1. |
- Borgefors, Gunilla, et al.
(författare)
-
Efficient shape representation by minimizing the set of centres of maximal discs/spheres
- 1997
-
Ingår i: Pattern Recognition Letters. - : ELSEVIER SCIENCE BV. - 0167-8655 .- 1872-7344. ; 18:5, s. 465-471
-
Tidskriftsartikel (refereegranskat)abstract
- Efficient shape representations are important for many image processing applications. Distance transform based algorithms can be used to compute the set of centres of maximal discs/spheres, that represents a shape. This paper describes a method that reduc
|
|
2. |
- Johansson, Jan-Olof, 1941-
(författare)
-
Measuring homogeneity of planar point-patterns by using kurtosis
- 2000
-
Ingår i: Pattern Recognition Letters. - Amsterdam : Elsevier. - 0167-8655 .- 1872-7344. ; 21:13-14, s. 1149-1156
-
Tidskriftsartikel (refereegranskat)abstract
- Kurtosis is generally associated with measurements of peakedness of a distribution. In this paper, we suggest a method where kurtosis can be used as a measure of homogeneity of any quantifiable property on a planar surface. A 2-dimensional, continuous and uniform distribution has kurtosis equal to 5.6. This value is also the limiting value for a discrete uniform distribution defined on a regular, rectangular grid when the number of grid points tend to infinity. Measurements of a planar surface, taken at regular grid points, are considered as realizations of random fields. These are associated with 2-dimensional random variables from which the value of kurtosis can be computed and used as a measure of the homogeneity of the field. A deviation from 5.6 indicates that the stochastic variable is not uniformly distributed and that the corresponding random field is not homogeneous. The model is applied on the spatial variation of the roughness on the surface of newsprint, an application where homogeneity is very important.
|
|
3. |
- Johansson, Jan-Olof, 1941-
(författare)
-
Parameter-estimation in the auto-binomial model using the coding-and pseudo-likelihood method approached with simulated annealing and numerical optimization
- 2001
-
Ingår i: Pattern Recognition Letters. - Amsterdam : Elsevier. - 0167-8655 .- 1872-7344. ; 22:11, s. 1233-1246
-
Tidskriftsartikel (refereegranskat)abstract
- In texture analysis, the Gibbs sampler constitutes an important tool in the generation of synthetic textures. The textures are modeled as distributions with specified parameters. In this paper, we study the estimation process of the parameters in such distributions and compare Besags coding method with a pseudo-likelihood method. We also compare simulated annealing with the Newton-Raphson method to find the global maximum of a likelihood or pseudo-likelihood function. For some textures, the two methods differ but in most case there are no important differences between them. The two maximization methods find the same maximum, but the Newton-Raphson method is much faster. However, the Newton-Raphson method cannot be applied in some cases when the location of the maximum differs too much from the starting points. Here, it is often possible to find the global maximum using simulated annealing. The methods have been used in an application with newsprint.
|
|
4. |
- Kermit, M., et al.
(författare)
-
Treatment of obstructive sleep apnea syndrome by monitoring patients airflow signals
- 2000
-
Ingår i: Pattern Recognition Letters. - 0167-8655 .- 1872-7344. ; 21:3, s. 277-281
-
Tidskriftsartikel (refereegranskat)abstract
- The breathing patterns from sleeping persons suffering from sleep apnea have been measured. A method based on the neural network-like O-algorithm has been applied to capture the onset of sleep apnea. This method is suggested as an indicator for early on-line detection of obstructions in the upper airway. Results from the system tested with airflow signals recorded from five patients during sleep indicate acceptable performance and treatment for developing apnea is possible.
|
|
5. |
- Nilsson, Kenneth, 1951-, et al.
(författare)
-
Localization of corresponding points in fingerprints by complex filtering
- 2003
-
Ingår i: Pattern Recognition Letters. - Amsterdam : Elsevier. - 0167-8655 .- 1872-7344. ; 24:13, s. 2135-2144
-
Tidskriftsartikel (refereegranskat)abstract
- For the alignment of two fingerprints certain landmark points are needed. These should be automaticaly extracted with low misidentification rate. As landmarks we suggest the prominent symmetry points (singular points, SPs) in the fingerprints. We identify an SP by its symmetry properties. SPs are extracted from the complex orientation field estimated from the global structure of the fingerprint, i.e. the overall pattern of the ridges and valleys. Complex filters, applied to the orientation field in multiple resolution scales, are used to detect the symmetry and the type of symmetry. Experimental results are reported.
|
|
6. |
- Smeraldi, F., et al.
(författare)
-
Retinal vision applied to facial features detection and face authentication
- 2002
-
Ingår i: Pattern Recognition Letters. - Amsterdam : North-Holland Publishing. - 0167-8655 .- 1872-7344. ; 23:4, s. 463-475
-
Tidskriftsartikel (refereegranskat)abstract
- Retinotopic sampling and the Gabor decomposition have a well-established role in computer vision in general as well as in face authentication. The concept of Retinal Vision we introduce aims at complementing these biologically inspired tools with models of higher-order visual process, specifically the Human Saccadic System. We discuss the Saccadic Search strategy, a general purpose attentional mechanism that identifies semantically meaningful structures in images by performing "jumps" (saccades) between relevant locations. Saccade planning relies on a priori knowledge encoded by SVM classifiers. The raw visual input is analysed by means of a log-polar retinotopic sensor, whose receptive fields consist in a vector of modified Gabor filters designed in the log-polar frequency plane. Applicability to complex cognitive tasks is demonstrated by facial landmark detection and authentication experiments over the M2VTS and Extended M2VTS (XM2VTS) databases.
|
|
7. |
- Svedberg, D., et al.
