| 1. |
|
|
| 2. |
- Alvén, Jennifer, 1989, et al.
(författare)
-
Shape-aware multi-atlas segmentation
- 2016
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. ; 0, s. 1101-1106
-
Konferensbidrag (refereegranskat)abstract
- Despite of having no explicit shape model, multi-atlas approaches to image segmentation have proved to be a top-performer for several diverse datasets and imaging modalities. In this paper, we show how one can directly incorporate shape regularization into the multi-atlas framework. Unlike traditional methods, our proposed approach does not rely on label fusion on the voxel level. Instead, each registered atlas is viewed as an estimate of the position of a shape model. We evaluate and compare our method on two public benchmarks: (i) the VISCERAL Grand Challenge on multi-organ segmentation of whole-body CT images and (ii) the Hammers brain atlas of MR images for segmenting the hippocampus and the amygdala. For this wide spectrum of both easy and hard segmentation tasks, our experimental quantitative results are on par or better than state-of-the-art. More importantly, we obtain qualitatively better segmentation boundaries, for instance, preserving fine structures.
|
|
| 3. |
- Arvidsson, Ida, et al.
(författare)
-
Prediction of Obstructive Coronary Artery Disease from Myocardial Perfusion Scintigraphy using Deep Neural Networks
- 2021
-
Ingår i: 2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR). - : IEEE COMPUTER SOC. - 1051-4651. - 9781728188089 ; , s. 4442-4449
-
Konferensbidrag (refereegranskat)abstract
- For diagnosis and risk assessment in patients with stable ischemic heart disease, myocardial perfusion scintigraphy is one of the most common cardiological examinations performed today. There are however many motivations for why an artificial intelligence algorithm would provide useful input to this task. For example to reduce the subjectiveness and save time for the nuclear medicine physicians working with this time consuming task. In this work we have developed a deep learning algorithm for multi-label classification based on a convolutional neural network to estimate the probability of obstructive coronary artery disease in the left anterior artery, left circumflex artery and right coronary artery. The prediction is based on data from myocardial perfusion scintigraphy studies conducted in a dedicated Cadmium-Zinc-Telluride cardio camera (D-SPECT Spectrum Dynamics). Data from 588 patients was available, with stress images in both upright and supine position, as well as a number of auxiliary parameters such as angina symptoms and age. The data was used to train and evaluate the algorithm using 5-fold cross-validation. We achieve state-of-the-art results for this task with an area under the receiver operating characteristics curve of 0.89 as average on per-vessel level and 0.95 on per-patient level.
|
|
| 4. |
- Berg, Axel, et al.
(författare)
-
Deep ordinal regression with label diversity
- 2021
-
Ingår i: 2020 25th International Conference on Pattern Recognition (ICPR). - 1051-4651. - 9781728188089 ; , s. 2740-2747
-
Konferensbidrag (refereegranskat)abstract
- Regression via classification (RvC) is a common method used for regression problems in deep learning, where the target variable belongs to a set of continuous values. By discretizing the target into a set of non-overlapping classes, it has been shown that training a classifier can improve neural network accuracy compared to using a standard regression approach. However, it is not clear how the set of discrete classes should be chosen and how it affects the overall solution. In this work, we propose that using several discrete data representations simultaneously can improve neural network learning compared to a single representation. Our approach is end-to-end differentiable and can be added as a simple extension to conventional learning methods, such as deep neural networks. We test our method on three challenging tasks and show that our method reduces the prediction error compared to a baseline RvC approach while maintaining a similar model complexity.
|
|
| 5. |
- Berg, Axel, et al.
(författare)
-
Points to patches: Enabling the use of self-attention for 3D shape recognition
- 2022
-
Ingår i: 2022 26th International Conference on Pattern Recognition (ICPR). - 1051-4651 .- 2831-7475. - 9781665490627 - 9781665490627 ; , s. 528-534
-
Konferensbidrag (refereegranskat)abstract
- While the Transformer architecture has become ubiquitous in the machine learning field, its adaptation to 3D shape recognition is non-trivial. Due to its quadratic computational complexity, the self-attention operator quickly becomes inefficient as the set of input points grows larger. Furthermore, we find that the attention mechanism struggles to find useful connections between individual points on a global scale. In order to alleviate these problems, we propose a two-stage Point Transformer-in-Transformer (Point-TnT) approach which combines local and global attention mechanisms, enabling both individual points and patches of points to attend to each other effectively. Experiments on shape classification show that such an approach provides more useful features for downstream tasks than the baseline Transformer, while also being more computationally efficient. In addition, we also extend our method to feature matching for scene reconstruction, showing that it can be used in conjunction with existing scene reconstruction pipelines.
|
|
| 6. |
|
|
| 7. |
- Bylow, Erik, et al.
(författare)
-
Robust Camera Tracking by Combining Color and Depth Measurements
- 2014
-
Ingår i: International Conference on Pattern Recognition. - 1051-4651.
-
Konferensbidrag (refereegranskat)abstract
- One of the major research areas in computer vision is scene reconstruction from image streams. The advent of RGB-D cameras, such as the Microsoft Kinect, has lead to new possibilities for performing accurate and dense 3D reconstruction. There are already well-working algorithms to acquire 3D models from depth sensors, both for large and small scale scenes. However, these methods often break down when the scene geometry is not so informative, for example, in the case of planar surfaces. Similarly, standard image-based methods fail for texture-less scenes. We combine both color and depth measurements from an RGB-D sensor to simultaneously reconstruct both the camera motion and the scene geometry in a robust manner. Experiments on real data show that we can accurately reconstruct large-scale 3D scenes despite many planar surfaces.
|
|
| 8. |
- Bylow, Erik, et al.
