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 20 of 53 for “"Superpixels"”.
-
Superpixels for Hyperspectral Image Analysis
… methods that efficiently and robustly exploits superpixels for hyperspectral data. We study and quantify the efficacy of state-of-the-art superpixel generation algorithms for a variety of hyperspectral images. In this work, superpixel level analysis is proposed for two different hyperspectral …
-
Content-driven superpixels and their applications
… random initialisations, achieved by producing superpixels directly corresponding to local image complexity. This is achieved by growing superpixels and dividing them on image variation. The existing analysis was not sufficient to take these properties into account so new measures of …
-
Superpatching for Image Analysis Using Transformers and Superpixels
… Networks (CNNs) and Transformers to leverage superpixels, clusters of pixels with shared characteristics that capture local feature boundaries effectively. We propose an architecture that segments images into a collection of superpixels, vectorizes these superpixels using a CNN, and passes the …
-
Stochastic methods for image segmentation based on stochastic superpixels
… ii) difficulty in generating well-structured superpixels under non-ideal scene conditions, iii) weak boundary separation between objects, and iv) difficulty to obtain hierarchical and nested image representations. Motivated to tackle these key challenges, this thesis introduces new methods for …
-
Superpixels and their Application for Visual Place Recognition in Changing Environments
Superpixels are the results of an image oversegmentation. They are an established intermediate level image representation and used for various applications including object detection, 3d reconstruction and semantic segmentation. While there are various approaches to create such segmentations, there …
-
Ensemble Graph Neural Networks on Melanoma and Cervical Cancer Screening Datasets using SLIC Superpixels
… generate graphs from the images by creating superpixels of the images and use them as our graph nodes instead of individual pixels. Then, we define edges on these nodes based on the distance of each superpixel to their closest ones. We propose two ensemble frameworks containing a pre-trained …
-
Low and Mid-level Shape Priors for Image Segmentation
… method for oversegmenting an image into compact superpixels, reducing the complexity of many high-level tasks. Unlike most low-level segmentation techniques, our geometric flow formulation enables us to impose additional compactness constraints, resulting in a fast method with minimal …
-
Superparsing with Improved Segmentation Boundaries through Nonparametric Context
… of the size, shape and compactness of the superpixels because SLICO is able to produce accurate boundaries. After all superpixel features have been extracted, feature-based matching of superpixels is performed to nd the nearest-neighbour superpixels in the retrieval set for each query …
-
Superpixel Segmentation of Outdoor Webcams to Infer Scene Structure
… a lot of memory. This thesis explores the use of superpixels to address these issues. Superpixels, an approach to image segmentation, over-segment a scene but attempt to ensure that each segment lies on only one scene element. Applying superpixels to webcams reduces the e∩¼Çect of noise on …
-
Efficient Nonlinear Dimensionality Reduction for Pixel-wise Classification of Hyperspectral Imagery
… task: Simple Linear Iterative Clustering (SLIC) superpixels and semi-supervised deep autoencoder networks (SSDAN). SLIC is a very popular algorithm developed for computing superpixels in RGB images that can easily be extended to HSI. Each superpixel includes hundreds or thousands of pixels based …
-
Propagated image Segmentation Using Edge-Weighted Centroidal Voronoi Tessellation based Methods
… the problem as a multilevel clustering process: superpixels in one level are clustered to obtain larger size superpixels in the next level. The clustering energy involves both color similarities and the proposed boundary smoothness of superpixels. We further extend HEWCVT to obtain supervoxels on …
-
Superpixel Based Active Learning and Online Feature Importance Estimation for Hyperspectral Image Analysis
… proposes an AL framework that leverages from superpixels. First, a semi-supervised AL method is proposed that leverages the label homogeneity of pixels in a superpixel, lead- ing to a faster convergence using few training samples. Secondly, a spatial-spectral AL method is proposed that …
-
Multi-scale local explanation approach for image analysis using model-agnostic explainable artificial intelligence (XAI)
… explanation highlighting the most important superpixels affecting the CNN’s decision. This thesis aims to explore and develop a multi-scale scheme of LIME to explain decisions made by CNN models through heatmaps of coarse to finer scales. More precisely, when LIME highlights large superpixels …
-
Superpixel Segmentation Systems: Design and Analysis
… order of 105 – 107 pixels to a few hundreds of superpixels. Thereby, the computation time is greatly reduced for further post-processing steps such as region merging for image segmentation, object tracking, detection, depth estimation, object recognition, image denoising, object-based …
-
Efficient Structured Prediction for Visual Scene Understanding
… of unsupervised segmentation in the form of superpixels, with the emphasis on speed and accuracy. To this end, a real-time coarse-to-fine topologically preserving segmentation algorithm [188] is proposed. In this algorithm, we define the problem as a markov random field (MRF) which preserves …
-
Graph representation learning for images
… This was done by both reducing the number of superpixels available to the model as well as by using the superpixel adjacencies, which provides less edges per node than previous bechmarks, which both reduces information and constrains information flow within the model. We then propose a novel …
-
Classification of Compact Polarimetric Synthetic Aperture Radar Images
… of CP data to identify homogeneous regions (superpixels) and a labeling step where a ground truth label is assigned to each super-pixel. An unsupervised segmentation algorithm is developed based on the existing Iterative Region Growing using Semantics (IRGS) for CP data and is called CP-IRGS. …
-
Superpixel-driven 360º image compression
… for spherical images, which uses spherical superpixels as coding units. Each superpixel is processed using a spherically-weighted graph Fourier transform and a latitude-adaptive quantization strategy, allowing for better alignment with the geometry and content distribution of the spherical …
Page 1 of 3