(författare)
-
Calibration, pose and novel views from single images of constrained scenes
- 2000
-
Ingår i: Pattern Recognition Letters. - 0167-8655 .- 1872-7344. ; 21:13-14, s. 1125-1133
-
Tidskriftsartikel (refereegranskat)abstract
- We exploit the common constraint of having a right-angle corner of two rectangular planes in the scene in order to calibrate a perspective projection camera and compute its pose relative to the coordinate system defined by the corner. No metric information about the corner is assumed. The camera is constrained to have its image x- and y-axes to be orthogonal with the same scale factor, which is valid for most real-world cameras. We then reproject the image of the corner to an arbitrary viewpoint. We can also compute the metric properties of the scene to scale. We report experimental results with subjectively acceptable quality. The approach shows the power of exploiting constraints that are abundant in typical architectural scenes.
|
|
8. |
- Svensson, Stina, et al.
(författare)
-
Curve skeletonization of surface-like objects in 3D images guided by voxel classification
- 2002
-
Ingår i: Pattern Recognition Letters. - 0167-8655 .- 1872-7344. ; 23:12, s. 1419-1426
-
Tidskriftsartikel (refereegranskat)abstract
- Skeletonization is a way to reduce dimensionality of digital objects. Here, we present an algorithm that computes the curve skeleton of a surface-like object in a 3D image, i.e., an object that in one of the three dimensions is at most two-voxel thick. A
|
|
9. |
- Verikas, Antanas, 1951-, et al.
(författare)
-
Colour image segmentation by modular neural network
- 1997
-
Ingår i: Pattern Recognition Letters. - Amsterdam : Elsevier. - 0167-8655 .- 1872-7344. ; 18:2, s. 173-185
-
Tidskriftsartikel (refereegranskat)abstract
- In this paper segmentation of colour images is treated as a problem of classification of colour pixels. A hierarchical modular neural network for classification of colour pixels is presented. The network combines different learning techniques, performs analysis in a rough to fine fashion and enables to obtain a high average classification speed and a low classification error. Experimentally, we have shown that the network is capable of distinguishing among the nine colour classes that occur in an image. A correct classification rate of about 98% has been obtained even for two very similar black colours.
|
|
10. |
- Verikas, Antanas, et al.
(författare)
-
Feature Selection with Neural Networks
- 2002
-
Ingår i: Pattern Recognition Letters. - Amsterdam : Elsevier. - 0167-8655 .- 1872-7344. ; 23:11, s. 1323-1335
-
Tidskriftsartikel (refereegranskat)abstract
- We present a neural network based approach for identifying salient features for classification in feedforward neural networks. Our approach involves neural network training with an augmented cross-entropy error function. The augmented error function forces the neural network to keep low derivatives of the transfer functions of neurons when learning a classification task. Such an approach reduces output sensitivity to the input changes. Feature selection is based on the reaction of the cross-validation data set classification error due to the removal of the individual features. We demonstrate the usefulness of the proposed approach on one artificial and three real-world classification problems. We compared the approach with five other feature selection methods, each of which banks on a different concept. The algorithm developed outperformed the other methods by achieving higher classification accuracy on all the problems tested.
|
|
11. |
- Verikas, Antanas, 1951-, et al.
(författare)
-
Soft combination of neural classifiers : a comparative study
- 1999
-
Ingår i: Pattern Recognition Letters. - Amsterdam : Elsevier. - 0167-8655 .- 1872-7344. ; 20:4, s. 429-444
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents four schemes for soft fusion of the outputs of multiple classifiers. In the first three approaches, the weights assigned to the classifiers or groups of them are data dependent. The first approach involves the calculation of fuzzy integrals. The second scheme performs weighted averaging with data-dependent weights. The third approach performs linear combination of the outputs of classifiers via the BADD defuzzification strategy. In the last scheme, the outputs of multiple classifiers are combined using Zimmermann's compensatory operator. An empirical evaluation using widely accessible data sets substantiates the validity of the approaches with data-dependent weights, compared to various existing combination schemes of multiple classifiers.
|
|
12. |
- Waldemark, J., et al.
(författare)
-
Image analysis for airborne reconnaissance and missile applications
- 2000
-
Ingår i: Pattern Recognition Letters. - 0167-8655 .- 1872-7344. ; 21:3, s. 239-251
-
Tidskriftsartikel (refereegranskat)abstract
- This paper describes how the pulse coupled neural network (PCNN) can be used in various image analysis applications. We especially focus on two time-critical applications, in particular, airborne reconnaissance and missile navigation. Today, biologically inspired sensor analysis systems such as the PCNN can be used in many different applications related to these two major applications. New ideas are shown on how to use PCNN in combination with other image processing transforms, e.g. the Radon transform and foveation point detection to solve image interpretation and missile navigation problems. This includes solving tasks such as image segmentation, object detection and target identification. Finally, a VHDL implementation of the PCNN targeting FPGA is presented.
|
|
13. |
|
|
14. |
- Abedan Kondori, Farid, 1983-, et al.
(författare)
-
Direct hand pose estimation for immersive gestural interaction
- 2015
-
Ingår i: Pattern Recognition Letters. - : Elsevier BV. - 0167-8655 .- 1872-7344. ; 66, s. 91-99
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents a novel approach for performing intuitive gesture based interaction using depth data acquired by Kinect. The main challenge to enable immersive gestural interaction is dynamic gesture recognition. This problem can be formulated as a combination of two tasks; gesture recognition and gesture pose estimation. Incorporation of fast and robust pose estimation method would lessen the burden to a great extent. In this paper we propose a direct method for real-time hand pose estimation. Based on the range images, a new version of optical flow constraint equation is derived, which can be utilized to directly estimate 3D hand motion without any need of imposing other constraints. Extensive experiments illustrate that the proposed approach performs properly in real-time with high accuracy. As a proof of concept, we demonstrate the system performance in 3D object manipulation On two different setups; desktop computing, and mobile platform. This reveals the system capability to accommodate different interaction procedures. In addition, a user study is conducted to evaluate learnability, user experience and interaction quality in 3D gestural interaction in comparison to 2D touchscreen interaction.
|
|
15. |
- Alonso-Fernandez, Fernando, 1978-, et al.
