Property:Abstract
From ISLAB/CAISR
Jump to navigationJump to searchThis is a property of type Text.
I
<p>We present a new iris segmentation algorithm based on the Generalized Structure Tensor (GST). We compare this approach with traditional iris segmentation systems based on Hough transform and integro-differential operators. Results are given using the CASIA-IrisV3-Interval database with respect to a segmentation made manually by a human expert. The proposed algorithm outperforms the baseline approaches, pointing out the validity of the GST as an alternative to classic iris segmentation systems. We also detect the cross positions between the eyelids and the outer iris boundary. Verification results using a publicly available iris recognition system based on 1D Log-Gabor wavelets are also given, showing the benefits of the eyelids removal step.</p> +
<p>Iris recognition research is heading towards enabling more relaxed acquisition conditions. This has effects on the quality and resolution of acquired images, severely affecting the accuracy of recognition systems if not tackled appropriately. In this paper, we evaluate a super-resolution algorithm used to reconstruct iris images based on iterative neighbor embedding of local image patches which tries to represent input low-resolution patches while preserving the geometry of the original high-resolution space. To this end, the geometry of the low- and high-resolution manifolds are jointly considered during the reconstruction process. We validate the system with a database of 1,872 near-infrared iris images, while fusion of two iris comparators has been adopted to improve recognition performance. The presented approach is substantially superior to bilinear/bicubic interpolations at very low resolutions, and it also outperforms a previous PCA-based iris reconstruction approach which only considers the geometry of the low-resolution manifold during the reconstruction process.</p> +
<p>This paper presents a state-of-the-art iris segmentation framework specifically for non-ideal irises. The framework adopts coarse-to-fine strategy to localize different boundaries. In the approach, pupil is coarsely detected using an iterative search method exploiting dynamic thresholding and multiple local cues. The limbic boundary is first approximated in polar space using adaptive filters and then refined in Cartesianspace. The framework is quite robust and unlike the previously reported works, does notrequire tuning of parameters for different databases. The segmentation accuracy (SA) is evaluated using well known measures; precision, recall and F-measure, using the publicly available ground truth data for challenging iris databases; CASIAV4-Interval, ND-IRIS-0405, and IITD. In addition, the approach is also evaluated on highly challenging periocular images of FOCS database. The validity of proposed framework is also ascertained by providing comprehensive comparisons with classical approaches as well asstate-of-the-art methods such as; CAHT, WAHET, IFFP, GST and Osiris v4.1. The results demonstrate that our approach provides significant improvements in segmentation accuracy as well as in recognition performance that too with lower computational complexity.</p> +
K
<p>We present a model-based feature extractor to describe neighborhoods around keypoints by finite expansion, estimating the spatially varying orientation by harmonic functions. The iso-curves of such functions are highly symmetric w.r.t. the origin (a keypoint) and the estimated parameters have well defined geometric interpretations. The origin is also a unique singularity of all harmonic functions, helping to determine thel ocation of a keypoint precisely, whereas the functions describe the object shape of the neighborhood. This is novel and complementary to traditional texture features which describe texture shape properties i.e. they are purposively invariant to translation (within a texture). We report on experiments of verification and identification of keypoints in forensic fingerprints by using publicly available data (NIST SD27), and discuss the results in comparison to other studies. These support our conclusions that the novel features can equip single cores or single minutia with a significant verification power at 19% EER, and an identification power of 24-78% for ranks of 1-20. Additionally, we report verification results of periocular biometrics using near infrared images, reaching an EER performance of 13%, whichis comparable to the state of the art. More importantly, fusion of two systems, our and texture features (Gabor), result in a measurable performance improvement. We report reduction ofthe EER to 9%, supporting the view that the novel features capture relevant visual</p> +
<p>In recent years more data is logged from the electronic control units on-board in commercial vehicles. Typically, the data is transferred from the vehicle at the workshop to a centralized storage for future analysis. This vast amount of data is used for debugging, as a knowledgebase for the design engineer and as a tool for service planning.</p><p>Manual analysis of this data is often time consuming, due to the rich amount of information contained. However, there is an opportunity to automatically assist in the process based on knowledge discovery techniques, even directly when the trucks data is first offloaded at the workshop. One typical example of how this technique could be helpful is when two groups of trucks behave differently, e.g. one well-functioning group and one faulty group, when the two groups have the same specification. The desired information is the specific difference in the logged data, e.g. what particular sensors or signals are different.</p><p>An evaluation cycle is proposed and applied to extract knowledge from three different large real-world data-sets measured on Volvo long haulage trucks. Information in the logged data that describes the vehicle’s operating environment, allows the detection of trucks that are operated differently from their intended use. Experiments to find such vehicles were conducted and recommendations for an automated application are given.</p> +