(författare)
-
Robust online 3D reconstruction combining a depth sensor and sparse feature points
- 2016
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. ; 0, s. 3709-3714, s. 3709-3714
-
Konferensbidrag (refereegranskat)abstract
- Online 3D reconstruction has been an active research area for a long time. Since the release of the Microsoft Kinect Camera and publication of KinectFusion [11] attention has been drawn how to acquire dense models in real-time. In this paper we present a method to make online 3D reconstruction which increases robustness for scenes with little structure information and little texture information. It is shown empirically that our proposed method also increases robustness when the distance between the camera positions becomes larger than what is commonly assumed. Quantitative and qualitative results suggest that this approach can handle situations where other well-known methods fail. This is important in, for example, robotics applications like when the camera position and the 3D model must be created online in real-time.
|
|
| 9. |
- Changrampadi, Mohamed Hashim, 1987, et al.
(författare)
-
Multi-Class Ada-Boost Classification of Object Poses through Visual and Infrared Image Information Fusion
- 2012
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. - 9784990644109 ; , s. 2865-2868
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a novel method for pose classification using fusion of visual and thermal infrared(IR) images. We propose a novel tree structure multi-class classification scheme with visual and IR sub-classifiers. These sub-classifiers are different from the conventional one-against-all or one-against-one strategies, where we handle the multi-class problem directly. We propose to use an accuracy score for the fusion of visual and IR subclassifiers. In addition, we propose to use the original Haar features plus an extra one, and a multi-threshold weak learner to obtain weak hypothesis. The experimental results on a visual and IR image dataset containing 3018 face images in three poses show that the proposed classifier achieves high classification rate of 99.50% on the test set. Comparisons are made to a fused one-vs-all method, a classifier with visual band only, and a classifier with IR band only. Results provide further support to the proposed method.
|
|
| 10. |
- Ciolfi, L., et al.
(författare)
-
The Shannon Portal Installation : Interaction Design for public spaces
- 2007
-
Ingår i: IEEE Computer Society. - : IEEE Computer Society. - 1051-4651. ; 40:7, s. 64-71
-
Tidskriftsartikel (refereegranskat)abstract
- The portal dolmen project at Ireland's Shannon airport tackled the challenges of a public exhibition and revealed the importance of focusing on situated activities as well as the crucial need for incorporating physical and aesthetic concerns into the design.
|
|
| 11. |
- Ciolfi, L., et al.
(författare)
-
The Shannon Portal Installation: An Example of Interaction Design for Public Places
- 2007
-
Ingår i: IEEE Computer Society. - : IEEE Communications Society. - 1051-4651. ; , s. 65-72
-
Tidskriftsartikel (refereegranskat)abstract
- The portal dolmen project at Ireland's Shannon airport tackled the challenges of a public exhibition and revealed the importance of focusing on situated activities as well as the crucial need for incorporating physical and aesthetic concerns into the design.
|
|
| 12. |
- Eriksson, Anders P, et al.
(författare)
-
Bijective image registration using thin-plate splines
- 2006
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. ; 3, s. 798-801
-
Konferensbidrag (refereegranskat)abstract
- Image registration is the process of geometrically aligning two or more images. In this paper we describe a method for registering pairs of images based on thin-plate spline mappings. The proposed algorithm minimizes the difference in gray-level intensity over bijective deformations. By using quadratic sufficient constraints for bijectivity and a least squares formulation this optimization problem can be addressed using quadratic programming and a modified Gauss-Newton method. This approach also results in a very computationally efficient algorithm. Example results from the algorithm on three different types of images are also presented.
|
|
| 13. |
- Faraj, Maycel Isaac, 1979-, et al.
(författare)
-
Motion Features from Lip Movement for Person Authentication
- 2006
-
Ingår i: The 18th International Conference on Pattern Recognition. - Washington, D.C. : IEEE Computer Society. - 0769525210 ; 3, s. 1059- 1062
-
Konferensbidrag (refereegranskat)abstract
- This paper describes a new motion based feature extraction technique for speaker identification using orientation estimation in 2D manifolds. The motion is estimated by computing the components of the structure tensor from which normal flows are extracted. By projecting the 3D spatiotemporal data to 2D planes, we obtain projection coefficients which we use to evaluate the 3D orientations of brightness patterns in TV like image sequences. This corresponds to the solutions of simple matrix eigenvalue problems in 2D, affording increased computational efficiency. An implementation based on joint lip movements and speech is presented along with experiments which confirm the theory, exhibiting a recognition rate of 98% on the publicly available XM2VTS database
|
|
| 14. |
|
|
| 15. |
- Floreby, L, et al.
(författare)
-
Boundary finding using Fourier surfaces of increasing order
- 1998
-
Ingår i: Proceeedings of the Fourteenth International Conference on Pattern Recognition. - 1051-4651. - 0818685123 ; 1, s. 465-467
-
Konferensbidrag (refereegranskat)abstract
- Boundary finding in simulated medical images is performed by optimizing the Fourier coefficients in a parametric surface representation with respect to an objective function. The deformable model is fitted to the data using the brightness gradient component which is normal to the surface. A low order (<10) Fourier series expansion offers a sufficiently accurate representation for many inherently smooth objects that occur in medical imaging. Experimental results are presented for simulated image objects corresponding to organs of the anthropomorphic Zubal phantom. Two different optimization methods are studied concerning robustness and computational efficiency. The effect of increasing the Fourier expansion order is investigated for various noise levels
|
|
| 16. |
- Floreby, L, et al.