(författare)
-
A survey on periocular biometrics research
- 2016
-
Ingår i: Pattern Recognition Letters. - Amsterdam : Elsevier. - 0167-8655 .- 1872-7344. ; 82, part 2, s. 92-105
-
Tidskriftsartikel (refereegranskat)abstract
- Periocular refers to the facial region in the vicinity of the eye, including eyelids, lashes and eyebrows. While face and irises have been extensively studied, the periocular region has emerged as a promising trait for unconstrained biometrics, following demands for increased robustness of face or iris systems. With a surprisingly high discrimination ability, this region can be easily obtained with existing setups for face and iris, and the requirement of user cooperation can be relaxed, thus facilitating the interaction with biometric systems. It is also available over a wide range of distances even when the iris texture cannot be reliably obtained (low resolution) or under partial face occlusion (close distances). Here, we review the state of the art in periocular biometrics research. A number of aspects are described, including: (i) existing databases, (ii) algorithms for periocular detection and/or segmentation, (iii) features employed for recognition, (iv) identification of the most discriminative regions of the periocular area, (v) comparison with iris and face modalities, (vi) soft-biometrics (gender/ethnicity classification), and (vii) impact of gender transformation and plastic surgery on the recognition accuracy. This work is expected to provide an insight of the most relevant issues in periocular biometrics, giving a comprehensive coverage of the existing literature and current state of the art. © 2015 Elsevier B.V. All rights reserved.
|
|
16. |
- Andersson, Thord, 1972-, et al.
(författare)
-
Geodesic registration for interactive atlas-based segmentation using learned multi-scale anatomical manifolds
- 2018
-
Ingår i: Pattern Recognition Letters. - : Elsevier. - 0167-8655 .- 1872-7344. ; 112, s. 340-345
-
Tidskriftsartikel (refereegranskat)abstract
- Atlas-based segmentation is often used to segment medical image regions. For intensity-normalized data, the quality of these segmentations is highly dependent on the similarity between the atlas and the target under the used registration method. We propose a geodesic registration method for interactive atlas-based segmentation using empirical multi-scale anatomical manifolds. The method utilizes unlabeled images together with the labeled atlases to learn empirical anatomical manifolds. These manifolds are defined on distinct scales and regions and are used to propagate the labeling information from the atlases to the target along anatomical geodesics. The resulting competing segmentations from the different manifolds are then ranked according to an image-based similarity measure. We used image volumes acquired using magnetic resonance imaging from 36 subjects. The performance of the method was evaluated using a liver segmentation task. The result was then compared to the corresponding performance of direct segmentation using Dice Index statistics. The method shows a significant improvement in liver segmentation performance between the proposed method and direct segmentation. Furthermore, the standard deviation in performance decreased significantly. Using competing complementary manifolds defined over a hierarchy of region of interests gives an additional improvement in segmentation performance compared to the single manifold segmentation.
|
|
17. |
- Assabie, Yaregal, 1975-, et al.
(författare)
-
Offline handwritten Amharic word recognition
- 2011
-
Ingår i: Pattern Recognition Letters. - Amsterdam : Elsevier. - 0167-8655 .- 1872-7344. ; 32:8, s. 1089-1099
-
Tidskriftsartikel (refereegranskat)abstract
- This paper describes two approaches for Amharic word recognition in unconstrained handwritten text using HMMs. The first approach builds word models from concatenated features of constituent characters and in the second method HMMs of constituent characters are concatenated to form word model. In both cases, the features used for training and recognition are a set of primitive strokes and their spatial relationships. The recognition system does not require segmentation of characters but requires text line detection and extraction of structural features, which is done by making use of direction field tensor. The performance of the recognition system is tested by a dataset of unconstrained handwritten documents collected from various sources, and promising results are obtained. (C) 2011 Elsevier B.V. All rights reserved.
|
|
18. |
|
|
19. |
- Bacauskiene, Marija, et al.
(författare)
-
Selecting salient features for classification based on neural network committees
- 2004
-
Ingår i: Pattern Recognition Letters. - Amsterdam : Elsevier Science. - 0167-8655 .- 1872-7344. ; 25:16, s. 1879-1891
-
Tidskriftsartikel (refereegranskat)abstract
- Aggregating outputs of multiple classifiers into a committee decision is one of the most important techniques for improving classification accuracy. The issue of selecting an optimal subset of relevant features plays also an important role in successful design of a pattern recognition system. In this paper, we present a neural network based approach for identifying salient features for classification in neural network committees. Feature selection is based on two criteria, namely the reaction of the cross-validation data set classification error due to the removal of the individual features and the diversity of neural networks comprising the committee. The algorithm developed removed a large number of features from the original data sets without reducing the classification accuracy of the committees. The accuracy of the committees utilizing the reduced feature sets was higher than those exploiting all the original features.
|
|
20. |
|
|
21. |
- Berg, Amanda, et al.
(författare)
-
Enhanced analysis of thermographic images for monitoring of district heat pipe networks
- 2016
-
Ingår i: Pattern Recognition Letters. - : Elsevier. - 0167-8655 .- 1872-7344. ; 83:2, s. 215-223
-
Tidskriftsartikel (refereegranskat)abstract
- We address two problems related to large-scale aerial monitoring of district heating networks. First, we propose a classification scheme to reduce the number of false alarms among automatically detected leakages in district heating networks. The leakages are detected in images captured by an airborne thermal camera, and each detection corresponds to an image region with abnormally high temperature. This approach yields a significant number of false positives, and we propose to reduce this number in two steps; by (a) using a building segmentation scheme in order to remove detections on buildings, and (b) to use a machine learning approach to classify the remaining detections as true or false leakages. We provide extensive experimental analysis on real-world data, showing that this post-processing step significantly improves the usefulness of the system. Second, we propose a method for characterization of leakages over time, i.e., repeating the image acquisition one or a few years later and indicate areas that suffer from an increased energy loss. We address the problem of finding trends in the degradation of pipe networks in order to plan for long-term maintenance, and propose a visualization scheme exploiting the consecutive data collections.
|
|
22. |
- Bernander, Karl B., et al.
