ZoomageTM: Super High Resolution Imaging & Visualization Tools
نویسندگان
چکیده
In this paper we describe and demonstrate our technology for creating super high resolution (SHR) & 3D digital content in a variety of applications including museum artifacts and galleries, archeology, anthropology, art design and heritage conservation. Our hardware can capture minute details of static scenes in a composite panoramic format with details surpassing the human eye. We also propose an approach to storing SHR images for efficient retrieval over bandwidth limited networks, such as the Internet. Regions of interest (ROIs) specified by users are stored in multiple levels of detail hierarchy. This hierarchy can be created by analyzing the contrast, texture or other feature changes with varying levels of resolution and creating a hierarchy of ROIs. The depth of the hierarchy for a given ROI is determined by following the chang& in the contrast (or other feature) gradient over adjacent levels. An inlplementation of the browser for Virtual Museums is also presented. In addition to browsing images, our software provides the ability to support "interactive story telling." As viewers interact with a picture using a mouse, the descriptions of objects in the scene appear depending on the location of the mouse and the level of detail in the scene. Finally, the "Zoomage" tools can be used by academic researchers for various applications including object recognition, digital archiving, accurate stereo reconstruction, and 3D visualization. *Contact address: Dept. of Computing Science, University of Alberta, [email protected].
منابع مشابه
Robust Fuzzy Content Based Regularization Technique in Super Resolution Imaging
Super-resolution (SR) aims to overcome the ill-posed conditions of image acquisition. SR facilitates scene recognition from low-resolution image(s). Generally assumes that high and low resolution images share similar intrinsic geometries. Various approaches have tried to aggregate the informative details of multiple low-resolution images into a high-resolution one. In this paper, we present a n...
متن کاملA Deep Model for Super-resolution Enhancement from a Single Image
This study presents a method to reconstruct a high-resolution image using a deep convolution neural network. We propose a deep model, entitled Deep Block Super Resolution (DBSR), by fusing the output features of a deep convolutional network and a shallow convolutional network. In this way, our model benefits from high frequency and low frequency features extracted from deep and shallow networks...
متن کاملResolution Enhancement of Biomedical Images to Augment Analysis
The field of biomedical image analysis is extremely broad and resolution enhancement is a fundamental aspect of virtually every implementation of an image analysis and visualization solution. Enhancement is a system component of all medical imaging modalities and a basic part of many diagnostic applications. Resolution enhancement can significantly aid diagnosis by highlighting regions and acce...
متن کاملReal-Time Super Resolution Contextual Close-up of Clinical Volumetric Data
We present an illustrative visualization system for real-time and high quality rendering of clinical volumetric medical data. Our technique is inspired by a medical illustration technique for depicting contextual close-up views of selected regions of interest where internal anatomical features are rendered in high detail. Our method integrates four important components: decimation of original v...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2001