(författare)
-
Deformable Fourier surfaces for volume segmentation in SPECT
- 1998
-
Ingår i: Proceeedings of the Fourteenth International Conference on Pattern Recognition. - 1051-4651. - 0818685123 ; 1, s. 358-360
-
Konferensbidrag (refereegranskat)abstract
- Three-dimensional boundary finding based on Fourier surface optimization is presented as a method for segmentation of SPECT images. Being robust against noise and adjustable with respect to its detail resolution, it forms an interesting alternative in this application area. A three-dimensional approach can also be assumed to increase the possibility of delineating low contrast regions, as compared to a two-dimensional slice-by-slice approach. We apply boundary finding to Monte Carlo simulated SPECT images of the computer-based anthropomorphic Zubal phantom in order to evaluate the influence of object contrast and noise on the segmentation accuracy. Segmentation is also performed in real patient images
|
|
| 17. |
- Fu, Keren, 1988, et al.
(författare)
-
Graph Construction for Salient Object Detection in Videos
- 2014
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. - 9781479952083 ; , s. 2371-2376
-
Konferensbidrag (refereegranskat)abstract
- Recently many graph-based salient region/object detection methods have been developed. They are rather effective for still images. However, little attention has been paid to salient region detection in videos. This paper addresses salient region detection in videos. A unified approach towards graph construction for salient object detection in videos is proposed. The proposed method combines static appearance and motion cues to construct graph, enabling a direct extension of original graph based salient region detection to video processing. To maintain coherence in both intra- and inter-frames, a spatial-temporal smoothing operation is proposed on a structured graph derived from consecutive frames. The effectiveness of the proposed method is tested and validated using seven videos from two video datasets.
|
|
| 18. |
- Gillsjö, David, et al.
(författare)
-
In Depth Bayesian Semantic Scene Completion
- 2021
-
Ingår i: 2020 25th International Conference on Pattern Recognition (ICPR). - 1051-4651. - 9781728188089 ; , s. 6335-6342
-
Konferensbidrag (refereegranskat)
|
|
| 19. |
- Gu, Irene Yu-Hua, 1953, et al.
(författare)
-
Grassmann Manifold Online Learning and Partial Occlusion Handling for Visual Object Tracking under Bayesian Formulation
- 2012
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. - 9784990644109 ; , s. 1463-1466
-
Konferensbidrag (refereegranskat)abstract
- This paper addresses issues of online learning and occlusion handling in video object tracking. Although manifold tracking is promising, large pose changes and long term partial occlusions of video objects remain challenging.We propose a novel manifold tracking scheme that tackles such problems, with the following main novelties: (a) Online estimation of object appearances on Grassmann manifolds; (b) Optimal criterion-based occlusion handling during online learning; (c) Nonlinear dynamic model for appearance basis matrix and its velocity; (b) Bayesian formulations separately for the tracking and the online learning process. Two particle filters are employed: one is on the manifold for generating appearance particles and another on the linear space for generating affine box particles. Tracking and online updating are performed in alternative fashion to mitigate the tracking drift. Experiments on videos have shown robust tracking performance especially when objects contain significantpose changes accompanied with long-term partial occlusions. Evaluations and comparisons with two existing methods provide further support to the proposed method.
|
|
| 20. |
- Haner, Sebastian, 1984, et al.
(författare)
-
Combining Foreground / Background Feature Points and Anisotropic Mean Shift For Enhanced Visual Object Tracking
- 2010
-
Ingår i: 20th International Conf. Pattern Recognition (ICPR 2010), 23-26 August, 2010, Istanbul, Turkey. - 1051-4651. - 9780769541099 ; , s. 3488-3491
-
Konferensbidrag (refereegranskat)abstract
- This paper proposes a novel visual object tracking scheme, exploiting both local point feature correspondences and global object appearance using the anisotropic mean shift tracker. Using a RANSAC cost function incorporating the mean shift motion estimate, motion smoothness and complexity terms, an optimal feature point set for motion estimation is found even when a high proportion of outliers is presented. The tracker dynamically maintains sets of both foreground and background features, the latter providing information on object occlusions. The mean shift motion estimate is further used to guide the inclusion of new point features in the object model. Our experiments on videos containing long term partial occlusions, object intersections and cluttered or close color distributed background have shown more stable and robust tracking performance in comparison to three existing methods.
|
|
| 21. |
- Hsu, Pohao, et al.
(författare)
-
Extremely Low-light Image Enhancement with Scene Text Restoration
- 2022
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. - 9781665490627 ; 2022-August, s. 317-323
-
Konferensbidrag (refereegranskat)abstract
- Deep learning based methods have made impressive progress in enhancing extremely low-light images - the image quality of the reconstructed images has generally improved. However, we found out that most of these methods could not sufficiently recover the image details, for instance the texts in the scene. In this paper, a novel image enhancement framework is proposed to specifically restore the scene texts, as well as the overall quality of the image simultaneously under extremely low-light images conditions. Particularly, we employed a selfregularised attention map, an edge map, and a novel text detection loss. The quantitative and qualitative experimental results have shown that the proposed model outperforms stateof-the-art methods in terms of image restoration, text detection, and text spotting on See In the Dark and ICDAR15 datasets.
|
|
| 22. |
- Karlsson, Johan, et al.