(författare)
-
Improving the stochastic watershed
- 2013
-
Ingår i: Pattern Recognition Letters. - : Elsevier BV. - 0167-8655 .- 1872-7344. ; 34:9, s. 993-1000
-
Tidskriftsartikel (refereegranskat)abstract
- The stochastic watershed is an unsupervised segmentation tool recently proposed by Angulo and Jeulin. By repeated application of the seeded watershed with randomly placed markers, a probability density function for object boundaries is created. In a second step, the algorithm then generates a meaningful segmentation of the image using this probability density function. The method performs best when the image contains regions of similar size, since it tends to break up larger regions and merge smaller ones. We propose two simple modifications that greatly improve the properties of the stochastic watershed: (1) add noise to the input image at every iteration, and (2) distribute the markers using a randomly placed grid. The noise strength is a new parameter to be set, but the output of the algorithm is not very sensitive to this value. In return, the output becomes less sensitive to the two parameters of the standard algorithm. The improved algorithm does not break up larger regions, effectively making the algorithm useful for a larger class of segmentation problems.
|
|
23. |
- Bigun, Josef, et al.
(författare)
-
Damascening video databases for evaluation of face tracking and recognition – The DXM2VTS database
- 2007
-
Ingår i: Pattern Recognition Letters. - Amsterdam : Elsevier. - 0167-8655 .- 1872-7344. ; 28:15, s. 2143-2156
-
Tidskriftsartikel (refereegranskat)abstract
- Performance quantification of biometric systems, such as face tracking and recognition highly depend on the database used for testing the systems. Systems trained and tested on realistic and representative databases evidently perform better. Actually, the main reason for evaluating any system on test data is that these data sets represent problems that systems might face in the real world. However, building biometric video databases with realistic background for testing is expensive especially due to its high demand of cooperation from the side of the participants. For example, XM2VTS database contain thousands of video recorded in a studio from 295 subjects. Recording these subjects repeatedly in public places such as supermarkets, offices, streets, etc., is not realistic. To this end, we present a procedure to separate the background of a video recorded in studio conditions with the purpose to replace it with an arbitrary complex background, e.g., outdoor scene containing motion, to measure performance, e.g., eye tracking. Furthermore, we present how an affine transformation and synthetic noise can be incorporated into the production of the new database to simulate natural noise, e.g. motion blur due to translation, zooming and rotation. The entire system is applied to the XM2VTS database, which already consists of several terabytes of data, to produce the DXM2VTS–Damascened XM2VTS database essentially without an increase in resource consumption, i.e., storage, bandwidth, and most importantly, the time of clients populating the database, and the time of the operators.
|
|
24. |
- Byeon, Wonmin, et al.
(författare)
-
Scene analysis by mid-level attribute learning using 2D LSTM networks and an application to web-image tagging
- 2015
-
Ingår i: Pattern Recognition Letters. - : Elsevier BV. - 0167-8655 .- 1872-7344. ; 63, s. 23-29
-
Tidskriftsartikel (refereegranskat)abstract
- This paper describes an approach to scene analysis based on supervised training of 2D Long Short-Term Memory recurrent neural networks (LSTM networks). Unlike previous methods, our approach requires no manual construction of feature hierarchies or incorporation of other prior knowledge. Rather, like deep learning approaches using convolutional networks, our recognition networks are trained directly on raw pixel values. However, in contrast to convolutional neural networks, our approach uses 2D LSTM networks at all levels. Our networks yield per pixel mid-level classifications of input images; since training data for such applications is not available in large numbers, we describe an approach to generating artificial training data, and then evaluate the trained networks on real-world images. Our approach performed significantly better than others methods including Convolutional Neural Networks (ConvNet), yet using two orders of magnitude fewer parameters. We further show the experiment on a recently published dataset, outdoor scene attribute dataset for fair comparisons of scene attribute learning which had significant performance improvement (ca. 21%). Finally, our approach is successfully applied on a real-world application, automatic web-image tagging.
|
|
25. |
|
|
26. |
- Cheddad, Abbas
(författare)
-
Structure Preserving Binary Image Morphing using Delaunay Triangulation
- 2017
-
Ingår i: Pattern Recognition Letters. - : Elsevier. - 0167-8655 .- 1872-7344. ; 85, s. 8-14
-
Tidskriftsartikel (refereegranskat)abstract
- Mathematical morphology has been of a great significance to several scientific fields. Dilation, as one of the fundamental operations, has been very much reliant on the common methods based on the set theory and on using specific shaped structuring elements to morph binary blobs. We hypothesised that by performing morphological dilation while exploiting geometry relationship between dot patterns, one can gain some advantages. The Delaunay triangulation was our choice to examine the feasibility of such hypothesis due to its favourable geometric properties. We compared our proposed algorithm to existing methods and it becomes apparent that Delaunay based dilation has the potential to emerge as a powerful tool in preserving objects structure and elucidating the influence of noise. Additionally, defining a structuring element is no longer needed in the proposed method and the dilation is adaptive to the topology of the dot patterns. We assessed the property of object structure preservation by using common measurement metrics. We also demonstrated such property through handwritten digit classification using HOG descriptors extracted from dilated images of different approaches and trained using Support Vector Machines. The confusion matrix shows that our algorithm has the best accuracy estimate in 80% of the cases. In both experiments, our approach shows a consistent improved performance over other methods which advocates for the suitability of the proposed method.
|
|
27. |
- Chojnacki, W., et al.
(författare)
-
The equivalence of two definitions of compatible homography matrices
- 2020
-
Ingår i: Pattern Recognition Letters. - : Elsevier BV. - 0167-8655 .- 1872-7344. ; 135, s. 38-43
-
Tidskriftsartikel (refereegranskat)abstract
- In many computer vision applications, one acquires images of planar surfaces from two different vantage points. One can use a projective transformation to map pixel coordinates associated with a particular planar surface from one image to another. The transformation, called a homography, can be represented by a unique, to within a scale factor, 3 × 3 matrix. One requires a different homography matrix, scale differences apart, for each planar surface whose two images one wants to relate. However, a collection of homography matrices forms a valid set only if the matrices satisfy consistency constraints implied by the rigidity of the motion and the scene. We explore what it means for a set of homography matrices to be compatible and show that two seemingly disparate definitions are in fact equivalent. Our insight lays the theoretical foundations upon which the derivation of various sets of homography consistency constraints can proceed. © 2020 Elsevier B.V.
|
|
28. |
- Curic, Vladimir, et al.
