric, has several advantages. In particular, ears can be measured remotely and are also relatively static in size and structure for each individual. Unfortunately, at present, good recognition rates require controlled conditions. For commercial use, these systems need to be much more robust. In particular, ears have to be recognized from different angles ( poses), under different lighting conditions, and with different cameras. It must also be possible to distinguish ears from background clutter and identify them when partly occluded by hair, hats, or other objects. The purpose of this paper is to suggest how progress toward such robustness might be achieved through a technique that improves ear registration. The approach focuses on 2-D images, treating the ear as a planar surface that is registered to a gallery using a homography transform calculated from scale-invariant feature-transform feature matches. The feature matches reduce the gallery size and enable a precise ranking using a simple 2-D distance algorithm. Analysis on a range of data sets demonstrates the technique to be robust to background clutter, viewing angles up to +/- 13 degrees, and up to 18% occlusion. In addition, recognition remains accurate with masked ear images as small as 20 x 35 pixels.

3D Morphable Model Construction for Robust Ear and Face Recognition

Recent work suggests that the human ear varies significantly between different subjects and can be used for identification. In principle, therefore, using ears in addition to the face within a recognition system could improve accuracy and robustness, particularly for non-frontal views. The paper describes work that investigates this hypothesis using an approach based on the construction of a 3D morphable model of the head and ear. One issue with creating a model that includes the ear is that existing training datasets contain noise and partial occlusion. Rather than exclude these regions manually, a classifier has been developed which automates this process. When combined with a robust registration algorithm the resulting system enables full head morphable models to be constructed efficiently using less constrained datasets. The algorithm has been evaluated using registration consistency, model coverage and minimalism metrics, which together demonstrate the accuracy of the approach. To make it easier to build on this work, the source code has been made available online.

Robust 2D Ear Registration and Recognition Based on SIFT Point Matching

Significant recent progress has shown ear recognition to be a viable biometric. Good recognition rates have been demonstrated under controlled conditions, using manual registration or with specialised equipment. This paper describes a new technique which improves the robustness of ear registration and recognition, addressing issues of pose variation, background clutter and occlusion. By treating the ear as a planar surface and creating a homography transform using SIFT feature matches, ears can be registered accurately. The feature matches reduce the gallery size and enable a precise ranking using a simple 2D distance algorithm. When applied to the XM2VTS database it gives results comparable to PCA with manual registration. Further analysis on more challenging datasets demonstrates the technique to be robust to background clutter, viewing angles up to +/- 13 degrees and with over 20% occlusion.

Pattern Recognition Approach for Road Collision Hotspots Analysis: Case Study of Northern Ireland

In order to address road safety effectively, it is essential to understand all the factors, which
attribute to the occurrence of a road collision. This is achieved through road safety
assessment measures, which are primarily based on historical crash data. Recent advances
in uncertain reasoning technology have led to the development of robust machine learning
techniques, which are suitable for investigating road traffic collision data. These techniques
include supervised learning (e.g. SVM) and unsupervised learning (e.g. Cluster Analysis).
This study extends upon previous research work, carried out in Coll et al. [3], which
proposed a non-linear aggregation framework for identifying temporal and spatial hotspots.
The results from Coll et al. [3] identified Lisburn area as the hotspot, in terms of road safety,
in Northern Ireland. This study aims to use Cluster Analysis, to investigate and highlight any
hidden patterns associated with collisions that occurred in Lisburn area, which in turn, will
provide more clarity in the causation factors so that appropriate countermeasures can be put
in place.

Gait period estimation algorithm based on the angles of extremities

Gait period estimation is an important step in the gait recognition framework. In this paper, we propose a new gait cycle detection method based on the angles of extreme points of both legs. In addition to that, to further improve the estimation of the gait period, the proposed algorithm divides the gait sequence into sections before identifying the maximum values. The proposed algorithm is scale invariant and less dependent on the silhouette shape. The performance of the proposed method was evaluated using the OU-ISIR speed variation gait database. The experimental results show that the proposed method achieved 90.2% gait recognition accuracy and outperforms previous methods found in the literature with the second best only achieved 67.65% accuracy.

A Fast Algorithm for Sparse Support Vector Machines for Mobile Computing Applications

This research presents a fast algorithm for projected support vector machines (PSVM) by selecting a basis vector set (BVS) for the kernel-induced feature space, the training points are projected onto the subspace spanned by the selected BVS. A standard linear support vector machine (SVM) is then produced in the subspace with the projected training points. As the dimension of the subspace is determined by the size of the selected basis vector set, the size of the produced SVM expansion can be specified. A two-stage algorithm is derived which selects and refines the basis vector set achieving a locally optimal model. The model expansion coefficients and bias are updated recursively for increase and decrease in the basis set and support vector set. The condition for a point to be classed as outside the current basis vector and selected as a new basis vector is derived and embedded in the recursive procedure. This guarantees the linear independence of the produced basis set. The proposed algorithm is tested and compared with an existing sparse primal SVM (SpSVM) and a standard SVM (LibSVM) on seven public benchmark classification problems. Our new algorithm is designed for use in the application area of human activity recognition using smart devices and embedded sensors where their sometimes limited memory and processing resources must be exploited to the full and the more robust and accurate the classification the more satisfied the user. Experimental results demonstrate the effectiveness and efficiency of the proposed algorithm. This work builds upon a previously published algorithm specifically created for activity recognition within mobile applications for the EU Haptimap project [1]. The algorithms detailed in this paper are more memory and resource efficient making them suitable for use with bigger data sets and more easily trained SVMs.

Embedded platform for ECG biometric recognition

Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia de Electrónica e Telecomunicações

Informal learning recognition through a cloud ecosystem

Learning and teaching processes, like all human activities, can be mediated through the use of tools. Information and communication technologies are now widespread within education. Their use in the daily life of teachers and learners affords engagement with educational activities at any place and time and not necessarily linked to an institution or a certificate. In the absence of formal certification, learning under these circumstances is known as informal learning. Despite the lack of certification, learning with technology in this way presents opportunities to gather information about and present new ways of exploiting an individual’s learning. Cloud technologies provide ways to achieve this through new architectures, methodologies, and workflows that facilitate semantic tagging, recognition, and acknowledgment of informal learning activities. The transparency and accessibility of cloud services mean that institutions and learners can exploit existing knowledge to their mutual benefit. The TRAILER project facilitates this aim by providing a technological framework using cloud services, a workflow, and a methodology. The services facilitate the exchange of information and knowledge associated with informal learning activities ranging from the use of social software through widgets, computer gaming, and remote laboratory experiments. Data from these activities are shared among institutions, learners, and workers. The project demonstrates the possibility of gathering information related to informal learning activities independently of the context or tools used to carry them out.