(författare)
-
A ground truth correspondence measure for benchmarking
- 2006
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. ; 3, s. 568-573
-
Konferensbidrag (refereegranskat)abstract
- Automatic localisation of correspondences for the construction of Statistical Shape Models from examples has been the focus of intense research during the last decade. Several algorithms are available and benchmarking is needed to rank the different algorithms. Prior work has focused on evaluating the quality of the models produced by the algorithms by measuring compactness, generality and specificity. In this paper problems with these standard measures are discussed. We propose that a ground truth correspondence measure (gcm) is used for benchmarking and in this paper benchmarking is performed on several state of the art algorithms. Minimum Description Length (MDL) with a curvature cost comes out as the winner of the automatic methods. Hand marked models turn out to be best but a semi-automatic method is shown to lie in between the best automatic method and the hand built models in performance.
|
|
| 23. |
- Karlsson, Johan, et al.
(författare)
-
MDL Patch Correspondences on Unlabeled Images with Occlusions
- 2008
-
Ingår i: 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops). - 9781424423392 ; , s. 999-1006, s. 3249-3253
-
Konferensbidrag (refereegranskat)abstract
- Automatic construction of Shape and Appearance Models from examples via establishing correspondences across the training set has been successful in the last decades. One successful measure for establishing correspondences of high quality is minimum description length (MDL). In other approaches it has been shown that parts+geometry models which model the appearance of parts of the object and the geometric relation between the parts have been successful for automatic model building. In this paper it is shown how to fuse the above approaches and use MDL to fully automatically build optimal parts+geometry models from unlabeled images.
|
|
| 24. |
- Kuang, Yubin, et al.
(författare)
-
Revisiting Trifocal Tensor Estimation Using Lines
- 2014
-
Ingår i: Pattern Recognition (ICPR), 2014 22nd International Conference on. - 1051-4651. ; , s. 2419-2423
-
Konferensbidrag (refereegranskat)abstract
- In this paper, we revisit the problem of estimating the trifocal tensor from image line measurements. With measurements of corresponding lines in three views, a linear method [1] requiring 13 lines was developed to estimate the trifocal tensor from which projective reconstruction of the scene is made possible. By further utilizing the nonlinear constraints on the trifocal tensor, we propose several new linear solvers that require fewer number of lines (10,11,12) than the previous linear method. We use methods based on algebraic geometry to incorporate the non-linear constraints in the estimation. We demonstrate the performance of the proposed solvers on synthetic data. We also test the solvers on real images and obtain promising results.
|
|
| 25. |
- Kårsnäs, Andreas, 1977-, et al.
(författare)
-
The Vectorial Minimum Barrier Distance
- 2012
-
Ingår i: International Conference on Pattern Recognition. - 1051-4651. - 9781467322164 ; , s. 792-795
-
Tidskriftsartikel (refereegranskat)abstract
- We introduce the vectorial Minimum Barrier Distance (MBD), a method for computing a gray-weighted distance transform while also incorporating information from vectorial data. Compared to other similar tools that use vectorial data, the proposed method requires no training and does not assume having only one background class. We describe a region growing algorithm for computing the vectorial MBD efficiently.The method is evaluated on two types of multi-channel images: color images and textural features. Different path-cost functions for calculating the multi-dimensional path-cost distance are also compared.The results show that by combining multi-channel images into vectorial information the performance ofthe vectorial MBD segmentation is improved compared to when one channel is used. This implies that the method can be a good way of incorporating multi-channel information in interactive segmentation.
|
|
| 26. |
- Landgren, Matilda, et al.
(författare)
-
A Measure of Septum Shape Using Shortest Path Segmentation in Echocardiographic Images of LVAD Patients
- 2014
-
Ingår i: Pattern Recognition (ICPR), 2014 22nd International Conference on. - 1051-4651. ; , s. 3398-3403
-
Konferensbidrag (refereegranskat)abstract
- Patients waiting for heart transplantation due to a failing heart can get a left ventricular assist device (LVAD) implanted through open chest surgery. The device consists of a pump that pumps blood from the left ventricle into the aorta. To get the correct rotation speed of the pump, the physicians consider a number of measurements as well as a sequence of echocardiographic images. The important information obtained from the images is the shape of the inter-ventricular septum. For instance, if the septum bulges towards the left ventricle the speed is too high and it might harm the right ventricular function. To get a measure of the shape of the septum, which can be incorporated in a decision support system, we perform a segmentation of the septum using a shortest path method. To reduce user interaction, the user only needs to annotate two anchor points in the first frame. They mark the endpoints of the septum and they are tracked through the sequence with our tracking algorithm. After the segmentation the septum is divided into two regions, the one closest to the right ventricle and the one closest to the left ventricle, and the desired measure is the difference between the areas of these regions divided by the total septum area. The performance of the segmentation algorithm is acceptable and the obtained septum measure corresponds in most cases to the assessments from a physician.
|
|
| 27. |
|
|
| 28. |
- Lindblad, Joakim, et al.