(författare)
-
Adaptive mathematical morphology – A survey of the field
- 2014
-
Ingår i: Pattern Recognition Letters. - : Elsevier BV. - 0167-8655 .- 1872-7344. ; 47, s. 18-28
-
Tidskriftsartikel (refereegranskat)abstract
- We present an up-to-date survey on the topic of adaptive mathematical morphology. A broad review of research performed within the field is provided, as well as an in-depth summary of the theoretical advances within the field. Adaptivity can come in many different ways, based on different attributes, measures, and parameters. Similarities and differences between a few selected methods for adaptive structuring elements are considered, providing perspective on the consequences of different types of adaptivity. We also provide a brief analysis of perspectives and trends within the field, discussing possible directions for future studies.
|
|
29. |
- Danelljan, Martin, 1989-, et al.
(författare)
-
Deep motion and appearance cues for visual tracking
- 2019
-
Ingår i: Pattern Recognition Letters. - : Elsevier. - 0167-8655 .- 1872-7344. ; 124, s. 74-81
-
Tidskriftsartikel (refereegranskat)abstract
- Generic visual tracking is a challenging computer vision problem, with numerous applications. Most existing approaches rely on appearance information by employing either hand-crafted features or deep RGB features extracted from convolutional neural networks. Despite their success, these approaches struggle in case of ambiguous appearance information, leading to tracking failure. In such cases, we argue that motion cue provides discriminative and complementary information that can improve tracking performance. Contrary to visual tracking, deep motion features have been successfully applied for action recognition and video classification tasks. Typically, the motion features are learned by training a CNN on optical flow images extracted from large amounts of labeled videos. In this paper, we investigate the impact of deep motion features in a tracking-by-detection framework. We also evaluate the fusion of hand-crafted, deep RGB, and deep motion features and show that they contain complementary information. To the best of our knowledge, we are the first to propose fusing appearance information with deep motion features for visual tracking. Comprehensive experiments clearly demonstrate that our fusion approach with deep motion features outperforms standard methods relying on appearance information alone.
|
|
30. |
- Devarakota, Pandu Ranga Rao, et al.
(författare)
-
Reliability estimation of a statistical classifier
- 2008
-
Ingår i: Pattern Recognition Letters. - : Elsevier BV. - 0167-8655 .- 1872-7344. ; 29:3, s. 243-253
-
Tidskriftsartikel (refereegranskat)abstract
- Statistical pattern classification techniques have been successfully applied to many practical classification problems. In real-world applications, the challenge is often to cope with patterns that lead to unreliable classification decisions. These situations occur either due to unexpected patterns, i.e., patterns which occur in the regions far from the training data or due to patterns which occur in the overlap region of classes. This paper proposes a method for estimating the reliability of a classifier to cope with these situations. While existing methods for quantifying the reliability are often solely based on the class membership probability estimated on global approximations, in this paper, the reliability is quantified in terms of a confidence interval on the class membership probability. The size of the confidence interval is calculated explicitly based on the local density of training data in the neighborhood of a test pattern. A synthetic example is given to illustrate the various aspects of the proposed approach. In addition, experimental evaluation on real data sets is conducted to demonstrate the effectiveness of the proposed approach to detect unexpected patterns. The lower bound of the confidence interval is used to detect the unexpected patterns. By comparing the performance with the state-of-the-art methods, we show our approach is well-founded.
|
|
31. |
|
|
32. |
- Faraj, Maycel Isaac, 1979-, et al.
(författare)
-
Audio–visual person authentication using lip-motion from orientation maps
- 2007
-
Ingår i: Pattern Recognition Letters. - Amsterdam : North-Holland. - 0167-8655 .- 1872-7344. ; 28:11, s. 1368-1382
-
Tidskriftsartikel (refereegranskat)abstract
- This paper describes a new identity authentication technique by a synergetic use of lip-motion and speech. The lip-motion is defined as the distribution of apparent velocities in the movement of brightness patterns in an image and is estimated by computing the velocity components of the structure tensor by 1D processing, in 2D manifolds. Since the velocities are computed without extracting the speaker’s lip-contours, more robust visual features can be obtained in comparison to motion features extracted from lip-contours. The motion estimations are performed in a rectangular lip-region, which affords increased computational efficiency. A person authentication implementation based on lip-movements and speech is presented along with experiments exhibiting a recognition rate of 98%. Besides its value in authentication, the technique can be used naturally to evaluate the “liveness” of someone speaking as it can be used in text-prompted dialogue. The XM2VTS database was used for performance quantification as it is currently the largest publicly available database (≈300 persons) containing both lip-motion and speech. Comparisons with other techniques are presented.
|
|
33. |
- Grosinger, Jasmin, 1984-, et al.
(författare)
-
Robots that Maintain Equilibrium : Proactivity by Reasoning About User Intentions and Preferences
- 2019
-
Ingår i: Pattern Recognition Letters. - : Elsevier. - 0167-8655 .- 1872-7344. ; 118, s. 85-93
-
Tidskriftsartikel (refereegranskat)abstract
- Robots need to exhibit proactive behavior if they are to be accepted in human-centered environments. A proactive robot must reason about the actions it can perform, the state of the environment, the state and the intentions of its users, and what the users deem desirable. This paper proposes a computational framework for proactive robot behavior that formalizes the above ingredients. The framework is grounded on the notion of Equilibrium Maintenance: current and future states are continuously evaluated to identify opportunities for acting that steer the system into more desirable states. We show that this process leads a robot to proactively generate its own goals and enact them, and that the obtained behavior depends on a model of user intentions, preferences, and the temporal horizon used in prediction. A number of examples show that our framework accounts for even slight variations in user preference models and perceived user intentions. We also show how the level of informedness of the system is easily customizable.
|
|
34. |
- Gustavson, Stefan, 1965-, et al.
