Text image super-resolution is a challenging yet open research problem in the computer vision community. In particular, low-resolution images hamper the performance of typical optical character recognition (OCR) systems. In this article, we summarize our entry to the ICDAR2015 Competition on Text Image Super-Resolution. Experiments are based on the provided ICDAR2015 TextSR dataset [3] and the ...

Legacy-resolution base data on the NEXRAD network consists of reflectivity on a 1 km-by-1 deg polar grid and Doppler velocity and spectrum width on a similar 250 m-by-1 deg grid. It has been shown through simulations that mesocyclone and tornado signatures can be detected at ranges 50% greater than the current detectable ranges using higher-resolution base data on a 250 m-by-0.5 deg grid (Brown...

Unmanned aerial vehicles (UAVs or drones) are a very promising branch of technology, and they have been utilized in agriculture-in cooperation with image processing technologies-for phenotyping and vigor diagnosis. One of the problems in the utilization of UAVs for agricultural purposes is the limitation in flight time. It is necessary to fly at a high altitude to capture the maximum number of ...

Angular super-resolution imaging in the forward-looking area of a scanning radar platform plays an important role in the application of scanning radar. However, the angular resolution of scanning radar is limited by the system parameters. Thus, improving the angular resolution of scanning radar beyond the limitation of the given system parameters is desired. We present an angular super-resoluti...

Previous stochastic localization-based super-resolution techniques are largely limited by the labeling density and the fidelity to the morphology of specimen. We report on an optical super-resolution imaging scheme implementing joint tagging using multiple fluorescent blinking dyes associated with super-resolution optical fluctuation imaging (JT-SOFI), achieving ultra-high labeling density supe...

Super-resolution (SR) image reconstruction is the process of combining several low resolution images into a single higher resolution image. There is a driving need for digital images of higher resolutions and quality. However, there is a limit to the spatial resolution that can be recorded by any digital device. Growing interest in super-resolution (SR) restoration of video sequences and the cl...

Video super-resolution for dual-mode cameras in single-view and mono-view scenarios is studied in this thesis. Dual-mode cameras are capable of generating high-resolution still images while shooting video sequences at low-resolution. High-resolution still images are used to form a regularization function for solving the inverse problem of super-resolution. Exploiting proposed regularization fun...

“Super-resolution” is the term used to denote the subset of imaging processing that tries to estimate a high-resolution image of a scene, given a set of low-resolution observations (Fig. 1). Colloquially, when superresolution researchers try to describe what they do to family, friends, and loved ones, we can use the example from the TV show CSI: whenever someone on CSI looks at low-resolution s...

Learning based super-resolution (SR) methods, which predict the high-resolution pixel values but not directly provide an estimation of uncertainty, are typically non-probabilistic and have limited generalization ability. Gaussian processes can provide a framework for deriving regression techniques with explicit uncertainty models, but Gaussian Process Regression (GPR) has a significant drawback...