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 35 for “"image input"”.
-
An experimental evaluation of image input degradation on machine learning performance
… in the field of autonomous driving where image data needs to be stored at a large scale. Such data can be reduced in size significantly by using lossy video compression at the cost of losing visual fidelity. This trade-off could potentially be balanced such that the data size of a dataset …
-
Facial Recognition With Image Signaling: Efficacy Of Two Factor Authentication Utilizing A Single Image Input Mechanism On A Smartphone
… for securing systems with sensitive data. Most input devices for computer systems (desktops, laptops, and mobile devices) are limited in the type and amount of data entered at one time. As examples, keyboards only input one character for each keypress, mouse clicks apply to only where the …
-
Realization of a Fast Automatic Correlation Algorithm for Registration of Satellite Images
… algorithm for registration of satellite images is discussed. An overview of current registration techniques is presented indicating a correlator, matching binary maps compressed from the original imagery, may provide the required throughput when implemented with a dedicated …
-
License Plate Image Quality Enhancement Utilizing Super Resolution Generative Adversarial Networks
This thesis focuses primarily on enhancing the image quality of blurred license plates through the use of Super-Resolution Generative Adversarial Networks (SRGANs) [1]. We propose a synthetic dataset with SRGAN model to promote blurred image quality enhancement, and allow for model evaluation on a …
-
Deep Learning for Robotic Scene Understanding
… can obtain state-of-the-art performance with RGB images only. In our framework, we exploit a pseudo-LiDAR using monocular depth estimation and propose a feature fusion network to fuse RGB and pseudo- LiDAR information. To optimize the network architecture and improve the efficiency of our network, …
-
Using convolutional neural networks for fine grained image classification of acute lymphoblastic leukemia
… involve hand-selecting features from cell images for input to a variety of standard machine learning classfiers. Underrepresented in WBC classification, yet successful in practice, is the convolutional neural network (CNN) that learns features from whole image input. Recently, CNNs are …
-
SEPARATING LAYERS IN IMAGES AND ITS APPLICATIONS
Image layer separation refers to one series of problems that try to decouple the input image into different component layers. While it has many practical applications, it is very challenging to solve due to its ill-posedness nature. Usually additional information and assumptions are required to …
-
Visual object tracking for UAVs using deep reinforcement learning
… which adds bounding box information to image input of training network. In addition, the convergence-based exploration and exploitation is adaptively applied to D3QN network aligned with epsilon-greedy algorithm. The tests are done in different simulation environments with different …
-
Modeling the self-organization of color selectivity in the visual cortex
… visual cortex is constructed using natural color image input. The modeled V1 develops realistic color-selective receptive fields, ocular dominance stripes, orientation maps, and color-selective regions, while the modeled V2 also creates realistic colorselective and orientation-selective neurons. …
-
Monocular 3D Object Detection via Ego View-to-Bird’s Eye View Translation
… enables software to understand the content of image and video. These autonomous agents require a three-dimensional modelling of its surrounding in order to operate reliably in the real-world. Despite the significant progress of 2D object detectors, they have a critical limitation in location …
-
3D Scene Reconstruction from A Monocular Image
… shape reconstruction from a single in-the-wild image. Without multiple views available, we rely on deep learning techniques. Recently, deep neural networks have been the dominant solution for various computer vision problems. Thus, we propose a two stage method based on learning-based methods. …
-
Self-supervised learning of structural representations of visual objects
… landmark autoencoding that can leverage powerful image discriminators used in adversarial learning. A by-product of these conditional autoencoding methods is that the generation can be interactively controlled by manipulating the keypoints in the bottleneck. We leverage this feature in a novel …
-
Learning Multi-step Robotic Manipulation Tasks through Visual Planning
… generate robust antipodal grasps from n-channel image input at real-time speeds (20ms). The proposed model architecture achieved a state-of-the-art accuracy on three standard grasping datasets. The adaptability of the proposed approach is demonstrated by directly transferring the trained model to …
-
Relative depth estimation from single monocular images with deep convolutional network
Depth estimation from single monocular images is a theoretical challenge in computer vision as well as a computational challenge in practice. This thesis addresses the problem of depth estimation from single monocular images using a deep convolutional neural fields framework; which consists of …
-
Untersuchungen zur Kontextabhängigkeit der visuellen Objekterkennung
Recognizing a 3D object from 2D images seems easy and occurs everyday, but it is in principle an ill-defined problem. Here we report two behavioural experiments investigating how representations of 3D objects are built under varying the conditions of the recognition context, i.e. the set of test …
-
Automated Software Testing of Deep Neural Network Programs
… of most DNN models is not known for a given input data, traditional software testing techniques cannot be directly applied. In the last few years, several papers have proposed testing techniques and adequacy criteria for testing DNNs. This thesis studies three types of DNN testing techniques, …
-
Multi-output Gaussian Processes for Large-scale Multi-class Classification and Hierarchical Data
… multi-class classification problems consists of image data, and MOGPs are not specifically designed to handle image datasets so MOGPs have poor performance on image data that has the nature of high dimensionality. Most applications of MOGPs are restricted to regression problems with a reduced …
-
Vision-based seam tracking and multi-modal defect detection in GMAW fillet welding using artificial intelligence
… camera and a microphone to collect real-time image and sound data. Our approach includes: • Vision-Based Seam Tracking: We develop a deep learning classification model to detect tacks, where the seam is not visible, and a keypoint detection model to locate the seam in non-tack images. …
-
Adversarial attacks on multi-modal 3D detection models
… using Deep Neural Nets (DNNs) to process camera images, and LiDAR point clouds. While DNN-based models are very powerful and accurate they may be vulnerable to adversarial attacks which introduce a small change to a model’s input and can result in great errors in its output. These attacks have …
-
A Machine Learning Approach to Real-time MRI Guidance for Robotic Needle-Based Procedures
… MRI-guidance. To realize the full potential of image-guided robotics, there is a need to integrate with real-time imaging for feedback during insertion.This work describes a novel data-driven approach to the integration of real-time imaging for the guidance of multi-needle robotic interventions. …
Page 1 of 2