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 25 for “"Invariant Features"”.
-
Human inspired pattern recognition via local invariant features
… examined using edge and optimized SIFT based features as inputs and produced extensible results from 3 to 50 objects based on classification performance. The classification results prove that we achieve a high level of pattern recognition that ranged from 96.1% to 100% for objects under …
-
Novel Invariant Features of the US Stock Market
… process. This thesis will outline some novel invariant features related to the fluctuations observed in the US stock market. First-passage-time distribution, which presents the likelihood of a stock reaching a pre-specified price at a given time, is useful in risk assessment and in valuation …
-
3D spherical harmonic invariant features for sensitive and robust quantitative shape and function analysis in brain MRI
… proposed. First, an efficient method to compute invariant spherical harmonics (SPHARM) based feature representation for real valued 3D functions was developed. This method addressed previous limitations of obtaining unique feature representations using a radial transform. The scale, rotation and …
-
Multi-Domain Text Classification with Adversarial Training
… through a minimax optimization to produce domain-invariant features. The domain-invariant features are supposed to be both transferable and discriminative, while shared-private employs domain-specific features to boost the discriminability of the domain-invariant features. In this thesis, we make …
-
Image segmentation and object classification for automatic detection of tuberculosis in sputum smears
… images with 20x magnification. Geometric change invariant features were extracted to describe segmented objects; Fourier coefficients, moment invariant features and colour features were used. All two-class object classifiers had balanced performance for 100x images, with sensitivity and …
-
Nearest neighbor search for cyro-electron microscopy images
… methods are able to capture more expressive features, and then the classification is performed according to these learned features. The four KNNS algorithms include hyperplane LSH, cross-polytope LSH, unsupervised stochastic generative hashing (SGH) as well as unsupervised deep hashing (DH). …
-
Iterative computation of camera paths in an image based rendering application
… camera paths of long image sequences. Scale Invariant Features are first extracted from the ordered set of images. These images are then matched pair-wise sequentially and correspondences are computed. An initial geometric path is found after by applying a bundle adjustment algorithm on these …
-
VIrginia Urban Dynamics Study Using DMSP/OLS Nighttime Imagery
… by using linear regression model and Pseudo Invariant Features (PIFs) method. Urban patches were delineated by applying thresholding techniques based on digital number (DN) values extracted from DMSP/OLS imagery. Compounded Night Light Index (CNLI) values were calculated to help estimate GDP, …
-
Features identification and tracking for an autonomous ground vehicle
This thesis attempts to develop features identification and tracking system for an autonomous ground vehicle by focusing on four fundamental tasks: Motion detection, object tracking, scene recognition, and object detection and recognition. For motion detection, we combined the background …
-
Multi-modal object detection in non-corresponding imagery using unsupervised techniques
… trained detection algorithm produces some LWIR invariant features. Subsequently, an unsupervised adaptation to this detection network is proposed to increase detection in LWIR imagery. For this adaptation, the distance between the source (RGB) and target (LWIR) distributions is minimised during …
-
Recherche d'images et classification par mots visuels et descripteurs flous
L'approche Bag of Visual Words (ou Bag of Features) décrit une image comme un ensemble de descripteurs locaux à l'aide d'un histogramme. Chaque groupe de l'histogramme représente l'importance d'un motif visuel (appelé mot visuel) dans l'image. Cette méthode d'indexation a été fréquemment utilisée …
-
Domain Adaptation with a Classifier Trained by Robust Pseudo-Labels
… domain adaptation (DA) aims to identify domain-invariant features between two different but related domains. This thesis proposes a state-of-the-art DA approach that overcomes the limitations of traditional DA methods. To capture fine-grained information for each category, I deploy …
-
2D image classification and alignment in single-particle Cryo-EM
… of images in each class. To perform rotation-invariant classification and rotation alignment, we first propose a non-uniform discrete Fourier transform (NUDFT) to calculate the Fourier transform of an image in polar coordinates. Based on the proposed NUDFT, we develop a rotation-invariant …
-
Detection and Recognition of U.S. Speed Signs from Grayscale Images for Intelligent Vehicles
… of regions. The recognition phase calculates the invariant features of the inner parts of the detected regions using Hu’s moments. It verifies the hypothesis first, before extracting the assigned speed limit from the detected region using a feed forward neural network. The proposed method was …
-
Sketch image recognition using deep features
… has attempted to address this task by exploring invariant features or looking for a shared subspace. In this paper, an end-to-end method has been proposed whereby the similarity score can be obtained directly when inputting a pair of sketch and photo-face images. In particular, this study …
-
Federated Learning With Generalization To New Domains
… locally to encourage clients to learn domain-invariant features, and globally at the server to obtain a more generalized aggregated model. Extensive experiments on four multi-domain datasets—PACS, OfficeHome, DomainNet, and TerraInc—show that FedGaLA outperforms comparable baselines. Ablation …
-
Modelling the emergence of a basis for vocal communication between artificial agents
… of sounds apparently devoid of any specifying invariant features. Despite this absence, we can effortlessly decode this stream and comprehend the utterances of others. Moreover, the form of these utterances is shared and mutually understood by a large population of speakers. In this thesis, we …
-
Natural scene classification, annotation and retrieval. Developing different approaches for semantic scene modelling based on Bag of Visual Words.
… (BOW) model for modelling images based on local invariant features computed at interest point locations has become a standard choice for many computer vision tasks. Based on this promising model, this thesis investigates three main problems: natural scene classification, annotation and retrieval. …
-
Transform texture classification
… Transfonn (KLT) extracts a vector of dominant features, optimally preserving texture information in the matrix. This approach is made possible by the introduction of a novel Multi-level Dominant Eigenvector Estimation (MDEE) algorithm, which reduces the computational complexity of the standard …
-
SARLBP and STMO-GA : two novel description and selection approaches for challenging feature classification problems
… Deep Learning-based methods extract millions of features thru a training process that requires a very large number of annotated images to generate a sequence of filters which can then be applied to the raw images. This process can pose an issue in problems with limited training data. In contrast, …
Page 1 of 2