(författare)
-
Anti-aliased Euclidean distance transform
- 2011
-
Ingår i: Pattern Recognition Letters. - : Elsevier BV. - 0167-8655 .- 1872-7344. ; 32:2, s. 252-257
-
Tidskriftsartikel (refereegranskat)abstract
- We present a modified distance measure for use with distance transforms of anti-aliased, area sampled grayscale images of arbitrary binary contours. The modified measure can be used in any vector-propagation Euclidean distance transform. Our test implementation in the traditional SSED8 algorithm shows a considerable improvement in accuracy and homogeneity of the distance field compared to a traditional binary image transform. At the expense of a 10× slowdown for a particular image resolution, we achieve an accuracy comparable to a binary transform on a supersampled image with 16 × 16 higher resolution, which would require 256 times more computations and memory.
|
|
35. |
- Hast, Anders
(författare)
-
Simple filter design for first and second order derivatives by a double filtering approach
- 2014
-
Ingår i: Pattern Recognition Letters. - : Elsevier. - 0167-8655 .- 1872-7344. ; 42, s. 65-71
-
Tidskriftsartikel (refereegranskat)abstract
- Spline filters are usually implemented in two steps, where in the first step the basis coefficients are computed by deconvolving the sampled function with a factorized filter and the second step reconstructs the sampled function. It will be shown how separable spline filters using different splines can be constructed with fixed kernels, requiring no inverse filtering. Especially, it is discussed how first and second order derivatives can be computed correctly using cubic or trigonometric splines by a double filtering approach giving filters of length 7.
|
|
36. |
- Hedman, Pontus, et al.
(författare)
-
On the effect of selfie beautification filters on face detection and recognition
- 2022
-
Ingår i: Pattern Recognition Letters. - Amsterdam : Elsevier. - 0167-8655 .- 1872-7344. ; 163, s. 104-111
-
Tidskriftsartikel (refereegranskat)abstract
- Beautification and augmented reality filters are very popular in applications that use selfie images. However, they can distort or modify biometric features, severely affecting the ability to recognise the individuals’ identity or even detect the face. Accordingly, we address the effect of such filters on the accuracy of automated face detection and recognition. The social media image filters studied modify the image contrast, illumination, or occlude parts of the face. We observe that the effect of some of these filters is harmful to face detection and identity recognition, especially if they obfuscate the eye or (to a lesser extent) the nose. To counteract such effect, we develop a method to reverse the applied manipulation with a modified version of the U-NET segmentation network. This method is observed to contribute to better face detection and recognition accuracy. From a recognition perspective, we employ distance measures and trained machine learning algorithms applied to features extracted using several CNN backbones. We also evaluate if incorporating filtered images into the training set of machine learning approaches is beneficial. Our results show good recognition when filters do not occlude important landmarks, especially the eyes. The combined effect of the proposed approaches also allows mitigating the impact produced by filters that occlude parts of the face. © 2022 The Authors. Published by Elsevier B.V.
|
|
37. |
- Henter, Gustav Eje, et al.
(författare)
-
Picking up the pieces : Causal states in noisy data, and how to recover them
- 2013
-
Ingår i: Pattern Recognition Letters. - : Elsevier BV. - 0167-8655 .- 1872-7344. ; 34:5, s. 587-594
-
Tidskriftsartikel (refereegranskat)abstract
- Automatic structure discovery is desirable in many Markov model applications where a good topology (states and transitions) is not known a priori. CSSR is an established pattern discovery algorithm for stationary and ergodic stochastic symbol sequences that learns a predictively optimal Markov representation consisting of so-called causal states. By means of a novel algebraic criterion, we prove that the causal states of a simple process disturbed by random errors frequently are too complex to be learned fully, making CSSR diverge. In fact, the causal state representation of many hidden Markov models, representing simple but noise-disturbed data, has infinite cardinality. We also report that these problems can be solved by endowing CSSR with the ability to make approximations. The resulting algorithm, robust causal states (RCS), is able to recover the underlying causal structure from data corrupted by random substitutions, as is demonstrated both theoretically and in an experiment. The algorithm has potential applications in areas such as error correction and learning stochastic grammars.
|
|
38. |
- Ilic, Vladimir, et al.
(författare)
-
Precise Euclidean distance transforms in 3D from voxel coverage representation
- 2015
-
Ingår i: Pattern Recognition Letters. - : Elsevier BV. - 0167-8655 .- 1872-7344. ; 65, s. 184-191
-
Tidskriftsartikel (refereegranskat)abstract
- Distance transforms (DTs) are, usually, defined on a binary image as a mapping from each background element to the distance between its centre and the centre of the closest object element. However, due to discretization effects, such DTs have limited precision, including reduced rotational and translational invariance. We show in this paper that a significant improvement in performance of Euclidean DTs can be achieved if voxel coverage values are utilized and the position of an object boundary is estimated with sub-voxel precision. We propose two algorithms of linear time complexity for estimating Euclidean DT with sub-voxel precision. The evaluation confirms that both algorithms provide 4-14 times increased accuracy compared to what is achievable from a binary object representation.
|
|
39. |
- Isaksson, Anders, et al.
(författare)
-
Cross-validation and bootstrapping are unreliable in small sample classification
- 2008
-
Ingår i: Pattern Recognition Letters. - : Elsevier BV. - 0167-8655 .- 1872-7344. ; 29:14, s. 1960-1965
-
Tidskriftsartikel (refereegranskat)abstract
- The interest in statistical classification for critical applications such as diagnoses of patient samples based on supervised learning is rapidly growing. To gain acceptance in applications where the subsequent decisions have serious consequences, e.g. choice of cancer therapy, any such decision support system must come with a reliable performance estimate. Tailored for small sample problems, cross-validation (CV) and bootstrapping (BTS) have been the most commonly used methods to determine such estimates in virtually all branches of science for the last 20 years. Here, we address the often overlooked fact that the uncertainty in a point estimate obtained with CV and BTS is unknown and quite large for small sample classification problems encountered in biomedical applications and elsewhere. To avoid this fundamental problem of employing CV and BTS, until improved alternatives have been established, we suggest that the final classification performance always should be reported in the form of a Bayesian confidence interval obtained from a simple holdout test or using some other method that yields conservative measures of the uncertainty.
|
|
40. |
- Kastrati, Zenun, 1984-, et al.