(författare)
-
De-noising of SRµCT Fiber Images by Total Variation Minimization
- 2010
-
Ingår i: Proceedings of the 20th International Conference on Pattern Recognition (ICPR10). - Istanbul, Turkey. - 1051-4651. - 9781424475421 ; , s. 4621-4624
-
Konferensbidrag (refereegranskat)abstract
- SRμCT images of paper and pulp fiber materials are characterized by a low signal to noise ratio. De-noising is therefore a common preprocessing step before segmentation into fiber and background components. We suggest a de-noising method based on total variation minimization using a modified Spectral Conjugate Gradient algorithm. Quantitative evaluation performed on synthetic 3D data and qualitative evaluation on real 3D paper fiber data confirm appropriateness of the suggested method for the particular application.
|
|
| 29. |
- Lindblad, Joakim, et al.
(författare)
-
Optimizing optics and imaging for pattern recognition based screening tasks
- 2014
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - : IEEE Computer Society. - 1051-4651. - 9781479952083 ; , s. 3333-3338
-
Konferensbidrag (refereegranskat)abstract
- We present a method for simulating lower quality images starting from higher quality ones, based on acquired image pairs from different optical setups. The method does not require estimates of point (or line) spread functions of the system, but utilizes the relative transfer function derived from images of real specimen of interest in the observed application. Thanks to the use of a larger number of real specimen, excellent stability and robustness of the method is achieved. The intended use is exploring the influence of image quality on features and classification accuracy in pattern recognition based screening tasks. Visual evaluation of the obtained images strongly confirms usefulness of the method. The approach is quantitatively evaluated by observing stability of feature values, proven useful for PAP-smear classification, between synthetic and real images from seven different microscope setups. The evaluation shows that features from the synthetically generated lower resolution images are as similar to features from real images at that resolution, as features from two different images of the same specimen, taken at the same low resolution, are to each other.
|
|
| 30. |
- Liu, Xixi, 1995, et al.
(författare)
-
Effortless Training of Joint Energy-Based Models with Sliced Score Matching
- 2022
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. - 9781665490627 ; 2022-August, s. 2643-2649
-
Konferensbidrag (refereegranskat)abstract
- Standard discriminative classifiers can be upgraded to joint energy-based models (JEMs) by combining the classification loss with a log-evidence loss. Hence, such models intrinsically allow detection of out-of-distribution (OOD) samples, and empirically also provide better-calibrated posteriors, i.e., prediction uncertainties. However, the training procedure suggested for JEMs (using stochastic gradient Langevin dynamics---or SGLD---to maximize the evidence) is reported to be brittle. In this work, we propose to utilize score matching---in particular sliced score matching---to obtain a stable training method for JEMs. We observe empirically that the combination of score matching with the standard classification loss leads to improved OOD detection and better-calibrated classifiers for otherwise identical DNN architectures. Additionally, we also analyze the impact of replacing the regular soft-max layer for classification with a gated soft-max one in order to improve the intrinsic transformation invariance and generalization ability.
|
|
| 31. |
- Liu, Xixi, 1995, et al.
(författare)
-
Joint Energy-based Model for Deep Probabilistic Regression
- 2022
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. - 9781665490627 ; 2022-August, s. 2693-2699
-
Konferensbidrag (refereegranskat)abstract
- It is desirable that a deep neural network trained on a regression task does not only achieve high prediction accuracy, but its prediction posteriors are also well-calibrated, especially in safety-critical settings. Recently, energy-based models specifically to enrich regression posteriors have been proposed and achieve state-of-art results in object detection tasks. However, applying these models at prediction time is not straightforward as the resulting inference methods require to minimize an underlying energy function. Furthermore, these methods empirically do not provide accurate prediction uncertainties. Inspired by recent joint energy-based models for classification, in this work we propose to utilize a joint energy model for regression tasks and describe architectural differences needed in this setting. Within this frame-work, we apply our methods to three computer vision regression tasks. We demonstrate that joint energy-based models for deep probabilistic regression improve the calibration property, do not require expensive inference, and yield competitive accuracy in terms of the mean absolute error (MAE).
|
|
| 32. |
- Malm, Henrik, et al.
(författare)
-
Motion dependent spatiotemporal smoothing for noise reduction in very dim light image sequences
- 2006
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. ; 3, s. 954-959
-
Konferensbidrag (refereegranskat)abstract
- A new method for noise reduction using spatiotemporal smoothing is presented in this paper. The method is developed especially for reducing the noise that arises when acquiring video sequences with a camera under very dim light conditions. The work is inspired by research on the vision of nocturnal animals and the adaptive spatial and temporal summation that is prevalent in the visual systems of these animals. From analysis using the so-called structure tensor in the three-dimensional spatiotemporal space, motion segmentation and global ego-motion estimation, Gaussian shaped smoothing kernels are oriented mainly in the direction of the motion and in spatially homogeneous directions. In static areas, smoothing along the temporal dimension is favoured for maximum preservation of structure. The technique has been applied to various dim light image sequences and results of these experiments are presented here.
|
|
| 33. |
- Mehnert, Andrew, 1967, et al.