<p>This article describes the work in progress on knowledge representation formalisms chosen for use in the European project SIARAS. Skill-Based Inspection and Assembly for Reconfigurable Automation Systems has a goal of creating intelligent support system for reconfiguration and adaptation of assembly systems. Knowledge is represented in an ontology expressed in OWL, for generic reasoning in Description Logic, and in a number of special-purpose reasoning modules, specific for the application domain.</p> +
<p>This article describes the work in progress on knowledge-based reconfiguration of a class of automation systems. The knowledge about manufacturing is represented in a number of formalisms and gathered around an ontology expressed in OWL, that allows generic reasoning in Description Logic. In the same time multiple representations facilitate efficient processing by a number of special-purpose reasoning modules, specific for the application domain. At the final stage of reconfiguration we exploit ontology-based rewriting, simplifying creation of the final configuration files.</p> +
L
Large-scale monitoring of operationally diverse district heating substations : A reference-group based approach +
<p>A well-understood prior model for a District Heating (DH) substation is rarely available. Alternatively, since DH substations in a network share a common task, one can assume that they are all operationally homogeneous. Any DH substation that does not conform with the majority is an outlier, and therefore ought to be investigated. However, a DH substation can be affected by varying social and technical factors. Such details are rarely available. Therefore, large-scale monitoring of DH substations in a network is challenging. Hence, in order to address these issues, we proposed a reference-group based monitoring approach. Herein, the operational monitoring of a DH substation, referred to as a target, is delegated to a reference-group which consists of DH substations experiencing a comparable operating regime along with the target. The approach was demonstrated on the monitoring of the return temperature variable for atypical\footnote{Here, "atypical" means that while it does not fit the definition of a normal operation, it is not faulty either and may also have some context.} and faulty operational behavior in $778$ DH substations associated with multi-dwelling buildings. No target substation specific information related to its normal, atypical or faulty operation was used. Instead, information from the target's reference-group was leveraged to track its operational behavior. In this manner, $44$ DH substations were found where a possible deviation in the return temperature was detected earlier compared to models assuming overall operational homogeneity among the DH substations. In addition, six frequent patterns of deviating behavior in the return temperature of DH substations were identified based on the proposed reference-group based approach, which were then further corroborated by the feedback from a DH domain expert. </p> +
<p>Navigation and obstacle avoidance in robotics using planar laser scans has matured over the last decades. They basically enable robots to penetrate highly dynamic and populated spaces, such as people's home, and move around smoothly. However, in an unconstrained environment the twodimensional perceptual space of a fixed mounted laser is not sufficient to ensure safe navigation. In this paper, we present an approach that pools a fast and reliable motion generation approach with modern 3D capturing techniques using a Timeof-Flight camera. Instead of attempting to implement full 3D motion control, which is computationally more expensive and simply not needed for the targeted scenario of a domestic robot, we introduce a "virtual laser". For the originally solely laserbased motion generation the technique of fusing real laser measurements and 3D point clouds into a continuous data stream is 100% compatible and transparent. The paper covers the general concept, the necessary extrinsic calibration of two very different types of sensors, and exemplarily illustrates the benefit which is to avoid obstacles not being perceivable in the original laser scan.</p> +
<p>Focus of research in Active contour models (ACM) area is mainly on development of various energy functions based on physical intuition. In this work, instead of designing a new energy function, we generate a multitude of contour candidates using various values of ACM parameters, assess their quality, and select the most suitable one for an object at hand. A random forest is trained to make contour quality assessments.We demonstrate experimentally superiority of the developed technique over three known algorithms in the P. minimum cells detection task solved via segmentation of phytoplankton images.</p> +