(författare)
-
Integrating word embeddings and document topics with deep learning in a video classification framework
- 2019
-
Ingår i: Pattern Recognition Letters. - : Elsevier. - 0167-8655 .- 1872-7344. ; 128, s. 85-92
-
Tidskriftsartikel (refereegranskat)abstract
- The advent of MOOC platforms brought an abundance of video educational content that made the selection of best fitting content for a specific topic a lengthy process. To tackle this challenge in this paper we report our research efforts of using deep learning techniques for managing and classifying educational content for various search and retrieval applications in order to provide a more personalized learning experience. In this regard, we propose a framework which takes advantages of feature representations and deep learning for classifying video lectures in a MOOC setting to aid effective search and retrieval. The framework consists of three main modules. The first module called pre-processing concerns with video-to-text conversion. The second module is transcript representation which represents text in lecture transcripts into vector space by exploiting different representation techniques including bag-of-words, embeddings, transfer learning, and topic modeling. The final module covers classifiers whose aim is to label video lectures into the appropriate categories. Two deep learning models, namely feed-forward deep neural network (DNN) and convolutional neural network (CNN) are examined as part of the classifier module. Multiple simulations are carried out on a large-scale real dataset using various feature representations and classification techniques to test and validate the proposed framework.
|
|
41. |
- Khan, Fahad Shahbaz, et al.
(författare)
-
Compact color–texture description for texture classification
- 2015
-
Ingår i: Pattern Recognition Letters. - : Elsevier. - 0167-8655 .- 1872-7344. ; 51, s. 16-22
-
Tidskriftsartikel (refereegranskat)abstract
- Describing textures is a challenging problem in computer vision and pattern recognition. The classification problem involves assigning a category label to the texture class it belongs to. Several factors such as variations in scale, illumination and viewpoint make the problem of texture description extremely challenging. A variety of histogram based texture representations exists in literature. However, combining multiple texture descriptors and assessing their complementarity is still an open research problem. In this paper, we first show that combining multiple local texture descriptors significantly improves the recognition performance compared to using a single best method alone. This gain in performance is achieved at the cost of high-dimensional final image representation. To counter this problem, we propose to use an information-theoretic compression technique to obtain a compact texture description without any significant loss in accuracy. In addition, we perform a comprehensive evaluation of pure color descriptors, popular in object recognition, for the problem of texture classification. Experiments are performed on four challenging texture datasets namely, KTH-TIPS-2a, KTH-TIPS-2b, FMD and Texture-10. The experiments clearly demonstrate that our proposed compact multi-texture approach outperforms the single best texture method alone. In all cases, discriminative color names outperforms other color features for texture classification. Finally, we show that combining discriminative color names with compact texture representation outperforms state-of-the-art methods by 7.8%,4.3%7.8%,4.3% and 5.0%5.0% on KTH-TIPS-2a, KTH-TIPS-2b and Texture-10 datasets respectively.
|
|
42. |
- Kruger, N., et al.
(författare)
-
An explicit and compact coding of geometric and structural image information applied to stereo processing
- 2004
-
Ingår i: Pattern Recognition Letters. - : Elsevier BV. - 0167-8655 .- 1872-7344. ; 25:8, s. 849-863
-
Tidskriftsartikel (refereegranskat)abstract
- We introduce a compact coding of image information in terms of local multi-modal image descriptors. This coding allows for an explicit separation of the local image information into different visual sub-modalities: geometric information (orientation) and structural image information (contrast transition and colour). Based on this image representation, we derive a similarity function that compares visual information in each of these sub-modalities. This allows for an investigation of the importance of the different factors for stereo matching on a large data set. From this investigation we conclude that it is the combination of visual modalities that gives the best results. Concrete weights for their relative importance are measured. In addition to these quantitative results, we can demonstrate by our simulations that although our image representation reduces image information by 97% we achieve a matching performance which is comparable to block matching techniques. This shows that our very condensed representation preserves the relevant visual information. © 2004 Elsevier B.V. All rights reserved.
|
|
43. |
- Landström, Anders, et al.
(författare)
-
Adaptive morphology using tensor-based elliptical structuring elements
- 2013
-
Ingår i: Pattern Recognition Letters. - : Elsevier BV. - 0167-8655 .- 1872-7344. ; 34:12, s. 1416-1422
-
Tidskriftsartikel (refereegranskat)abstract
- Mathematical Morphology is a common strategy for non-linear filtering of image data. In its traditional form the filters used, known as structuring elements, have constant shape once set. Such rigid structuring elements are excellent for detecting patterns of a specific shape, but risk destroying valuable information in the data as they do not adapt in any way to its structure.We present a novel method for adaptive morphological filtering where the local structure tensor, a well-known method for estimation of structure within image data, is used to construct adaptive elliptical structuring elements which vary from pixel to pixel depending on the local image structure. More specifically, their shape varies from lines in regions of strong single-directional characteristics to disks at locations where the data has no prevalent direction.
|
|
44. |
- Lidayová, Kristína, et al.
