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 275 for “"Image Datasets"”.

  1. Auto-curation of Large Evolving Image Datasets

    <p>Large image collections are becoming common in many fields and offer tantalizing opportunities to transform how research, work, and education are conducted if the information and associated insights could be extracted from them. However, major obstacles to this vision exist. First, image …

    utk-theses Repository record for Auto-curation of Large Evolving Image Datasets (opens in a new tab)

  2. Visualizing large medical image datasets using the 3D scale-invariant feature transform (SIFT)

    This thesis proposes an image classification paradigm where instead of fully automatic classification, the goal is to generate a highly-informative visual summary of class-related information for human interpretation. Rather than providing a single classification, we provide a visualisation …

    ets-quebec Download PDF for Visualizing large medical image datasets using the 3D scale-invariant feature transform (SIFT) (opens in a new tab)

  3. ON ANNOTATION EFFICIENT LEARNING FOR COMPUTER VISION TASKS AND ITS APPLICATION ON MEDICAL IMAGE DATASETS

    … self-supervised method, which can learn general image and video features from large-scale unlabelled data without using any human-annotated labels. Finally, borrowing ideas from self and semi-supervised learning, we propose a patch-based and point-based contrastive learning framework to perform …

    nus Repository record for ON ANNOTATION EFFICIENT LEARNING FOR COMPUTER VISION TASKS AND ITS APPLICATION ON MEDICAL IMAGE DATASETS (opens in a new tab) Download file for ON ANNOTATION EFFICIENT LEARNING FOR COMPUTER VISION TASKS AND ITS APPLICATION ON MEDICAL IMAGE DATASETS (opens in a new tab)

  4. Development of Ground-Level Hyperspectral Image Datasets and Analysis Tools, and their use towards a Feature Selection based Sensor Design Method for Material Classification

    … in the ability to identify materials in the image. This hardware has not been studied in the context of autonomy as the sensors are large, expensive, and have non-trivial image capture times. This work presents three novel contributions: a Labeled Hyperspectral Image Dataset (LHID) of …

    vt Repository record for Development of Ground-Level Hyperspectral Image Datasets and Analysis Tools, and their use towards a Feature Selection based Sensor Design Method for Material Classification (opens in a new tab)

  5. Object Classification Using Stacked Autoencoder and Convolutional Neural Network

    … the advances in machine learning research. Many image datasets such as MNIST, CIFAR-10, SVHN, Imagenet, Caltech, etc. are available which contain a broad spectrum of image data for training and testing purposes. Numerous deep learning architectures have been developed in the last few years, and …

    ndsu Repository record for Object Classification Using Stacked Autoencoder and Convolutional Neural Network (opens in a new tab)

  6. A SELECTIVE GAN-BASED DATA AUGMENTATION METHOD FOR MEDICAL IMAGE CLASSIFICATION

    … classification tasks, the available medical image datasets are often inadequate and imbalanced, hindering the development of accurate models for disease diagnosis and treatment. In this research, a selective GAN-based data augmentation method for imbalanced classification tasks is proposed. …

    nus Repository record for A SELECTIVE GAN-BASED DATA AUGMENTATION METHOD FOR MEDICAL IMAGE CLASSIFICATION (opens in a new tab) Download file for A SELECTIVE GAN-BASED DATA AUGMENTATION METHOD FOR MEDICAL IMAGE CLASSIFICATION (opens in a new tab)

  7. Learning 3D information from large image collections

    … implicit yet rich 3D information. <br><br>As 2D images are much easier to capture than 3D data, the past decade of technological advance has catalyzed the creation of image datasets that are much larger and more diverse compared to their 3D counterparts. This has led to significant improvements …

    oxford Repository record for Learning 3D information from large image collections (opens in a new tab)

  8. Few-shot Learning for Medical Image Classification

    … and therapeutic procedures. Collecting medical image data is complex and time consuming. As a result, the sizes of medical image datasets are usually much smaller than the sizes of natural image datasets. It hinders the application of deep learning methods in medical image field. Few-shot …

    unsw Repository record for Few-shot Learning for Medical Image Classification (opens in a new tab)

  9. Unravelling the Spatial Distribution of Individual-Level Abandoned Houses at Large Scale Using Open-Access Remotely Sensed Data

