Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 18 of 18 for “"Interactive Image Segmentation"”.
-
Elastic map: interactive image segmentation using a few seed-points
Over the past two decades interactive methods for clinical and biomedical image segmentation have been investigated since the pioneering work of Live-Wire, Live-Lane [17] and Intelligent Scissors [1]. Fully automatic image segmentation is essential for quantitative analysis but remains an unsolved …
-
Feedback augmentation of pde-based image segmentation algorithms using application-specific exogenous data
… Next, chapter II provides background material on image processing with partial differential equations and a review of prior work in the field. Chapter III covers the medical imaging portion of the research; the key contribution is a control-based algorithm for interactive image segmentation. …
-
User-centered design and evaluation of interactive segmentation methods for medical images
Segmentation of medical images is a challenging task that aims to identify a particular structure present on the image. Among the existing methods involving the user at different levels, from a fully-manual to a fully-automated task, interactive segmentation methods provide assistance to the user …
-
Interactive Brain Tumor Segmentation using Convolutional Neural Networks
Machine learning based image segmentation relies on having access to a large dataset of labeled scans. Challenges arise when a sufficient training dataset is not available. To build a labeled dataset, one can manually create segmentations either by hand or assisted by a semi-automatic interactive …
-
Neutro-Connectedness Theory, Algorithms and Applications
… to solve many challenging problems in natural image and low-quality biomedical image segmentation. The newly proposed Neutro-Connectedness (NC) theory makes it possible to describe the part and the whole relationship and to model the "hidden factors" influencing the decision-making. By applying …
-
Randomly-connected Non-Local Conditional Random Fields
… CRFs are one of the most powerful frameworks in image modeling. However practical CRFs typically have edges only between nearby nodes. Utilizing more interactions and expressive relations among nodes make these methods impractical for large-scale applications, due to the high computational …
-
Statistical methods for coupling expert knowledge and automatic image segmentation and registration
… couple an expert user's guidance with automatic image segmentation and registration algorithms. Often, complex processes such as fire, anatomical changes/variations in human bodies, or unpredictable human behavior produce the target images; in these cases, creating a model that precisely …
-
A virtual engineering framework to support progressive interaction in engineering design
… of the designer could be enhanced by creating an interactive virtual engineering framework. This research presents progressive interaction with the designer-in-the-loop whose intelligence is blended with the computational power to suitably control the optimization. Progressive interaction is a …
-
Haptic Image Exploration
The haptic exploration of 2-D images is a challenging problem in computer haptics. Research on the topic has primarily been focused on the exploration of maps and curves. This thesis describes the design and implementation of a system for the haptic exploration of photographs. The system builds on …
-
A discrete graph Laplacian for signal processing
… on graphs to effect two fundamental problems of image processing: denoising and segmentation. We treat these two low-level vision problems on the pixel-wise level under a unified framework: a graph embedding. Using this framework opens us up to the possibilities of exploiting recently introduced …
-
Holistic image understanding with deep learning and dense random fields
<p>One aim of holistic image understanding is not only to recognise the things and stuff in images but also to localise where they are exactly. Semantic image segmentation is set up to achieve this goal. The purpose of this task is to recognise and delineate the visual objects. The solution to this …
-
Efficient Visualization and Reconstruction of 3D Geometric Models from Neuro- Biological Confocal Microscope Scans
… to the generation of geometrical models from 3D image data. This includes visualization of the primary data and the resulting models as well as image segmentation, extraction of line structures and triangulation of labelings. Our primary motivation has been to create a practically usable working …
-
Enabling Human-Machine Collaborative Inspections through Smart Infrastructure Metaverse
… corrosion, etc.) from visual data (e.g., images, LiDAR). However, despite an urgent need for such technology in managing infrastructure, widespread adoption of these technologies in the field has been quite limited. One of the main obstacles is the lack of real-time communication and …
-
An SVD Guided Active Learning Approach for Medical Image Segmentation
… the human effort required to create voxel level segmentation masks for medical images; second, we present a novel approach to improve the interpretability of convolutional neural networks used in medical image segmentation. This approach involves computing the truncated singular value …
-
Human machine collaboration for foreground segmentation in images and videos
Foreground segmentation is defined as the problem of generating pixel level foreground masks for all the objects in a given image or video. Accurate foreground segmentations in images and videos have several potential applications such as improving search, training richer object detectors, image …
-
Interaktivní segmentace popředí/pozadí na mobilním telefonu
Práce se zabývá technikami pro interaktivní segmentaci popředí a pozadí na mobilních zařízeních. Cílem je nalézt nebo vytvořit vhodné metody pro oddělení uživatelem označeného objektu od pozadí. V úvahu je brána zejména rychlost segmentace a kvalita výstupu. Jsou popsány principy již existujících …