(författare)
-
Fast vascular skeleton extraction algorithm
- 2016
-
Ingår i: Pattern Recognition Letters. - : Elsevier. - 0167-8655 .- 1872-7344. ; 76, s. 67-75
-
Tidskriftsartikel (refereegranskat)abstract
- Vascular diseases are a common cause of death, particularly in developed countries. Computerized image analysis tools play a potentially important role in diagnosing and quantifying vascular pathologies. Given the size and complexity of modern angiographic data acquisition, fast, automatic and accurate vascular segmentation is a challenging task.In this paper we introduce a fully automatic high-speed vascular skeleton extraction algorithm that is intended as a first step in a complete vascular tree segmentation program. The method takes a 3D unprocessed Computed Tomography Angiography (CTA) scan as input and produces a graph in which the nodes are centrally located artery voxels and the edges represent connections between them. The algorithm works in two passes where the first pass is designed to extract the skeleton of large arteries and the second pass focuses on smaller vascular structures. Each pass consists of three main steps. The first step sets proper parameters automatically using Gaussian curve fitting. In the second step different filters are applied to detect voxels - nodes - that are part of arteries. In the last step the nodes are connected in order to obtain a continuous centerline tree for the entire vasculature. Structures found, that do not belong to the arteries, are removed in a final anatomy-based analysis. The proposed method is computationally efficient with an average execution time of 29s and has been tested on a set of CTA scans of the lower limbs achieving an average overlap rate of 97% and an average detection rate of 71%.
|
|
45. |
- Lindblad, Joakim, et al.
(författare)
-
Coverage segmentation based on linear unmixing and minimization of perimeter and boundary thickness
- 2012
-
Ingår i: Pattern Recognition Letters. - : Elsevier BV. - 0167-8655 .- 1872-7344. ; 33:6, s. 728-738
-
Tidskriftsartikel (refereegranskat)abstract
- We present a method for coverage segmentation, where the, possibly partial, coverage of each image element by each of the image components is estimated. The method combines intensity information with spatial smoothness criteria. A model for linear unmixing of image intensities is enhanced by introducing two additional conditions: (i) minimization of object perimeter, leading to smooth object boundaries, and (ii) minimization of the thickness of the fuzzy object boundary, and to some extent overall image fuzziness, to respond to a natural assumption that imaged objects are crisp, and that fuzziness is mainly due to the imaging and digitization process. The segmentation is formulated as an optimization problem and solved by the Spectral Projected Gradient method. This fast, deterministic optimization method enables practical applicability of the proposed segmentation method. Evaluation on both synthetic and real images confirms very good performance of the algorithm.
|
|
46. |
- Längkvist, Martin, 1983-, et al.
(författare)
-
A review of unsupervised feature learning and deep learning for time-series modeling
- 2014
-
Ingår i: Pattern Recognition Letters. - : Elsevier. - 0167-8655 .- 1872-7344. ; 42:1, s. 11-24
-
Forskningsöversikt (refereegranskat)abstract
- This paper gives a review of the recent developments in deep learning and unsupervised feature learning for time-series problems. While these techniques have shown promise for modeling static data, such as computer vision, applying them to time-series data is gaining increasing attention. This paper overviews the particular challenges present in time-series data and provides a review of the works that have either applied time-series data to unsupervised feature learning algorithms or alternatively have contributed to modifications of feature learning algorithms to take into account the challenges present in time-series data.
|
|
47. |
- Läthén, Gunnar, et al.
(författare)
-
Blood vessel segmentation using multi-scale quadrature filtering
- 2010
-
Ingår i: Pattern Recognition Letters. - : Elsevier. - 0167-8655 .- 1872-7344. ; 31:8, s. 762-767
-
Tidskriftsartikel (refereegranskat)abstract
- The segmentation of blood vessels is a common problem in medical imagingand various applications are found in diagnostics, surgical planning, trainingand more. Among many dierent techniques, the use of multiple scales andline detectors is a popular approach. However, the typical line lters usedare sensitive to intensity variations and do not target the detection of vesselwalls explicitly. In this article, we combine both line and edge detection usingquadrature lters across multiple scales. The lter result gives well denedvessels as linear structures, while distinct edges facilitate a robust segmentation.We apply the lter output to energy optimization techniques for segmentationand show promising results in 2D and 3D to illustrate the behavior of ourmethod. The conference version of this article received the best paper award inthe bioinformatics and biomedical applications track at ICPR 2008.
|
|
48. |
- Maergner, Paul, et al.
(författare)
-
Combining graph edit distance and triplet networks for offline signature verification
- 2019
-
Ingår i: Pattern Recognition Letters. - : Elsevier. - 0167-8655 .- 1872-7344. ; 125, s. 527-533
-
Tidskriftsartikel (refereegranskat)abstract
- Offline signature verification is a challenging pattern recognition task where a writer model is inferred using only a small number of genuine signatures. A combination of complementary writer models can make it more difficult for an attacker to deceive the verification system. In this work, we propose to combine a recent structural approach based on graph edit distance with a statistical approach based on deep triplet networks. The combination of the structural and statistical models achieve significant improvements in performance on four publicly available benchmark datasets, highlighting their complementary perspectives.
|
|
49. |
- Mahbod, Amirreza, et al.
(författare)
-
Automatic brain segmentation using artificial neural networks with shape context
- 2018
-
Ingår i: Pattern Recognition Letters. - : Elsevier. - 0167-8655 .- 1872-7344. ; 101, s. 74-79
-
Tidskriftsartikel (refereegranskat)abstract
- Segmenting brain tissue from MR scans is thought to be highly beneficial for brain abnormality diagnosis, prognosis monitoring, and treatment evaluation. Many automatic or semi-automatic methods have been proposed in the literature in order to reduce the requirement of user intervention, but the level of accuracy in most cases is still inferior to that of manual segmentation. We propose a new brain segmentation method that integrates volumetric shape models into a supervised artificial neural network (ANN) framework. This is done by running a preliminary level-set based statistical shape fitting process guided by the image intensity and then passing the signed distance maps of several key structures to the ANN as feature channels, in addition to the conventional spatial-based and intensity-based image features. The so-called shape context information is expected to help the ANN to learn local adaptive classification rules instead of applying universal rules directly on the local appearance features. The proposed method was tested on a public datasets available within the open MICCAI grand challenge (MRBrainS13). The obtained average Dice coefficient were 84.78%, 88.47%, 82.76%, 95.37% and 97.73% for gray matter (GM), white matter (WM), cerebrospinal fluid (CSF), brain (WM + GM) and intracranial volume respectively. Compared with other methods tested on the same dataset, the proposed method achieved competitive results with comparatively shorter training time.
|
|
50. |
|
|