This paper explores several statistical pattern recognition techniques to classify utterances according to their emotional content. We have recorded a corpus containing emotional speech with over a 1000 utterances from different speakers. We present a new method of extracting prosodic features from speech, based on a smoothing spline approximation of the pitch contour. To make maximal use of the limited amount of training data available, we introduce a novel pattern recognition technique: majority voting of subspace specialists. Using this technique, we obtain classification performance that is close to human performance on the task.
We present a novel algorithm for the registration of pulmonary CT scans. Our method is designed for large respiratory motion by integrating sparse keypoint correspondences into a dense continuous optimization framework. The detection of keypoint correspondences enables robustness against large deformations by jointly optimizing over a large number of potential discrete displacements, whereas the dense continuous registration achieves subvoxel alignment with smooth transformations. Both steps are driven by the same normalized gradient fields data term. We employ curvature regularization and a volume change control mechanism to prevent foldings of the deformation grid and restrict the determinant of the Jacobian to physiologically meaningful values. Keypoint correspondences are integrated into the dense registration by a quadratic penalty with adaptively determined weight. Using a parallel matrix-free derivative calculation scheme, a runtime of about 5 min was realized on a standard PC. The proposed algorithm ranks first in the EMPIRE10 challenge on pulmonary image registration. Moreover, it achieves an average landmark distance of 0.82 mm on the DIR-Lab COPD database, thereby improving upon the state of the art in accuracy by 15%. Our algorithm is the first to reach the inter-observer variability in landmark annotation on this dataset.
Introduction/ BackgroundImage Registration of whole slide histology images allows the fusion of fine-grained information like different immunohistochemical stains from neighboring tissue slides. Traditionally, pathologists fuse this information by looking subsequently at one slide at a time. If the slides are digitized and accurately aligned at cell-level, automatic analysis can be used to ease the pathologist's work. However, the size of those images exceeds the memory capacity of regular computers, preventing the application of established image registration methods at a high magnification. AimsAn accurate and automatic alignment helps the pathologist to analyze the combination of different antibodies without memorizing multiple slides. For some applications, cell-level accuracy is needed. This also enables automatic image analysis to take advantage of multislide information. MethodsWe extend available registration methods by using image data at fine spatial resolution. However, this data is not simultaneously globally available due to the computer's memory restrictions. Typical approaches either reduce the amount of data to be processed by downsampling or partition the data into smaller chunks to be processed separately. We combine the patch based approach with an elastic deformation model to obtain a global registration result. Our method first registers the complete images on a low resolution with a nonlinear deformation model and later refines this result on patches by using a second nonlinear registration on each patch. The deformation information on the individual patches can be contradictory and needs to be combined into one global model. As an extension to our previous work, the global solution is computed by minimizing an energy function that preserves the patch-wise deformation and establishes global smoothness. The NGF distance measure is used to handle multi-stain images. ResultsThe method will be applied to whole slide image pairs. The alignment of corresponding structures will be measured by comparing manual segmentations from neighboring slides. First results show an improvement of the registration accuracy compared to the low-resolution nonlinear registration.
No abstract
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.