(författare)
-
A Structural texture approach for characterising malignancy associated changes in pap smears based on mean-shift and the watershed transform
- 2014
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - : IEEE Computer Society. - 1051-4651. - 9781479952083 ; , s. 1189-1193
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a novel structural approach to quantitatively characterising nuclear chromatin texture in light microscope images of Pap smears. The approach is based on segmenting the chromatin into blob-like primitives and characterising their properties and arrangement. The segmentation approach makes use of multiple focal planes. It comprises two basic steps: (i) mean-shift filtering in the feature space formed by concatenating pixel spatial coordinates and intensity values centred around the best all-in-focus plane, and (ii) hierarchical marker-based watershed segmentation. The paper also presents an empirical evaluation of the approach based on the classification of 43 routine clinical Pap smears. Two variants of the approach were compared to a reference approach (employing extended depth-of-field rather than mean-shift) in a feature selection/classification experiment, involving 138 segmentation-based features, for discriminating normal and abnormal slides. The results demonstrate improved performance over the reference approach. The results of a second feature selection/classification experiment, including additional classes of features from the literature, show that a combination of the proposed structural and conventional features yields a classification performance of 0.919±0.015 (AUC ± Std. Dev.). Overall the results demonstrate the efficacy of the proposed structural approach and confirm that it is indeed possible to detect malignancy associated changes (MACs) in conventional Papanicolaou stain.
|
|
| 34. |
- Moliner, Olivier, et al.
(författare)
-
Better Prior Knowledge Improves Human-Pose-Based Extrinsic Camera Calibration
- 2021
-
Ingår i: 2020 25th International Conference on Pattern Recognition (ICPR). - 1051-4651. - 9781728188089 ; , s. 4758-4765
-
Konferensbidrag (refereegranskat)abstract
- Accurate extrinsic calibration of wide baseline multi-camera systems enables better understanding of 3D scenes for many applications and is of great practical importance. Classical Structure-from-Motion calibration methods require special calibration equipment so that accurate point correspondences can be detected between different views. In addition, an operator with some training is usually needed to ensure that data is collected in a way that leads to good calibration accuracy. This limits the ease of adoption of such technologies. Recently, methods have been proposed to use human pose estimation models to establish point correspondences, thus removing the need for any special equipment. The challenge with this approach is that human pose estimation algorithms typically produce much less accurate feature points compared to classical patch-based methods. Another problem is that ambient human motion might not be optimal for calibration. We build upon prior works and introduce several novel ideas to improve the accuracy of human-pose-based extrinsic calibration. Our first contribution is a robust reprojection loss based on a better understanding of the sources of pose estimation error. Our second contribution is a 3D human pose likelihood model learned from motion capture data. We demonstrate significant improvements in calibration accuracy by evaluating our method on four publicly available datasets.
|
|
| 35. |
- Nilsson, Jonas, 1979, et al.
(författare)
-
Pedestrian Detection using Augmented Training Data
- 2014
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. - 9781479952083 ; , s. 4548-4553
-
Konferensbidrag (refereegranskat)abstract
- Detecting pedestrians is a challenging and widely explored problem in computer vision. Many approaches rely on large quantities of manually labelled training data to learn apedestrian classifier. To reduce the need for collecting and manually labelling real image training data, this paper investigates the possibility to use augmented images to train a pedestrian classifier. Augmented images are generated by rendering virtual pedestrians onto real image backgrounds. Classifiers learned from real or augmented training data are evaluated on real image test data from the widely used Daimler Mono Pedestrian benchmark data set. Results show that augmented training data generated from a single 200 frame image sequence reach 70% average detection rate at one False Positives Per Image (FPPI), compared to 81% for a classifier trained by a large-scale real data set.Results also show that complementing real training data withaugmented data improves detection performance, compared tousing real training data only.
|
|
| 36. |
- Nilsson, Mikael
(författare)
-
Elastic Net Regularized Logistic Regression using Cubic Majorization
- 2014
-
Ingår i: 2014 22nd International Conference on Pattern Recognition (ICPR). - 1051-4651. ; , s. 3446-3451
-
Konferensbidrag (refereegranskat)abstract
- In this work, a coordinate solver for elastic net regularized logistic regression is proposed. In particular, a method based on majorization maximization using a cubic function is derived. This to reliably and accurately optimize the objective function at each step without resorting to line search. Experiments show that the proposed solver is comparable to, or improves, state-of-the-art solvers. The proposed method is simpler, in the sense that there is no need for any line search, and can directly be used for small to large scale learning problems with elastic net regularization.
|
|
| 37. |
- Nilsson, Niclas, et al.
(författare)
-
Estimates of Classification Complexity for Myoelectric Pattern Recognition
- 2016
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. ; 0, s. 2682-2687
-
Konferensbidrag (refereegranskat)abstract
- Myoelectric pattern recognition (MPR) can be used for intuitive control of virtual and robotic effectors in clinical applications such as prosthetic limbs and the treatment of phantom limb pain. The conventional approach is to feed classifiers with descriptive electromyographic (EMG) features that represent the aimed movements. The complexity and consequently classification accuracy of MPR is highly affected by the separability of such features. In this study, classification complexity estimating algorithms were investigated as a potential tool to estimate MPR performance. An early prediction of MPR accuracy could inform the user of faulty data acquisition, as well as suggest the repetition or elimination of detrimental movements in the repository of classes. Two such algorithms, Nearest Neighbor Separability (NNS) and Separability Index (SI), were found to be highly correlated with classification accuracy in three commonly used classifiers for MPR (Linear Discriminant Analysis, Multi-Layer Perceptron, and Support Vector Machine). These Classification Complexity Estimating Algorithms (CCEAs) were implemented in the open source software BioPatRec and are available freely online. This work deepens the understanding of the complexity of MPR for the prediction of motor volition.
|
|
| 38. |
- Olsson, Carl, et al.