    … cities is unrealizable. Nowadays, open-access image datasets, i.e., very-high-resolution remote sensing and street view images, associated with the booming field of machine learning, emerge as potential candidates to realize a cost-effective way to explore and analyze the spatial distribution …

    buffalo Repository record for Unravelling the Spatial Distribution of Individual-Level Abandoned Houses at Large Scale Using Open-Access Remotely Sensed Data (opens in a new tab)

  10. Cubic-panorama image dataset compression for image-based virtual environment navigation

    This thesis addresses the key issues of image dataset compression, especially cubic-panorama image dataset compression, used in image-based virtual environment navigation to develop effective and efficient compression techniques and schemes. To my knowledge, this is the first work to be published …

    ottawa-retro Repository record for Cubic-panorama image dataset compression for image-based virtual environment navigation (opens in a new tab)

  11. Design of crossbar architecture for vector processing

    … focus on deep learning application such as image classification. The crossbar structure uses emerging non-volatile memory (eNVM) array architecture and is simulated with complex neural networks to obtain metrics such as accuracy, inference and run-time. Model validation is performed by …

    gatech Repository record for Design of crossbar architecture for vector processing (opens in a new tab)

  12. Learning Binary Code Representations for Effective and Efficient Image Retrieval

    The size of online image datasets is constantly increasing. Considering an image dataset with millions of images, image retrieval becomes a seemingly intractable problem for exhaustive similarity search algorithms. Hashing methods, which encodes high-dimensional descriptors into compact binary …

    maryland Repository record for Learning Binary Code Representations for Effective and Efficient Image Retrieval (opens in a new tab)

  13. Multi-Label Lifelong Machine Learning Using Deep Generative Replay

    … a framework for learning from multi-label image datasets across a sequence of tasks with minimal forgetting. As an initial task, the MLDGR approach assigns multiple labels to images. This is achieved by utilizing a convolutional neural network (CNN) for feature extraction from images, which …

    ottawa-retro Repository record for Multi-Label Lifelong Machine Learning Using Deep Generative Replay (opens in a new tab)

  14. Feed-forward weakly supervised deep learning models for breast cancer diagnosis from histological images

    … breast cancer, the gold standard is histological image analysis. However, these images are very large and require both time and expertise to be correctly interpreted. Research in computer vision algorithms has shown great potential to assist practitioners in making faster and more accurate …

    ets-quebec Download PDF for Feed-forward weakly supervised deep learning models for breast cancer diagnosis from histological images (opens in a new tab)

  15. Hierarchical Intelligent Systems And Their Applications To Survivability

    … results of hierarchical fuzzy logic are given. Image processing has become one of the major research areas because of its applications in different fields such as engineering, bio-medical, defense etc. With the expansion of social media, the applications of image processing have reached …

    wayne-thes Repository record for Hierarchical Intelligent Systems And Their Applications To Survivability (opens in a new tab)

  16. Sistemų mokymosi algoritmų taikymas biologinės kilmės vaizdams klasifikuoti /

    … on two similar, but different tree leaf image datasets with the aim to find simple universal learning algorithm for leaf classification. K-nearest neighbourhoods, Support Vector machines and logistic regression algorithms gave the most accurate score, but PCA dimension reduction algorithm …

    vilnius Repository record for Sistemų mokymosi algoritmų taikymas biologinės kilmės vaizdams klasifikuoti / (opens in a new tab)

  17. Generative Adversarial Networks Based on a General Parameterized Family of Generator Loss Functions

    … we systematically conduct experiments on three image datasets for different manifestations of our GAN system to illustrate their performance and stability.

    queens Repository record for Generative Adversarial Networks Based on a General Parameterized Family of Generator Loss Functions (opens in a new tab)

  18. AI-Driven Digital Twinning and Monitoring of Concrete Dams

    … due to three gaps: the lack of dam-specific image datasets, the high cost of pixel-level annotation for training deep learning-based segmentation models, and the absence of an integrated framework that connects 2D damage detection with accurate 3D digital twins.

    ku Repository record for AI-Driven Digital Twinning and Monitoring of Concrete Dams (opens in a new tab)

  19. Cubic-Panorama Image Dataset Analysis for Storage and Transmission

    … a field referred to as telepresence. Recent image-based representations such as Google map's street view provide a familiar example. Several areas of research are open; such image-based representations are huge in size and the necessity to compress data efficiently for storage is inevitable. …

    ottawa-retro Repository record for Cubic-Panorama Image Dataset Analysis for Storage and Transmission (opens in a new tab)

Page 1 of 14