Image segmentation has long been an important problem in the computer vision community. In our recent work we have addressed the problem of texture segmentation, where we combined top-down and bottom-up views of the image into a unified procedure. In this paper we extend our work by proposing a modified procedure which makes use of graphs of image regions. In the topdown procedure a quadtree of...

Object segmentation is a challenging and important problem in computer vision. The difficulties to obtain accurate segmentations using only the traditional Topdown or Bottom-up approaches have introduced new proposals based on the idea of combining them in order to obtain better results. In this paper we present a novel approach for object segmentation based on the following two steps: 1) overs...

In this paper, we propose a new approach to sea ice segmentation in SAR intensity imagery by combining an edge-preserving region (EPR)-based representation with region-level MRF models. The EPR-based representation gives an initial segmentation of SAR images in the form of primitive regions, with the goal of efficiently suppressing oversegmentation within objects while accurately locating regio...

To reduce the gap between performance of traditional speech recognition systems and human speech recognition skills, a new architecture is required. A system that is capable of incremental learning offers one such solution to this problem. This thesis introduces a bottom-up approach for such a speech processing system, consisting of a novel blind speech segmentation algorithm, a segmental featu...

Lung diseases such as COPD and asthma affect airway morphology. Automated segmentation is an essential first step toward the analysis of airways. We propose a fully-automated algorithm to segment the airway tree from chest CT scans. The proposed algorithm requires no manual intervention and uses a 3D region growing based method and allows for accurate detection of leakage by growing regions wit...

We present a novel variational approach to top-down image segmentation, which accounts for significant projective transformations between a single prior image and the image to be segmented. The proposed segmentation process is coupled with reliable estimation of the transformation parameters, without using point correspondences. The prior shape is represented by a generalized cone that is based...

Serial sectioning methods continue to produce a wealth of image data for quantifying the three-dimensional nature of material microstructures. In this work, we discuss a computational methodology for automated detection and 3D characterization of dendrite cores from images taken from slices of a production turbine blade made of a heat-treated single crystal Ni-based superalloy. The dendrite cor...

While automatic methods for phonetic segmentation of speech can help with rapid annotation of corpora, most methods rely either on manually segmented data to initially train the process or manual post-processing. This is very time-consuming and slows down porting of speech systems to new languages. In the context of prosody corpora for text-to-speech (TTS) systems, we investigated methods for f...

Spinal cord segmentation is a developing area of research intended to aid the processing and interpretation of advanced magnetic resonance imaging (MRI). For example, high resolution three-dimensional volumes can be segmented to provide a measurement of spinal cord atrophy. Spinal cord segmentation is difficult due to the variety of MRI contrasts and the variation in human anatomy. In this stud...

Representing objects using elements from a visual dictionary is widely used in object detection and categorization. Prior work on dictionary learning has shown improvements in the accuracy of object detection and categorization by learning discriminative dictionaries. However none of these dictionaries are learnt for joint object categorization and segmentation. Moreover, dictionary learning is...