<p>With an increasing amount of data in intelligent transportation systems, methods are needed to automatically extract general representations that accurately predict not only known tasks but also similar tasks that can emerge in the future. Creation of low-dimensional representations can be unsupervised or can exploit various labels in multi-task learning (when goal tasks are known) or transfer learning (when they are not) settings. Finding a general, low-dimensional representation suitable for multiple tasks is an important step toward knowledge discovery in aware intelligent transportation systems. This paper evaluates several approaches mapping high-dimensional sensor data from Volvo trucks into a low-dimensional representation that is useful for prediction. Original data are bivariate histograms, with two types--turbocharger and engine--considered. Low-dimensional representations were evaluated in a supervised fashion by mean equal error rate (EER) using a random forest classifier on a set of 27 1-vs-Rest detection tasks. Results from unsupervised learning experiments indicate that using an autoencoder to create an intermediate representation, followed by $t$-distributed stochastic neighbor embedding, is the most effective way to create low-dimensional representation of the original bivariate histogram. Individually, $t$-distributed stochastic neighbor embedding offered best results for 2-D or 3-D and classical autoencoder for 6-D or 10-D representations. Using multi-task learning, combining unsupervised and supervised objectives on all 27 available tasks, resulted in 10-D representations with a significantly lower EER compared to the original 400-D data. In transfer learning setting, with topmost diverse tasks used for representation learning, 10-D representations achieved EER comparable to the original representation.</p> +
<p>In this paper, an approach to weighting features for classification based on the nearest-neighbour rules is proposed. The weights are adaptive in the sense that the weight values are different in various regions of the feature space. The values of the weights are found by performing a random search in the weight space. A correct classification rate is the criterion maximised during the search. Experimentally, we have shown that the proposed approach is useful for classification. The weight values obtained during the experiments show that the importance of features may be different in different regions of the feature space</p> +
<p>Fuel used by heavy duty trucks is a major cost for logistics companies, and therefore improvements in this area are highly desired. Many of the factors that influence fuel consumption, such as the road type, vehicle configuration or external environment, are difficult to influence. One of the most under-explored ways to lower the costs is training and incentivizing drivers. However, today it is difficult to measure driver performance in a comprehensive way outside of controlled, experimental setting.</p><p>This paper proposes a machine learning methodology for quantifying and qualifying driver performance, with respect to fuel consumption, that is suitable for naturalistic driving situations. The approach is a knowledge-based feature extraction technique, constructing a normalizing fuel consumption value denoted Fuel under Predefined Conditions (FPC), which captures the effect of factors that are relevant but are not measured directly.</p><p>The FPC, together with information available from truck sensors, is then compared against the actual fuel used on a given road segment, quantifying the effects associated with driver behavior or other variables of interest. We show that raw fuel consumption is a biased measure of driver performance, being heavily influenced by other factors such as high load or adversary weather conditions, and that using FPC leads to more accurate results. In this paper we also show evaluation the proposed method using large-scale, real-world, naturalistic database of heavy-duty vehicle operation.</p> +
<p>We study agents situated in partially observable environments, who do not have sufficient resources to create conformant plans. Instead, they generate plans which are conditional and partial, execute or simulate them, and learn to evaluate their quality from experience. Our agent employs an incomplete symbolic deduction system based on Active Logic and Situation Calculus for reasoning about actions and their consequences. An Inductive Logic Programming algorithm generalises observations and deduced knowledge, allowing the agent to execute a good plan. We show results of using PROGOL learning algorithm to distinguish "bad" plans early in the reasoning process, before too many resources are wasted on considering them. We show that additional knowledge needs to be provided before learning can be successful, but argue that the benefits achieved make it worthwhile. Finally, we identify several assumptions made by PROGOL, shared by other similarly universal algorithms, which are well justified in general, but fail to exploit the properties of the class of problems faced by rational agents.</p> +
<p>Application of ocular biometrics in mobile and at a distance environments still has several open challenges, with the lack quality and resolution being an evident issue that can severely affects performance. In this paper, we evaluate two trained image reconstruction algorithms in the context of smart-phone biometrics. They are based on the use of coupled dictionaries to learn the mapping relations between low and high resolution images. In addition, reconstruction is made in local overlapped image patches, where up-scaling functions are modelled separately for each patch, allowing to better preserve local details. The experimental setup is complemented with a database of 560 images captured with two different smart-phones, and two iris comparators employed for verification experiments. We show that the trained approaches are substantially superior to bilinear or bicubic interpolations at very low resolutions (images of 13×13 pixels). Under such challenging conditions, an EER of ∼7% can be achieved using individual comparators, which is further pushed down to 4-6% after the fusion of the two systems. © 2017 IEEE</p> +