(författare)
-
Local Refinement for Stereo Regularization
- 2014
-
Ingår i: Pattern Recognition (ICPR), 2014 22nd International Conference on. - 1051-4651. ; , s. 4056-4061
-
Konferensbidrag (refereegranskat)abstract
- Stereo matching is an inherently difficult problem due to ambiguous and noisy texture. The non-convexity and non- differentiability makes local linear (or quadratic) approximations poor, thereby preventing the use of standard local descent methods. Therefore recent methods are predominantly based on discretization and/or random sampling of some class of approximating surfaces (e.g. planes). While these methods are very efficient in generating a rough surface estimate, via either fusion of proposals or label propagation, the end result is usually not as smooth as desired. In this paper we show that, if the objective function is decomposed correctly, local refinement of candidate solutions can be performed using an ADMM approach. This allows searching over more general function classes, thereby resulting in visually more appealing smooth surface estimations.
|
|
| 39. |
- Olsson, Carl, et al.
(författare)
-
Optimal estimation of perspective camera pose
- 2006
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. ; 2, s. 5-8
-
Konferensbidrag (refereegranskat)abstract
- In this paper we propose apractical and efficient method for finding the globally optimal solution to the problem of camera pose estimation for calibrated cameras. While traditional methods may get trapped in local minima, due to the non-convexity of the problem, we have developed an approach that guarantees global optimality. The scheme is based on ideas from global optimization theory, in particular, convex under-estimators in combination with branch and bound. We provide aprovably optimal algorithm and demonstrate good performance on both synthetic and real data.
|
|
| 40. |
- Olsson, Carl, et al.
(författare)
-
Solving Quadratically Constrained Geometrical Problems using Lagrangian Duality
- 2008
-
Ingår i: 19th International Conference on Pattern Recognition, 2008. ICPR 2008.. - 1051-4651. - 9781424421749 ; , s. 2469-2473
-
Konferensbidrag (refereegranskat)abstract
- In this paper we consider the problem of solving different pose and registration problems under rotational constraints. Traditionally, methods such as the iterative closest point algorithm have been used to solve these problems. They may however get stuck in local minima due to the non-convexity of the problem. In recent years methods for finding the global optimum, based on Branch and Bound and convex under-estimators, have been developed. These methods are provably optimal, however since they are based on global optimization methods they are in general more time consuming than local methods. In this paper we adopt a dual approach. Rather than trying to find the globally optimal solution we investigate the quality of the solutions obtained using Lagrange duality. Our approach allows its to formulate a single convex semidefinite program that approximates the original problem well.
|
|
| 41. |
- Oskarsson, Magnus, et al.
(författare)
-
Prime Rigid Graphs and Multidimensional Scaling with Missing Data
- 2014
-
Ingår i: Pattern Recognition (ICPR), 2014 22nd International Conference on. - 1051-4651. ; , s. 750-755
-
Konferensbidrag (refereegranskat)abstract
- In this paper we investigate the problem of embedding a number of points given certain (but typically not all) inter-pair distance measurements. This problem is relevant for multi-dimensional scaling problems with missing data, and is applicable within anchor-free sensor network node calibration and anchor-free node localization using radio or sound TOA measurements. There are also applications within chemistry for deducing molecular 3D structure given inter-atom distance measurements and within machine learning and visualization of data, where only similarity measures between sample points are provided. The problem has been studied previously within the field of rigid graph theory. Our aim is here to construct numerically stable and efficient solvers for finding all embeddings of such minimal rigid graphs. The method is based on the observation that all graphs are either irreducibly rigid, here called prime rigid graphs, or contain smaller rigid graphs. By solving the embedding problem for the prime rigid graphs and for ways of assembling such graphs to other minimal rigid graphs, we show how to (i) calculate the number of embeddings and (ii) construct numerically stable and efficient algorithms for obtaining all embeddings given inter-node measurements. The solvers are verified with experiments on simulated data.
|
|
| 42. |
- Sintorn, Ida-Maria, et al.
(författare)
-
Regional Zernike Moments for Texture Recognition
- 2012
-
Ingår i: Proceedings of the 21st International Conference on Pattern Recognition (ICPR). - 1051-4651. ; , s. 1635-1638
-
Konferensbidrag (refereegranskat)abstract
- Zernike moments are commonly used in pattern recognition but are not suited for texture analysis. In this paper we introduce regional Zernike moments (RZM) where we combine the Zernike moments for the pixels in a region to create a measure suitable for texture analysis. We compare our proposed measures to texture measures based on Gabor filters, Haralick co-occurrence matrices and local binary patterns on two different texture image sets, and show that they are noise insensitive and very well suited for texture recognition.
|
|
| 43. |
- Sintorn, Ida-Maria, et al.
(författare)
-
Virus recognition based on local texture
- 2014
-
Ingår i: Proceedings 22nd International Conference on Pattern Recognition (ICPR), 2014. - 1051-4651. - 9781479952083 ; , s. 3227-3232
-
Konferensbidrag (refereegranskat)abstract
- To detect and identify viruses in electron microscopy images is crucial in certain clinical emergency situations. It is currently a highly manual task, requiring an expert sittingat the microscope to perform the analysis visually. Here wefocus on and investigate one aspect towards automating the virusdiagnostic task, namely recognizing the virus type based on theirtexture once possible virus objects have been segmented. Weshow that by using only local texture descriptors we achievea classification rate of almost 89% on texture patches from 15different virus types and a debris (false object) class. We compareand combine 5 different types of local texture descriptors andshow that by combining the different types a lower classificationerror is achieved. We use a Random Forest Classifier and comparetwo approaches for feature selection.
|
|
| 44. |
|
|
| 45. |
- Spagnolli, Anna, et al.
