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 10 of 10 for “"image decomposition"”.
-
Color Models for Image Decomposition
Decomposing an image into components provides a method through which meaningful information can be extracted from an image. This work is a study of image decomposition techniques for color images. The decomposition of color images presents a new challenge since the choice of the color model has an …
-
Scale-Driven Image Decomposition With Applications to Recognition, Registration, and Segmentation
… vision, public security, surveillance, medical image analysis, and other related fields.
-
Learning coupled conditional random field for image decomposition : theory and application in object categorization
… is able to identify object categories within images. To this end, this thesis proposes a computational model of "recognition-through-decomposition-and-fusion" based on the psychophysical theories of information dissociation and integration in human visual perception. At the lowest level, …
-
Learning and evaluating image representations
… by incorporating domain knowledge. For example, image prediction tasks such as intrinsic image decomposition were approached by thinking about what reflectance and shading look like. In the case of reflectance, a Mondrian image; and in the case of shading, a smooth image. The difficult portion …
-
Modelling the human perception of shape-from-shading
… as a solution to the problem of intrinsic image decomposition in the field of image processing. With regard to the shape computation unit, a link between luminance variations and estimated surface norms is identified by testing participants on simple gratings with several different …
-
Sampling in computer vision and Bayesian nonparametric mixtures
… achieves state-of-the-art results in intrinsic image decomposition by leveraging the DP Sub-Cluster algorithm. By addressing these problems, we demonstrate the applicability of MCMC methods to computer vision, and highlight the importance of designing fast sampling algorithms.
-
Photometric stereo for micro-scale shape reconstruction
… reflectance model (DRM) using color input images is proposed to generalize PS applicable to a wider range of surfaces with non-Lambertian reflectances. The proposed method not only estimates surface orientations from diffuse reflection but also exploits information from specularities owing …
-
Exploring knowledge in generative models
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms
-
Adaptation of Generative Models for Image Manipulation and Recontextualization
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-02-04 without embargo terms
-
First-order gradient regularisation methods for image restoration: reconstruction of tomographic images with thin structures and denoising piecewise affine images
The focus of this thesis is variational image restoration techniques that involve novel non-smooth first-order gradient regularisers: Total Variation (TV) regularisation in image and data space for reconstruction of thin structures from PET data and regularisers given by an infimal-convolution of …