<p>Application of ocular biometrics in mobile and at a distance environments still has several open challenges, with the lack quality and resolution being an evident issue that can severely affects performance. In this paper, we evaluate two trained image reconstruction algorithms in the context of smart-phone biometrics. They are based on the use of coupled dictionaries to learn the mapping relations between low and high resolution images. In addition, reconstruction is made in local overlapped image patches, where up-scaling functions are modelled separately for each patch, allowing to better preserve local details. The experimental setup is complemented with a database of 560 images captured with two different smart-phones, and two iris comparators employed for verification experiments. We show that the trained approaches are substantially superior to bilinear or bicubic interpolations at very low resolutions (images of 13×13 pixels). Under such challenging conditions, an EER of ∼7% can be achieved using individual comparators, which is further pushed down to 4-6% after the fusion of the two systems.</p> +
<p>To improve estimation results, outputs of multiple neural networks can be aggregated into a committee output. In this paper, we study the usefulness of the leverages based information for creating accurate neural network committees. Based on the approximate leave-one-out error and the suggested, generalization error based, diversity test, accurate and diverse networks are selected and fused into a committee using data dependent aggregation weights. Four data dependent aggregation schemes – based on local variance, covariance, Choquet integral, and the generalized Choquet integral – are investigated. The effectiveness of the approaches is tested on one artificial and three real world data sets.</p> +
<p>The Brahmi descended Sinhala script is used by 75% of the 18 million population in Sri Lanka. To the best of our knowledge, none of the Brahmi descended scripts used by hundreds of millions of people in South Asia, possess commercial OCR products. In the process of implementation of an OCR system for the printed Sinhala script which is easily adoptable to similar scripts (Premaratne, L., Assabie, Y., Bigun, J., 2004. Recognition of modification-based scripts using direction tensors. In: 4th Indian Conf. on Computer Vision, Graphics and Image Processing (ICVGIP2004), pp. 587–592); a segmentation-free recognition method using orientation features has been proposed in (Premaratne, H.L., Bigun, J., 2004. A segmentation-free approach to recognise printed Sinhala script using linear symmetry. Pattern Recognition 37, 2081–2089). Due to the limitations in image analysis techniques the character level accuracy of the results directly produced by the proposed character recognition algorithm saturates at 94%. The false rejections from the recognition algorithm are initially identified only as ‘missing character positions’ or ‘blank characters’. It is necessary to identify suitable substitutes for such ‘missing character positions’ and optimise the accuracy of words to an acceptable level. This paper proposes a novel method that explores the lexicon in association with the hidden Markov models to improve the rate of accuracy of the recognised script. The proposed method could easily be extended with minor changes to other modification-based scripts consisting of confusing characters. The word-level accuracy which was at 81.5% is improved to 88.5% by the proposed optimisation algorithm.</p> +
<p>This paper describes an offline handwriting recognition system for Amharic words based on lexicon. The system computes direction fields of scanned handwritten documents, from which pseudo-characters are segmented. The pseudo-characters are organized based on their proximity and direction to form text lines. Words are then segmented by analyzing the relative gap between subsequent pseudocharacters in text lines. For each segmented word image, the structural characteristics of pseudo-characters are syntactically analyzed to predict a set of plausible characters forming the word. The most likelihood word is finally selected among candidates by matching against the lexicon. The system is tested by a database of unconstrained handwritten Amharic documents collected from various sources. The lexicon is prepared from words appearing in the collected database.</p> +
<p>This paper presents a speaker-independent audio-visual digit recognition system that utilizes speech and visual lip signals. The extracted visual features are based on line-motion estimation obtained from video sequences with low resolution (128 ×128 pixels) to increase the robustness of audio recognition. The core experiments investigate lip motion biometrics as stand-alone as well as merged modality in speech recognition system. It uses Support Vector Machines, showing favourable experimental results with digit recognition featuring 83% to 100% on the XM2VTS database depending on the amount of available visual information.</p> +
