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 13 of 13 for “"Binarization"”.
-
Webcam-Based Optical Mark Reader for Grading Assessments
… particular, we propose a new variant of the Otsu binarization technique for image segmentation to effectively separate the background and foreground. The proposed grading solution aims at maximizing the criteria for acceptable operations so that 100% accurate grading among those accepted ones can …
-
Queer(ing) Space: Potentials of the In-Between
… architecture beyond accepted structures - beyond binarization and oppositional logic. By tracing the historical context of specific events, sites, and urban zones, that have come to define LGBTQI2+ movements and culture, this study remains grounded in queer identities while uncovering an attitude …
-
Inductive logic programming with gradient descent for supervised binary classification
… to numerical data using a threshold-gate based binarization technique. We test our implementations on datasets with varying pattern structures and noise levels, and select our best performing implementation. We then present an example where our method generates an accurate and interpretable rule …
-
An adaptive pruning algorithm for DNN compression
… Techniques such as pruning, quantization and binarization have been developed to reduce network parameter size. Pruning is the one of well-studied methods to solve network over-parameterization and reduce computational complexity. A typical pruning process includes three stages: train the …
-
Classification on real-time videos of galvanized steel surface defect using support vector machines and convolutional neural network, based on data created by generative adversarial networks
… inference time, techniques such as pruning and binarization were tested. While the binarized architecture showed a significant drop in accuracy, pruning showed a 30% compression ratio for the same accuracy. In parallel, to increase the robustness, different Generated Adversarial Networks …
-
Mapping myths of the medina : French colonial urbanism, Oriental brandscapes and the politics of tourism in Marrakesh
… its burgeoning tourism industry, this colonial binarization of the urban layout and demography lives on in Marrakesh, resulting in the creation of a medina that is still marketed through an orientalizing lens, heralded as little more than an exotic spectacle. This study seeks to understand the …
-
An image processing technique for erosion analysis on compressor blade geometry
… radii, and area at the blade tip using image binarization and a pixel-to-inch scaling factor and 2) qualitative visualization of material loss on the blade surface by aligning pre- and post-ingestion images of a rotor blade using feature-based detection. These methods are tested on a …
-
An interferometric study of unsteady passing shock flow in a turbine cascade
… Image analysis techniques used include adaptive binarization and Hilditch line thinning. Further areas for improvement are also discussed. In addition to the interferometric study, a boundary layer transition study was also undertaken. Magnified boundary layer spark shadowgraphs were taken on …
-
Power efficient machine learning-based hardware architectures for biomedical applications
… n-bit (n = 8,16) integer quantization, and binarization on hyper-parameters, are also employed. These models significantly reduced the power consumption rate by 5x, size by 13x, and improved the model latency. For efficient use of these models, especially in biomedical applications, a sleep …
-
Multi-Modal Ocular Recognition in presence of occlusion in Mobile Devices
… segmentation, followed by mathematical and binarization operations. The scheme showed a 100% eyeglasses detection and 91% segmentation accuracy by our proposed approach. Also, the second segmentation scheme was the convolutional de-convolutional network. This CNN model has been implemented …
-
Hash code learning for large scale similarity search
… ones. Furthermore we explain why the proposed binarization based on Hamming metric outperformed the original Euclidean metric. Particularly, in low-SNR regimes, such as that of features obtained from CNNs trained on another dataset, dissimilar samples have been shown to be much better separated …
-
Multimodal Indexing of Presentation Videos
… we present a novel locally optimal adaptive binarization algorithm, implemented with integral histograms. It determines of an optimal threshold that maximizes the between-classes variance within a subwindow, with computational complexity independent from the size of the window itself. We …
-
Discrete Approximations, Relaxations, and Applications in Quadratically Constrained Quadratic Programming
We present works on theory and applications for Mixed Integer Quadratically Constrained Quadratic Programs (MIQCQP). We introduce new mixed integer programming (MIP)-based relaxation and approximation schemes for general Quadratically Constrained Quadratic Programs (QCQP's), and also study …