(författare)
-
Eco-Feedback on the Go : Motivating Energy Awareness
- 2011
-
Ingår i: IEEE Computer Society. - : IEEE Computer Society. - 1051-4651. ; 44:5, s. 38-45
-
Tidskriftsartikel (refereegranskat)abstract
- The EnergyLife mobile interface incorporates lessons from environmental psychology and feedback intervention to relay information from appliance sensors, offeringa gaming environment that rewards usersfor decreased electricity consumption.
|
|
| 46. |
- Sternby, Jakob
(författare)
-
Class dependent cluster refinement
- 2006
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. ; 2, s. 833-836
-
Konferensbidrag (refereegranskat)abstract
- Unsupervised classification is a very common problem in pattern recognition even when the classes are known. In many areas intra-class variations may be greater than the inter-class variations causing a need for a subdivision of the training set of a class into smaller subunits often referred to as clusters. The subdivision or clustering is often performed independently of the relative properties of the other present classes in the recognition task. This paper presents a novel class-dependent approach to the clustering problem. Experiments with online handwriting data show that the novel clustering approach CDCR produces a clustering better suited for the task of pattern recognition. Although only validated for two recognition methods in this paper, the same approach could be applied to other methods as well as to other pattern recognition problems.
|
|
| 47. |
- Tegen, Agnes, et al.
(författare)
-
Image Segmentation and Labeling Using Free-Form Semantic Annotation
- 2014
-
Ingår i: [Host publication title missing]. - 1051-4651. ; , s. 2281-2286
-
Konferensbidrag (refereegranskat)abstract
- In this paper we investigate the problem of segmenting images using the information in text annotations. In contrast to the general image understanding problem, this type of annotation guided segmentation is less ill-posed in the sense that for the output there is higher consensus among human annotations. In the paper we present a system based on a combined visual and semantic pipeline. In the visual pipeline, a list of tentative figure-ground segmentations is first proposed. Each such segmentation is classified into a set of visual categories. In the natural language processing pipeline, the text is parsed and chunked into objects. Each chunk is then compared with the visual categories and the relative distance is computed using the word-net structure. The final choice of segments and their correspondence to the chunked objects are then obtained using combinatorial optimization. The output is compared to manually annotated ground-truth images. The results are promising and there are several interesting avenues for continued research.
|
|
| 48. |
- Toft, Carl, 1990, et al.
(författare)
-
Azimuthal Rotational Equivariance in Spherical Convolutional Neural Networks
- 2022
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. ; 2022-August, s. 3808-3814
-
Konferensbidrag (refereegranskat)abstract
- In this work, we analyze linear operators on the space of square integrable functions on the sphere. Specifically, we characterize the operators which are equivariant to azimuthal rotations, that is, rotations around the z-axis. Several high-performing neural networks defined on the sphere are equivariant to azimuthal rotations, but not to full SO(3) rotations. Our main result is to show that a linear operator acting on band-limited functions on the sphere is equivariant to azimuthal rotations if and only if it can be realized as a block-diagonal matrix acting on the spherical harmonic expansion coefficients of its input. Further, we show that such an operation can be interpreted as a convolution, or equivalently, a correlation in the spatial domain. Our theoretical findings are backed up with experimental results demonstrating that a state-of-the-art pipeline can be improved by making it equivariant to azimuthal rotations.
|
|
| 49. |
- Wallin, Erik, 1991, et al.
(författare)
-
DoubleMatch: Improving Semi-Supervised Learning with Self-Supervision
- 2022
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. ; 2022-August, s. 2871-2877
-
Konferensbidrag (refereegranskat)abstract
- Following the success of supervised learning, semi-supervised learning (SSL) is now becoming increasingly popular. SSL is a family of methods, which in addition to a labeled training set, also use a sizable collection of unlabeled data for fitting a model. Most of the recent successful SSL methods are based on pseudo-labeling approaches: letting confident model predictions act as training labels. While these methods have shown impressive results on many benchmark datasets, a drawback of this approach is that not all unlabeled data are used during training. We propose a new SSL algorithm, DoubleMatch, which combines the pseudo-labeling technique with a self-supervised loss, enabling the model to utilize all unlabeled data in the training process. We show that this method achieves state-of-the-art accuracies on multiple benchmark datasets while also reducing training times compared to existing SSL methods. Code is available at https://github.com/walline/doublematch.
|
|
| 50. |
- Yilmaz, Kaan, et al.
(författare)
-
AV-SLAM: Autonomous vehicle SLAM with gravity direction initialization
- 2020
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. ; , s. 8093-8100
-
Konferensbidrag (refereegranskat)abstract
- Simultaneous localization and mapping (SLAM) algorithms aimed for autonomous vehicles (AVs) are required to utilize sensor redundancies specific to AVs and enable accurate, fast and repeatable estimations of pose and path trajectories. In this work, we present a combination of three SLAM algorithms that utilize a different subset of available sensors such as inertial measurement unit (IMU), a gray-scale mono-camera, and a Lidar. Also, we propose a novel acceleration-based gravity direction initialization (AGI) method for the visual-inertial SLAM algorithm. We analyze the SLAM algorithms and initialization methods for pose estimation accuracy, speed of convergence and repeatability on the KITTI odometry sequences. The proposed VI-SLAM with AGI method achieves relative pose errors less than 2%, convergence in half a minute or less and convergence time variability less than 3s, which makes it preferable for AVs.
|
|
